CN116246787B - Risk prediction method and device for non-recurrent death - Google Patents
Risk prediction method and device for non-recurrent death Download PDFInfo
- Publication number
- CN116246787B CN116246787B CN202310526434.4A CN202310526434A CN116246787B CN 116246787 B CN116246787 B CN 116246787B CN 202310526434 A CN202310526434 A CN 202310526434A CN 116246787 B CN116246787 B CN 116246787B
- Authority
- CN
- China
- Prior art keywords
- concentration
- recurrent
- factor
- death
- time point
- 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.)
- Active
Links
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
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)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The application provides a risk prediction method and device for non-recurrent death, which belong to the technical field of medical care informatics, wherein the method comprises the following steps: obtaining the concentration of sST2 and the concentration of TNFR1 of a target object at a plurality of time points within a preset time after hematopoietic stem cell transplantation; dynamically calculating non-recurrent mortality probability of the target object at each of the plurality of time points based on a prediction model established in advance according to the sST2 concentration and the TNFR1 concentration at the plurality of time points; and comparing the non-recurrent death probability of each time point with a preset probability threshold to determine the risk degree of the non-recurrent death of the target object at each time point. The method solves the problem of low prediction accuracy caused by single factor prediction, solves the problem of unsuitable risk monitoring caused by prediction based on a specific time point, and achieves the technical effects of effectively improving the accuracy of non-recurrent death prediction and being more suitable for risk monitoring.
Description
Technical Field
The application belongs to the technical field of medical care informatics, namely information and communication technology special for treating or processing medical or health data, and particularly relates to a risk prediction method and device for non-recurrent death.
Background
After transplantation, about 10% of patients still face non-recurrent deaths caused by complications such as infection, acute graft versus host disease, etc. Biomarkers (biostators) have a predictive value for predicting non-recurrent deaths, e.g., there is a significant association of biostators (sST 2) at day 30 post-transplant with non-recurrent deaths at day 720.
However, existing prediction of non-recurrent death is generally based on single-biomarker-based prediction, with low prediction accuracy, and existing prediction of non-recurrent death, which is generally focused on a specific time point, is not suitable for risk monitoring.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The application aims to provide a method and a device for predicting risk of non-recurrent death, which are used for improving accuracy of non-recurrent death prediction after hematopoietic stem cell transplantation and are more suitable for risk monitoring.
The application provides a risk prediction method and device for non-recurrent death, which are realized by the following steps:
a method of risk prediction for non-recurrent death comprising:
obtaining the concentration of sST2 and the concentration of TNFR1 of a target object at a plurality of time points within a preset time after hematopoietic stem cell transplantation;
Dynamically calculating non-recurrent mortality probabilities of the target object at each of a plurality of time points based on a predictive model established in advance according to the sST2 concentration and the TNFR1 concentration at the plurality of time points;
and comparing the non-recurrent death probability of each time point with a preset probability threshold to determine the risk degree of the non-recurrent death of the target object at each time point.
In one embodiment, the expression of the basic training model of the predictive model is:
wherein P represents the probability of non-recurrent death,represents sST2 concentration,/->The TNFR1 concentration is shown, and a, b and c are parameters obtained by training a predictive model.
In one embodiment, the trained expression of the predictive model is:
wherein P represents the probability of non-recurrent death,represents sST2 concentration,/->TNFR1 concentration was expressed.
In one embodiment, the method further comprises: the predictive model is established as follows:
monitoring concentration values of biomarkers for a plurality of sample subjects at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation, wherein the biomarkers comprise: sST2, reg3α, and TNFR1;
constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues according to the sST2 concentration, the REG3 alpha concentration and the TNFR1 concentration of each sample object in the plurality of sample objects at a plurality of time points;
Randomly dividing the constructed three peak concentration data queues based on a single factor and four peak concentration queues based on multiple factors according to the proportion of 2:1 to obtain a training set and a testing set;
training and predicting three single-factor-based non-recurrent death models and four multi-factor-based non-recurrent death models by dividing the training set and the testing set;
determining, from the results of training and prediction, that AUC of a non-recurrent death model based on sST2 concentration and TNFR1 concentration is highest among three non-recurrent death models based on single factor and four non-recurrent death models based on multiple factor;
a non-recurrent death model based on sST2 concentration and TNFR1 concentration was used as the pre-established predictive model.
