Systems, methods, media, and apparatuses for predicting survival probability of parkinson's disease

Abstract

The present application relates to a kind of prediction system, method, medium and equipment of Parkinson's disease survival probability.The prediction system includes: acquisition module is configured to obtain six target indicators of the person tested, the target indicators include onset age, diabetes status, UPDRS III score, HY staging, depression state and cognitive impairment state;Prediction module is configured to predict the survival probability of the person tested within a set time in the future based on all the target indicators, combined with Parkinson's disease survival prediction nomogram.The technical scheme provided by the present application can quickly estimate the survival probability of the person tested within a set time in the future by means of the pre-constructed Parkinson's disease survival prediction nomogram, which can be used by clinicians for the survival prognosis prediction of PD patients, and the present application has higher clinical benefits and stronger referenceability of conclusion.

Description

Technical Field

[0001] The present invention relates to the field of Parkinson's disease prognosis assessment, and in particular to a prediction system, method, medium and device for Parkinson's disease survival probability. Background Art

[0002] Parkinson's disease (PD), a neurodegenerative disorder, has an incidence of approximately 0.5% to 1% in people aged 60 to 65, rising to 1% to 3% in those over 80. The prevalence increases with age and is slightly higher in men than in women. According to statistics, the direct treatment and care costs for a PD patient in the United States are approximately $10,349 per year. This, combined with indirect costs such as lost productivity and unpaid caregiving by family members, creates a significant burden on society and the patients' families. Therefore, conducting survivorship surveys of PD patients has become an important component of understanding the burden of the disease.

[0003] Cox proportional hazards regression combined with Kaplan-Meier survival curves are used to study the risk factors for mortality in patients with Parkinson's disease (PD). Numerous studies have shown that the average age of death in PD patients ranges from 72.7 to 82.9 years, with a median survival of 10 to 20 years. However, there are currently no definitive results on the risk factors for mortality in PD and whether PD affects mortality. For example, studies have shown that risk factors for mortality in Parkinson's disease include older age at onset, cognitive impairment, and more severe motor symptoms. However, there are conflicting results regarding whether factors such as gender, hallucinations, depression, autonomic dysfunction, smoking, and deep brain stimulation (DBS) surgery affect survival in PD patients. Furthermore, the Standardized Mortality Ratio (SMR) value in PD patients can also be used to investigate whether PD affects survival. Previous studies have shown that SMR values ​​for PD patients range from 0.5 to 3.8 compared to healthy controls, and SMR values ​​vary across countries and regions. Summary of the Invention

[0004] In view of this, embodiments of the present application provide a system, method, medium, and device for predicting the survival probability of Parkinson's disease in order to solve at least one problem existing in the background technology.

[0005] In a first aspect, an embodiment of the present application provides a system for predicting the survival probability of Parkinson's disease, comprising:

[0006] an acquisition module configured to acquire six target indicators of the test subject, wherein the target indicators include age of onset, diabetes status, UPDRS III score, HY stage, depression status, and cognitive impairment status;

[0007] The prediction module is configured to predict the survival probability of the test subject within a set future time period based on all the target indicators and in combination with the Parkinson's disease survival prediction nomogram.

[0008] In conjunction with the first aspect of the present application, in an optional implementation manner, in the target indicators:

[0009] The age of onset is a categorical variable, and the value of the age of onset indicates whether the subject is under 50 years old or over 50 years old;

[0010] The diabetes status is a categorical variable, and the value of the diabetes status indicates whether the subject suffers from diabetes;

[0011] The UPDRSⅢ score is a continuous variable, and the value of the UPDRSⅢ score is the Unified Parkinson's Disease Rating Scale Ⅲ score of the test subject;

[0012] The HY stage is a categorical variable, and the value of the HY stage represents the HY stage content of the test subject;

[0013] The depression state is a categorical variable, and the value of the depression state indicates whether the subject suffers from depression;

[0014] The cognitive impairment status is a categorical variable, and the value of the cognitive impairment status indicates whether the subject suffers from cognitive impairment.

[0015] In conjunction with the first aspect of the present application, in an optional embodiment, the Parkinson's disease survival prediction nomogram includes a single score line segment, six target indicator line segments, a total score line segment, and a survival probability line segment within a set future time period;

[0016] The value of the target indicator on the corresponding target indicator line segment corresponds to the score on the individual score line segment;

[0017] The sum of the scores of all the target indicators is the score on the total score line segment;

[0018] The value of the survival probability within the set future time on the corresponding survival probability line segment corresponds to the score on the total score line segment;

[0019] The individual score line segment, target indicator line segment, total score line segment, and survival probability line segment within a set future time period each occupy a row on the Parkinson's disease survival prediction nomogram.

