CN114566282A - Treatment decision system based on echocardiogram detection report - Google Patents
Treatment decision system based on echocardiogram detection report Download PDFInfo
- Publication number
- CN114566282A CN114566282A CN202210232472.4A CN202210232472A CN114566282A CN 114566282 A CN114566282 A CN 114566282A CN 202210232472 A CN202210232472 A CN 202210232472A CN 114566282 A CN114566282 A CN 114566282A
- Authority
- CN
- China
- Prior art keywords
- analysis
- patient
- disease
- coefficient
- grade
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of cardiogram detection and analysis, which is used for solving the problem that the existing echocardiogram treatment decision-making system can not match the disease development trend of a patient according to the treatment rehabilitation progress of the disease of the patient, in particular to a treatment decision-making system based on an echocardiogram detection report, which comprises a treatment platform, wherein the treatment platform is in communication connection with a report analysis module, a trend analysis module, a treatment recommendation module and a comprehensive analysis module, the report analysis module is used for analyzing the disease of the patient through echocardiogram detection data to obtain the disease coefficient of the patient, the trend analysis module is used for analyzing the disease trend of the patient and screening to obtain a matching object, and the trend analysis module is used for performing matching analysis on the matching object to obtain a trend object; the invention analyzes and grades the diagnosis result of the patient by combining the report analysis module with the cardiogram detection report, and timely makes a response scheme through the treatment curve of the trend object to prevent the disease from deteriorating.
Description
Technical Field
The invention relates to the technical field of cardiogram detection and analysis, in particular to a treatment decision system based on an echocardiogram detection report.
Background
The echocardiogram is that the ultrasonic wave is transmitted through the chest wall and soft tissues to measure the periodic activities of the structures such as the heart wall, the ventricle and the valve under the ultrasonic wave by applying the ultrasonic short-wave distance measurement principle, the relationship curve between the corresponding activities of the structures and the time is displayed on a display, and the curves are recorded by a recorder, namely the echocardiogram;
the existing echocardiogram can analyze the disease according to the image detection result, but does not have the function of recommending the disease treatment trend and the treatment scheme by combining the historical detection result, so the existing echocardiogram treatment decision-making system can not match the disease development trend of the patient according to the treatment rehabilitation progress of the disease of the patient, and provides the most appropriate treatment scheme for the patient;
a solution is now proposed to address the technical drawback in this respect.
Disclosure of Invention
The invention aims to provide a treatment decision system based on an echocardiogram detection report, aiming at solving the problem that the existing echocardiogram treatment decision system can not match the disease development trend of a patient according to the treatment rehabilitation progress of the disease of the patient.
The purpose of the invention can be realized by the following technical scheme:
a treatment decision system based on an echocardiogram detection report comprises a treatment platform, wherein the treatment platform is in communication connection with a report analysis module, a trend analysis module, a treatment recommendation module and a comprehensive analysis module;
the report analysis module is used for analyzing the disease of the patient through echocardiogram detection data to obtain a disease coefficient of the patient, and the echocardiogram detection data comprises a pulmonary artery inner diameter, a left ventricle inner diameter and a right ventricle inner diameter;
the trend analysis module is used for carrying out disease condition trend analysis on the patient and screening to obtain a matched object, and the trend analysis module carries out matching analysis on the matched object to obtain a trend object;
the treatment recommendation module is used for recommending a treatment scheme for the patient;
the comprehensive analysis module is used for comprehensively analyzing the treatment progress of the patient, and comprises a primary analysis unit, a secondary analysis unit and a tertiary analysis unit, and if the disease grade of an analysis object is tertiary, the analysis object is comprehensively analyzed by the tertiary analysis unit; if the disease grade of the analysis object is second grade, a second-grade analysis unit is adopted to carry out comprehensive analysis on the analysis object; and if the disease grade of the analysis object is second grade, performing comprehensive analysis on the analysis object by using a second-grade analysis unit.
As a preferred embodiment of the invention, the pulmonary artery inner diameter, the left ventricle inner diameter and the right ventricle inner diameter of the patient are acquired through an echocardiogram detection report and are respectively marked as FD, ZS and YS, and if the requirements that FD is more than or equal to 12 and less than or equal to 26, ZS is more than 35 and less than 50 and YS is more than 7 and less than 23 are met, the cardiogram detection result of the patient is judged to be normal; if not, performing deep analysis on the disease of the patient;
the depth analysis process comprises the following steps: and calculating the inner diameter of the pulmonary artery, the inner diameter of the left chamber and the inner diameter of the right chamber to obtain a patient coefficient BH, comparing the patient coefficient BH with patient thresholds BHmin and BHmax, and judging the patient grade of the patient according to the comparison result of the patient coefficient and the patient thresholds.