In one embodiment, constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues from the sST2 concentration, REG3 alpha concentration, and TNFR1 concentration of each sample object of the plurality of sample objects at a plurality of time points comprises:
three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues were constructed as follows:
calculating a distance value between biomarker concentrations for the current sample object at each time point;
And taking the biomarker concentration at the corresponding time point when the distance value is maximum as the peak concentration of the current sample object so as to establish a peak concentration data queue.
In one embodiment, calculating the distance value between biomarker concentrations for the current sample object at each time point comprises:
the distance value between the biomarker concentrations of the current sample object at each time point is calculated according to the following formula:
where value represents a distance value, x represents a concentration value of the factor involved, n=1 represents a single factor, and n=2 or 3 represents a multiple factor.
In one embodiment, comparing the probability of non-recurrent death at each time point to a preset probability threshold to determine the degree of risk of non-recurrent death of the target subject at each time point, comprising:
determining that the target subject is at high risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is greater than or equal to a first threshold;
determining that the target subject is at low risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is less than or equal to a second threshold, wherein the first threshold is greater than the second threshold;
And determining that the target object is at risk of non-recurrent death at the current time point if the non-recurrent death probability at the current time point is smaller than the first threshold and larger than the second threshold.
A risk prediction device for non-recurrent death, comprising:
an acquisition module for acquiring the sST2 concentration and TNFR1 concentration of the target subject at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation;
a calculation module for dynamically calculating non-recurrent mortality probabilities of the target object at each of a plurality of time points based on a prediction model established in advance according to sST2 concentration and TNFR1 concentration at the plurality of time points;
and the determining module is used for comparing the non-recurrent death probability of each time point with a preset probability threshold value so as to determine the risk degree of the non-recurrent death of the target object at each time point.
An electronic device comprising a processor and a memory for storing processor-executable instructions, which when executed by the processor implement the steps of the above-described method.
A computer readable storage medium having stored thereon a computer program/instruction which when executed by a processor performs the steps of the above method.
The risk prediction method and device for non-recurrent death provided by the application are characterized in that the sST2 concentration and the TNFR1 concentration of a target object at a plurality of time points in a preset time period after hematopoietic stem cell transplantation are obtained, and then the non-recurrent death probability of the target object at each time point in the plurality of time points is dynamically calculated based on a prediction model established in advance according to the sST2 concentration and the TNFR1 concentration of the plurality of time points, so that the risk degree of the non-recurrent death of the target object at each time point is determined. Because prediction of non-recurrent death probability is performed based on a plurality of time points, a plurality of factors and based on sST2 concentration, TNFR1 concentration and two multi-factors, the problem of low prediction accuracy caused by the existing single factor prediction can be effectively solved, the problem that prediction based on a specific time point is unsuitable for risk monitoring is solved, and the technical effects of effectively improving the accuracy of non-recurrent death prediction and being more suitable for risk monitoring are achieved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of a method of model construction and application for implementing non-recurrent death prediction provided herein;
FIG. 2 is a schematic diagram of the logic provided herein for creating a peak concentration data queue;
FIG. 3 is a flow chart of a method of training a non-recurrent death prediction model provided herein;
FIG. 4 is a auc profile of predicted non-recurrent deaths on 100 training and test sets based on different biomarker peak concentration combinations provided herein;
FIG. 5 is a method flow chart of a method of risk prediction for non-recurrent death provided herein;
FIG. 6 is a block diagram of the hardware architecture of an electronic device for a method of risk prediction of non-recurrent death provided herein;
fig. 7 is a block diagram of a non-recurrent death risk prediction device provided herein.
Detailed Description
In order to better understand the technical solutions in the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
Considering that the existing prediction of non-recurrent death after hematopoietic stem cell transplantation is mainly focused on the prediction of non-recurrent death by a bioligic marker at a specific time point, the characteristic of dynamic change of the bioligic marker in a patient is not considered, and the prediction of non-recurrent death by a single factor of peak concentration of the bioligic marker is mainly aimed at, and the value of multi-factor combination prediction is not considered. Based on this, in this example, a non-recurrent death prediction based on the peak concentrations of sST2 (soluble growth-stimulated expressed gene 2 protein) and TNFR1 (tumor necrosis factor receptor, tumor necrosis factor receptor 1) was proposed, i.e., by establishing a non-recurrent death prediction model based on the peak concentrations of sST2 and TNFR1 (determined to be a better combination of boom), a non-recurrent death prediction after hematopoietic stem cell transplantation was performed.
