WO2019035639A1 - Deep learning-based septicemia early detection method and program - Google Patents
Deep learning-based septicemia early detection method and program Download PDFInfo
- Publication number
- WO2019035639A1 WO2019035639A1 PCT/KR2018/009338 KR2018009338W WO2019035639A1 WO 2019035639 A1 WO2019035639 A1 WO 2019035639A1 KR 2018009338 W KR2018009338 W KR 2018009338W WO 2019035639 A1 WO2019035639 A1 WO 2019035639A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- sepsis
- time
- computer
- data
- time point
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- the present invention relates to a method and program for early detection of septicemia based on deep running.
- Sepsis is a condition in which a microorganism is infected and a serious inflammatory reaction occurs in the whole body. Sepsis is rarely detected immediately after infection, and is confirmed by precise examination with suspected suspicious symptoms or developmental patterns based on various vital signs and test values. For example, hyperthyroidism with body temperature rising to 38 degrees or less, hypothermia with less than 36 degrees, breathing more than 24 times per minute (brisk breathing), heart rate more than 90 beats per minute (tachycardia), increased blood leukocyte count (SIRS), which is called septicemia when the systemic inflammatory response syndrome is due to infection by microorganisms. This is called systemic inflammatory response syndrome (SIRS). It takes time to first diagnose sepsis after preliminary signs such as SIRS, and if not prepared for sepsis early, multiple organ dysfunction syndrome (MODS) may occur and the patient may die.
- SIRS systemic inflammatory response syndrome
- the present invention provides a deep-learning-based sepsis early detection method and program for calculating the possibility of sepsis after a specific time by applying a data set generated based on medical data described in medical records to a deep learning algorithm I want to.
- a method for early detection of septicemia based on deep learning comprising: acquiring a feature data set within a unit time of N units before a reference point; Inputting the feature data set to a sepsis detection model by a computer; And providing a prediction result of a sepsis occurrence at a specific predicted time point, wherein the sepsis detection model is generated by learning learning data based on deep learning, and the prediction time is calculated from k k is a specific natural number), the septic event occurrence prediction result is a result of whether an event of occurrence of septicemia occurs at the predicted time, and the feature data set includes medical data stored in the electronic medical record . ≪ / RTI >
- the computer further comprises calculating a correlation between each basic feature data for one or more medical data by only basic feature data through the septicemia detection model, And extracting at least one representative value from the at least one medical data recorded in the medical record.
- the learning data includes a target time point for a plurality of sepsis patients and a characteristic data set in N unit time periods before a specific time from the target time point
- the septicemia detection model is generated by applying the feature data set in N unit time periods in the learning data to the deep learning algorithm by matching the k pieces of septicemia occurrence results after k units of unit time elapses.
- the time point at which the sepsis development pattern is first confirmed is an initial time point when the systemic inflammatory response syndrome persists beyond the reference time.
- the step of acquiring the feature data set includes extracting at least one representative value for at least one of systolic blood pressure, pulse pressure, heart rate, body temperature, respiratory rate, leukocyte count, hydrogen ion index, .
- the unit time is any one of a time interval for recording specific first medical data on the electronic medical record or an integer multiple of the time interval.
- the characteristic data set acquisition step may include calculating at least one of successive second medical data values when specific second medical data is acquired at a time interval longer than the unit time .
- the feature data is constructed by interpolating or interpolating a value measured at a unit time at a point adjacent to a reference time point of the first medical data from the medical data, A predetermined number of unit times as the unit time of the adjacent time in the order of closest to the unit time of the reference time including the unit time of the nearest time point from the unit time of the base time of the medical data.
- the septicemia detection model uses a long short-term memory (LSTM) algorithm.
- LSTM long short-term memory
- the sepsis generation prediction result providing step performs a sepsis occurrence prediction with N feature data sets changed every unit time for a specific patient.
- the deep learning-based septicemia early detection program is combined with a hardware computer to execute the above-mentioned deep learning-based septicemia early detection method and is stored in the medium.
- the learned septicemia sensing model optimally generates feature data based on the basic feature data, the user does not have to perform a process of generating a feature (i.e., a Referece Feature) advantageous to prediction.
- a feature i.e., a Referece Feature
- the occurrence of sepsis can be predicted early and accurately compared with the existing regression model. For example, it is possible to predict the onset of systemic inflammatory response syndrome (SIRS), which is one of the pre-symptom symptoms prior to the occurrence of sepsis, and to prepare for the progression of the patient's sepsis.
- SIRS systemic inflammatory response syndrome
- data recorded in electronic medical records can be directly applied to a septicemia detection model to predict the possibility of SIRS occurrence after a specific time in real time.
- FIG. 1 is a flowchart of an early detection method of sepsis according to an embodiment of the present invention.
- FIG. 2 is an exemplary table of feature data sets obtained from a plurality of medical data sets in accordance with an embodiment of the present invention.
- FIG. 3 is a diagram illustrating a process of constructing learning data based on SIRS initial occurrence time, which is one of symptoms of septic shock according to an embodiment of the present invention.
- a method for early detection of septicemia based on deep learning comprising: acquiring a feature data set within a unit time of N units before a reference point; Inputting the feature data set to a sepsis detection model by a computer; And providing a prediction result of a sepsis occurrence at a specific predicted time point, wherein the sepsis detection model is generated by learning learning data based on deep learning, and the prediction time is calculated from k k is a specific natural number), the septic event occurrence prediction result is a result of whether an event of occurrence of septicemia occurs at the predicted time, and the feature data set includes medical data stored in the electronic medical record . ≪ / RTI >
- the term " computer " as used herein includes various devices capable of performing arithmetic processing to visually present results to a user.
- the computer may be a smart phone, a tablet PC, a cellular phone, a personal communication service phone (PCS phone), a synchronous / asynchronous A mobile terminal of IMT-2000 (International Mobile Telecommunication-2000), a Palm Personal Computer (PC), a personal digital assistant (PDA), and the like.
- the computer may also be a medical device that acquires or observes medical images.
- the computer may be a server computer connected to various client computers.
- the computer may also be comprised of one or more devices.
- FIG. 1 is a flowchart of an early detection method of sepsis according to an embodiment of the present invention.
- a method for early detection of a deep-learning based septicemia includes a step S200 of acquiring a feature data set within a unit time of N units before a reference time point; The computer inputting the feature data set into a sepsis detection model (S400); And a step (S600) in which the computer provides a prediction result of a sepsis occurrence at a specific predicted time point.
- S400 sepsis detection model
- S600 step in which the computer provides a prediction result of a sepsis occurrence at a specific predicted time point.
- the computer acquires the feature data set within N unit time before the reference point (S200; feature data set acquisition step). That is, the computer acquires a dataset for input to the sepsis detection model described below.
- the feature data set is calculated based on medical data stored in electronic medical records.
- the computer does not acquire new medical data from the patient using a separate sensor or device from the patient to predict the occurrence of sepsis, and periodically measures the patient's condition in the Intensive Care Unit (ICU) .
- the computer in the obtaining of the feature data set (S200), stores medical data used for forming the feature data set, such as systolic blood pressure, pulse pressure, heart rate, body temperature, respiratory rate, leukocyte count, hydrogen ion index, At least one of them.
- the feature data set is formed by extracting one or more representative values (e.g., average value, maximum value, and minimum value) for one or more medical data recorded in the electronic medical record.
- the computer obtains three characteristic data (features) by calculating an average value, a maximum value, and a minimum value for specific medical data (for example, pulse pressure).
- the computer uses only the basic feature data calculated from each medical data obtained from the electronic medical record, and sets the reference feature data (reference data) set to reflect the correlation, temporal change, Reference Feature Data) is not performed.
- the reference feature data since the computer calculates various correlations using the basic feature data through the sepsis detection model using the deep learning algorithm, the reference feature data may not be used.
- the unit time is any one of a time interval for recording specific first medical data on the electronic medical record or an integer multiple of the time interval. For example, as shown in FIG. 2, since the patient's specific first medical data (for example, systolic pressure) is measured every 1 hour, 30 minutes, or 15 minutes in the ICU, One hour, which is the same or an integer multiple of the time interval (that is, the measurement period) for recording the medical data, can be set as the unit time.
- the patient's specific first medical data for example, systolic pressure
- the computer can set a time, which is equal to or an integral multiple of the measurement period of various medical data, as a unit time. For example, if a sick blood pressure is recorded every 30 minutes in a particular hospital intensive care unit and the heart rate is recorded every 15 minutes, the computer can set an hour, which is an integral number of 30 minutes and 15 minutes, in unit time.
- the computer calculates one or more representative values (e.g., average value, maximum value, and minimum value) based on one or more measured values obtained within a unit time for specific medical data, and uses each representative value as the characteristic data. For example, when the body temperature is recorded in the medical record every 10 minutes, the computer calculates the average value (Average) and the maximum value (Max) of the six body temperature data measured within one hour as the unit time do.
- one or more representative values e.g., average value, maximum value, and minimum value
- the computer when the specific second medical data is acquired at a time interval longer than the unit time, the computer can acquire at least one of successive second medical data values . That is, if there is no value to be measured within the unit time, the computer builds the feature data by filling the adjacent value. For example, as shown in the figure, the hydrogen ion exponent is irregularly measured at a longer time period than the unit time at 2 hours, 4 hours intervals, etc. Therefore, when the hydrogen ion exponent is not measured in a unit time, The value measured at the time is applied or corrected.
- the computer acquires a plurality of feature data for N consecutive unit times to form a feature data set. For example, when 20 characteristic data are calculated per unit time using systolic blood pressure, pulse pressure, heart rate, body temperature, respiratory rate, leukocyte count, hydrogen ion index and blood oxygen concentration as medical data as in FIG. 2,
- the computer sets 5 * N (e.g., 100) pieces of feature data acquired for N consecutive unit times (e.g., 5 hours) into one feature data set.
- the computer can set the current time as a reference time point. That is, in order to determine whether there is a possibility of occurrence of a sepsis occurrence pattern defined previously after a predetermined time from the present time, the computer uses a feature data set acquired within N unit hours before the present point in time, And the possibility of post-transplant sepsis. For example, since systemic inflammatory response syndrome (SIRS) occurs in sepsis patients in many cases, the computer can not detect N (N) hours before the current time (for example, 3 hours) The computer calculates the probability of occurrence of SIRS after a lapse of a specific time in real time by using the feature data set obtained within the unit time of each unit. , It is possible to continuously calculate the possibility that the sepsis will start at a certain time (for example, 3 hours). Through this, the computer can continuously perform the possibility of sepsis in a patient admitted to the ICU at a unit time interval.