As a preferred embodiment of the present invention, the comparing process of the patient coefficient and the patient threshold value comprises: if BH is less than or equal to BHmin, judging the patient grade of the patient to be three-level, and sending a three-level patient signal to the treatment platform by the report analysis module;
if BHmin is less than BH and less than BHmax, the patient grade of the patient is judged to be second grade, and a report analysis module sends a second grade patient signal to a treatment platform;
if the BH is larger than or equal to the BHmax, the patient grade of the patient is judged to be the first grade, and a report analysis module sends a first-grade patient signal to a treatment platform.
As a preferred embodiment of the present invention, the acquisition process of the matching object includes: marking the patient subjected to disease condition trend analysis as an analysis object, acquiring the disease grade of the analysis object, acquiring the gender and the age of the analysis object if the disease grade of the analysis object is second grade, and marking all patients with disease grades, which are the same as the gender and have the age difference of three years, as second grade as reference objects; the time of the disease level of the reference object from the third level to the second level is obtained and marked as JSc, the time of the disease level of the analysis object from the third level to the second level is marked as JSf, the evolutionary matching value JSp of the reference object is obtained through the formula JHp ═ JSc-JSf ═ and ten reference objects with the minimum evolutionary matching value JSp are marked as matching objects.
As a preferred embodiment of the present invention, the specific process of performing matching analysis on the matching object by the trend analysis model includes: acquiring a history detection report of the matching object for performing the cardiogram detection, marking the history disease coefficient of the matching object as PHt, wherein t is 1, 2, …, m, m is the frequency of performing the cardiogram detection on the matching object, acquiring the history detection report of performing the cardiogram detection on the analysis object, marking the history disease coefficient of the analysis object as FHq, q is 1, 2, …, u, u is the frequency of performing the cardiogram detection on the analysis object, comparing m with u, deleting m-u disease coefficients in PHt randomly if m is more than u, marking the deleted PHt as PHq, and calculating FHq and PHq to obtain a deviation coefficient PS of the matching object; if u is larger than m, randomly deleting u-m patient coefficients in FHq, marking FHq after deletion as FHt, and calculating FHt and PHt to obtain a deviation coefficient PS of the matched object;
and marking the matched object with the minimum deviation coefficient PS value as a trend object, and sending the trend object to the treatment platform by the trend analysis module.
As a preferred embodiment of the present invention, the specific process of treatment protocol recommendation comprises: obtaining a historical patient coefficient PHt of a matched object for performing the cardiogram detection, marking the difference value between PHt +1 and PHt as a recovery value HZ, marking the number of the recovery values HZ with positive values as y, marking the number of the recovery values HZ with negative values as v, marking the ratio of the y to the v as a recovery ratio HB, marking the patient coefficient of the matched object for performing the cardiogram detection for the last time as BHz, and calculating BHz and the recovery ratio HB to obtain a recovery coefficient HX of the matched object; marking the matching object with the maximum recovery coefficient HX value as a recommended object, acquiring the treatment data of the recommended object and sending the treatment data of the recommended object to a treatment platform; the treatment data of the recommended subject includes a treating physician, a treatment plan, a time of first diagnosis, and a history disease coefficient of the recommended subject.
As a preferred embodiment of the present invention, the process of performing the comprehensive analysis on the analysis object by the tertiary analysis unit includes: the time difference between the first diagnosis time of the analysis object and the current system time is obtained and marked as SC3, the average value of the historical patient coefficient of the analysis object is marked as BH3, the patient coefficient of the analysis object which is subjected to the cardiogram detection for the last time is marked as BX3, and the comprehensive coefficient ZH3 of the three-stage patient is obtained by calculating SC3, BH3 and BX 3.
As a preferred embodiment of the present invention, the specific process of the secondary analysis unit performing the comprehensive analysis on the analysis object includes: the method comprises the steps of marking time when a disease grade of an analysis object is evolved from three levels to two levels as deterioration time, obtaining time difference between first diagnosis time and deterioration time of the analysis object and marking as SC2, obtaining time difference between deterioration time of the analysis object and current system time and marking as EH2, obtaining average disease coefficient BH2 when the disease grade of the analysis object is three levels, obtaining average disease coefficient BE2 when the disease grade of the analysis object is two levels, marking the disease coefficient of the analysis object which is subjected to cardiogram detection for the last time as BX2, and calculating SC2, EH2, Bh2, BE2 and BX2 to obtain comprehensive coefficient ZH2 of the second-level disease.