To achieve non-recurrent death prediction, the construction and application of the model may be performed, specifically, as shown in fig. 1, including the following steps:
step 101: index monitoring is carried out on the boom:
in practice, a plurality of patients can be selected as sample patients, and the number of sample patients can be examined by a Luminex platform for a biomarker (sST 2, REG 3. Alpha., TNFR 1) index at different time points, and the patients can be divided into two groups according to whether or not non-recurrent death occurs. At the time of testing, the test frequency may be set to at least 3 biomarker index monitors per patient within 100 days after implantation, with at least one week between measurements.
Step 102: constructing a peak concentration data queue:
the distance value (value) between the biomarker index factors at each time point for each sample patient was calculated according to the following formula:
wherein x is i The concentration of biomarker (in pg/ml) is indicated.
The concentration of the biomarker at the time point when the value of each patient reaches the maximum is taken as the peak concentration to establish a data queue.
Specifically, when n=1, a single-factor peak concentration data queue (3 groups, sST2, reg3α, TNFR 1) is established, and when n=2 or 3, a multi-factor peak concentration data queue (4 groups, sst2+reg3α, sst2+tnfr1, reg3α+tnfr1, sst2+reg3α+tnfr1) is established, one piece of data being selected for each patient in each data queue.
As shown in FIG. 2, by taking the single factor sST2 as an examplePeak concentration was determined for each patient, and queue 1 was determined, by +.>Peak concentration was determined for each patient, and queue 2 was determined, by taking 3 factors sst2+reg3α+tnfr1 as an exampleThe peak concentration for each patient is determined and the cohort 3 is determined.
Step 103: model training and selection:
as shown in fig. 3, each set of peak concentration data queues (e.g., modeling queue 463 examples) obtained above is aligned to 2:1 is randomly divided into 100 sets of training sets (train, n=310) and test sets (test, n=153). A plurality of non-recurrent death prediction models (Biomarker Peak models) are established on the training set by adopting a Fine-gray proportional risk regression method, then auc (Area Under, defined as the Area distribution Under the ROC Curve enclosed by the axis, the auc distribution of each non-recurrent death prediction model is determined by a test set to determine the optimal Biomarker Peak model for prediction, and further, model verification is performed by an independent verification queue (for example, 158 cases).
Specifically, when determining the optimal Biomarker Peak model, it may be determined that the AUC distribution of 100 groups of non-recurrent death models respectively established on 7 groups of Peak concentration data queues in step 102 over the test set, for example, as shown in fig. 4, the model AUC mean based on the Peak concentrations of sST2 and TNFR1 is 0.8572, which is superior to the Peak models based on other Biomarker combinations (sST 2,0.8254; reg3α,0.7189; TNFR1,0.7718; sst2+reg3α,0.8162; tnfr1+reg3α,0.7533; sst2+tnfr1+reg3α, 0.8253).
From this, it can be determined that a non-recurrent death prediction model was established based on the peak concentrations of sST2 and TNFR 1:
is the most accurate relative.
Further, building a non-recurrent death prediction model based on sST2 and TNFR1 peak concentrations showed AUC of non-recurrent death within 6 months after predicting peak concentrations on independent validation sets to be 0.9432 (95% ci: 0.91-0.98, n=158).
Step 104: and carrying out non-recurrent death risk prediction through a determined non-recurrent death prediction model:
the risk of non-recurrent death (P) at the time of patient biomarker sampling was calculated based on a non-recurrent death prediction model of sST2 and TNFR1 peak concentrations. Specifically, the medium or low risk may be determined in such a way that, for example, when P is greater than or equal to 0.1602, it is indicated that the current patient is at high risk of non-recurrent death; when P is less than or equal to 0.0683, indicating that the current patient is at low risk of non-recurrent death; when P is between 0.0683 and 0.1602, the current patient is at risk of non-recurrent death.
That is, a non-recurrent death prediction model based on peak concentrations of sST2 and TNFR1 was provided, which was constructed based on a more optimal combination of biolakers (sST 2 and TNFR 1) predicted at peak concentrations, and which was able to effectively predict non-recurrent death within 6 months after the peak of the patient: AUC on the modeling set was 0.8633 (95% ci: 0.8-0.93, n=463) and AUC on the independent validation set was 0.9432 (95% ci: 0.91-0.98, n=158). And the predictive effect on non-recurrent deaths is further enhanced relative to peak concentrations of individual factors.
FIG. 5 is a method flow diagram of one embodiment of a method for risk prediction of non-recurrent death provided herein. Although the present application provides a method operation step or apparatus structure as shown in the following examples or figures, more or fewer operation steps or module units may be included in the method or apparatus based on routine or non-inventive labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of the steps or the module structure of the apparatus is not limited to the execution order or the module structure shown in the drawings and described in the embodiments of the present application. The described methods or module structures may be implemented sequentially or in parallel (e.g., in a parallel processor or multithreaded environment, or even in a distributed processing environment) in accordance with the embodiments or the method or module structure connection illustrated in the figures when implemented in a practical device or end product application.