- SIRS systemic inflammatory response syndrome
- the computer inputs the feature data set to the sepsis detection model (S400). That is, the computer inputs a feature data set obtained from a patient in unit time intervals or in real time to a sepsis detection model.
- the septicemia detection model is generated by learning learning data based on deep learning.
- the training data for training the septicemia sensing model includes a target time point for a plurality of sepsis patients and a set of N characteristic data within a time unit of N times before a specific time from the target time point. That is, the septicemia detection model includes a feature data set in N units of time in the learning data and a target time point after k units of unit time elapse (that is, a time point when a condition that can be judged as the occurrence of sepsis (hereinafter referred to as a sepsis judgment condition) ) And applying it to the deep learning algorithm.
- a time point for determining the criteria for determining sepsis may be the time of the first occurrence of SIRS. Since SIRS occurs in a large number of patients prior to sepsis, the occurrence of SIRS can be used as an element for early detection of sepsis. That is, as shown in FIG. 3, the target time point is the time when the SIRS first occurs in a patient admitted to the intensive care unit (particularly, the Medical Intensive Care Unit (MICU)) before diagnosis of sepsis.
- MICU Medical Intensive Care Unit
- the method of constructing the feature data sets in N unit time for each patient is performed in the same manner as the method of acquiring the feature data set inputted to the septicemia detection model in order to calculate the possibility of occurrence of SIRS after a specific time.
- the computer extracts a patient who has experienced SIRS among patients diagnosed with sepsis in the past, and then generates a feature data set based on the medical data of the patients. Since the learning data is generated only from the medical data of the patient who has been diagnosed as sepsis after the SIRS condition, the computer can construct the learning data for predicting the sepsis symptom accompanied by the SIRS condition.
- an embodiment of a process for constructing learning data used for training (learning) of a sepsis detection model for early diagnosis of sepsis accompanied by SIRS state is as follows. First, the computer extracts patients with a history of sepsis diagnosis. Thereafter, the computer extracts the patient whose SIRS state lasted for a certain time or longer before the time of the sepsis diagnosis. For example, the computer continuously extracts patients who continue to have SIRS status for 5 hours. Then, as shown in FIG. 3, the computer extracts the starting point at which the SIRS state starts, as the target point in time. Then, the computer extracts the feature data set within N unit time before the predetermined predicted interval time (k unit time, for example, 3 hours) from the target time. At this time, the feature data set is formed by calculating representative values (for example, an average value, a maximum value, a minimum value, and the like) for general medical data included in the electronic medical record of a plurality of extracted patients by each unit time.
- representative values for example, an average
- the septicemia sensing model may utilize Deep Feedforward Network (DFN) or Long Short-Term Memory (LSTM) algorithms.
- DNN Deep Feedforward Network
- LSTM Long Short-Term Memory
- a typical DFN has a network structure consisting of an input layer, one or more hidden layers, and an output layer.
- the data is input to the neuron of the input layer and calculated final values by calculating the weights of the connected edges and the sum of the values delivered from the previous node and functions until reaching the output layer, Through the comparison, learning proceeds in the direction of minimizing the difference between them.
- LSTM is one of the recurrent neural network (RNN) methodologies that reflect temporal variability in time series data among several techniques of deep learning. It solves the problem of learning disability on deep network (eg Vanishing Gradient) in general RNN And is used in various research and development fields.
- RNN recurrent neural network
- the RNN is advantageous for learning patterns within a temporal change, and thus is useful for analyzing biomedical data in which data is acquired continuously over time.
- the sepsis detection model for analyzing learning data can provide higher accuracy when applying LSTM.
- the computer provides a prediction result of occurrence of sepsis at a specific predicted time point (S600).
- the prediction time is a time point that has elapsed by k unit time intervals from the reference time point. That is, the prediction time is a time point that has elapsed by a time interval between the N unit time and the target time for acquiring the feature data set in the learning data from the reference time point (for example, the current time point).
- the computer uses the septicemia detection model to calculate the likelihood that one of the defined sepsis incidence patterns will occur at the time of the prediction. That is, the prediction result of the sepsis occurrence indicates whether any one of the precondition of the occurrence of the sepsis occurs at the predicted time.
- the sepsis detection model detects the target time at which the SIRS state in the learning data starts and the characteristic in the N unit time obtained before k unit time from the target time The data set is learned, and a prediction result of a sepsis occurrence at a prediction time when k unit times has elapsed is calculated by using the feature data set within N unit time before the present point in time.
- the predicted sepsis occurrence result indicates whether the SIRS state, which is a precursor state of the occurrence of sepsis, starts at the predicted time.
- the step of providing the sepsis occurrence prediction result (S600) may calculate the possibility of sepsis by using N feature data sets changed every unit time for a specific patient.
- the deep-learning-based septicemia early detection method may be implemented as a program (or an application) to be executed in combination with a hardware computer and stored in a medium.
- the above-described program may be stored in a computer-readable medium such as C, C ++, JAVA, machine language, or the like that can be read by the processor (CPU) of the computer through the device interface of the computer, And may include a code encoded in a computer language of the computer.
- code may include a functional code related to a function or the like that defines necessary functions for executing the above methods, and includes a control code related to an execution procedure necessary for the processor of the computer to execute the functions in a predetermined procedure can do.
- code may further include memory reference related code as to whether the additional information or media needed to cause the processor of the computer to execute the functions should be referred to at any location (address) of the internal or external memory of the computer have.
- the code may be communicated to any other computer or server remotely using the communication module of the computer
- a communication-related code for determining whether to communicate, what information or media should be transmitted or received during communication, and the like.
- the medium to be stored is not a medium for storing data for a short time such as a register, a cache, a memory, etc., but means a medium that semi-permanently stores data and is capable of being read by a device.
- examples of the medium to be stored include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like, but are not limited thereto.
- the program may be stored in various recording media on various servers to which the computer can access, or on various recording media on the user's computer.
- the medium may be distributed to a network-connected computer system so that computer-readable codes may be stored in a distributed manner.
- the learned septicemia sensing model optimally generates feature data based on the basic feature data, the user does not have to perform a process of generating a feature (i.e., a Referece Feature) advantageous to prediction.
- a feature i.e., a Referece Feature
- the occurrence of sepsis can be predicted early and accurately compared with the existing regression model. For example, it is possible to predict the onset of systemic inflammatory response syndrome (SIRS), which is one of the pre-symptom symptoms prior to the occurrence of sepsis, and to prepare for the progression of the patient's sepsis.
- SIRS systemic inflammatory response syndrome
- data recorded in electronic medical records can be directly applied to a septicemia detection model to predict the possibility of SIRS occurrence after a specific time in real time.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- Epidemiology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention relates to a deep learning-based septicemia early detection method and program. The deep learning-based septicemia early detection method, according to one embodiment of the present invention, comprises the steps of: acquiring, by a computer, a feature data set within N unit times before a reference time point (S200); inputting, by the computer, the feature data set in a septicemia detection model (S400); and providing, by the computer, a result of predicting the occurrence of septicemia at a specific prediction time point (S600).
Description
본 발명은 딥러닝 기반의 패혈증 조기 감지방법 및 프로그램에 관한 것이다.The present invention relates to a method and program for early detection of septicemia based on deep running.
패혈증은 미생물에 감염되어 전신에 심각한 염증 반응이 나타나는 상태를 말한다. 패혈증은 감염 직후 발견되는 경우가 드물고, 여러 생체신호 및 검사값 기반의 전조 증상 혹은 발생양상으로 의심되어 정밀한 검사를 통해 확진을 하게 된다. 일례로 체온이 38도 이상으로 올라가는 발열 증상 혹은 36도 이하로 내려가는 저체온증, 호흡수가 분당 24회 이상으로 증가(빈호흡), 분당 90회 이상의 심박수(빈맥), 혈액 검사상 백혈구 수의 증가 혹은 현저한 감소 중 두 가지 이상의 증상을 보이는 경우, 이를 전신성 염증 반응 증후군(systemic inflammatory response syndrome; SIRS)이라고 부르는데, 이러한 전신성 염증 반응 증후군이 미생물의 감염에 의한 것일 때 패혈증이라고 한다. 최초에 SIRS와 같은 사전 징후가 발생한 후 패혈증임을 진단할 때까지 시간이 소요되게 되고, 조기에 패혈증에 대비하지 않으면 다장기 기능장애증후군(MODS)가 발생하고 환자가 사망할 수 있다.Sepsis is a condition in which a microorganism is infected and a serious inflammatory reaction occurs in the whole body. Sepsis is rarely detected immediately after infection, and is confirmed by precise examination with suspected suspicious symptoms or developmental patterns based on various vital signs and test values. For example, hyperthyroidism with body temperature rising to 38 degrees or less, hypothermia with less than 36 degrees, breathing more than 24 times per minute (brisk breathing), heart rate more than 90 beats per minute (tachycardia), increased blood leukocyte count (SIRS), which is called septicemia when the systemic inflammatory response syndrome is due to infection by microorganisms. This is called systemic inflammatory response syndrome (SIRS). It takes time to first diagnose sepsis after preliminary signs such as SIRS, and if not prepared for sepsis early, multiple organ dysfunction syndrome (MODS) may occur and the patient may die.
기존에는 다양한 참조특징데이터를 생성하여 회귀분석 및 기계학습법에 적용하였다. 패혈증의 발생 및 악화예측을 위해 각각의 의료데이터간의 상관관계 등을 파악할 수 있는 새로운 특징데이터를 생성하여 이용하였다. 이 때, 어떠한 새로운 특징데이터를 선택하여 사용하느냐에 따라 분석결과에 영향을 미치며, 사람이 이해할 수 있는 형태로 가공한 사람편향적(human-biased) 특징데이터이므로 질환의 발생양상 혹은 개인별 대안한 질환변화 패턴을 다각도로 고려하지 못해 패혈증 예측모델의 성능향상에 어려운 문제가 있었다.In the past, various reference feature data were generated and applied to regression analysis and machine learning method. To generate the sepsis and to predict the exacerbation of the sepsis, new feature data was generated and used to grasp the correlation between each medical data. In this case, since the human-biased characteristic data processed in a human-understandable form affects the analysis result according to which new feature data is selected and used, the pattern of occurrence of the disease or the alternative disease change pattern Because of the lack of consideration of multiple angles.