As a preferred embodiment of the present invention, the specific process of the primary analysis module performing the comprehensive analysis on the analysis object includes: marking the time of the disease grade of an analysis object from the third grade to the second grade as deterioration time, acquiring the time difference between the first diagnosis time and the deterioration time of the analysis object and marking as SC1, marking the time of the disease grade of the analysis object from the second grade to the first grade as evolution time, acquiring the time difference between the deterioration time and the evolution time and marking as JH1, acquiring the time difference between the evolution time and the current system time and marking as XT1, acquiring the average disease coefficient of the analysis object when the disease grade is the third grade and marking as BH1, acquiring the average disease coefficient of the analysis object when the disease grade is the second grade and marking as BE1, acquiring the average disease coefficient of the analysis object when the disease coefficient is the first grade and marking as BY1, and acquiring the disease coefficient BX1 of the analysis object which carries out the latest cardiogram detection, the comprehensive coefficient ZH1 of the primary patients is obtained by calculating SC1, JH1, XT1, BH1, BE1 and BX 1.
In a preferred embodiment of the present invention, the method of operation of the treatment decision system comprises the steps of:
the method comprises the following steps: the report analysis module analyzes the disease of the patient through the cardiogram detection data to obtain a patient coefficient, and judges the patient grade of the patient according to the comparison result of the patient coefficient and the patient threshold value;
step two: the trend analysis module screens out a matched object for the analysis object according to the age, the sex and the disease grade, and performs matching analysis on the matched object through a trend analysis model to obtain a trend object;
step three: the treatment recommendation module obtains a recovery ratio according to the ratio of the number of positive values to the number of negative values of the recovery value, obtains a recovery coefficient through calculation of the recovery ratio, and marks the matching object with the maximum recovery coefficient value as a recommended object;
step four: comprehensive analysis is carried out on the treatment progress of the analyzed patient through a comprehensive analysis module to obtain comprehensive coefficients of the first-level patient, the second-level patient and the third-level patient, and the comprehensive coefficients of the analyzed object are sent to a treatment platform.
Compared with the prior art, the invention has the beneficial effects that:
1. the report analysis module is combined with the cardiogram detection report to analyze and grade the diagnosis result of the patient, the trend analysis module is combined with the treatment curves of other patients to perform trend analysis on the analysis object and screen the patient which is closest to the treatment curve of the analysis object to be used as a trend object, so that the treatment effect prediction is made on the analysis object according to the treatment effect of the trend object, and a response scheme is made in time through the treatment curve of the trend object to prevent the disease from deteriorating;
2. the treatment recommending module analyzes the treatment effect of the matched objects, obtains the patient with the best treatment effect in the matched objects by combining the historical cardiogram detection report and the patient coefficient curve screening and takes the patient as the recommended object, provides the most appropriate treatment scheme for the analyzed object by combining the treatment scheme and the treatment effect of the recommended object, simultaneously analyzes the treatment effect of the patients with different grades by combining the comprehensive analyzing module, and feeds back the screening accuracy of the recommended object through the treatment effect analysis to ensure that the optimized treatment scheme is obtained by screening the analyzed object.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is a schematic block diagram of a first embodiment of the present invention;
FIG. 2 is a flowchart of a method according to a second embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1, a treatment decision system based on echocardiogram detection reports includes a treatment platform, which is communicatively connected with a report analysis module, a trend analysis module, a treatment recommendation module, and a comprehensive analysis module;
the report analysis module is used for analyzing the disease of the patient through the echocardiography detection data, the echocardiography detection data comprises the internal diameter of the pulmonary artery, the internal diameter of the left ventricle and the internal diameter of the right ventricle, and the specific process of the disease analysis comprises the following steps: acquiring the inner diameter of the pulmonary artery, the inner diameter of the left ventricle and the inner diameter of the right ventricle of the patient through an echocardiogram detection report, respectively marking the inner diameters as FD, ZS and YS, and if the FD is more than or equal to 12 and less than or equal to 26, the ZS is more than 35 and less than 50 and the YS is more than 7 and less than 23, judging that the cardiogram detection result of the patient is normal; if not, carrying out deep analysis on the disease of the patient:
obtaining a disease coefficient BH by BH alpha 1 x FD-19 + alpha 2 x BOp-42.5 + alpha 3 x BOs-15, wherein alpha 1, alpha 2 and alpha 3 are all proportionality coefficients, and alpha 3 > alpha 2 > alpha 1 > 0; it should be noted that the patient coefficient is a value reflecting the severity of the disease condition of the patient, and the larger the value of the patient coefficient is, the more severe the disease condition of the corresponding patient is, the patient coefficient BH is compared with the patient thresholds BHmin and BHmax:
if BH is less than or equal to BHmin, judging the patient grade of the patient to be three-level, and sending a three-level patient signal to the treatment platform by the report analysis module;
if BHmin is less than BH and less than BHmax, the patient grade of the patient is judged to be second grade, and a report analysis module sends a second grade patient signal to a treatment platform;
if the BH is larger than or equal to the BHmax, the patient grade of the patient is judged to be the first grade, and a report analysis module sends a first-grade patient signal to a treatment platform.