Specifically, as shown in fig. 5, the method for predicting risk of non-recurrent death described above may include the steps of:
step 501: obtaining the concentration of sST2 and the concentration of TNFR1 of a target object at a plurality of time points within a preset time after hematopoietic stem cell transplantation;
specifically, the concentration of sST2 and TNFR1 at different time points within 100 days after the transplantation of the hematopoietic stem cells of the target subject may be measured, and the selection of the predetermined period may be selected according to the actual situation and the requirement, for example, may be 100 days, or may be 90 days. At the time of implementation, at least 3 serum biomarker measurements may be performed within 100 days after the target is transplanted, and a minimum interval between the two measurements is one week to ensure the validity of the data.
Step 502: dynamically calculating non-recurrent mortality probabilities of the target object at each of a plurality of time points based on a predictive model established in advance according to the sST2 concentration and the TNFR1 concentration at the plurality of time points;
wherein, the expression of the basic training model of the prediction model can be expressed as:
wherein P represents the probability of non-recurrent death,represents sST2 concentration,/->The TNFR1 concentration is shown, and a, b and c are parameters obtained by training a predictive model.
After training, determining the values of a, b and c, for example, determining the trained expression of the valued prediction model as:
wherein P represents the probability of non-recurrent death,represents sST2 concentration,/->TNFR1 concentration was expressed.
It should be noted, however, that the values of a, b and c are preferred implementations, and that there may be a range of fluctuations in the values of a, b and c when actually implemented.
The prediction model can be established as follows:
s1: monitoring concentration values of biomarkers for a plurality of sample subjects at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation, wherein the biomarkers comprise: sST2, reg3α, and TNFR1;
s2: constructing three peak concentration data queues based on single factors (sST 2, REG3 a, TNFR 1) and four peak concentration queues based on multiple factors (sST 2 and REG3 a, sST2 and TNFR1, REG3 a and TNFR1, sST2 and REG3 a and TNFR 1) based on sST2 concentration, REG3 a concentration, and TNFR1 concentration of each sample object at a plurality of time points in the plurality of sample objects;
specifically, three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues may be constructed as follows: calculating a distance value between biomarker concentrations for the current sample object at each time point; and taking the biomarker concentration at the corresponding time point when the distance value is maximum as the peak concentration of the current sample object so as to establish a peak concentration data queue.
Wherein the distance value between the biomarker concentrations of the current sample object at each time point can be calculated according to the following formula:
where value represents a distance value, x represents a concentration value of the factor involved, n=1 represents a single factor, and n=2 or 3 represents a multiple factor.
S3: randomly dividing the constructed three peak concentration data queues based on a single factor and four peak concentration queues based on multiple factors according to the proportion of 2:1 to obtain a training set and a testing set;
s4: training and predicting three single-factor-based non-recurrent death models and four multi-factor-based non-recurrent death models by dividing the training set and the testing set;
s5: determining, from the results of training and prediction, that AUC of a non-recurrent death model based on sST2 concentration and TNFR1 concentration is highest among three non-recurrent death models based on single factor and four non-recurrent death models based on multiple factor;
s6: a non-recurrent death model based on sST2 concentration and TNFR1 concentration was used as the pre-established predictive model.
Step 503: and comparing the non-recurrent death probability of each time point with a preset probability threshold to determine the risk degree of the non-recurrent death of the target object at each time point.
Specifically, the risk level determination may be performed as follows:
1) Determining that the target subject is at high risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is greater than or equal to a first threshold;
2) Determining that the target subject is at low risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is less than or equal to a second threshold, wherein the first threshold is greater than the second threshold;
3) And determining that the target object is at risk of non-recurrent death at the current time point if the non-recurrent death probability at the current time point is smaller than the first threshold and larger than the second threshold.
The method embodiments provided in the above embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the example of running on an electronic device, fig. 6 is a block diagram of the hardware structure of the electronic device of a risk prediction method for non-recurrent death provided in the present application. As shown in fig. 6, the electronic device 10 may include one or more (only one is shown in the figure) processors 02 (the processors 02 may include, but are not limited to, a microprocessor MCU, a programmable logic device FPGA, etc. processing means), a memory 04 for storing data, and a transmission module 06 for communication functions. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 6 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the electronic device 10 may also include more or fewer components than shown in FIG. 6, or have a different configuration than shown in FIG. 6.