[0020] In conjunction with the first aspect of the present application, in an optional embodiment, in the Parkinson's disease survival prediction nomogram, the score range of the single score line segment is 0 to 100;

[0021] If the age of onset of the tested person is under 50 years old, the value of the age of onset corresponds to 0 on the single score line segment; if the age of onset of the tested person is over 50 years old, the value of the age of onset corresponds to 100 on the single score line segment;

[0022] If the subject does not have diabetes, the value of the diabetes status corresponds to 0 on the single score line segment; if the subject has diabetes, the value of the diabetes status corresponds to 45.8 on the single score line segment;

[0023] If the UPDRS III score of the test subject ranges from 0 to 108, the maximum value of the UPDRS III score corresponds to 63.7 on the single score line segment, the minimum value corresponds to 0, and the corresponding relationship between the value and the score is a linear relationship;

[0024] If the HY stage of the test subject is 1 stage, 2 stages, 2.5 stages, 3 stages, 4 stages or 5 stages, the HY stage value corresponds to 0, 25.4, 36.6, 42.4, 50.3 or 68.0 on the single score line segment;

[0025] If the subject is not depressed, the value of the depression state corresponds to 0 on the single score line segment; if the subject suffers from depression, the value of the depression state corresponds to 16.3 on the single score line segment;

[0026] If the subject has no cognitive impairment, the value of the cognitive impairment state corresponds to 0 on the single score segment; if the subject has cognitive impairment, the value of the cognitive impairment state corresponds to 22.8 on the single score segment.

[0027] In conjunction with the first aspect of the present application, in an optional embodiment, in the Parkinson's disease survival prediction nomogram, the survival probability line segment within the future set time period includes a 10-year survival probability line segment and a 20-year survival probability line segment, the values ​​on the same survival probability line segment are unequally divided continuous variables, and the score range of the total score line segment is 0 to 300;

[0028] The value range of the 10-year survival probability line segment is 0.5 to 0.95, corresponding to 107 to 275 on the total score line segment, wherein the values ​​0.5, 0.7, 0.8, 0.9, and 0.95 correspond to 275, 232, 202, 154, and 107 on the total score line segment, respectively;

[0029] The value range of the 20-year survival probability line segment is 0.1 to 0.95, corresponding to 14.7 to 259.1 on the total score line segment, among which the values ​​0.1, 0.3, 0.5, 0.7, 0.8, 0.9, and 0.95 correspond to 259.1, 217.5, 182.0, 139.3, 109.2, 60.9, and 14.7 on the total score line segment respectively.

[0030] In conjunction with the first aspect of the present application, in an optional embodiment, the optimal cutoff value of the Parkinson's disease survival prediction nomogram is 150.

[0031] In conjunction with the first aspect of the present application, in an optional implementation manner, the method further includes:

[0032] The display module is configured to display the predicted survival probability of the test subject within a set future time period.

[0033] In a second aspect, an embodiment of the present application provides a method for predicting the survival probability of Parkinson's disease, which is applied to the prediction system for the survival probability of Parkinson's disease as described in the first aspect. The prediction method includes:

[0034] Obtaining six target indicators of the test subject, including age of onset, diabetes status, UPDRS III score, HY stage, depression status, and cognitive impairment status;

[0035] Based on all the target indicators and in combination with the Parkinson's disease survival prediction nomogram, the survival probability of the test subject within a set future time period is predicted.

[0036] A third aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method described in the second aspect.

[0037] A fourth aspect of the present application provides an electronic device, including:

[0038] processor; and

[0039] A memory having executable code stored thereon, which, when executed by the processor, causes the processor to execute the method described in the second aspect.

[0040] The beneficial effects of the technical solutions provided in the embodiments of the present application include:

[0041] The present application provides a prediction system for Parkinson's disease survival probability, including an acquisition module and a prediction module. The acquisition module is configured to acquire multiple target indicators of a test subject, including age of onset, diabetes status, UPDRS III score, HY stage, depression status, and cognitive impairment status. The prediction module is configured to predict the test subject's survival probability within a set future time period based on all target indicators and in combination with a Parkinson's disease survival prediction nomogram. In the prediction system, based on the test subject's target indicators, that is, selected death risk factors, with the help of a pre-constructed Parkinson's disease survival prediction nomogram, the test subject's survival probability within a set future time period is quickly estimated. This can be convenient for clinicians to use in predicting the survival prognosis of Parkinson's disease patients. In addition, compared with the conventional UPDRS III score and HY stage for roughly inferring the survival probability of Parkinson's disease patients, the present application embodiment has greater clinical benefits and more reference value for the conclusion.