The trend analysis module is used for analyzing the illness state trend of the patient, and the specific illness state trend analysis process comprises the following steps: marking the patient subjected to disease condition trend analysis as an analysis object, acquiring the disease grade of the analysis object, acquiring the sex and the age of the analysis object if the disease grade of the analysis object is second grade, marking all patients with the disease grade of second grade, which are the same as the sex and the age difference of the analysis object, as reference objects, wherein the reference objects are screened patients which are closest to the analysis object in the aspects of sex, age and the like, and the constitution of the reference objects is closest to the analysis object; acquiring time of a disease grade of a reference object from a third level to a second level and marking the time as JSc, acquiring time of the disease grade of an analysis object from the third level to the second level and marking the time as JSf, acquiring an evolution matching value JSp of the reference object by a formula JHp ═ JSc-JSf |, wherein the evolution matching value represents the proximity degree of the disease deterioration process of the reference object and the disease deterioration process of the analysis object, marking ten reference objects with the minimum evolution matching value JSp as matching objects, and sending the matching objects to a trend analysis model for matching analysis;
trend of theThe specific process of the analysis model for carrying out matching analysis on the matching object comprises the following steps: acquiring a historical detection report of a matched object for performing cardiogram detection, marking the historical disease coefficient of the matched object as PHt, wherein t is 1, 2, …, m is the number of times of the matched object for performing cardiogram detection, acquiring the historical detection report of the analyzed object for performing cardiogram detection, marking the historical disease coefficient of the analyzed object as FHq, q is 1, 2, …, u is the number of times of the analyzed object for performing cardiogram detection, comparing m with u, deleting m-u disease coefficients in PHt if m is more than u, marking PHt after deletion as PHq, and using a formula to detect the disease coefficients by using a formula
Obtaining a deviation coefficient PS of the matched object, matching the matched object with a historical disease coefficient of the analyzed object, and obtaining the deviation coefficient of the matched object through the matched disease coefficient, wherein the deviation coefficient represents the proximity degree of a treatment curve of the matched object and a treatment curve of the analyzed object; if u > m, u-m patient coefficients are randomly deleted in FHq, the deleted FHq is labeled FHt, and the formula is used
Obtaining a deviation coefficient PS of the matched object, matching the matched object with a historical disease coefficient of the analyzed object, and obtaining the deviation coefficient of the matched object through the matched disease coefficient, wherein the deviation coefficient represents the proximity degree of a treatment curve of the matched object and a treatment curve of the analyzed object; the matching object with the minimum deviation coefficient PS value is marked as a trend object, the treatment condition of the matching object with the minimum deviation coefficient PS value is closest to the analysis object, so that the treatment trend prediction is carried out on the analysis object according to the subsequent treatment condition of the trend object, and the trend analysis module sends the trend object to the treatment platform.
The treatment recommendation module is used for recommending a treatment scheme for the patient, and the specific treatment scheme recommendation process comprises the following steps: obtaining PHt historical patient coefficients of a matching object for performing cardiogram detection, marking the difference value between PHt +1 and PHt as a recovery value HZ, marking the number of the recovery values HZ with positive values as y, marking the number of the recovery values HZ with negative values as v, marking the ratio of the y to the v as a recovery ratio HB, marking the patient coefficient of the matching object for performing cardiogram detection for the last time as BHz, obtaining a recovery coefficient HX of the matching object by a formula HX (beta 1 × HB)/(beta 2 × BHz), wherein the recovery coefficient is a value reflecting the treatment effect of the matching object, the larger the recovery coefficient value is, the better the treatment effect of the corresponding matching object is, wherein beta 1 and beta 2 are both proportional coefficients, and beta 1 is more than beta 2; marking the matching object with the maximum recovery coefficient HX value as a recommended object, acquiring the treatment data of the recommended object and sending the treatment data of the recommended object to a treatment platform; the treatment data of the recommended object comprises a treating physician, a treatment scheme, the time of first diagnosis and a historical disease coefficient of the recommended object, and the most appropriate treatment scheme is formulated for the analysis object by combining the treatment data of the recommended object.