The memory 04 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the method for predicting risk of non-recurrent death in the embodiments of the present application, and the processor 02 executes various functional applications and data processing by running the software programs and modules stored in the memory 04, that is, implements the method for predicting risk of non-recurrent death of the application program. Memory 04 may include high-speed random access memory, but may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 04 may further include memory located remotely from processor 02, which may be connected to electronic device 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module 06 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communications provider of the electronic device 10. In one example, the transmission module 06 includes a network adapter (Network Interface Controller, NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission module 06 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
At the software level, the risk prediction apparatus for non-recurrent death may include, as shown in fig. 7:
an acquisition module 701 for acquiring the sST2 concentration and the TNFR1 concentration of the target subject at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation;
a calculation module 702 for dynamically calculating non-recurrent mortality probabilities of the target subject at each of a plurality of time points based on a prediction model established in advance according to sST2 concentration and TNFR1 concentration at the plurality of time points;
the determining module 703 is configured to compare the probability of non-recurrent death at each time point with a preset probability threshold, so as to determine the risk level of the target subject for non-recurrent death at each time point.
In one embodiment, the expression of the underlying training model of the predictive model may be expressed as:
wherein P represents the probability of non-recurrent death,represents sST2 concentration,/->The TNFR1 concentration is shown, and a, b and c are parameters obtained by training a predictive model.
In one embodiment, the trained expression of the predictive model may be expressed as:
wherein P represents the probability of non-recurrent death,represents sST2 concentration,/->TNFR1 concentration was expressed.
In one embodiment, the predictive model may be established as follows:
Monitoring concentration values of biomarkers for a plurality of sample subjects at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation, wherein the biomarkers comprise: sST2, reg3α, and TNFR1;
constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues according to the sST2 concentration, the REG3 alpha concentration and the TNFR1 concentration of each sample object in the plurality of sample objects at a plurality of time points;
randomly dividing the constructed three peak concentration data queues based on a single factor and four peak concentration queues based on multiple factors according to the proportion of 2:1 to obtain a training set and a testing set;
training and predicting three single-factor-based non-recurrent death models and four multi-factor-based non-recurrent death models by dividing the training set and the testing set;
determining, from the results of training and prediction, that AUC of a non-recurrent death model based on sST2 concentration and TNFR1 concentration is highest among three non-recurrent death models based on single factor and four non-recurrent death models based on multiple factor;
a non-recurrent death model based on sST2 concentration and TNFR1 concentration was used as the pre-established predictive model.
In one embodiment, constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues from the sST2 concentration, REG3 alpha concentration, and TNFR1 concentration of each sample object of the plurality of sample objects at a plurality of time points may include: three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues were constructed as follows: calculating a distance value between biomarker concentrations for the current sample object at each time point; and taking the biomarker concentration at the corresponding time point when the distance value is maximum as the peak concentration of the current sample object so as to establish a peak concentration data queue.
In one embodiment, the distance value between biomarker concentrations for the current sample object at each time point may be calculated as follows:
where value represents a distance value, x represents a concentration value of the factor involved, n=1 represents a single factor, and n=2 or 3 represents a multiple factor.
In one embodiment, comparing the probability of non-recurrent death at each time point with a preset probability threshold to determine the degree of risk of non-recurrent death of the target subject at each time point may include:
Determining that the target subject is at high risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is greater than or equal to a first threshold;
determining that the target subject is at low risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is less than or equal to a second threshold, wherein the first threshold is greater than the second threshold;
and determining that the target object is at risk of non-recurrent death at the current time point if the non-recurrent death probability at the current time point is smaller than the first threshold and larger than the second threshold.
The embodiment of the present application further provides a specific implementation manner of an electronic device capable of implementing all the steps in the risk prediction method for non-recurrent death in the foregoing embodiment, where the electronic device specifically includes the following contents: a processor (processor), a memory (memory), a communication interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete communication with each other through the bus; the processor is configured to invoke the computer program in the memory, where the processor executes the computer program to implement all the steps in the method for predicting risk of non-recurrent death in the above embodiment, for example, the processor executes the computer program to implement the following steps:
Step 1: obtaining the concentration of sST2 and the concentration of TNFR1 of a target object at a plurality of time points within a preset time after hematopoietic stem cell transplantation;
step 2: dynamically calculating non-recurrent mortality probabilities of the target object at each of a plurality of time points based on a predictive model established in advance according to the sST2 concentration and the TNFR1 concentration at the plurality of time points;
step 3: and comparing the non-recurrent death probability of each time point with a preset probability threshold to determine the risk degree of the non-recurrent death of the target object at each time point.