중환자실에 입원한 환자에게 패혈증이 발생하기 전, 가능한 한 조기에 여러 전조증상이 나타나는 시점에 감지하여야 패혈증에 의한 환자 사망을 막을 수 있으므로, 보다 조기에 패혈증을 감지하는 정확도 높은 방법이 필요하다. 이를 위해, 본 발명은 의무기록에 기재되는 의료데이터를 바탕으로 생성된 데이터셋을 딥러닝 알고리즘에 적용하여 특정시간 이후의 패혈증 발생가능성을 산출하는, 딥러닝 기반의 패혈증 조기 감지방법 및 프로그램을 제공하고자 한다.Patients admitted to the ICU need to have a precise method for detecting sepsis earlier because the patient's death due to sepsis can be prevented before the occurrence of sepsis as early as possible before the occurrence of sepsis. To this end, the present invention provides a deep-learning-based sepsis early detection method and program for calculating the possibility of sepsis after a specific time by applying a data set generated based on medical data described in medical records to a deep learning algorithm I want to.
본 발명이 해결하고자 하는 과제들은 이상에서 언급된 과제로 제한되지 않으며, 언급되지 않은 또 다른 과제들은 아래의 기재로부터 통상의 기술자에게 명확하게 이해될 수 있을 것이다.The problems to be solved by the present invention are not limited to the above-mentioned problems, and other problems which are not mentioned can be clearly understood by those skilled in the art from the following description.
본 발명의 일실시예에 따른 딥러닝 기반의 패혈증 조기 감지 방법은, 컴퓨터가 기준시점 이전의 N개 단위시간 내에서 특징데이터셋을 획득하는 단계; 컴퓨터가 상기 특징데이터셋을 패혈증감지모델에 입력하는 단계; 및 컴퓨터가 특정한 예측시점의 패혈증 발생 예측결과를 제공하는 단계;를 포함하되, 상기 패혈증감지모델은 딥러닝을 기반으로 학습데이터를 학습하여 생성된 것이며, 상기 예측시점은 상기 기준시점으로부터 k개(k는 특정한 자연수)의 단위시간 간격만큼 경과된 시점이며, 상기 패혈증 발생 예측결과는 상기 예측시점에 패혈증 발생양상이 초기 발생되는지에 대한 결과이며, 상기 특징데이터셋은 전자의무기록에 저장되는 의료데이터를 기반으로 산출되는 것이다.According to an embodiment of the present invention, there is provided a method for early detection of septicemia based on deep learning, comprising: acquiring a feature data set within a unit time of N units before a reference point; Inputting the feature data set to a sepsis detection model by a computer; And providing a prediction result of a sepsis occurrence at a specific predicted time point, wherein the sepsis detection model is generated by learning learning data based on deep learning, and the prediction time is calculated from k k is a specific natural number), the septic event occurrence prediction result is a result of whether an event of occurrence of septicemia occurs at the predicted time, and the feature data set includes medical data stored in the electronic medical record . ≪ / RTI >
또한, 다른 일실시예로, 컴퓨터가 상기 패혈증감지모델을 통해 기본특징데이터만으로 하나 이상의 의료데이터에 대한 각 기본특징데이터 간의 상관관계를 산출하는 단계;를 더 포함하고, 상기 기본특징데이터는 상기 전자의무기록에 기록되는 상기 하나 이상의 의료데이터에 대해 하나 이상의 대표값을 추출하여 형성된 것이다.Further, in another embodiment, the computer further comprises calculating a correlation between each basic feature data for one or more medical data by only basic feature data through the septicemia detection model, And extracting at least one representative value from the at least one medical data recorded in the medical record.
또한, 다른 일실시예로, 상기 학습데이터는, 복수의 패혈증 환자에 대해 타겟시점과 상기 타겟시점으로부터 특정시간 이전의 N개 단위시간 내 특징데이터셋를 포함하고, 상기 타겟시점은 패혈증 환자에게 패혈증 발생양상이 최초 확인된 시점이고, 상기 패혈증감지모델은, 상기 학습데이터 내의 N개 단위시간 내 특징데이터셋과 k개의 단위시간 경과 후의 패혈증발생결과를 매칭하여 딥러닝 알고리즘에 적용하여 생성되는 것이다.In another embodiment, the learning data includes a target time point for a plurality of sepsis patients and a characteristic data set in N unit time periods before a specific time from the target time point, And the septicemia detection model is generated by applying the feature data set in N unit time periods in the learning data to the deep learning algorithm by matching the k pieces of septicemia occurrence results after k units of unit time elapses.
또한, 다른 일실시예로, 상기 패혈증 발생양상이 최초 확인된 시점은, 기준시간 이상으로 전신성 염증 반응 증후군이 지속될 때의 초기 시점이다.In another embodiment, the time point at which the sepsis development pattern is first confirmed is an initial time point when the systemic inflammatory response syndrome persists beyond the reference time.
또한, 다른 일실시예로, 상기 특징데이터셋 획득단계는, 수축기혈압, 맥압, 심박수, 체온, 호흡수, 백혈구수치, 수소이온지수, 혈중 산소 농도 중 적어도 하나에 대해 하나 이상의 대표값을 추출하는 것을 특징으로 한다.In another embodiment, the step of acquiring the feature data set includes extracting at least one representative value for at least one of systolic blood pressure, pulse pressure, heart rate, body temperature, respiratory rate, leukocyte count, hydrogen ion index, .
또한, 다른 일실시예로, 상기 단위시간은, 상기 전자의무기록 상에 특정한 제1의료데이터를 기록하는 시간간격 또는 상기 시간간격의 정수배 중 어느 하나이다.In another embodiment, the unit time is any one of a time interval for recording specific first medical data on the electronic medical record or an integer multiple of the time interval.
또한, 다른 일실시예로, 상기 특징데이터셋 획득단계는, 특정한 제2의료데이터가 상기 단위시간보다 긴 시간 간격으로 획득되는 경우, 연속되는 제2의료데이터값 중 적어도 하나를 이용하여 산출하는 것을 특징으로 한다.In another embodiment, the characteristic data set acquisition step may include calculating at least one of successive second medical data values when specific second medical data is acquired at a time interval longer than the unit time .
또한, 다른 일실시예로, 상기 의료데이터가 복수개인 경우, 각각의 측정주기마다 측정된 각 의료데이터가 상기 제1의료데이터에 의한 기준 시점의 단위시간을 포함하지 않는 경우에는, 컴퓨터는 상기 각 의료데이터 중에서 상기 제1의료데이터의 기준 시점의 단위 시간과 인접한 시점의 단위 시간에서 측정된 값을 내삽 또는 보간하여 특징데이터를 구축하는 것을 특징으로 하고, 상기 인접한 시점의 단위 시간은, 상기 제1의료데이터의 기준 시점의 단위 시간으로부터 가장 인접한 시점의 단위 시간을 포함하여, 상기 기준 시점의 단위 시간과 가장 가까운 순서대로 인접한 시점의 단위 시간으로서, 미리 정해진 개수의 단위 시간을 포함한다.In another embodiment, when there are a plurality of pieces of the medical data, when each of the pieces of medical data measured for each measurement period does not include the unit time of the reference time point by the first medical data, Characterized in that the feature data is constructed by interpolating or interpolating a value measured at a unit time at a point adjacent to a reference time point of the first medical data from the medical data, A predetermined number of unit times as the unit time of the adjacent time in the order of closest to the unit time of the reference time including the unit time of the nearest time point from the unit time of the base time of the medical data.
또한, 다른 일실시예로, 상기 패혈증감지모델은, LSTM(Long Short-term Memory) 알고리즘을 이용하는 것이다.In another embodiment, the septicemia detection model uses a long short-term memory (LSTM) algorithm.
또한, 다른 일실시예로, 상기 패혈증 발생예측결과 제공단계는, 특정한 환자에게 대해 단위시간이 경과할 때마다 변경된 N개의 특징데이터셋으로 패혈증 발생 예측을 수행한다.In another embodiment, the sepsis generation prediction result providing step performs a sepsis occurrence prediction with N feature data sets changed every unit time for a specific patient.
본 발명의 다른 일실시예에 따른 딥러닝 기반의 패혈증 조기 감지프로그램은, 하드웨어인 컴퓨터와 결합되어 상기 언급된 딥러닝 기반의 패혈증 조기 감지 방법을 실행하며, 매체에 저장된다.The deep learning-based septicemia early detection program according to another embodiment of the present invention is combined with a hardware computer to execute the above-mentioned deep learning-based septicemia early detection method and is stored in the medium.
상기와 같은 본 발명에 따르면, 아래와 같은 다양한 효과들을 가진다.According to the present invention as described above, the following various effects are obtained.
첫째, 학습된 패혈증감지모델이 기본특징데이터를 기반으로 최적으로 특징데이터(Feature)를 산출하므로, 사용자가 예측에 유리한 특징(즉, Referece Feature)을 생성하는 과정을 수행하지 않아도 된다.First, since the learned septicemia sensing model optimally generates feature data based on the basic feature data, the user does not have to perform a process of generating a feature (i.e., a Referece Feature) advantageous to prediction.
둘째, 기존의 회귀모델에 비해 패혈증 발생을 조기에 정확하게 예측할 수 있다. 예를 들어, 패혈증 발생 전의 전조증상 중 하나인 전신성 염증 반응 증후군(systemic inflammatory response syndrome; SIRS)이 발생되는 초기시점을 정확하게 예측하여 환자의 패혈증 진행을 대비할 수 있다.Second, the occurrence of sepsis can be predicted early and accurately compared with the existing regression model. For example, it is possible to predict the onset of systemic inflammatory response syndrome (SIRS), which is one of the pre-symptom symptoms prior to the occurrence of sepsis, and to prepare for the progression of the patient's sepsis.
셋째, 환자로부터 패혈증 조기감지를 위한 별도의 의료데이터를 획득할 필요없이 일반적으로 중환자실(ICU)에서 획득되어 전자의무기록(EMR)에 기록되는 데이터만으로 패혈증을 조기에 예측할 수 있다. 따라서, 병원에서 별도의 장치를 사용하지 않고 컴퓨터를 이용하여 패혈증 조기 감지를 수행할 수 있다.Thirdly, it is possible to predict sepsis early by only the data acquired in the ICU and recorded in the electronic medical record (EMR), without having to obtain separate medical data for early detection of sepsis from the patient. Therefore, early detection of septicemia can be performed using a computer without using a separate device in a hospital.
넷째, 전자의무기록에 기록되는 데이터를 바로 패혈증감지모델에 적용하여 실시간으로 특정시간 이후의 SIRS 발생가능성을 예측할 수 있다.Fourth, data recorded in electronic medical records can be directly applied to a septicemia detection model to predict the possibility of SIRS occurrence after a specific time in real time.