The comprehensive analysis module is used for comprehensively analyzing the treatment progress of the patient, the comprehensive analysis module comprises a primary analysis unit, a secondary analysis unit and a tertiary analysis unit, and the specific comprehensive analysis process comprises the following steps: acquiring the disease grade of an analysis object;
when the disease grade of the analysis object is three-level, the analysis object is comprehensively analyzed by adopting a three-level analysis unit: obtaining the time difference between the first time of diagnosis and the current system time of the analysis object and marking as SC3, marking the average value of the historical disease coefficient of the analysis object as BH3, marking the disease coefficient of the analysis object which carries out the cardiogram detection for the last time as BX3, and carrying out the detection according to the formula
Obtaining a comprehensive coefficient ZH3 of the third-level patient, wherein gamma 3 is a proportionality coefficient;
when the disease grade of the analysis object is two-grade, a two-grade analysis unit is adopted to comprehensively analyze the analysis object: marking the time of the disease grade of the analysis object from the third stage to the second stage as the deterioration time, acquiring the time difference between the first diagnosis time and the deterioration time of the analysis object and marking as SC2, acquiring the time difference between the deterioration time and the current system time of the analysis object and marking as EH2, and acquiring the analysis objectThe average disease coefficient BH2 when the disease level is the third level, the average disease coefficient BE2 when the disease level of the analysis object is the second level is obtained, the disease coefficient of the analysis object which carries out the cardiogram detection for the last time is marked as BX2, and the patient coefficient is obtained through a formula
Obtaining a comprehensive coefficient ZH2 of the second-level patient, wherein gamma 2 is a proportionality coefficient;
when the disease grade of the analysis object is first grade, a first-grade analysis module is adopted to carry out comprehensive analysis on the analysis object: marking the time of the disease grade of an analysis object from three-level evolution to two-level evolution as deterioration time, acquiring the time difference between the first diagnosis time and the deterioration time of the analysis object and marking the time difference as SC1, marking the time of the disease grade of the analysis object from two-level evolution to one-level evolution as evolution time, acquiring the time difference between the deterioration time and the evolution time and marking the time difference as JH1, acquiring the time difference between the evolution time and the current system time and marking the time difference as XT1, acquiring the average disease coefficient of the analysis object when the disease grade is three-level and marking the average disease coefficient as BH1, acquiring the average disease coefficient of the analysis object when the disease grade is two-level and marking the average disease coefficient as BE1, acquiring the average disease coefficient of the analysis object when the disease coefficient is one-level and marking the average disease coefficient as BY1, acquiring the disease coefficient BX1 of the analysis object which carries out the latest cardiogram detection through a formula, and adopting a formula
Obtaining a comprehensive coefficient ZH1 of a first-class patient, wherein gamma 1 is a proportionality coefficient;
and the comprehensive analysis module sends the comprehensive coefficients ZH1, ZH2 and ZH3 of the primary patient, the secondary patient and the tertiary patient obtained by analysis to a treatment platform.
Example two
Referring to fig. 2, a method for making a treatment decision based on echocardiogram detection report includes the following steps:
the method comprises the following steps: the report analysis module analyzes the disease of the patient through the cardiogram detection data to obtain a patient coefficient, and judges the patient grade of the patient according to the comparison result of the patient coefficient and the patient threshold value;
step two: the trend analysis module screens out a matched object for the analysis object according to the age, the sex and the disease grade, and performs matching analysis on the matched object through a trend analysis model to obtain a trend object;
step three: the treatment recommendation module obtains a recovery ratio according to the ratio of the number of positive values to the number of negative values of the recovery value, obtains a recovery coefficient through calculation of the recovery ratio, and marks the matching object with the maximum recovery coefficient value as a recommended object;
step four: comprehensive analysis is carried out on the treatment progress of the analyzed patient through a comprehensive analysis module to obtain comprehensive coefficients of the first-level patient, the second-level patient and the third-level patient, and the comprehensive coefficients of the analyzed object are sent to a treatment platform.
When the device is used, the report analysis module analyzes the disease of a patient through the cardiogram detection data and obtains a disease coefficient and a disease grade; the trend analysis module performs matching analysis on the matched object through a trend analysis model to obtain a trend object; the treatment recommendation module obtains a recovery ratio through the ratio of the positive value number to the negative value number of the recovery value, obtains a recovery coefficient through calculation of the recovery ratio, and marks the matching object with the maximum recovery coefficient value as a recommended object; comprehensive analysis is carried out on the treatment progress of the analyzed patient through a comprehensive analysis module to obtain comprehensive coefficients of the first-level, second-level and third-level patients.
The formulas are obtained by acquiring a large amount of data and performing software simulation, and the coefficients in the formulas are set by the technicians in the field according to actual conditions; such as: formula HX ═ β 1 × HB)/(β 2 × BHz; collecting multiple groups of sample data by technicians in the field and setting corresponding recovery coefficients for each group of sample data; substituting the set recovery coefficient and the acquired sample data into formulas, forming a linear equation set by any two formulas, screening the calculated coefficients and taking the mean value to obtain values of beta 1 and beta 2 which are respectively 2.54 and 1.23;
the coefficient is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is facilitated, and the coefficient is determined by the number of sample data and the corresponding recovery coefficient preliminarily set by a person skilled in the art for each group of sample data; it is sufficient if the proportional relationship between the parameters and the quantized values is not affected, for example, the recovery coefficient is proportional to the recovery ratio.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand the invention for and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (10)
1. A treatment decision system based on an echocardiogram detection report is characterized by comprising a treatment platform, wherein the treatment platform is in communication connection with a report analysis module, a trend analysis module, a treatment recommendation module and a comprehensive analysis module;
the report analysis module is used for analyzing the disease of the patient through echocardiogram detection data to obtain a disease coefficient of the patient, and the echocardiogram detection data comprises a pulmonary artery inner diameter, a left ventricle inner diameter and a right ventricle inner diameter;
the trend analysis module is used for carrying out disease condition trend analysis on the patient and screening to obtain a matched object, and the trend analysis module carries out matching analysis on the matched object to obtain a trend object;
the treatment recommendation module is used for recommending a treatment scheme for the patient;
the comprehensive analysis module is used for comprehensively analyzing the treatment progress of the patient, and comprises a primary analysis unit, a secondary analysis unit and a tertiary analysis unit, and if the disease grade of an analysis object is tertiary, the analysis object is comprehensively analyzed by the tertiary analysis unit; if the disease grade of the analysis object is two-grade, a two-grade analysis unit is adopted to carry out comprehensive analysis on the analysis object; and if the disease grade of the analysis object is second grade, performing comprehensive analysis on the analysis object by using a second-grade analysis unit.