As can be seen from the above description, in the embodiment of the present application, the sST2 concentration and the TNFR1 concentration of the target object at a plurality of time points within a predetermined period after hematopoietic stem cell transplantation are obtained, and then, based on the sST2 concentration and the TNFR1 concentration at the plurality of time points, the probability of non-recurrent death of the target object at each of the plurality of time points is dynamically calculated based on a prediction model established in advance, thereby determining the risk level of non-recurrent death of the target object at each of the time points. Because prediction of non-recurrent death probability is performed based on a plurality of time points, a plurality of factors and based on sST2 concentration, TNFR1 concentration and two multi-factors, the problem of low prediction accuracy caused by the existing single factor prediction can be effectively solved, the problem that prediction based on a specific time point is unsuitable for risk monitoring is solved, and the technical effects of effectively improving the accuracy of non-recurrent death prediction and being more suitable for risk monitoring are achieved.
The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the risk prediction method for non-recurrent death in the above embodiments, the computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements all the steps in the risk prediction method for non-recurrent death in the above embodiments, for example, the processor implements the following steps when executing the computer program:
step 1: obtaining the concentration of sST2 and the concentration of TNFR1 of a target object at a plurality of time points within a preset time after hematopoietic stem cell transplantation;
step 2: dynamically calculating non-recurrent mortality probabilities of the target object at each of a plurality of time points based on a predictive model established in advance according to the sST2 concentration and the TNFR1 concentration at the plurality of time points;
step 3: and comparing the non-recurrent death probability of each time point with a preset probability threshold to determine the risk degree of the non-recurrent death of the target object at each time point.
As can be seen from the above description, in the embodiment of the present application, the sST2 concentration and the TNFR1 concentration of the target object at a plurality of time points within a predetermined period after hematopoietic stem cell transplantation are obtained, and then, based on the sST2 concentration and the TNFR1 concentration at the plurality of time points, the probability of non-recurrent death of the target object at each of the plurality of time points is dynamically calculated based on a prediction model established in advance, thereby determining the risk level of non-recurrent death of the target object at each of the time points. Because prediction of non-recurrent death probability is performed based on a plurality of time points, a plurality of factors and based on sST2 concentration, TNFR1 concentration and two multi-factors, the problem of low prediction accuracy caused by the existing single factor prediction can be effectively solved, the problem that prediction based on a specific time point is unsuitable for risk monitoring is solved, and the technical effects of effectively improving the accuracy of non-recurrent death prediction and being more suitable for risk monitoring are achieved.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a hardware+program class embodiment, the description is relatively simple, as it is substantially similar to the method embodiment, as relevant see the partial description of the method embodiment.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Although the present application provides method operational steps as described in the examples or flowcharts, more or fewer operational steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented by an actual device or client product, the instructions may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment) as shown in the embodiments or figures.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a car-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Although the present description provides method operational steps as described in the examples or flowcharts, more or fewer operational steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in an actual device or end product, the instructions may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed data processing environment) as illustrated by the embodiments or by the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, it is not excluded that additional identical or equivalent elements may be present in a process, method, article, or apparatus that comprises a described element.
For convenience of description, the above devices are described as being functionally divided into various modules, respectively. Of course, when implementing the embodiments of the present disclosure, the functions of each module may be implemented in the same or multiple pieces of software and/or hardware, or a module that implements the same function may be implemented by multiple sub-modules or a combination of sub-units, or the like. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller can be regarded as a hardware component, and means for implementing various functions included therein can also be regarded as a structure within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description embodiments may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present embodiments may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments. In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means 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 embodiments of the present specification. In this specification, schematic representations of the above terms are not necessarily directed 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. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
The foregoing is merely an example of an embodiment of the present disclosure and is not intended to limit the embodiment of the present disclosure. Various modifications and variations of the illustrative embodiments will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of the embodiments of the present specification, should be included in the scope of the claims of the embodiments of the present specification.