[0042] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 A schematic diagram of the structure of a device for predicting the survival probability of Parkinson's disease provided in one embodiment of the present application;

[0045] Figure 2 A nomogram for predicting Parkinson's disease survival provided in one embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the survival curves of high-risk patients and low-risk patients in a test population based on the Parkinson's disease survival prediction nomogram in one embodiment of the present application;

[0047] Figure 4 for Figure 3 Schematic diagram of the corresponding 10-year cumulative survival rate and 20-year cumulative survival rate for each level;

[0048] Figure 5 and Figure 6 These are the calibration curves of the first and second verification groups in one embodiment of the present application;

[0049] Figure 7 and Figure 8 These are the ROC curves of the first and second validation groups in an embodiment of the present application;

[0050] Figure 9The nomograms, UPDRS III scores, and DCA curves of HY stages for the first and second validation groups, respectively, for 10-year survival time, and the nomograms, UPDRS III scores, and DCA curves of HY stages for the first and second validation groups, respectively, for 20-year survival time;

[0051] Figure 10 A flow chart of a method for predicting the survival probability of Parkinson's disease provided in one embodiment of the present application;

[0052] Figure 11 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0053] To make the technical solutions and beneficial effects of the present invention more clearly understood, the following detailed description is given by way of specific embodiments. The accompanying drawings are not necessarily drawn to scale, and local features may be enlarged or reduced to more clearly illustrate the details of the local features. Unless otherwise defined, the technical and scientific terms used herein have the same meanings as those in the technical field to which this application belongs.

[0054] like Figure 1 As shown, an embodiment of the present application provides a system for predicting the survival probability of Parkinson's disease, including an acquisition module 101 and a prediction module 102.

[0055] The acquisition module 101 is configured to acquire six target indicators of the test subject, including age of onset, diabetes status, UPDRS III score, HY stage, depression status and cognitive impairment status.

[0056] In this embodiment, the test subject's relevant mortality risk factors are preferably age of onset, diabetes status, UPDRS III score, HY stage, depression, and cognitive impairment. Age of onset, diabetes status, HY stage, depression, and cognitive impairment are all categorical variables, while the UPDRS III score is a continuous variable. The UPDRS III score is the Unified Parkinson's Disease Rating Scale III score, which is used to assess the motor function of Parkinson's disease patients, including tremor, muscle rigidity, bradykinesia, postural balance disorders, and other aspects. Each item in the scale is scored according to the severity of the symptoms, and the total score is the sum of the scores of each item, which is the UPDRS III score. A lower UPDRS III score generally indicates that the patient's motor dysfunction is mild, while a higher UPDRS III score indicates that the motor dysfunction is more severe.

[0057] Among the target indicators: the value of age of onset indicates whether the test subject's age of onset is under 50 years old or over 50 years old; the value of diabetes status indicates whether the test subject has diabetes; the value of UPDRSⅢ score is the test subject's Unified Parkinson's Disease Rating Scale III score, and the value range of the test subject's UPDRSⅢ score is 0-108; HY stage, also known as Hoehn-Yahr stage, is a categorical variable used to assess the severity of Parkinson's disease, and the HY stage content of the test subject can be indicated by the value of HY stage, which includes stage 1, stage 2, stage 2.5, stage 3, stage 4 and stage 5; the value of depression status indicates whether the test subject suffers from depression; the value of cognitive impairment status indicates whether the test subject suffers from cognitive impairment.

[0058] Obviously, the target indicators of age of onset, diabetes status, depression status, and cognitive impairment status all have two variable values, and the HY stage has 6 variable values. Preferably, the UPDRS III score is a positive integer ranging from 0 to 108, which can be regarded as a continuous variable with several variable values.

[0059] The prediction module 102 is configured to predict the survival probability of the test subject within a set time period in the future based on all target indicators and in combination with the Parkinson's disease survival prediction nomogram.

[0060] In the prediction module 102, the prediction module 102 includes a Parkinson's disease survival prediction nomogram. The Parkinson's disease survival prediction nomogram includes individual score segments, six target indicator segments, a total score segment, and a survival probability segment within a set future time period. The target indicator values ​​on the corresponding target indicator segments correspond to the scores on the individual score segments. The sum of the scores of all target indicators is the score on the total score segment. The survival probability values ​​on the corresponding survival probability segments within a set future time period correspond to the scores on the total score segment. The individual score segments, target indicator segments, total score segments, and survival probability segments within a set future time period each occupy a row on the Parkinson's disease survival prediction nomogram.