2. The echocardiogram detection report-based treatment decision system according to claim 1, wherein the specific process of the disease analysis includes: acquiring the inner diameter of the pulmonary artery, the inner diameter of the left ventricle and the inner diameter of the right ventricle of the patient through an echocardiogram detection report, respectively marking the inner diameters as FD, ZS and YS, and if the FD is more than or equal to 12 and less than or equal to 26, the ZS is more than 35 and less than 50 and the YS is more than 7 and less than 23, judging that the cardiogram detection result of the patient is normal; if not, performing deep analysis on the disease of the patient;
the depth analysis process comprises the following steps: and calculating the inner diameter of the pulmonary artery, the inner diameter of the left chamber and the inner diameter of the right chamber to obtain a patient coefficient BH, comparing the patient coefficient BH with patient thresholds BHmin and BHmax, and judging the patient grade of the patient according to the comparison result of the patient coefficient and the patient thresholds.
3. The echocardiogram detection report-based treatment decision system according to claim 2, wherein the comparison of the patient coefficient to the patient threshold comprises: if BH is less than or equal to BHmin, judging the patient grade of the patient to be three-level, and sending a three-level patient signal to the treatment platform by the report analysis module;
if BHmin is less than BH and less than BHmax, the patient grade of the patient is judged to be second grade, and a report analysis module sends a second grade patient signal to a treatment platform;
if the BH is larger than or equal to the BHmax, the patient grade of the patient is judged to be the first grade, and a report analysis module sends a first-grade patient signal to a treatment platform.
4. The echocardiogram detection report-based treatment decision system according to claim 3, wherein the matching subject acquisition process includes: marking the patient subjected to disease condition trend analysis as an analysis object, acquiring the disease grade of the analysis object, acquiring the gender and the age of the analysis object if the disease grade of the analysis object is second grade, and marking all patients with disease grades, which are the same as the gender and have the age difference of three years, as second grade as reference objects; the time of the disease level of the reference object from the third level to the second level is obtained and marked as JSc, the time of the disease level of the analysis object from the third level to the second level is marked as JSf, the evolutionary matching value JSp of the reference object is obtained through a formula JHp ═ JSc-JSf |, and the ten reference objects with the minimum evolutionary matching value JSp are marked as matching objects.
5. The echocardiogram detection report-based therapy decision making system according to claim 4, wherein the specific process of matching analysis of the matching object by the trend analysis model comprises: acquiring a history detection report of the matching object for performing the cardiogram detection, marking the history disease coefficient of the matching object as PHt, wherein t is 1, 2, …, m, m is the number of times of performing the cardiogram detection on the matching object, acquiring the history detection report of performing the cardiogram detection on the analysis object, marking the history disease coefficient of the analysis object as FHq, q is 1, 2, …, u, u is the number of times of performing the cardiogram detection on the analysis object, comparing m with u, deleting m-u disease coefficients at random in PHt if m is more than u, marking PHt after deletion as PHq, and calculating FHq and PHq to obtain a deviation coefficient PS of the matching object; if u is larger than m, randomly deleting u-m patient coefficients in FHq, marking FHq after deletion as FHt, and calculating FHt and PHt to obtain a deviation coefficient PS of the matched object;
and marking the matched object with the minimum deviation coefficient PS value as a trend object, and sending the trend object to the treatment platform by the trend analysis module.
6. The echocardiogram detection report-based treatment decision system according to claim 5, wherein the specific process of treatment plan recommendation includes: obtaining a historical patient coefficient PHt of a matched object for performing the cardiogram detection, marking the difference value between PHt +1 and PHt as a recovery value HZ, marking the number of the recovery values HZ with positive values as y, marking the number of the recovery values HZ with negative values as v, marking the ratio of the y to the v as a recovery ratio HB, marking the patient coefficient of the matched object for performing the cardiogram detection for the last time as BHz, and calculating BHz and the recovery ratio HB to obtain a recovery coefficient HX of the matched object; marking the matching object with the maximum recovery coefficient HX value as a recommended object, acquiring the treatment data of the recommended object and sending the treatment data of the recommended object to a treatment platform; the treatment data of the recommended subject includes a treating physician, a treatment plan, a time of first diagnosis, and a history disease coefficient of the recommended subject.