Claims (7)
1. A method of predicting risk of non-recurrent death, the method comprising:
obtaining the concentration of sST2 and the concentration of TNFR1 of a target object at a plurality of time points within a preset time after hematopoietic stem cell transplantation;
dynamically calculating non-recurrent mortality probabilities of the target object at each of a plurality of time points based on a predictive model established in advance according to the sST2 concentration and the TNFR1 concentration at the plurality of time points;
comparing the non-recurrent death probability of each time point with a preset probability threshold to determine the risk degree of the non-recurrent death of the target object at each time point;
wherein, still include: the predictive model is established as follows:
monitoring concentration values of biomarkers for a plurality of sample subjects at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation, wherein the biomarkers comprise: sST2, reg3α, and TNFR1;
Constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues according to the sST2 concentration, the REG3 alpha concentration and the TNFR1 concentration of each sample object in the plurality of sample objects at a plurality of time points;
randomly dividing the constructed three peak concentration data queues based on a single factor and four peak concentration queues based on multiple factors according to the proportion of 2:1 to obtain a training set and a testing set;
training and predicting three single-factor-based non-recurrent death models and four multi-factor-based non-recurrent death models by dividing the training set and the testing set;
determining, from the results of training and prediction, that AUC of a non-recurrent death model based on sST2 concentration and TNFR1 concentration is highest among three non-recurrent death models based on single factor and four non-recurrent death models based on multiple factor;
taking a non-recurrent death model based on sST2 concentration and TNFR1 concentration as the pre-established predictive model;
wherein constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues according to the sST2 concentration, the REG3 alpha concentration and the TNFR1 concentration of each sample object in the plurality of sample objects at a plurality of time points comprises:
Three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues were constructed as follows:
calculating a distance value between biomarker concentrations for the current sample object at each time point;
taking the biomarker concentration of the corresponding time point when the distance value is maximum as the peak concentration of the current sample object to establish a peak concentration data queue;
wherein calculating a distance value between biomarker concentrations for the current sample object at each time point comprises:
the distance value between the biomarker concentrations of the current sample object at each time point is calculated according to the following formula:
where value represents a distance value, x represents a concentration value of a factor involved, n=1 represents a single factor, and n=2 or n=3 represents a multiple factor.
2. The method of claim 1, wherein the expression of the underlying training model of the predictive model is:
wherein P represents the probability of non-recurrent death, +.>Represents sST2 concentration,/->The TNFR1 concentration is shown, and a, b and c are parameters obtained by training a predictive model.
3. The method of claim 1, wherein the trained expression of the predictive model is:
Wherein P represents the probability of non-recurrent death, +.>Represents sST2 concentration,/->TNFR1 concentration was expressed.
4. A method according to any one of claims 1 to 3, wherein comparing the probability of non-recurrent death at each time point to a pre-set probability threshold to determine the degree of risk of non-recurrent death of the target subject at each time point comprises:
determining that the target subject is at high risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is greater than or equal to a first threshold;
determining that the target subject is at low risk of non-recurrent death at the current time point if the probability of non-recurrent death at the current time point is less than or equal to a second threshold, wherein the first threshold is greater than the second threshold;
and determining that the target object is at risk of non-recurrent death at the current time point if the non-recurrent death probability at the current time point is smaller than the first threshold and larger than the second threshold.
5. A risk prediction device for non-recurrent death, comprising:
an acquisition module for acquiring the sST2 concentration and TNFR1 concentration of the target subject at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation;
A calculation module for dynamically calculating non-recurrent mortality probabilities of the target object at each of a plurality of time points based on a prediction model established in advance according to sST2 concentration and TNFR1 concentration at the plurality of time points;
the determining module is used for comparing the non-recurrent death probability of each time point with a preset probability threshold value so as to determine the risk degree of the non-recurrent death of the target object at each time point;
wherein, still include: the predictive model is established as follows:
monitoring concentration values of biomarkers for a plurality of sample subjects at a plurality of time points within a predetermined period of time after hematopoietic stem cell transplantation, wherein the biomarkers comprise: sST2, reg3α, and TNFR1;
constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues according to the sST2 concentration, the REG3 alpha concentration and the TNFR1 concentration of each sample object in the plurality of sample objects at a plurality of time points;
randomly dividing the constructed three peak concentration data queues based on a single factor and four peak concentration queues based on multiple factors according to the proportion of 2:1 to obtain a training set and a testing set;
training and predicting three single-factor-based non-recurrent death models and four multi-factor-based non-recurrent death models by dividing the training set and the testing set;
Determining, from the results of training and prediction, that AUC of a non-recurrent death model based on sST2 concentration and TNFR1 concentration is highest among three non-recurrent death models based on single factor and four non-recurrent death models based on multiple factor;
taking a non-recurrent death model based on sST2 concentration and TNFR1 concentration as the pre-established predictive model;
wherein constructing three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues according to the sST2 concentration, the REG3 alpha concentration and the TNFR1 concentration of each sample object in the plurality of sample objects at a plurality of time points comprises:
three single-factor-based peak concentration data queues and four multi-factor-based peak concentration queues were constructed as follows:
calculating a distance value between biomarker concentrations for the current sample object at each time point;
taking the biomarker concentration of the corresponding time point when the distance value is maximum as the peak concentration of the current sample object to establish a peak concentration data queue;
wherein calculating a distance value between biomarker concentrations for the current sample object at each time point comprises:
the distance value between the biomarker concentrations of the current sample object at each time point is calculated according to the following formula:
Where value represents a distance value, x represents a concentration value of a factor involved, n=1 represents a single factor, and n=2 or n=3 represents a multiple factor.