[0061] It should be noted that the nomogram, as a visualization tool for predicting the probability of a specific event or evaluating a certain result, is usually composed of several line segments with scales. Each line segment represents a variable. By finding the value of the target indicator on the corresponding line segment and then drawing a vertical line upward, the individual score corresponding to the target indicator can be obtained on the individual score segment. Finally, all individual scores are added together, and the predicted event probability or result can be read on a specific survival prediction segment through the total score.

[0062] Furthermore, in the Parkinson's disease survival prediction nomogram, the score range of the single score segment is 0 to 100; if the age of onset of the test subject is under 50 years old, the value of the onset age corresponds to 0 on the single score segment; if the age of onset of the test subject is over 50 years old, the value of the onset age corresponds to 100 on the single score segment; if the test subject has no diabetes, the value of the diabetes status corresponds to 0 on the single score segment; if the test subject has diabetes, the value of the diabetes status corresponds to 45.8 on the single score segment; if the UPDRSⅢ score of the test subject ranges from 0 to 108, the maximum value of the UPDRSⅢ score corresponds to 63.7 on the single score segment, and the minimum value corresponds to 0. The value corresponds to 0, and the correspondence between the value and the score is linear; if the HY stage of the test subject is stage 1, stage 2, stage 2.5, stage 3, stage 4 or stage 5, the value of the HY stage corresponds to 0, 25.4, 36.6, 42.4, 50.3 or 68.0 on the single score line segment respectively; if the test subject is not depressed, the value of the depression state corresponds to 0 on the single score line segment; if the test subject has depression, the value of the depression state corresponds to 16.3 on the single score line segment; if the test subject has no cognitive impairment, the value of the cognitive impairment state corresponds to 0 on the single score line segment; if the test subject has cognitive impairment, the value of the cognitive impairment state corresponds to 22.8 on the single score line segment. Therefore, the corresponding values ​​can be determined based on the characteristics corresponding to each target indicator of the test subject, and then the score on the single score line segment can be found based on the value of the target indicator on the target indicator line segment in the Parkinson's disease survival prediction nomogram, that is, the single score of the target indicator.

[0063] In the embodiment of the present application, the value of each target indicator has a corresponding score on the single score segment. For example, the single score of the test subject whose onset age is over 50 years old corresponds to 100 on the single score segment, etc. The mapping relationship between the value of the target indicator and the score can be referred to the above records and will not be repeated here in detail.

[0064] Furthermore, in the Parkinson's disease survival prediction nomogram, the survival probability segments within the future set time period include the 10-year survival probability segment and the 20-year survival probability segment. The values ​​on the same survival probability segment are continuous variables with uneven distribution, and the total score segment ranges from 0 to 300. The 10-year survival probability segment ranges from 0.5 to 0.95, corresponding to the total score segment of 107 to 275, where the values ​​are 0.5, 0.7, 0.8, 0.9, and 0. 95 corresponds to 275, 232, 202, 154, and 107 on the total score line segment respectively. The value range of the 20-year survival probability line segment is 0.1 to 0.95, corresponding to 14.7 to 259.1 on the total score line segment. Among them, the values ​​0.1, 0.3, 0.5, 0.7, 0.8, 0.9, and 0.95 correspond to 259.1, 217.5, 182.0, 139.3, 109.2, 60.9, and 14.7 on the total score line segment respectively.

[0065] In this embodiment, there are preferably two survival probability segments: a 10-year survival probability segment and a 20-year survival probability segment. Taking the 10-year survival probability segment as an example, the value on the 10-year survival probability segment represents the probability that the subject will survive 10 years from the age of onset. Based on the actual situation of the subject, a value that matches the target indicator is selected from the target indicator. The values ​​of the target indicators corresponding to the scores on the individual score segments are described above. The individual scores of all target indicators are determined. In this embodiment, the sum of the individual scores of all target indicators is equal to the score on the total score segment. Therefore, a total score can be found on the total score segment based on the sum of the individual scores of all target indicators. This total score is then used to map the values ​​on the 10-year survival probability segment and the 20-year survival probability segment.

[0066] It should be noted that if Figure 2 As shown in the figure, if the total score of the test subject is 5, the total score cannot find a clear value on the 10-year survival probability segment and the 20-year survival probability segment. It can be inferred that the 10-year survival probability of the test subject is much greater than 0.95, and the 20-year survival probability is greater than 0.95.

[0067] Preferably, the optimal cutoff value of the Parkinson's disease survival prediction nomogram is 150. In an embodiment of the present application, Parkinson's patients are divided into high-risk patients and low-risk patients according to the optimal cutoff value. Among them, the total score of the test subject, that is, the risk value, can be calculated from the Parkinson's disease survival prediction nomogram. If the risk value is above the optimal cutoff value of 150, the test subject can be divided into a high-risk patient, that is, the test subject has a high risk of death, otherwise it is a low-risk patient. It can be seen that the embodiment of the present application can also classify the test subject according to the actual situation of the test subject through the optimal cutoff value of the Parkinson's disease survival prediction nomogram, and divide it into high-risk patients and low-risk patients, which can also be regarded as a grade division. Then, high-risk patients can be included in the high-risk group, and low-risk patients can be included in the low-risk group.

[0068] In some embodiments, the prediction system further includes a display module 103, which is configured to display the predicted survival probability of the test subject within a set future time period. In practical applications, the predicted survival probability of the test subject within a set future time period can be displayed in a visual manner through the display module 103. Of course, embodiments of the present application include, but are not limited to, displaying the survival probability, and can also visually display other related data.

[0069] In this embodiment, the Parkinson's disease survival prediction nomogram is a constructed nomogram. Based on the values ​​of each target indicator, the scores corresponding to each target indicator are obtained on the individual score segments. The total score on the total score segment is calculated based on the sum of all the obtained scores. Finally, the probability value is read on the 10-year survival probability segment based on the total score, and the probability value is read on the 20-year survival probability segment based on the total score. The Parkinson's disease survival prediction nomogram can be converted into a webpage formula for calculation, such as the webpage https: / / pdmdcnc-pd.shinyapps.io / PD-survival / . Simply enter the six target indicators on the webpage to directly obtain the 10-year survival probability and 20-year survival probability results.

[0070] The present invention provides a system for predicting the survival probability of Parkinson's disease, which can address the current lack of clarity regarding the contribution of risk factors to the mortality of Parkinson's patients. The nomogram, as a visual tool, displays the weights of different target indicators for the mortality of Parkinson's patients, thereby obtaining 10-year and 20-year survival probabilities, providing effective assistance in Parkinson's disease monitoring and risk stratification. The present invention can facilitate clinicians in predicting the survival prognosis of Parkinson's patients. Compared with the conventional UPDRS III score and HY stage for roughly inferring the survival probability of PD patients, the present invention has greater clinical benefits and more reliable conclusions.

[0071] The present application is described in detail below with reference to a specific embodiment.

[0072] like Figure 2 As shown in Figure 1, this is a nomogram for Parkinson's disease survival prediction. The nomogram has ten rows. The first row is the individual score line segment, with a score range of 0 to 100. Rows two through seven are the target indicator lines, which are, in order, age of onset, diabetes status, UPDRS III score, HY stage, depression status, and cognitive impairment status. Each value of the target indicator in rows two through seven corresponds to a score on the individual score line segment, and this variable is the independent variable. Row eight is the total score line segment, with a score range of 0 to 300. Rows nine through ten are the 10-year and 20-year survival probability line segments, respectively, and this variable is the dependent variable. The survival probabilities in rows nine and ten are unequally distributed on these survival probability lines. Each value of the survival probability variable in rows nine and ten corresponds to a total score on the total score line segment, and the sum of the scores for the six target indicators equals the total score on the total score line segment.

[0073] In the Parkinson's disease survival prediction nomogram, the age of onset includes two variable values, namely, the age of onset is under 50 years old and the age of onset is over 50 years old. The single score of the age of onset is 0 for the age of onset is under 50 years old, and the single score of the age of onset is 100; the diabetes status includes two variable values, namely, the presence or absence of diabetes. The single score of no diabetes is 0, and the single score of diabetes is 45.8; the variable value of UPDRSⅢ score ranges from 0 to 108, and UPDRSⅢ The maximum score of 108 corresponds to a single score of 63.7, and the minimum score of 0 corresponds to a single score of 0. Different single scores are determined according to different values, and the corresponding relationship between the UPDRSⅢ score and the single score is a linear relationship; the HY stage includes 6 variable values, namely HY1, HY2, HY2.5, HY3, HY4 and HY5, and the corresponding single scores are 0, 25.4, 36.6, 42.4, 50.3 and 68.0 respectively. ; Depression status includes two variable values, namely, the presence or absence of depression. The single score of no depression is 0, and the single score of depression is 16.3; Cognitive impairment status includes two variable values, namely, the presence or absence of cognitive impairment. The single score of no cognitive impairment is 0, and the single score of cognitive impairment is 22.8; The value range of the 10-year survival probability line segment is 0.5-0.95, corresponding to 107-275 on the total score line segment, among which the values ​​of 10-year survival probability are 0.5, 0.7, and 0.8 , 0.9, and 0.95 correspond to total scores of 275, 232, 202, 154, and 107, respectively; the value range of the 20-year survival probability segment is 0.1-0.95, corresponding to the total score segment of 14.7-259.1, among which the 20-year survival probability values ​​of 0.1, 0.3, 0.5, 0.7, 0.8, 0.9, and 0.95 correspond to total scores of 259.1, 217.5, 182.0, 139.3, 109.2, 60.9, and 14.7, respectively.

[0074] like Figure 3 As shown, it is a schematic diagram of the survival curves of high-risk patients and low-risk patients in the test population. In this embodiment, the optimal cutoff value of the Parkinson's disease survival prediction nomogram is 150. According to the optimal cutoff value of 150, the test population is divided into two levels, one high and the other low, where the high value indicates that the test subject is a high-risk patient. The test population can be obtained from my country's Parkinson's disease registration grade system, and the Kaplan-Meier curve is used to show the changing trend of survival rates of different grades, as shown in Figure 2. Figure 3 As shown in , the 10-year cumulative survival rate and 20-year cumulative survival rate of each level can also be calculated, as shown in Figure 4 The results showed that the 20-year cumulative survival rate of high-risk patients was much lower than that of low-risk patients. There was a gap in the 10-year cumulative survival rate, but it was far less than the 20-year cumulative survival rate.

[0075] Confirmatory analysis was performed using the "createDataPartition" function in R language to divide the Parkinson's disease test population into a first validation group and a second validation group in a ratio of 7:3 to ensure that the outcome events were randomly distributed between the two groups. The accuracy of the above-mentioned Parkinson's disease survival prediction nomogram was verified and evaluated using two different validation groups. The evaluation indicators included C-Index (concordance index) and time-dependent AUC (Area Under the Curve).

[0076] It should be noted that the value range of C-Index is 0.5 to 1.0. When C-Index is 0.5, it means that the prediction is completely random; when C-Index is 1, it means that the prediction is completely accurate. Generally speaking, the higher the value of C-Index, the higher the prediction accuracy. Usually, a C-Index value greater than 0.7 indicates that the prediction accuracy is reasonable. In addition, the time-dependent AUC refers to the area under the Receiver Operating Characteristic curve (ROC curve). The ROC curve is a curve drawn by continuously changing the diagnostic threshold, with the true positive rate (sensitivity) as the vertical axis and the false positive rate (1-specificity) as the horizontal axis. The value of AUC ranges from 0.5 to 1. The closer the value is to 1, the better the prediction performance. AUC values ​​greater than 0.7 indicate reasonable prediction accuracy.

[0077] like Figure 5 and Figure 6 As shown, they are the calibration curves of the first and second validation groups respectively. Figure 5 It can be seen that in the first validation group, the C-Index (C-index) of the 10-year survival probability is 0.7353, and the C-Index of the 20-year survival probability is 0.8021, and both C-Index are above 0.7. Figure 6 As can be seen, in the second validation group, the C-Index (C-value) for the 10-year survival probability was 0.7253, and the C-Index for the 20-year survival probability was 0.7588, both of which were above 0.7. As can be seen from the two calibration curves, both the first and second validation groups demonstrated the rationality of the Parkinson's disease survival prediction nomogram.

[0078] like Figure 7 and Figure 8 As shown, they are the ROC curves of the first and second validation groups respectively. Figure 7It can be seen that in the first validation group, the AUC of the 10-year survival probability was 0.74, and the AUC of the 20-year survival probability was 0.80, both of which were above 0.7. Figure 8 As can be seen, in the second validation group, the AUC for the 10-year survival probability was 0.73, and the AUC for the 20-year survival probability was 0.76, both of which were above 0.7. It can be inferred from the two ROC curves that both the first and second validation groups can demonstrate the rationality of the Parkinson's disease survival prediction nomogram.

[0079] The embodiment of the present application uses multiple different evaluation indicators to verify the Parkinson's disease survival prediction nomogram, which can reflect the accuracy of the nomogram in estimating the survival probability of the test subjects.

[0080] like Figure 9 As shown, the DCA (Decision Curve Analysis) curves of the nomogram, UPDRS III score, and HY stage corresponding to the first and second validation groups for 10-year survival time, and the DCA curves of the nomogram, UPDRS III score, and HY stage corresponding to the first and second validation groups for 20-year survival time, where Figure 9 On the left are the nomogram, UPDRSⅢ score and DCA curve of HY stage of the first validation group, and the nomogram, UPDRSⅢ score and DCA curve of HY stage of the second validation group. Figure 9 The two sets of DCA curves in the paper plotted the curves of the scenario where all deaths occurred (representing the highest clinical cost) and the scenario where no deaths occurred (representing no clinical benefit) as two references. DCA, or decision curve analysis, is one of the methods for evaluating clinical predictions, diagnostic tests, and treatment strategies. It is mainly used to compare the net benefits of different strategies under different threshold probabilities, helping clinicians and decision makers make more reasonable decisions in actual clinical settings. By drawing DCA curves, you can intuitively see the advantages and disadvantages of different strategies in different situations. Figure 9 It is not difficult to find that the net benefit corresponding to the nomogram is relatively the highest. Therefore, compared with the conventional UPDRS III score and HY stage to roughly infer the survival probability of PD patients, the clinical benefit of the embodiment of the present application is higher and the conclusion is more referenceable.

[0081] Corresponding to the aforementioned application function implementation system embodiment, the present application also provides a method for determining the survival probability of Parkinson's patients, an electronic device, and corresponding embodiments.

[0082] Figure 10 This is a flow chart of a method for predicting the survival probability of Parkinson's disease according to an embodiment of the present application.

[0083] like Figure 10 As shown, the embodiment of the present application provides a method for predicting the survival probability of Parkinson's disease, which is applied to the above-mentioned prediction system for the survival probability of Parkinson's disease. The prediction method includes:

[0084] Step S1001: Acquire six target indicators of the test subject, including age of onset, diabetes status, UPDRS III score, HY stage, depression status, and cognitive impairment status;

[0085] Step S1002: Based on all target indicators and in combination with the Parkinson's disease survival prediction nomogram, the survival probability of the test subject within a set time period in the future is predicted.

[0086] Regarding the method in the above embodiment, the specific manner of operation of each process has been described in detail in the embodiment of the system, and will not be elaborated again here.

[0087] The present application embodiment can be system, method and / or computer program product.Computer program product can comprise computer-readable storage medium, carries thereon the computer-readable program instruction for making processor realize the various aspects of the present application.Computer program product can write the program code for performing the operation of the present application embodiment with any combination of one or more programming languages, and programming language comprises object-oriented programming language, such as Java, C++ etc., also comprises conventional procedural programming language, such as " C " language or similar programming language.Program code can be executed completely on user computing device, partially on user device, execute as an independent software package, partly on user computing device, partly on remote computing device, or execute completely on remote computing device or server.In the situation relating to remote computer, remote computer can be connected to user computer by any kind of network-including local area network (LAN) or wide area network (WAN), or, can be connected to external computer (such as utilizing Internet service provider to connect by Internet). In some embodiments, by utilizing state information of computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions, thereby implementing various aspects of the present application.

[0088] Computer-readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. A computer-readable storage medium is a tangible device that can maintain and store the instructions used by the instruction execution device. The readable storage medium can, for example, include but is not limited to a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination thereof. The computer-readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0089] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0090] Various aspects of the present application are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0091] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0092] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0093] An embodiment of the present application also provides an electronic device. Figure 11 Shown is a structural schematic diagram of an electronic device provided in one embodiment of the present application.

[0094] like Figure 11 As shown, the electronic device 1100 includes:

[0095] Processor 1101;

[0096] The memory 1102 is used to store computer executable instructions. When the executable code is executed by the processor, the processor executes the method as described above.

[0097] The processor 1101 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0098] Memory 1102 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and processor 1101 may execute the program instructions to implement the steps of the text recognition method of each embodiment of the present application described above and / or other desired functions.

[0099] In one example, the electronic device 1100 may further include: an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown in the figure).

[0100] In addition, the input device may also include, for example, a keyboard, a mouse, a microphone, etc. The output device may output various information to the outside, and may include, for example, a display, a speaker, a printer, a communication network and its connected remote output devices, etc.

[0101] Of course, to simplify, Figure 11 Only a portion of the components related to the present application in the electronic device 1100 is shown, omitting components such as a bus, input device / output interface, etc. In addition, the electronic device 1100 may further include any other appropriate components according to specific application scenarios.

[0102] It should be noted that the system embodiment, method embodiment, medium embodiment and device embodiment for predicting the survival probability of Parkinson's disease provided in the embodiments of the present application belong to the same concept; the technical features in the technical solutions recorded in each embodiment can be arbitrarily combined without conflict.

[0103] It should be understood that the above embodiments are exemplary and are not intended to encompass all possible implementations of the claims. Various modifications and variations may be made to the above embodiments without departing from the scope of this disclosure. Similarly, the various technical features of the above embodiments may be arbitrarily combined to form additional embodiments of the present invention that may not be explicitly described. Therefore, the above embodiments merely illustrate several implementations of the present invention and do not limit the scope of protection of the patent of this invention.

Claims

1. A system for predicting the survival probability of Parkinson's disease, characterized in that: include: an acquisition module configured to acquire six target indicators of the test subject, wherein the target indicators include age of onset, diabetes status, UPDRS III score, HY stage, depression status, and cognitive impairment status; The prediction module is configured to predict the survival probability of the test subject within a set time in the future based on all the target indicators and in combination with the Parkinson's disease survival prediction nomogram; wherein, The Parkinson's disease survival prediction nomogram includes a single score line segment, six target indicator line segments, a total score line segment, and a survival probability line segment within a set time in the future; If the age of onset is under 50 years old, the corresponding score line segment is 0; if the age of onset is over 50 years old, the corresponding score line segment is 100; If there is no diabetes, the corresponding value is 0 on the individual score line segment; if there is diabetes, the corresponding value is 45.8 on the individual score line segment; If the UPDRSⅢ score ranges from 0 to 108, then the corresponding value is 0-63.7 on the individual score line segment, and the corresponding relationship between the value and the score is a linear relationship; If the HY installment content is 1 period, 2 periods, 2.5 periods, 3 periods, 4 periods or 5 periods, the corresponding individual score line segments are 0, 25.4, 36.6, 42.4, 50.3 or 68.0 respectively; If there is no depression, the corresponding score is 0 on the single score line segment; if there is depression, the corresponding score is 16.3 on the single score line segment; If there is no cognitive impairment, the corresponding score is 0 on the single score line segment; if there is cognitive impairment, the corresponding score is 22.8 on the single score line segment; The individual scores corresponding to the six target indicators obtained on the individual score line segment are added together to obtain the total score. The predicted event probability or result is read on the survival probability line segment within a set time in the future using the total score; The survival probability line segment within the future set time period includes a 10-year survival probability line segment, and the value range of the 10-year survival probability line segment is 0.5~0.95, corresponding to 107~275 on the total score line segment.

2. The system for predicting the survival probability of Parkinson's disease according to claim 1, characterized in that: Among the target indicators: The age of onset is a categorical variable, and the value of the age of onset indicates whether the subject is under 50 years old or over 50 years old; The diabetes status is a categorical variable, and the value of the diabetes status indicates whether the subject suffers from diabetes; The UPDRSⅢ score is a continuous variable, and the value of the UPDRSⅢ score is the Unified Parkinson's Disease Rating Scale Ⅲ score of the test subject; The HY stage is a categorical variable, and the value of the HY stage represents the HY stage content of the test subject; The depression state is a categorical variable, and the value of the depression state indicates whether the subject suffers from depression; The cognitive impairment status is a categorical variable, and the value of the cognitive impairment status indicates whether the subject suffers from cognitive impairment.

3. The system for predicting the survival probability of Parkinson's disease according to claim 2, characterized in that: The value of the target indicator on the corresponding target indicator line segment corresponds to the score on the individual score line segment; The sum of the scores of all the target indicators is the score on the total score line segment; The value of the survival probability within the set future time on the corresponding survival probability line segment corresponds to the score on the total score line segment; The individual score line segment, target indicator line segment, total score line segment, and survival probability line segment within a set future time period each occupy a row on the Parkinson's disease survival prediction nomogram.

4. The system for predicting the survival probability of Parkinson's disease according to claim 3, characterized in that: In the Parkinson's disease survival prediction nomogram, the score range of the single score segment is 0-100.

5. The system for predicting the survival probability of Parkinson's disease according to claim 3, characterized in that: In the Parkinson's disease survival prediction nomogram, the survival probability line segment within the future set time period also includes a 20-year survival probability line segment, the values ​​on the same survival probability line segment are continuous variables with unequal distribution, and the score range of the total score line segment is 0-300; The value range of the 20-year survival probability line segment is 0.1~0.95, corresponding to 14.7~259.1 on the total score line segment, among which the values ​​0.1, 0.3, 0.5, 0.7, 0.8, 0.9, and 0.95 correspond to 259.1, 217.5, 182.0, 139.3, 109.2, 60.9, and 14.7 on the total score line segment respectively.

6. The system for predicting the survival probability of Parkinson's disease according to claim 5, characterized in that: The optimal cutoff value of the Parkinson's disease survival prediction nomogram was 150.

7. The system for predicting the survival probability of Parkinson's disease according to claim 1, characterized in that: Also includes: The display module is configured to display the predicted survival probability of the test subject within a set future time period.

8. A method for predicting the survival probability of Parkinson's disease, characterized in that: The system for predicting the survival probability of Parkinson's disease according to any one of claims 1 to 7, wherein the prediction method comprises: Obtaining six target indicators of the test subject, including age of onset, diabetes status, UPDRS III score, HY stage, depression status, and cognitive impairment status; Based on all the target indicators and in combination with the Parkinson's disease survival prediction nomogram, the survival probability of the test subject within a set future time period is predicted.

9. A computer-readable storage medium, characterized in that An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method according to claim 8.

10. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to perform the method according to claim 8.

Images