7. The echocardiogram detection report-based treatment decision system according to claim 1, wherein the process of comprehensively analyzing the analysis object by the tertiary analysis unit includes: the time difference between the first diagnosis time of the analysis object and the current system time is obtained and marked as SC3, the average value of the historical patient coefficient of the analysis object is marked as BH3, the patient coefficient of the analysis object which is subjected to the cardiogram detection for the last time is marked as BX3, and the comprehensive coefficient ZH3 of the three-stage patient is obtained by calculating SC3, BH3 and BX 3.
8. The echocardiogram detection report-based treatment decision system according to claim 1, wherein the specific process of the secondary analysis unit performing the comprehensive analysis on the analysis object includes: the method comprises the steps of marking time when a disease grade of an analysis object is evolved from three levels to two levels as deterioration time, obtaining time difference between first diagnosis time and deterioration time of the analysis object and marking as SC2, obtaining time difference between deterioration time of the analysis object and current system time and marking as EH2, obtaining average disease coefficient BH2 when the disease grade of the analysis object is three levels, obtaining average disease coefficient BE2 when the disease grade of the analysis object is two levels, marking the disease coefficient of the analysis object which is subjected to cardiogram detection for the last time as BX2, and calculating SC2, EH2, Bh2, BE2 and BX2 to obtain comprehensive coefficient ZH2 of the second-level disease.
9. The echocardiogram detection report-based therapy decision making system according to claim 1, wherein the primary analysis module performs a comprehensive analysis of the analysis object by a specific process comprising: marking the time of the disease grade of an analysis object from the third grade to the second grade as deterioration time, acquiring the time difference between the first diagnosis time and the deterioration time of the analysis object and marking as SC1, marking the time of the disease grade of the analysis object from the second grade to the first grade as evolution time, acquiring the time difference between the deterioration time and the evolution time and marking as JH1, acquiring the time difference between the evolution time and the current system time and marking as XT1, acquiring the average disease coefficient of the analysis object when the disease grade is the third grade and marking as BH1, acquiring the average disease coefficient of the analysis object when the disease grade is the second grade and marking as BE1, acquiring the average disease coefficient of the analysis object when the disease coefficient is the first grade and marking as BY1, and acquiring the disease coefficient BX1 of the analysis object which carries out the latest cardiogram detection, the comprehensive coefficient ZH1 of the primary patients is obtained by calculating SC1, JH1, XT1, BH1, BE1 and BX 1.
10. The echocardiogram detection report-based therapy decision system according to any one of claims 1-9, wherein the method of operation of the therapy decision system includes the steps of:
the method comprises the following steps: the report analysis module analyzes the disease of the patient through the cardiogram detection data to obtain a patient coefficient, and judges the patient grade of the patient according to the comparison result of the patient coefficient and the patient threshold value;
step two: the trend analysis module screens out a matched object for the analysis object according to the age, the sex and the disease grade, and performs matching analysis on the matched object through a trend analysis model to obtain a trend object;
step three: the treatment recommendation module obtains a recovery ratio according to the ratio of the number of positive values to the number of negative values of the recovery value, obtains a recovery coefficient through calculation of the recovery ratio, and marks the matching object with the maximum recovery coefficient value as a recommended object;
step four: comprehensive analysis is carried out on the treatment progress of the analyzed patient through a comprehensive analysis module to obtain comprehensive coefficients of the first-level patient, the second-level patient and the third-level patient, and the comprehensive coefficients of the analyzed object are sent to a treatment platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210232472.4A CN114566282B (en) | 2022-03-09 | 2022-03-09 | Treatment decision system based on echocardiogram detection report |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210232472.4A CN114566282B (en) | 2022-03-09 | 2022-03-09 | Treatment decision system based on echocardiogram detection report |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114566282A true CN114566282A (en) | 2022-05-31 |
| CN114566282B CN114566282B (en) | 2022-10-04 |
Family
ID=81718645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210232472.4A Active CN114566282B (en) | 2022-03-09 | 2022-03-09 | Treatment decision system based on echocardiogram detection report |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114566282B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114974576A (en) * | 2022-07-12 | 2022-08-30 | 曜立科技(北京)有限公司 | Cardiovascular and cerebrovascular disease diagnosis and management system based on metadata |