6. An electronic device comprising a processor and a memory for storing processor-executable instructions, wherein the processor, when executing the instructions, performs the steps of the method of any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon a computer program/instruction, which when executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310526434.4A CN116246787B (en) | 2023-05-11 | 2023-05-11 | Risk prediction method and device for non-recurrent death |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310526434.4A CN116246787B (en) | 2023-05-11 | 2023-05-11 | Risk prediction method and device for non-recurrent death |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116246787A CN116246787A (en) | 2023-06-09 |
CN116246787B true CN116246787B (en) | 2023-07-21 |
Family
ID=86633473
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310526434.4A Active CN116246787B (en) | 2023-05-11 | 2023-05-11 | Risk prediction method and device for non-recurrent death |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116246787B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117542529B (en) * | 2024-01-10 | 2024-04-02 | 北京博富瑞基因诊断技术有限公司 | Method, system, device and storage medium for predicting non-recurrent death risk of HLA-incompatible allogeneic hematopoietic stem cell transplantation |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8119358B2 (en) * | 2005-10-11 | 2012-02-21 | Tethys Bioscience, Inc. | Diabetes-related biomarkers and methods of use thereof |
WO2018075869A1 (en) * | 2016-10-21 | 2018-04-26 | Icahn School Of Medicine At Mount Sinai | Method of predicting graft versus host disease |
CN113012813A (en) * | 2021-02-25 | 2021-06-22 | 北京博富瑞基因诊断技术有限公司 | Biomar predictive research method for real world data |
CN114464320A (en) * | 2022-02-09 | 2022-05-10 | 北京博富瑞医学检验实验室有限公司 | Non-recurrent death risk monitoring model based on aGVHD biomarker |
-
2023
- 2023-05-11 CN CN202310526434.4A patent/CN116246787B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN116246787A (en) | 2023-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116246787B (en) | Risk prediction method and device for non-recurrent death | |
CN109976998B (en) | Software defect prediction method and device and electronic equipment | |
CN108615096A (en) | Server, the processing method of Financial Time Series and storage medium | |
CN111310784B (en) | Resource data processing method and device | |
CN116973797A (en) | Battery pack consistency judging method, device, equipment and storage medium | |
CN111107497A (en) | Base station fingerprint database data source supplementing method and device, server and storage medium | |
CN117236805B (en) | Power equipment control method, device, electronic equipment and computer readable medium | |
CN116087814B (en) | Method and device for improving voltage sampling precision and electronic equipment | |
CN116827971A (en) | Block chain-based carbon emission data storage and transmission method, device and equipment | |
CN109271453B (en) | Method and device for determining database capacity | |
CN109429282B (en) | Frequency point configuration method and device | |
CN116594568A (en) | Data storage method and device, electronic equipment and storage medium | |
CN110868737B (en) | Load balancing method and device | |
CN116245422A (en) | External data quality evaluation method and device and electronic equipment | |
CN115797726A (en) | Model obtaining method and device, electronic equipment and storage medium | |
CN113495845B (en) | Data testing method and device, electronic equipment and storage medium | |
CN115509931A (en) | System-based performance test method and device, electronic equipment and storage medium | |
Perracchione et al. | An RBF-PSO based approach for modeling prostate cancer | |
CN111585789B (en) | Data prediction method and device | |
CN107748711A (en) | Method, terminal device and the storage medium of Automatic Optimal Storm degree of parallelisms | |
CN106301880A (en) | One determines that cyberrelationship degree of stability, Internet service recommend method and apparatus | |
CN111598390A (en) | Server high availability evaluation method, device, equipment and readable storage medium | |
CN110647466B (en) | Program quality supervision method and device based on DevOps | |
CN114910711B (en) | Uncertainty analysis method and device for test grid introduction in OTA test | |
CN115618962B (en) | Model training method, business wind control method and device |
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 |