도 1은 본 발명의 일실시예에 따른 딥러닝 기반의 패혈증 조기감지방법의 순서도이다.FIG. 1 is a flowchart of an early detection method of sepsis according to an embodiment of the present invention.
도 2는 본 발명의 일실시예에 따른 복수의 의료데이터로부터 획득되는 특징데이터셋에 대한 예시 표이다.2 is an exemplary table of feature data sets obtained from a plurality of medical data sets in accordance with an embodiment of the present invention.
도 3은 본 발명의 일실시예에 따른 패혈증 전조증상 중 하나인 SIRS 초기발생시점 기반으로 학습데이터를 구축하는 과정에 대한 도면이다.FIG. 3 is a diagram illustrating a process of constructing learning data based on SIRS initial occurrence time, which is one of symptoms of septic shock according to an embodiment of the present invention.
본 발명의 일실시예에 따른 딥러닝 기반의 패혈증 조기 감지 방법은, 컴퓨터가 기준시점 이전의 N개 단위시간 내에서 특징데이터셋을 획득하는 단계; 컴퓨터가 상기 특징데이터셋을 패혈증감지모델에 입력하는 단계; 및 컴퓨터가 특정한 예측시점의 패혈증 발생 예측결과를 제공하는 단계;를 포함하되, 상기 패혈증감지모델은 딥러닝을 기반으로 학습데이터를 학습하여 생성된 것이며, 상기 예측시점은 상기 기준시점으로부터 k개(k는 특정한 자연수)의 단위시간 간격만큼 경과된 시점이며, 상기 패혈증 발생 예측결과는 상기 예측시점에 패혈증 발생양상이 초기 발생되는지에 대한 결과이며, 상기 특징데이터셋은 전자의무기록에 저장되는 의료데이터를 기반으로 산출되는 것이다.According to an embodiment of the present invention, there is provided a method for early detection of septicemia based on deep learning, comprising: acquiring a feature data set within a unit time of N units before a reference point; Inputting the feature data set to a sepsis detection model by a computer; And providing a prediction result of a sepsis occurrence at a specific predicted time point, wherein the sepsis detection model is generated by learning learning data based on deep learning, and the prediction time is calculated from k k is a specific natural number), the septic event occurrence prediction result is a result of whether an event of occurrence of septicemia occurs at the predicted time, and the feature data set includes medical data stored in the electronic medical record . ≪ / RTI >
이하, 첨부된 도면을 참조하여 본 발명의 바람직한 실시예를 상세히 설명한다. 본 발명의 이점 및 특징, 그리고 그것들을 달성하는 방법은 첨부되는 도면과 함께 상세하게 후술되어 있는 실시예들을 참조하면 명확해질 것이다. 그러나 본 발명은 이하에서 게시되는 실시예들에 한정되는 것이 아니라 서로 다른 다양한 형태로 구현될 수 있으며, 단지 본 실시예들은 본 발명의 게시가 완전하도록 하고, 본 발명이 속하는 기술분야에서 통상의 지식을 가진 자에게 발명의 범주를 완전하게 알려주기 위해 제공되는 것이며, 본 발명은 청구항의 범주에 의해 정의될 뿐이다. 명세서 전체에 걸쳐 동일 참조 부호는 동일 구성 요소를 지칭한다.Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. To fully disclose the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.
다른 정의가 없다면, 본 명세서에서 사용되는 모든 용어(기술 및 과학적 용어를 포함)는 본 발명이 속하는 기술분야에서 통상의 지식을 가진 자에게 공통적으로 이해될 수 있는 의미로 사용될 수 있을 것이다. 또 일반적으로 사용되는 사전에 정의되어 있는 용어들은 명백하게 특별히 정의되어 있지 않는 한 이상적으로 또는 과도하게 해석되지 않는다.Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense commonly understood by one of ordinary skill in the art to which this invention belongs. Also, commonly used predefined terms are not ideally or excessively interpreted unless explicitly defined otherwise.
본 명세서에서 사용된 용어는 실시예들을 설명하기 위한 것이며 본 발명을 제한하고자 하는 것은 아니다. 본 명세서에서, 단수형은 문구에서 특별히 언급하지 않는 한 복수형도 포함한다. 명세서에서 사용되는 "포함한다(comprises)" 및/또는 "포함하는(comprising)"은 언급된 구성요소 외에 하나 이상의 다른 구성요소의 존재 또는 추가를 배제하지 않는다.The terminology used herein is for the purpose of illustrating embodiments and is not intended to be limiting of the present invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. The terms " comprises " and / or " comprising " used in the specification do not exclude the presence or addition of one or more other elements in addition to the stated element.
본 명세서에서 '컴퓨터'는 연산처리를 수행하여 사용자에게 결과를 시각적으로 제시할 수 있는 다양한 장치들이 모두 포함된다. 예를 들어, 컴퓨터는 데스크 탑 PC, 노트북(Note Book) 뿐만 아니라 스마트폰(Smart phone), 태블릿 PC, 셀룰러폰(Cellular phone), 피씨에스폰(PCS phone; Personal Communication Service phone), 동기식/비동기식 IMT-2000(International Mobile Telecommunication-2000)의 이동 단말기, 팜 PC(Palm Personal Computer), 개인용 디지털 보조기(PDA; Personal Digital Assistant) 등도 해당될 수 있다. 또한, 컴퓨터는 의료영상을 획득하거나 관찰하는 의료장비도 해당될 수 있다. 또한, 컴퓨터는 다양한 클라이언트 컴퓨터와 연결되는 서버 컴퓨터가 해당될 수 있다. 또한, 컴퓨터는 하나 이상의 장치로 이루어질 수도 있다.The term " computer " as used herein includes various devices capable of performing arithmetic processing to visually present results to a user. For example, the computer may be a smart phone, a tablet PC, a cellular phone, a personal communication service phone (PCS phone), a synchronous / asynchronous A mobile terminal of IMT-2000 (International Mobile Telecommunication-2000), a Palm Personal Computer (PC), a personal digital assistant (PDA), and the like. The computer may also be a medical device that acquires or observes medical images. In addition, the computer may be a server computer connected to various client computers. The computer may also be comprised of one or more devices.
이하, 도면을 참조하여 본 발명의 실시예들에 따른 딥러닝 기반의 패혈증 예측방법 및 프로그램에 대해 설명하기로 한다.Hereinafter, a method and program for predicting a deep-run-based sepsis according to embodiments of the present invention will be described with reference to the drawings.
도 1은 본 발명의 일실시예에 따른 딥러닝 기반의 패혈증 조기 감지 방법의 순서도이다.FIG. 1 is a flowchart of an early detection method of sepsis according to an embodiment of the present invention.
도 1을 참조하면, 본 발명의 일실시예에 따른 딥러닝 기반의 패혈증 조기 감지 방법은, 컴퓨터가 기준시점 이전의 N개 단위시간 내에서 특징데이터셋을 획득하는 단계(S200); 컴퓨터가 상기 특징데이터셋을 패혈증감지모델에 입력하는 단계(S400); 및 컴퓨터가 특정한 예측시점의 패혈증 발생 예측결과를 제공하는 단계(S600);를 포함한다. 이하, 각 단계에 대한 상세한 설명을 기재한다.Referring to FIG. 1, a method for early detection of a deep-learning based septicemia according to an embodiment of the present invention includes a step S200 of acquiring a feature data set within a unit time of N units before a reference time point; The computer inputting the feature data set into a sepsis detection model (S400); And a step (S600) in which the computer provides a prediction result of a sepsis occurrence at a specific predicted time point. Hereinafter, a detailed description of each step will be described.
먼저, 컴퓨터가 기준시점 이전의 N개 단위시간 내에서 특징데이터셋을 획득한다(S200; 특징데이터셋 획득단계). 즉, 컴퓨터는 후술되는 패혈증감지모델에 입력하기 위한 데이터셋을 획득한다. First, the computer acquires the feature data set within N unit time before the reference point (S200; feature data set acquisition step). That is, the computer acquires a dataset for input to the sepsis detection model described below.
상기 특징데이터셋은 전자의무기록에 저장되는 의료데이터를 기반으로 산출되는 것이다. 즉, 컴퓨터는 패혈증 발생을 예측하기 위해 환자로부터 별도 센서나 장치를 이용하여 신규의료데이터를 획득하지 않고, 중환자실(ICU)에서 환자 상태 파악을 위해 주기적으로 측정하여 의무기록에 기재하는 의료데이터를 이용한다. 일실시예로, 상기 특징데이터셋 획득단계(S200)에서, 컴퓨터는 특징데이터셋 형성에 이용되는 의료데이터로 수축기혈압, 맥압, 심박수, 체온, 호흡수, 백혈구수치, 수소이온지수, 혈중 산소 농도 중 적어도 하나를 이용한다.The feature data set is calculated based on medical data stored in electronic medical records. In other words, the computer does not acquire new medical data from the patient using a separate sensor or device from the patient to predict the occurrence of sepsis, and periodically measures the patient's condition in the Intensive Care Unit (ICU) . In one embodiment, in the obtaining of the feature data set (S200), the computer stores medical data used for forming the feature data set, such as systolic blood pressure, pulse pressure, heart rate, body temperature, respiratory rate, leukocyte count, hydrogen ion index, At least one of them.
또한, 다른 일실시예로, 상기 특징데이터셋은 전자의무기록에 기록되는 하나 이상의 의료데이터에 대해 하나 이상의 대표값(예를 들어, 평균값, 최대값 및 최소값)을 추출하여 형성된다. 예를 들어, 도 2에서와 같이, 컴퓨터는 특정한 의료데이터(예를 들어, 맥압)에 대해 평균값, 최대값 및 최소값을 산출하여 3개의 특징데이터(feature)를 획득한다. Further, in another embodiment, the feature data set is formed by extracting one or more representative values (e.g., average value, maximum value, and minimum value) for one or more medical data recorded in the electronic medical record. For example, as shown in FIG. 2, the computer obtains three characteristic data (features) by calculating an average value, a maximum value, and a minimum value for specific medical data (for example, pulse pressure).
이를 통해, 컴퓨터는 전자의무기록에서 획득되는 각각의 의료데이터에서 산출되는 기본특징데이터(Basic Feature Data)만 이용하고, 각 기본특징데이터 간의 상관관계, 시간적 변화 등을 반영하기 위해 설정된 참조특징데이터(Reference Feature Data)를 산출하는 과정을 수행하지 않는다. 후술되는 바와 같이, 컴퓨터는 딥러닝 알고리즘을 이용한 패혈증감지모델을 통해 기본특징데이터를 이용하여 다양한 상관관계를 산출해내므로 참조특징데이터(Reference Feature Data)를 이용하지 않아도 된다.In this way, the computer uses only the basic feature data calculated from each medical data obtained from the electronic medical record, and sets the reference feature data (reference data) set to reflect the correlation, temporal change, Reference Feature Data) is not performed. As described later, since the computer calculates various correlations using the basic feature data through the sepsis detection model using the deep learning algorithm, the reference feature data may not be used.
또한, 다른 일실시예로, 상기 단위시간은, 상기 전자의무기록 상에 특정한 제1의료데이터를 기록하는 시간간격 또는 상기 시간간격의 정수배 중 어느 하나이다. 예를 들어, 도 2에서와 같이, 중환자실에서 환자의 특정한 제1의료데이터(예를 들어, 수축기혈압(Systolic pressure))를 1시간, 30분 또는 15분마다 측정하므로, 컴퓨터는 특정한 제1의료데이터를 기록하는 시간간격(즉, 측정주기)와 같거나 정수배인 1시간을 단위시간으로 설정할 수 있다. In another embodiment, the unit time is any one of a time interval for recording specific first medical data on the electronic medical record or an integer multiple of the time interval. For example, as shown in FIG. 2, since the patient's specific first medical data (for example, systolic pressure) is measured every 1 hour, 30 minutes, or 15 minutes in the ICU, One hour, which is the same or an integer multiple of the time interval (that is, the measurement period) for recording the medical data, can be set as the unit time.
또한, 복수의 의료데이터를 각각의 측정주기마다 측정하므로, 컴퓨터는 여러 의료데이터의 측정주기와 같거나 정수배인 시간을 단위시간으로 설정할 수 있다. 예를 들어, 특정한 병원의 중환자실에서 수축기혈압은 30분마다 기록하고 심박수는 15분마다 기록하는 경우, 컴퓨터는 30분과 15분의 정수배인 1시간을 단위시간으로 설정할 수 있다.Further, since a plurality of medical data is measured for each measurement period, the computer can set a time, which is equal to or an integral multiple of the measurement period of various medical data, as a unit time. For example, if a sick blood pressure is recorded every 30 minutes in a particular hospital intensive care unit and the heart rate is recorded every 15 minutes, the computer can set an hour, which is an integral number of 30 minutes and 15 minutes, in unit time.
컴퓨터는 특정한 의료데이터에 대해 단위시간 내에 획득된 하나 이상의 측정값을 기반으로 하나 이상의 대표값(예를 들어, 평균값, 최대값 및 최소값)을 산출하고 각각의 대표값을 특징데이터로 사용한다. 예를 들어, 체온을 10분마다 의무기록으로 기재하는 경우, 컴퓨터는 단위시간인 1시간 이내에 측정된 6회의 체온데이터의 평균값(Average)과 최대값(Max)를 해당 단위시간의 특징데이터로 산출한다.The computer calculates one or more representative values (e.g., average value, maximum value, and minimum value) based on one or more measured values obtained within a unit time for specific medical data, and uses each representative value as the characteristic data. For example, when the body temperature is recorded in the medical record every 10 minutes, the computer calculates the average value (Average) and the maximum value (Max) of the six body temperature data measured within one hour as the unit time do.
또한, 다른 일실시예로, 상기 특징데이터셋 획득단계(S200)에서, 특정한 제2의료데이터가 상기 단위시간보다 긴 시간 간격으로 획득되는 경우, 컴퓨터는 연속되는 제2의료데이터값 중 적어도 하나를 이용하여 산출한다. 즉, 단위시간 내에 측정되는 값이 없는 경우, 컴퓨터는 인접한 값을 채워서 특징데이터를 구축한다. 예를 들어, 도 에서와 같이, 수소이온지수는 2시간, 4시간 간격 등으로 단위시간에 비해 긴시간 주기로 불규칙적으로 측정되므로, 수소이온지수 측정이 이루어지지 않은 단위시간인 경우, 컴퓨터는 가장 인접한 시간에 측정되었던 값을 그대로 또는 보정하여 적용한다.Further, in another embodiment, in the characteristic data set acquiring step (S200), when the specific second medical data is acquired at a time interval longer than the unit time, the computer can acquire at least one of successive second medical data values . That is, if there is no value to be measured within the unit time, the computer builds the feature data by filling the adjacent value. For example, as shown in the figure, the hydrogen ion exponent is irregularly measured at a longer time period than the unit time at 2 hours, 4 hours intervals, etc. Therefore, when the hydrogen ion exponent is not measured in a unit time, The value measured at the time is applied or corrected.
컴퓨터는 연속되는 N개의 단위시간에 대해 복수의 특징데이터가 획득하여 특징데이터셋을 형성한다. 예를 들어, 도 2에서와 같이, 수축기혈압, 맥압, 심박수, 체온, 호흡수, 백혈구수치, 수소이온지수 및 혈중 산소 농도를 의료데이터로 사용하여 단위시간마다 20개의 특징데이터를 산출하는 경우, 컴퓨터는 연속되는 N개의 단위시간(예를 들어, 5시간)동안 획득된 5*N개(예를 들어, 100개)의 특징데이터를 하나의 특징데이터셋으로 설정한다.The computer acquires a plurality of feature data for N consecutive unit times to form a feature data set. For example, when 20 characteristic data are calculated per unit time using systolic blood pressure, pulse pressure, heart rate, body temperature, respiratory rate, leukocyte count, hydrogen ion index and blood oxygen concentration as medical data as in FIG. 2, The computer sets 5 * N (e.g., 100) pieces of feature data acquired for N consecutive unit times (e.g., 5 hours) into one feature data set.
또한, 일실시예로, 컴퓨터는 기준시점으로 현재시점을 설정할 수 있다. 즉, 현재시점으로부터 미리 정해진 시간 이후에 기존에 규정된 패혈증 발생양상이 발생할 가능성이 있는지 판단하기 위해, 컴퓨터는 현재시점 이전으로 N개 단위시간 내에서 획득된 특징데이터셋을 이용하여 실시간으로 특정시간 경과 후 패혈증 발생 가능성을 산출한다. 예를 들어, 패혈증 환자에게서 많은 경우에 패혈증 전조 증상으로 전신염증반응증후군(Systemic Inflammatory Response Syndrome; 이하, SIRS)이 발생하므로, 컴퓨터는 현재시점으로부터 k시간(예를 들어, 3시간) 이전의 N개 단위시간 내에서 획득된 특징데이터셋을 이용하여 실시간으로 특정시간 경과 후 SIRS 발생 가능성을 산출한다.또한, 다른 일실시예로, 컴퓨터는 단위시간이 경과되어 새로운 특징데이터가 추가되는 시점을 기준으로 특정시간(예를 들어, 3시간) 경과되는 시점에 패혈증이 시작될 가능성을 계속해서 산출할 수 있다. 이를 통해, 컴퓨터는 계속해서 중환자실(ICU)에 입원한 환자의 패혈증 발생 가능성을 단위시간 간격으로 수행할 수 있다. Also, in one embodiment, the computer can set the current time as a reference time point. That is, in order to determine whether there is a possibility of occurrence of a sepsis occurrence pattern defined previously after a predetermined time from the present time, the computer uses a feature data set acquired within N unit hours before the present point in time, And the possibility of post-transplant sepsis. For example, since systemic inflammatory response syndrome (SIRS) occurs in sepsis patients in many cases, the computer can not detect N (N) hours before the current time (for example, 3 hours) The computer calculates the probability of occurrence of SIRS after a lapse of a specific time in real time by using the feature data set obtained within the unit time of each unit. , It is possible to continuously calculate the possibility that the sepsis will start at a certain time (for example, 3 hours). Through this, the computer can continuously perform the possibility of sepsis in a patient admitted to the ICU at a unit time interval.
그 후, 컴퓨터가 특징데이터셋을 패혈증감지모델에 입력한다(S400). 즉, 컴퓨터는 환자에게서 단위시간 간격 또는 실시간으로 획득되는 특징데이터셋을 패혈증감지모델에 입력한다. 상기 패혈증감지모델은 딥러닝을 기반으로 학습데이터를 학습하여 생성된 것이다. Thereafter, the computer inputs the feature data set to the sepsis detection model (S400). That is, the computer inputs a feature data set obtained from a patient in unit time intervals or in real time to a sepsis detection model. The septicemia detection model is generated by learning learning data based on deep learning.
일실시예로, 상기 패혈증감지모델을 트레이닝하는 학습데이터는, 복수의 패혈증 환자에 대해 타겟시점과 상기 타겟시점으로부터 특정시간 이전의 N개 단위시간 내 특징데이터셋을 포함한다. 즉, 상기 패혈증감지모델은 상기 학습데이터 내의 N개 단위시간 내 특징데이터셋과 k개의 단위시간 경과 후의 타겟시점(즉, 패혈증 발생으로 판단할 수 있는 조건(이하, 패혈증판단조건)이 확인되는 시점)을 매칭하여 딥러닝 알고리즘에 적용하여 생성되는 것이다.In one embodiment, the training data for training the septicemia sensing model includes a target time point for a plurality of sepsis patients and a set of N characteristic data within a time unit of N times before a specific time from the target time point. That is, the septicemia detection model includes a feature data set in N units of time in the learning data and a target time point after k units of unit time elapse (that is, a time point when a condition that can be judged as the occurrence of sepsis (hereinafter referred to as a sepsis judgment condition) ) And applying it to the deep learning algorithm.
예를 들어, 패혈증판단조건 확인시점은 SIRS 최초발생시점이 될 수 있다. 패혈증 이전에 많은 수의 환자에게서 SIRS 상태가 발생하게 되므로, SIRS 발생을 패혈증 조기감지를 위한 요소로 활용할 수 있다. 즉, 상기 타겟시점은, 도 3에서와 같이, 패혈증진단 이전에 중환자실(특히, Medical Intensive Care Unit; MICU)에 입원한 환자에게서 SIRS가 최초로 발생되는 시점이다. 즉, 컴퓨터는 전신염증반응증후군 (즉, SIRS)의 조건인 (1) 체온>38℃이거나 <36℃, (2) 심박수>90/분, (3) 호흡수>20/분 또는 PaCO2<32mmHg, (4) 백혈구수>12,000/㎕, <4,000/㎕, 또는 막대핵호중구(band neutrophil)>10% 중 적어도 2개 이상에 해당하게 되는(즉, SIRS 조건을 만족하는) 상황이 5시간 연속으로 발생할 때의 최초시점을 타겟시점으로 추출한다.For example, a time point for determining the criteria for determining sepsis may be the time of the first occurrence of SIRS. Since SIRS occurs in a large number of patients prior to sepsis, the occurrence of SIRS can be used as an element for early detection of sepsis. That is, as shown in FIG. 3, the target time point is the time when the SIRS first occurs in a patient admitted to the intensive care unit (particularly, the Medical Intensive Care Unit (MICU)) before diagnosis of sepsis. (3) respiratory rate> 20 / minute, or PaCO2 <32 mmHg, (3) respiratory rate> 20 / minute, or (4) at least two of the leukocyte count> 12,000 / μl, <4,000 / μl, or band neutrophil> 10% (ie, satisfying the SIRS condition) To the target point in time.
또한, 각 환자에 대한 N개 단위시간 내 특징데이터셋을 구축하는 방식은 특정시간 이후의 SIRS 발생가능성을 산출하기 위해 패혈증감지모델에 입력되는 특징데이터셋을 획득하는 방식과 동일하게 수행된다. In addition, the method of constructing the feature data sets in N unit time for each patient is performed in the same manner as the method of acquiring the feature data set inputted to the septicemia detection model in order to calculate the possibility of occurrence of SIRS after a specific time.
또한, 컴퓨터는 과거에 패혈증으로 진단된 환자 중에서 SIRS 상태가 발생하였던 환자를 추출한 후, 해당 환자들의 의료데이터를 기반으로 특징데이터셋을 생성한다. SIRS조건을 만족하였던 환자 중에서 이후에 패혈증으로 진단된 환자의 의료데이터만으로 학습데이터를 생성하므로, 컴퓨터는 SIRS상태를 수반하는 패혈증 증상 예측을 위한 학습데이터를 구축할 수 있다.In addition, the computer extracts a patient who has experienced SIRS among patients diagnosed with sepsis in the past, and then generates a feature data set based on the medical data of the patients. Since the learning data is generated only from the medical data of the patient who has been diagnosed as sepsis after the SIRS condition, the computer can construct the learning data for predicting the sepsis symptom accompanied by the SIRS condition.
구체적으로, SIRS상태를 수반하는 패혈증을 조기진단하기 위한 패혈증감지모델의 트레이닝(학습)에 이용되는 학습데이터를 구축하는 과정의 일실시예는 다음과 같다. 먼저, 컴퓨터가 패혈증 진단이력이 존재하는 환자를 추출한다. 그 후, 컴퓨터가 패혈증 진단시점 이전에 SIRS 상태가 특정시간 이상 지속된 환자를 추출한다. 예를 들어, 컴퓨터는 5시간 동안 계속해서 SIRS상태가 지속되는 환자를 추출한다. 그 후, 도 3에서와 같이, 컴퓨터는 SIRS상태가 시작되는 최초시점을 타겟시점으로 추출한다. 그 후, 컴퓨터는 타겟시점으로부터 미리 정해진 예측간격시간(k개 단위시간, 예를 들어, 3시간) 이전의 N개 단위시간 내에서 특징데이터셋을 추출한다. 이 때, 특징데이터셋은 추출된 복수의 환자의 전자의무기록 내에 포함되어 있는 일반적인 의료데이터에 대한 대표값(예를 들어, 평균값, 최대값, 최소값 등)을 각 단위시간별로 산출하여 형성된다.Specifically, an embodiment of a process for constructing learning data used for training (learning) of a sepsis detection model for early diagnosis of sepsis accompanied by SIRS state is as follows. First, the computer extracts patients with a history of sepsis diagnosis. Thereafter, the computer extracts the patient whose SIRS state lasted for a certain time or longer before the time of the sepsis diagnosis. For example, the computer continuously extracts patients who continue to have SIRS status for 5 hours. Then, as shown in FIG. 3, the computer extracts the starting point at which the SIRS state starts, as the target point in time. Then, the computer extracts the feature data set within N unit time before the predetermined predicted interval time (k unit time, for example, 3 hours) from the target time. At this time, the feature data set is formed by calculating representative values (for example, an average value, a maximum value, a minimum value, and the like) for general medical data included in the electronic medical record of a plurality of extracted patients by each unit time.
학습데이터를 트레이닝하는 패혈증감지모델은 다양한 딥러닝 알고리즘이 적용될 수 있다. 일실시예로, 상기 패혈증감지모델은, DFN(Deep Feedforward Network) 또는 LSTM(Long Short-term Memory) 알고리즘을 이용할 수 있다.A variety of deep-running algorithms can be applied to the sepsis detection model that trains the training data. In one embodiment, the septicemia sensing model may utilize Deep Feedforward Network (DFN) or Long Short-Term Memory (LSTM) algorithms.
일반적인 DFN은 입력층(input layer)과 하나 이상의 숨겨진 층(hidden layer), 그리고 출력층(output layer)로 구성되는 네트워크 구조를 가지고 있다. 데이터는 입력층의 뉴런(neuron)으로 들어와 출력층 에 도달할 때까지 연결된 에지(edge)들의 가중치와 이전 노드에서 전달된 값들의 합 및 함수들의 계산을 통해 최종값을 계산하고, 목표변수값과의 비교를 통해 이들간 차이를 최소화하는 방향으로 학습을 진행한다. A typical DFN has a network structure consisting of an input layer, one or more hidden layers, and an output layer. The data is input to the neuron of the input layer and calculated final values by calculating the weights of the connected edges and the sum of the values delivered from the previous node and functions until reaching the output layer, Through the comparison, learning proceeds in the direction of minimizing the difference between them.
LSTM은 딥러닝의 여러 기법 중 시계열 데이터에 대해 시간적인 변동성을 반영해주는 RNN(Recurrent Neural Network)의 방법론 중 하나로, 일반적인 RNN에서 깊은 네트워크상에서의 학습 장애에 대한 문제(예: Vanishing Gradient)를 해결하기 위한 대안으로 제시되었으며 여러 연구개발 분야에서 활용되고 있다. RNN은 시간적 변화 내에서 패턴을 학습해내기에 유리하므로, 시간흐름에 따라 데이터가 연속적으로 획득되는 생체데이터 분석에 유용하다. 따라서, 학습데이터를 분석하기 위한 패혈증감지모델은 LSTM 적용 시에 더 높은 정확도를 제공할 수 있다.LSTM is one of the recurrent neural network (RNN) methodologies that reflect temporal variability in time series data among several techniques of deep learning. It solves the problem of learning disability on deep network (eg Vanishing Gradient) in general RNN And is used in various research and development fields. The RNN is advantageous for learning patterns within a temporal change, and thus is useful for analyzing biomedical data in which data is acquired continuously over time. Thus, the sepsis detection model for analyzing learning data can provide higher accuracy when applying LSTM.
컴퓨터가 특정한 예측시점의 패혈증 발생 예측결과를 제공한다(S600). 상기 예측시점은 상기 기준시점으로부터 k개의 단위시간 간격만큼 경과된 시점이다. 즉, 예측시점은 기준시점(예를 들어, 현재시점)으로부터 학습데이터 내에서 특징데이터셋을 획득하는 N개 단위시간과 타겟시점 사이의 시간간격만큼 경과된 시점이다. 컴퓨터는 패혈증감지모델을 통해 예측시점에 기 규정된 패혈증 발생양상 중 하나가 발생할 가능성을 산출한다. 즉, 상기 패혈증 발생 예측결과는 예측시점에 패혈증 발생의 전조상태 중 어느 하나가 발생되는지 여부를 말한다.The computer provides a prediction result of occurrence of sepsis at a specific predicted time point (S600). The prediction time is a time point that has elapsed by k unit time intervals from the reference time point. That is, the prediction time is a time point that has elapsed by a time interval between the N unit time and the target time for acquiring the feature data set in the learning data from the reference time point (for example, the current time point). The computer uses the septicemia detection model to calculate the likelihood that one of the defined sepsis incidence patterns will occur at the time of the prediction. That is, the prediction result of the sepsis occurrence indicates whether any one of the precondition of the occurrence of the sepsis occurs at the predicted time.
일실시예로, 기 규정된 패혈증 발생양상이 SIRS상태의 발생인 경우, 패혈증감지모델이 학습데이터 내의 SIRS상태가 시작된 타겟시점과 타겟시점으로부터 k개 단위시간 이전까지 획득된 N개 단위시간 내의 특징데이터셋를 학습하여, 현재시점 이전의 N개 단위시간 내의 특징데이터셋을 이용하여 k개 단위시간이 경과된 예측시점의 패혈증 발생 예측결과를 산출한다. 이 때, 상기 패혈증 발생 예측결과는 예측시점에 패혈증 발생의 전조상태인 SIRS상태가 시작될지 여부를 말한다.In one embodiment, when the specified sepsis occurrence pattern is the occurrence of the SIRS state, the sepsis detection model detects the target time at which the SIRS state in the learning data starts and the characteristic in the N unit time obtained before k unit time from the target time The data set is learned, and a prediction result of a sepsis occurrence at a prediction time when k unit times has elapsed is calculated by using the feature data set within N unit time before the present point in time. At this time, the predicted sepsis occurrence result indicates whether the SIRS state, which is a precursor state of the occurrence of sepsis, starts at the predicted time.
또한, 다른 일실시예로, 상기 패혈증 발생예측결과 제공단계(S600)는, 특정한 환자에게 대해 단위시간이 경과할 때마다 변경된 N개의 특징데이터셋으로 패혈증 발생 가능성을 산출한다.According to another embodiment, the step of providing the sepsis occurrence prediction result (S600) may calculate the possibility of sepsis by using N feature data sets changed every unit time for a specific patient.
이상에서 전술한 본 발명의 일 실시예에 따른 딥러닝 기반의 패혈증 조기 감지 방법은, 하드웨어인 컴퓨터와 결합되어 실행되기 위해 프로그램(또는 어플리케이션)으로 구현되어 매체에 저장될 수 있다.As described above, the deep-learning-based septicemia early detection method according to an embodiment of the present invention may be implemented as a program (or an application) to be executed in combination with a hardware computer and stored in a medium.
상기 전술한 프로그램은, 상기 컴퓨터가 프로그램을 읽어 들여 프로그램으로 구현된 상기 방법들을 실행시키기 위하여, 상기 컴퓨터의 프로세서(CPU)가 상기 컴퓨터의 장치 인터페이스를 통해 읽힐 수 있는 C, C++, JAVA, 기계어 등의 컴퓨터 언어로 코드화된 코드(Code)를 포함할 수 있다. 이러한 코드는 상기 방법들을 실행하는 필요한 기능들을 정의한 함수 등과 관련된 기능적인 코드(Functional Code)를 포함할 수 있고, 상기 기능들을 상기 컴퓨터의 프로세서가 소정의 절차대로 실행시키는데 필요한 실행 절차 관련 제어 코드를 포함할 수 있다. 또한, 이러한 코드는 상기 기능들을 상기 컴퓨터의 프로세서가 실행시키는데 필요한 추가 정보나 미디어가 상기 컴퓨터의 내부 또는 외부 메모리의 어느 위치(주소 번지)에서 참조되어야 하는지에 대한 메모리 참조관련 코드를 더 포함할 수 있다. 또한, 상기 컴퓨터의 프로세서가 상기 기능들을 실행시키기 위하여 원격(Remote)에 있는 어떠한 다른 컴퓨터나 서버 등과 통신이 필요한 경우, 코드는 상기 컴퓨터의 통신 모듈을 이용하여 원격에 있는 어떠한 다른 컴퓨터나 서버 등과 어떻게 통신해야 하는지, 통신 시 어떠한 정보나 미디어를 송수신해야 하는지 등에 대한 통신 관련 코드를 더 포함할 수 있다. The above-described program may be stored in a computer-readable medium such as C, C ++, JAVA, machine language, or the like that can be read by the processor (CPU) of the computer through the device interface of the computer, And may include a code encoded in a computer language of the computer. Such code may include a functional code related to a function or the like that defines necessary functions for executing the above methods, and includes a control code related to an execution procedure necessary for the processor of the computer to execute the functions in a predetermined procedure can do. Further, such code may further include memory reference related code as to whether the additional information or media needed to cause the processor of the computer to execute the functions should be referred to at any location (address) of the internal or external memory of the computer have. Also, when the processor of the computer needs to communicate with any other computer or server that is remote to execute the functions, the code may be communicated to any other computer or server remotely using the communication module of the computer A communication-related code for determining whether to communicate, what information or media should be transmitted or received during communication, and the like.
상기 저장되는 매체는, 레지스터, 캐쉬, 메모리 등과 같이 짧은 순간 동안 데이터를 저장하는 매체가 아니라 반영구적으로 데이터를 저장하며, 기기에 의해 판독(reading)이 가능한 매체를 의미한다. 구체적으로는, 상기 저장되는 매체의 예로는 ROM, RAM, CD-ROM, 자기 테이프, 플로피디스크, 광 데이터 저장장치 등이 있지만, 이에 제한되지 않는다. 즉, 상기 프로그램은 상기 컴퓨터가 접속할 수 있는 다양한 서버 상의 다양한 기록매체 또는 사용자의 상기 컴퓨터상의 다양한 기록매체에 저장될 수 있다. 또한, 상기 매체는 네트워크로 연결된 컴퓨터 시스템에 분산되어, 분산방식으로 컴퓨터가 읽을 수 있는 코드가 저장될 수 있다.The medium to be stored is not a medium for storing data for a short time such as a register, a cache, a memory, etc., but means a medium that semi-permanently stores data and is capable of being read by a device. Specifically, examples of the medium to be stored include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like, but are not limited thereto. That is, the program may be stored in various recording media on various servers to which the computer can access, or on various recording media on the user's computer. In addition, the medium may be distributed to a network-connected computer system so that computer-readable codes may be stored in a distributed manner.
상기와 같은 본 발명에 따르면, 아래와 같은 다양한 효과들을 가진다.According to the present invention as described above, the following various effects are obtained.
첫째, 학습된 패혈증감지모델이 기본특징데이터를 기반으로 최적으로 특징데이터(Feature)를 산출하므로, 사용자가 예측에 유리한 특징(즉, Referece Feature)을 생성하는 과정을 수행하지 않아도 된다.First, since the learned septicemia sensing model optimally generates feature data based on the basic feature data, the user does not have to perform a process of generating a feature (i.e., a Referece Feature) advantageous to prediction.
둘째, 기존의 회귀모델에 비해 패혈증 발생을 조기에 정확하게 예측할 수 있다. 예를 들어, 패혈증 발생 전의 전조증상 중 하나인 전신성 염증 반응 증후군(systemic inflammatory response syndrome; SIRS)이 발생되는 초기시점을 정확하게 예측하여 환자의 패혈증 진행을 대비할 수 있다.Second, the occurrence of sepsis can be predicted early and accurately compared with the existing regression model. For example, it is possible to predict the onset of systemic inflammatory response syndrome (SIRS), which is one of the pre-symptom symptoms prior to the occurrence of sepsis, and to prepare for the progression of the patient's sepsis.
셋째, 환자로부터 패혈증 조기감지를 위한 별도의 의료데이터를 획득할 필요없이 일반적으로 중환자실(ICU)에서 획득되어 전자의무기록(EMR)에 기록되는 데이터만으로 패혈증을 조기에 예측할 수 있다. 따라서, 병원에서 별도의 장치를 사용하지 않고 컴퓨터를 이용하여 패혈증 조기 감지를 수행할 수 있다.Thirdly, it is possible to predict sepsis early by only the data acquired in the ICU and recorded in the electronic medical record (EMR), without having to obtain separate medical data for early detection of sepsis from the patient. Therefore, early detection of septicemia can be performed using a computer without using a separate device in a hospital.
넷째, 전자의무기록에 기록되는 데이터를 바로 패혈증감지모델에 적용하여 실시간으로 특정시간 이후의 SIRS 발생가능성을 예측할 수 있다.Fourth, data recorded in electronic medical records can be directly applied to a septicemia detection model to predict the possibility of SIRS occurrence after a specific time in real time.
이상, 첨부된 도면을 참조로 하여 본 발명의 실시예를 설명하였지만, 본 발명이 속하는 기술분야의 통상의 기술자는 본 발명이 그 기술적 사상이나 필수적인 특징을 변경하지 않고서 다른 구체적인 형태로 실시될 수 있다는 것을 이해할 수 있을 것이다. 그러므로, 이상에서 기술한 실시예들은 모든 면에서 예시적인 것이며, 제한적이 아닌 것으로 이해해야만 한다.While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, You will understand. Therefore, it should be understood that the above-described embodiments are illustrative in all aspects and not restrictive.
Claims (11)
- 컴퓨터가 기준시점 이전의 N개 단위시간 내에서 특징데이터셋을 획득하는 단계;The computer acquiring the feature data set within N unit time prior to the reference time point;컴퓨터가 상기 특징데이터셋을 패혈증감지모델에 입력하는 단계; 및Inputting the feature data set to a sepsis detection model by a computer; And컴퓨터가 특정한 예측시점의 패혈증 발생 예측결과를 제공하는 단계;를 포함하되,The computer providing a prediction result of a sepsis occurrence at a specific predicted time point,상기 패혈증감지모델은 딥러닝을 기반으로 학습데이터를 학습하여 생성된 것이며,The septicemia detection model is generated by learning learning data based on deep learning,상기 예측시점은 상기 기준시점으로부터 k개(k는 특정한 자연수)의 단위시간 간격만큼 경과된 시점이며,The prediction time point is a time point that has elapsed from the reference point by k unit time intervals (k is a specific natural number)상기 패혈증 발생 예측결과는 상기 예측시점에 패혈증 발생양상이 초기 발생되는지에 대한 결과이며,The result of predicting the occurrence of sepsis is a result of whether or not the occurrence of the sepsis occurs at the predicted time,상기 특징데이터셋은 전자의무기록에 저장되는 의료데이터를 기반으로 산출되는 것인, 딥러닝 기반의 패혈증 조기 감지 방법.Wherein the feature data set is computed based on medical data stored in an electronic medical record.
- 제1항에 있어서,The method according to claim 1,컴퓨터가 상기 패혈증감지모델을 통해 기본특징데이터만으로 하나 이상의 의료데이터에 대한 각 기본특징데이터 간의 상관관계를 산출하는 단계;를 더 포함하고,Further comprising the step of the computer calculating a correlation between each basic characteristic data for one or more medical data by only the basic characteristic data through the sepsis detection model,상기 기본특징데이터는,Wherein the basic feature data comprises:상기 전자의무기록에 기록되는 상기 하나 이상의 의료데이터에 대해 하나 이상의 대표값을 추출하여 형성된 것인, 딥러닝 기반의 패혈증 조기 감지 방법.Wherein at least one representative value is extracted from the at least one medical data recorded in the electronic medical record.
- 제1항에 있어서, The method according to claim 1,상기 학습데이터는, The learning data includes:복수의 패혈증 환자에 대해 타겟시점과 상기 타겟시점으로부터 특정시간 이전의 N개 단위시간 내 특징데이터셋를 포함하고,And a feature data set in N time units before a specific time from the target time point for a plurality of sepsis patients,상기 타겟시점은 패혈증 환자에게 패혈증 발생양상이 최초 확인된 시점이고,The target time point is a point in time when a sepsis occurrence pattern is first confirmed in a sepsis patient,상기 패혈증감지모델은,In the sepsis detection model,상기 학습데이터 내의 N개 단위시간 내 특징데이터셋과 k개의 단위시간 경과 후의 패혈증발생결과를 매칭하여 딥러닝 알고리즘에 적용하여 생성되는 것인, 딥러닝 기반의 패혈증 조기 감지 방법.Wherein the feature data sets in N time units in the learning data are generated by applying the feature data sets to the deep learning algorithm by matching k pieces of septicemia occurrence results after k unit time elapses.
- 제3항에 있어서, The method of claim 3,상기 패혈증 발생양상이 최초 확인된 시점은,When the appearance of the sepsis was first confirmed,기준시간 이상으로 전신성 염증 반응 증후군이 지속될 때의 초기 시점인, 딥러닝 기반의 패혈증 조기 감지 방법.An early detection method for sepsis based on deep running, which is the earliest time when the systemic inflammatory response syndrome persists beyond the reference time.
- 제1항에 있어서, The method according to claim 1,상기 특징데이터셋 획득단계는,The feature data set acquiring step includes:수축기혈압, 맥압, 심박수, 체온, 호흡수, 백혈구수치, 수소이온지수, 혈중 산소 농도 중 적어도 하나에 대해 하나 이상의 대표값을 추출하는 것을 특징으로 하는, 딥러닝 기반의 패혈증 조기 감지 방법.Wherein at least one representative value is extracted for at least one of systolic blood pressure, pulse pressure, heart rate, body temperature, respiratory rate, white blood cell count, hydrogen ion index, and blood oxygen concentration.
- 제1항에 있어서, The method according to claim 1,상기 단위시간은,The unit time may be,상기 전자의무기록 상에 특정한 제1의료데이터를 기록하는 시간간격 또는 상기 시간간격의 정수배 중 어느 하나인, 딥러닝 기반의 패혈증 조기 감지 방법.Wherein the electronic medical record is one of a time interval for recording specific first medical data on the electronic medical record or an integral multiple of the time interval.
- 제6항에 있어서, The method according to claim 6,상기 특징데이터셋 획득단계는,The feature data set acquiring step includes:특정한 제2의료데이터가 상기 단위시간보다 긴 시간 간격으로 획득되는 경우, 연속되는 제2의료데이터값 중 적어도 하나를 이용하여 산출하는 것을 특징으로 하는, 딥러닝 기반의 패혈증 조기 감지 방법.Wherein when the specific second medical data is acquired at a time interval longer than the unit time, the calculation is performed using at least one of successive second medical data values.
- 제6항에 있어서, The method according to claim 6,상기 의료데이터가 복수개인 경우,When there are a plurality of medical data,각각의 측정주기마다 측정된 각 의료데이터가 상기 제1의료데이터에 의한 기준 시점의 단위시간을 포함하지 않는 경우에는, When each medical data measured for each measurement period does not include a unit time at a reference time point by the first medical data,컴퓨터는 상기 각 의료데이터 중에서 상기 제1의료데이터의 기준 시점의 단위 시간과 인접한 시점의 단위 시간에서 측정된 값을 내삽 또는 보간하여 특징데이터를 구축하는 것을 특징으로 하고, Wherein the computer constructs the characteristic data by interpolating or interpolating a value measured at a unit time at a point adjacent to the reference time point of the first medical data among the medical data,상기 인접한 시점의 단위 시간은,The unit time of the adjacent time point상기 제1의료데이터의 기준 시점의 단위 시간으로부터 가장 인접한 시점의 단위 시간을 포함하여, 상기 기준 시점의 단위 시간과 가장 가까운 순서대로 인접한 시점의 단위 시간으로서, 미리 정해진 개수의 단위 시간을 포함하는,Wherein the unit time of the first time point is a unit time of a time point adjacent to the time point of the reference time point including the unit time of the nearest time point from the unit time of the reference time point of the first medical data,딥러닝 기반의 패혈증 조기 감지 방법. Deep learning based early detection of sepsis.
- 제1항에 있어서, The method according to claim 1,상기 패혈증감지모델은,In the sepsis detection model,LSTM(Long Short-term Memory) 알고리즘을 이용하는 것인, 딥러닝 기반의 패혈증 조기 감지 방법.Using a long-short-term memory (LSTM) algorithm.
- 제1항에 있어서, The method according to claim 1,상기 패혈증 발생예측결과 제공단계는,Wherein the step of providing the sepsis occurrence prediction result comprises:특정한 환자에 대해 단위시간이 경과할 때마다 변경된 N개의 특징데이터셋으로 패혈증 발생 예측을 수행하는, 딥러닝 기반의 패혈증 조기 감지 방법.A method for early detection of sepsis based on deep running, the method comprising: predicting occurrence of sepsis with N feature data sets changed every unit time for a particular patient.
- 하드웨어인 컴퓨터와 결합되어, 제1항 내지 제10항 중 어느 한 항의 방법을 실행시키기 위하여 매체에 저장된, 딥러닝 기반의 패혈증 조기 감지프로그램.10. A deep-run-based septicemia early detection program stored in a medium for performing the method of any one of claims 1 to 10 in combination with a computer which is hardware.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020170103448A KR101886374B1 (en) | 2017-08-16 | 2017-08-16 | Method and program for early detection of sepsis with deep neural networks |
KR10-2017-0103448 | 2017-08-16 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019035639A1 true WO2019035639A1 (en) | 2019-02-21 |
Family
ID=63252052
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2018/009338 WO2019035639A1 (en) | 2017-08-16 | 2018-08-14 | Deep learning-based septicemia early detection method and program |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR101886374B1 (en) |
WO (1) | WO2019035639A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110123274A (en) * | 2019-04-29 | 2019-08-16 | 上海电气集团股份有限公司 | A kind of monitoring system of septicopyemia |
CN110123277A (en) * | 2019-05-17 | 2019-08-16 | 上海电气集团股份有限公司 | A kind of data processing system of septicopyemia |
CN113017572A (en) * | 2021-03-17 | 2021-06-25 | 上海交通大学医学院附属瑞金医院 | Severe warning method and device, electronic equipment and storage medium |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102446376B1 (en) * | 2018-10-10 | 2022-09-22 | 연세대학교 산학협력단 | Method for predicting of mortality risk or sepsis risk and device for predicting of mortality risk or sepsis risk using the same |
KR102049824B1 (en) * | 2018-11-15 | 2019-11-28 | 주식회사 뷰노 | Method for generating prediction results for prediction of specific symptoms of a subject and apparatus using the same |
CN111374639A (en) * | 2018-12-28 | 2020-07-07 | 陈柏龄 | Septicemia strain prediction system and method |
KR102238762B1 (en) | 2019-01-31 | 2021-04-16 | 주식회사 이노제닉스 | Image recognition system for diagnosis sepsis by reading the result of reverse blot hybridization assay and image recognition method using the same |
CN113822420B (en) * | 2021-09-27 | 2024-04-19 | 中国航天科工集团七三一医院 | Dead space fraction model building method and system based on volumetric carbon dioxide diagram |
CN115050451B (en) * | 2022-08-17 | 2022-11-04 | 合肥工业大学 | Automatic generation system for clinical sepsis medication scheme |
KR102623020B1 (en) * | 2023-09-11 | 2024-01-10 | 주식회사 슈파스 | Method, computing device and computer program for early predicting septic shock through bio-data analysis based on artificial intelligence |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140141534A (en) * | 2013-05-31 | 2014-12-10 | 가톨릭대학교 산학협력단 | Method and system for predicting sepsis risk |
KR20150113700A (en) * | 2014-03-31 | 2015-10-08 | 삼성전자주식회사 | System and method for diagnosis |
KR20160096460A (en) * | 2015-02-05 | 2016-08-16 | 삼성전자주식회사 | Recognition system based on deep learning including a plurality of classfier and control method thereof |
KR20170023770A (en) * | 2014-06-25 | 2017-03-06 | 삼성전자주식회사 | Diagnosis model generation system and method |
KR20170053693A (en) * | 2014-09-09 | 2017-05-16 | 레이도스 이노베이션즈 테크놀로지 인크. | Method and apparatus for disease detection |
-
2017
- 2017-08-16 KR KR1020170103448A patent/KR101886374B1/en active IP Right Review Request
-
2018
- 2018-08-14 WO PCT/KR2018/009338 patent/WO2019035639A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140141534A (en) * | 2013-05-31 | 2014-12-10 | 가톨릭대학교 산학협력단 | Method and system for predicting sepsis risk |
KR20150113700A (en) * | 2014-03-31 | 2015-10-08 | 삼성전자주식회사 | System and method for diagnosis |
KR20170023770A (en) * | 2014-06-25 | 2017-03-06 | 삼성전자주식회사 | Diagnosis model generation system and method |
KR20170053693A (en) * | 2014-09-09 | 2017-05-16 | 레이도스 이노베이션즈 테크놀로지 인크. | Method and apparatus for disease detection |
KR20160096460A (en) * | 2015-02-05 | 2016-08-16 | 삼성전자주식회사 | Recognition system based on deep learning including a plurality of classfier and control method thereof |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110123274A (en) * | 2019-04-29 | 2019-08-16 | 上海电气集团股份有限公司 | A kind of monitoring system of septicopyemia |
CN110123277A (en) * | 2019-05-17 | 2019-08-16 | 上海电气集团股份有限公司 | A kind of data processing system of septicopyemia |
CN113017572A (en) * | 2021-03-17 | 2021-06-25 | 上海交通大学医学院附属瑞金医院 | Severe warning method and device, electronic equipment and storage medium |
CN113017572B (en) * | 2021-03-17 | 2023-11-28 | 上海交通大学医学院附属瑞金医院 | Severe early warning method, apparatus, electronic device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
KR101886374B1 (en) | 2018-08-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019035639A1 (en) | Deep learning-based septicemia early detection method and program | |
Martinez-Velazquez et al. | Cardio Twin: A Digital Twin of the human heart running on the edge | |
WO2015199258A1 (en) | Diagnosis model generation system and method | |
WO2019031794A1 (en) | Method for generating prediction result for predicting occurrence of fatal symptoms of subject in advance and device using same | |
CN115769302A (en) | Epidemic disease monitoring system | |
WO2022119155A1 (en) | Apparatus and method for diagnosing explainable multiple electrocardiogram arrhythmias | |
WO2021040373A1 (en) | Complex stress index-based stress management method | |
WO2019054553A1 (en) | System and computer program for predicting hyperthyroidism by using wearable device | |
CN113990482A (en) | Health data processing system and method | |
Chen et al. | Edge2Analysis: a novel AIoT platform for atrial fibrillation recognition and detection | |
CN115778403B (en) | Electrocardiogram analysis method, apparatus, electronic device, and storage medium | |
WO2022114791A1 (en) | Big data-based disease risk prediction system, prediction method, and program | |
CN110755047B (en) | Cardiovascular and cerebrovascular disease prevention method, device, terminal and storage medium | |
WO2024128720A1 (en) | Method and device for calculating blood pressure level using feature value of photoplethysmogram | |
WO2021010734A1 (en) | Medical examination result sheet generation system | |
Oei et al. | Towards early sepsis detection from measurements at the general ward through deep learning | |
WO2023038254A1 (en) | Method and apparatus for non-invasive estimation of glycated hemoglobin or blood glucose by using machine learning | |
Kalogiannis et al. | Geriatric group analysis by clustering non-linearly embedded multi-sensor data | |
CN116798604A (en) | Heating respiratory syndrome monitoring and early warning method and system based on multi-source data | |
WO2018097541A1 (en) | Apparatus and method for determining circulatory disease potential | |
WO2013055184A1 (en) | Method of calculating xml-based well-being framework and well-being index | |
CN113017572A (en) | Severe warning method and device, electronic equipment and storage medium | |
WO2022196944A1 (en) | Method and device for predicting recurrence of early seizure | |
WO2016024717A1 (en) | Personalized blood glucose management method using hypoglycemia numerical value | |
WO2023287118A1 (en) | Method, system, and non-transitory computer-readable recording medium for managing output data of analysis model for bio-signal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18846720 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18846720 Country of ref document: EP Kind code of ref document: A1 |