| CN115620872A (en) * | 2022-12-20 | 2023-01-17 | 安徽猫头鹰科技有限公司 | Spectral modulation processing system and method for illumination luminescence |
| US11966374B2 (en) | 2022-07-12 | 2024-04-23 | Serv Medical Pte. Ltd. | Medical clinical data quality analysis system based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190125298A1 (en) * | 2016-04-21 | 2019-05-02 | The University Of British Columbia | Echocardiographic image analysis |
| CN110010218A (en) * | 2019-05-13 | 2019-07-12 | 聂文红 | A kind of patient in department of cardiology case and illness type management statistics system |
| US20200185084A1 (en) * | 2018-12-11 | 2020-06-11 | International Business Machines Corporation | Automated Normality Scoring of Echocardiograms |
| CN112256754A (en) * | 2020-10-19 | 2021-01-22 | 柳州市妇幼保健院 | Ultrasonic detection analysis system and method based on standard model |
| WO2021242097A1 (en) * | 2020-05-25 | 2021-12-02 | Ecg Excellence B.V. | Ecg based method providing acquired cardiac disease detection |
-
2022
- 2022-03-09 CN CN202210232472.4A patent/CN114566282B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190125298A1 (en) * | 2016-04-21 | 2019-05-02 | The University Of British Columbia | Echocardiographic image analysis |
| US20200185084A1 (en) * | 2018-12-11 | 2020-06-11 | International Business Machines Corporation | Automated Normality Scoring of Echocardiograms |
| CN110010218A (en) * | 2019-05-13 | 2019-07-12 | 聂文红 | A kind of patient in department of cardiology case and illness type management statistics system |
| WO2021242097A1 (en) * | 2020-05-25 | 2021-12-02 | Ecg Excellence B.V. | Ecg based method providing acquired cardiac disease detection |
| CN112256754A (en) * | 2020-10-19 | 2021-01-22 | 柳州市妇幼保健院 | Ultrasonic detection analysis system and method based on standard model |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114974576A (en) * | 2022-07-12 | 2022-08-30 | 曜立科技(北京)有限公司 | Cardiovascular and cerebrovascular disease diagnosis and management system based on metadata |
| US11966374B2 (en) | 2022-07-12 | 2024-04-23 | Serv Medical Pte. Ltd. | Medical clinical data quality analysis system based on big data |
| CN115620872A (en) * | 2022-12-20 | 2023-01-17 | 安徽猫头鹰科技有限公司 | Spectral modulation processing system and method for illumination luminescence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114566282B (en) | 2022-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114566282B (en) | Treatment decision system based on echocardiogram detection report | |
| CN110584605B (en) | Similarity-matched diagnosis and monitoring comprehensive medical system and matching method thereof | |
| US20220300809A1 (en) | Data generation system, learning apparatus, data generation apparatus, data generation method, and computer-readable storage medium storing a data generation program | |
| CN110600109B (en) | Diagnosis and monitoring comprehensive medical system with color image fusion and fusion method thereof | |
| TW202004776A (en) | Establishing method of bone age assessment and height prediction model, bone age assessment and height prediction system, and bone age assessment and height prediction method | |
| CN114359629B (en) | Deep migration learning-based X-chest X-ray pneumonia classification and identification method | |
| CN110782990B (en) | Method, system and mobile platform for stroke risk assessment of basic public and satellite service | |
| CN111223564A (en) | Noise hearing loss prediction system based on convolutional neural network | |
| CN109788275A (en) | Naturality, structure and binocular asymmetry are without reference stereo image quality evaluation method | |
| CN111598868B (en) | Lung ultrasonic image identification method and system | |
| US20190008417A1 (en) | Method and system for postural stability assessment | |
| CN110580951B (en) | Diagnosis monitoring comprehensive medical system with encrypted communication and communication encryption method thereof | |
| KR101603308B1 (en) | Biological age calculation model generation method and system thereof, biological age calculation method and system thereof | |
| CN110427987A (en) | A kind of the plantar pressure characteristic recognition method and system of arthritic | |
| CN111711816B (en) | Video objective quality evaluation method based on observable coding effect intensity | |
| CN101596125A (en) | A kind of health and fitness information display system, method and interface thereof that possesses demonstration directly perceived | |
| CN117338234A (en) | Diopter and vision joint detection method | |
| JP2024061599A (en) | A system for identifying abnormalities in the course of medical treatment based on a hierarchical neural network | |
| CN114240934B (en) | Image data analysis method and system based on acromegaly | |
| CN116230198A (en) | Multidimensional Tibetan medicine AI intelligent auxiliary decision-making device and system | |
| CN114913585A (en) | Household old man falling detection method integrating facial expressions | |
| CN107256544A (en) | A kind of prostate cancer image diagnosing method and system based on VCG16 | |
| CN118044813B (en) | Psychological health condition assessment method and system based on multitask learning | |
| CN117379009B (en) | Early warning and monitoring system for critical cardiovascular and cerebrovascular diseases of old people in community | |
| CN117238434B (en) | Nursing method and system based on prevention of potential complications of cardiology department |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |