Construction method of Parkinson's disease curative effect prediction model and STN-DBS operation decision-making auxiliary system

Abstract

The invention relates to the technical field of medical data processing, and discloses a Parkinson's disease curative effect prediction model construction method and an STN-DBS operation decision-making auxiliary system, and aims at constructing a Parkinson's disease curative effect prediction model by utilizing an elastic network of machine learning according to data of multiple dimensions such as clinical information, motion function scores, emotion scores, cognitive function scores and the like before and after a target group receives STN-DBS treatment. According to the method, the Parkinson's disease patients subjected to subthalamic nuclear brain deep electrical stimulation can be accurately screened before an operation, and the accuracy and efficiency of making individualized operation decisions for the Parkinson's disease patients with different clinical symptoms are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a method for constructing a Parkinson's disease efficacy prediction model and an STN-DBS surgery decision-making auxiliary system. Background Art

[0002] Subthalamic nucleus deep brain stimulation (STN-DBS) is an emerging treatment for Parkinson's disease (PD). Several randomized controlled trials conducted since the 1990s have shown that STN-DBS has more benefits and advantages than drug interventions, and its efficacy is usually measured using the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) sponsored by the Movement Disorder Society. In order to improve the efficacy of STN-DBS, the selection of the best surgical candidates, accurate target positioning, adequate stimulation regimens, and appropriate drug management are required. However, even for experienced movement disorder specialists, it is still challenging to make individualized surgical decisions for patients with different clinical symptoms, and tools are needed to predict potential surgical outcomes based on preoperative evaluation.

[0003] Therefore, there is an urgent need for a method to construct a Parkinson's disease efficacy prediction model and a STN-DBS surgery decision-making support system. Summary of the invention

[0004] The present invention provides a method for constructing a Parkinson's disease efficacy prediction model and an STN-DBS surgery decision-making auxiliary system, which are used to solve the defect of lacking auxiliary tools for predicting potential surgical results based on preoperative evaluation.

[0005] The present invention provides a method for constructing a Parkinson's disease efficacy prediction model, comprising:

[0006] Obtain clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, where the target group includes Parkinson's disease patients;

[0007] Based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, factor regression analysis was used to obtain characteristic variables related to the efficacy of STN-DBS.

[0008] According to the characteristic variables related to the efficacy of STN-DBS, a Parkinson's disease efficacy prediction model was constructed through the elastic network.

[0009] In one embodiment, the clinical information includes any one or any combination of the following: disease duration, age at surgery, age at onset, levodopa equivalent dose (LED), and levodopa medication improvement rate.

[0010] In one embodiment, the motor function score comprises a motor function score obtained by the Unified Parkinson's Disease Rating Scale (UPDRS).

[0011] In one embodiment, the mood score includes a first mood score obtained by the Hamilton Anxiety Rating Scale (HAMA) and a second mood score obtained by the Hamilton Depression Rating Scale (HAMD).

[0012] In one embodiment, the cognitive function score includes a first cognitive function score obtained by the Mini-Mental State Examination (MMSE) and a second cognitive function score obtained by the Montreal Cognitive Assessment (MoCA).

[0013] In one embodiment, the factor regression analysis method includes univariate COX regression analysis and multivariate COX regression analysis, wherein the factor regression analysis method is used to obtain characteristic variables related to the efficacy of STN-DBS based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, including:

[0014] Based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, the first potential risk factor related to the efficacy of STN-DBS was obtained using univariate COX regression analysis;

[0015] According to the first potential risk factor related to the efficacy of STN-DBS, the second potential risk factor related to the efficacy of STN-DBS was used as the characteristic variable related to the efficacy of STN-DBS using multivariate COX regression analysis.

[0016] In one embodiment, the first potential risk factor related to STN-DBS efficacy is obtained by using univariate COX regression analysis based on the clinical information, motor function score, emotional score, and cognitive function score of the target group, including:

[0017] According to the clinical information, motor function score, emotional score, and cognitive function score of the target group, the univariate COX regression analysis method was used, and the factor corresponding to the probability value P1<0.05 in the univariate COX regression analysis results was taken as the first potential risk factor related to the efficacy of STN-DBS.

[0018] In one embodiment, the second potential risk factor related to STN-DBS efficacy is analyzed by multivariate COX regression analysis based on the first potential risk factor related to STN-DBS efficacy as a characteristic variable related to STN-DBS efficacy, including:

[0019] According to the first potential risk factor related to the efficacy of STN-DBS, the multivariate COX regression analysis method was used, and the first potential risk factor corresponding to the probability value P2<0.05 in the multivariate COX regression analysis results was taken as the second potential risk factor related to the efficacy of STN-DBS, and at the same time as a characteristic variable related to the efficacy of STN-DBS.

[0020] In one embodiment, the Parkinson's disease efficacy prediction model is constructed based on characteristic variables related to STN-DBS efficacy, comprising:

[0021] According to the characteristic variables related to the efficacy of STN-DBS, a Parkinson's disease efficacy prediction model was constructed using the elastic network, where the Parkinson's disease efficacy prediction model was presented in the form of a nomogram.

[0022] The present invention also provides a system for constructing a Parkinson's disease efficacy prediction model, comprising:

[0023] The data acquisition module is used to obtain clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, wherein the target group includes the Parkinson's disease patient group;

[0024] The preprocessing module is used to obtain characteristic variables related to the efficacy of STN-DBS based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group using factor regression analysis;

[0025] The construction module is used to: construct a Parkinson's disease efficacy prediction model through an elastic network based on characteristic variables related to STN-DBS efficacy.

[0026] The invention also provides a STN-DBS surgery decision support system, comprising:

[0027] The data receiving module is used to: receive clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery;

[0028] A prediction module is used to: obtain a prediction result of whether the subject is suitable for STN-DBS surgery based on the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment and the Parkinson's efficacy prediction model obtained by any of the above-mentioned methods for constructing a Parkinson's efficacy prediction model;

[0029] The data output module is used to send the prediction result of whether the subject is suitable for STN-DBS surgery back to the at least one terminal.

[0030] The present invention also provides an electronic device, comprising a processor and a memory storing a computer program, wherein the processor implements any of the above-mentioned methods for constructing a Parkinson's disease efficacy prediction model when executing the computer program.

[0031] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for constructing any of the above-mentioned Parkinson's disease efficacy prediction models is implemented.

[0032] The present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute any of the above-mentioned methods for constructing a Parkinson's efficacy prediction model.

[0033] The present invention provides a method for constructing a Parkinson's disease efficacy prediction model and an STN-DBS surgery decision-making support system. According to the clinical information, motor function scores, emotion scores, cognitive function scores and other dimensional data of the target group before and after STN-DBS treatment, a high-precision Parkinson's disease efficacy prediction model is constructed through a machine learning elastic network. The model can achieve accurate preoperative screening of Parkinson's disease patients who undergo subthalamic nucleus deep brain stimulation, and effectively improve the accuracy and efficiency of making individualized surgical decisions for Parkinson's disease patients with different clinical symptoms. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A schematic flow chart of a method for constructing a Parkinson's disease efficacy prediction model provided by the present invention.

[0036] Figure 2 The figure is a schematic diagram of cross-validation through a training set and a validation set in the process of constructing a Parkinson's disease efficacy prediction model according to an embodiment of the present invention.

[0037] Figure 3 The figure is a schematic diagram of performing specificity and sensitivity tests on a training set and a validation set in the process of constructing a Parkinson's disease efficacy prediction model according to an embodiment of the present invention.

[0038] Figure 4This is a schematic diagram of verifying the effectiveness of the model using a calibration curve and an ROC curve through a training set in the process of constructing a Parkinson's disease efficacy prediction model according to an embodiment of the present invention.

[0039] Figure 5 The figure is a schematic diagram of verifying the effectiveness of the model by using a calibration curve and an ROC curve through a validation set in the process of constructing a Parkinson's disease efficacy prediction model according to an embodiment of the present invention.

[0040] Figure 6 A schematic diagram showing a Parkinson's disease efficacy prediction model constructed according to an embodiment of the present invention.

[0041] Figure 7 A schematic diagram of the structure of a system for constructing a Parkinson's disease efficacy prediction model provided by the present invention.

[0042] Figure 8 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments, and they should not be understood as limitations on the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0044] Combine the following Figure 1-Figure 8 The present invention describes a method for constructing a Parkinson's efficacy prediction model and a STN-DBS surgery decision support system. It should be noted that the execution subject of the method for constructing a Parkinson's efficacy prediction model provided by the present invention can be any network-side device / terminal-side device that meets the technical requirements, such as a device for constructing a Parkinson's efficacy prediction model.

[0045] Figure 1 Schematic diagram of the method for constructing a Parkinson's disease efficacy prediction model provided by the present invention. Figure 1 The present invention provides a method for constructing a Parkinson's disease efficacy prediction model, which may include:

[0046] Step S110, obtaining clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, wherein the target group includes a Parkinson's patient group. This embodiment obtains clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before STN-DBS treatment, and one year and five years after the target group receives STN-DBS treatment, which helps the Parkinson's efficacy prediction model to understand the relationship between clinical information, motor function scores, emotional scores, cognitive function scores and the long-term and short-term efficacy of STN-DBS treatment.

[0047] This example uses 496 PD patients who underwent bilateral DBS as the target group and collects their clinical information, motor function scores, mood scores, and cognitive function scores. The inclusion criteria include: (1) meeting the 2006 diagnostic criteria for primary PD of the Movement Disorders and PD Group of the Neurology Branch of the Chinese Medical Association; (2) Parkinson's disease course > 4 years; (3) significant decline in drug efficacy, or symptom fluctuations and dyskinesias of the "on-off" phenomenon, which affect the patient's quality of life; (4) patients and their families signed informed consent. Exclusion criteria include: (1) patients with contraindications to DBS; (2) patients with moderate or severe cognitive impairment or persistent severe mental disorders; (3) patients with severe brain atrophy and diffuse cerebral ischemic lesions shown by cranial MRI; (4) patients who were unable to complete postoperative follow-up.

[0048] Specifically, the clinical information includes any one of the following or any combination thereof: disease course, age at surgery, age at onset, levodopa equivalent dose (LED) and levodopa medication improvement rate, wherein levodopa medication improvement rate = (baseline score before medication - lowest score after medication) / baseline score before medication × 100%.

[0049] Motor function scores include motor function scores obtained through the Unified Parkinson's Disease Rating Scale (UPDRS). The Unified Parkinson's Disease Rating Scale is an internationally recognized Parkinson's disease symptom rating scale, including 4 subscales (UPDRS-Ⅰ, II, III, IV). The higher the score on this scale, the more severe the symptoms. UPDRS-Ⅰ is a mental, behavioral and emotional score that assesses the patient's mental state, including 1 to 4 items, with a total score of 0 to 16 points. The higher the score, the more severe the symptoms. UPDRS-Ⅱ is a score for daily living activities, including 13 items such as writing, dressing, personal hygiene, and turning over, with a total score of 0 to 52 points. The higher the total score, the worse the daily living ability and the more unable to take care of oneself. UPDRS-Ⅲ is a motor examination score, including 14 items such as facial expression, tremor, rigidity, bradykinesia, posture disorder, gait examination, with a total score of 0 to 56 points. The higher the score, the more severe the somatic motor symptoms. UPDRS-Ⅳ is a motor complication score, including the assessment of complications such as dyskinesia and symptom fluctuations, with a total score of 0 to 23 points. A score of >1 in item 32 indicates that the PD patient has dyskinesia; a score of =1 in item 36 indicates that the patient has a "switch" phenomenon. UPDRS uses a 0-4 grading scale, with a total score of 199. The scores of each part are weighted to obtain the total score, and a higher total score indicates a more severe condition.

[0050] The mood scores include a first mood score obtained by the Hamilton Anxiety Rating Scale (HAMA) and a second mood score obtained by the Hamilton Depression Rating Scale (HAMD).

[0051] The first emotion score includes scores for 14 domains: anxious mood, tension, fear, insomnia, cognitive function (or memory, attention disorder), depressed mood, somatic anxiety, somatic anxiety, cardiovascular system symptoms, respiratory system symptoms, gastrointestinal symptoms, genitourinary system symptoms, autonomic nervous system symptoms, and behavioral performance during interviews. All HAMA items use a 5-level scoring method of 0 to 4 points, and the standards for each level are: 0 points: no symptoms; 1 point: mild; 2 points: moderate; 3 points: severe; 4 points: extremely severe. The total score of HAMA can better reflect the severity of anxiety symptoms. The total score can be used to evaluate the severity of anxiety symptoms in patients with anxiety and depressive disorders and to evaluate the effects of various drugs and psychological interventions. According to the data provided by the scale collaboration group in my country: a total score of ≥29 points may be severe anxiety; ≥21 points, there must be obvious anxiety; ≥14 points, there must be anxiety; more than 7 points, there may be anxiety; if it is less than 7 points, there is no anxiety symptom.

[0052] The second emotion score includes 24 items such as depression, guilt, suicide, difficulty falling asleep, physical anxiety, general symptoms and insight. Each item is expressed as 0-2 points or 0-4 points to indicate the severity. The sum of the scores is the HAMD score. A total score of ≥35 points indicates severe depressive symptoms; a total score of ≥30 points and <35 points indicates moderate depressive symptoms; a total score of ≥20 points and <30 points indicates mild or moderate depressive symptoms; a total score of ≥8 points and <20 points indicates no obvious depressive symptoms; a total score of <8 points indicates no depressive symptoms.

[0053] The cognitive function scores included the first cognitive function score obtained by the Mini-Mental State Examination (MMSE) and the second cognitive function score obtained by the Montreal Cognitive Assessment (MoCA).

[0054] The first cognitive function score includes scores for five subdomains: orientation, attention, memory, language ability, and executive ability.

[0055] MMSE scale criteria: (1) Cognitive dysfunction: the highest score is 30 points, scores between 27 and 30 are normal, and scores <27 are cognitive dysfunction; (2) Dementia classification criteria: illiterate ≤ 17 points, primary school level ≤ 20 points, secondary school level (including technical secondary school) ≤ 22 points, university level (including junior college) ≤ 23 points; (3) Dementia severity classification: mild MMSE ≥ 21 points, moderate MMSE 10-20 points, severe MMSE ≤ 9 points. The MMSE scale examines the patient's cognitive level by evaluating the following five aspects: (1) Orientation: Orientation refers to a person's ability to recognize time, place, people, and their own status. In the scale examination, this item is reflected in questions such as "date, season, province, city". (2) Memory: Memory is the ability to recognize, retain, re-recognize and reproduce the content and experience reflected by objective things. In the memory examination, the doctor usually tells the subject that he will ask several questions to check his memory. The doctor says the names of three unrelated things and then asks the subject to repeat them. (3) Attention and calculation ability: Attention refers to the ability of a person's mental activities to be directed and focused on a certain thing. In this part of the examination, the doctor will ask the subject to subtract 7 from 100, then subtract 7 again, and continue subtracting 5 times. (4) Recall ability: In the examination of recall ability, the doctor will ask the subject to repeat the names of three unrelated things that the doctor had previously said to test the subject's recall ability. (5) Language ability: Language ability refers to the ability to master language. This ability is manifested in the ability to speak or understand unprecedented, grammatical sentences, the ability to distinguish ambiguous sentences, the ability to distinguish sentences with the same surface form but different actual semantics or sentences with different surface forms but similar actual semantics, and the ability to use language skills such as listening, speaking, reading, writing and translating. In the MMSE scale, language ability is evaluated in the following six aspects: (1) Naming ability: the doctor will take out some cards and objects for the subjects to see, and ask the subjects to say the names of the objects shown on the cards; (2) Repetition ability: the doctor will say a sentence and ask the subjects to pay attention to the sentence and repeat it; (3) Three-step command: the doctor will ask the subjects to complete a series of actions according to the doctor's orders; (4) Reading ability: the doctor will provide a card and ask the subjects to read the text on the card and complete the actions according to the text requirements; (5) Writing ability: the doctor will ask the subjects to write a complete sentence spontaneously; (6) Structural ability: the doctor will provide a picture and ask the subjects to copy it.

[0056] The second cognitive function score includes scores for eight subdomains: visual-spatial and executive ability, naming ability, attention, calculation ability, language ability, abstract thinking ability, delayed memory, and orientation.

[0057] The MoCA scale has a full score of 30 points, ≥26 points are normal, 18-26 points are mild cognitive impairment (MCI), 10-17 points are moderate, and less than 10 points are severe. MCI patients score about 22 points (19-25 points), and AD patients score between 11-21 points. If the subject has ≤12 years of education (high school level), 1 point can be added to the result, but the total score cannot exceed 30 points. If the patient is illiterate or has a low cultural level, a basic test can be selected.

[0058] Step S120, based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, the factor regression analysis method is used to obtain characteristic variables related to the efficacy of STN-DBS, wherein the factor regression analysis method includes univariate COX regression analysis method and multivariate COX regression analysis method.

[0059] In one embodiment, step S120 may include:

[0060] According to the clinical information, motor function score, emotional score, and cognitive function score of the target group, the univariate COX regression analysis method was used, and the factor corresponding to the probability value P1<0.05 in the univariate COX regression analysis results was taken as the first potential risk factor related to the efficacy of STN-DBS;

[0061] According to the first potential risk factor related to the efficacy of STN-DBS, the multivariate COX regression analysis method was used, and the first potential risk factor corresponding to the probability value P2<0.05 in the multivariate COX regression analysis results was taken as the second potential risk factor related to the efficacy of STN-DBS, and at the same time as a characteristic variable related to the efficacy of STN-DBS.

[0062] After the univariate cox regression analysis, the data results may be affected by multiple other factors. Therefore, the multivariate cox regression analysis is performed in this embodiment to eliminate the influence of multiple factors on the surgical efficacy at the same time.

[0063] Table 1 shows the results of univariate COX regression analysis of preoperative risk factors (i.e., clinical information, motor function score, emotional score, and cognitive function score of the target group before and after STN-DBS treatment) in this embodiment, with disease duration, levodopa equivalent dose, motor function score, levodopa drug improvement rate, emotional score, and cognitive function score as the first potential risk factor. Table 2 shows the results of multivariate COX regression analysis based on the results of univariate COX regression analysis in this embodiment, with disease duration, motor function score, levodopa drug improvement rate, and emotional score as the second potential risk factor, as characteristic variables related to the efficacy of STN-DBS.

[0064] Table 1

[0065]

[0066] Table 2

[0067]

[0068]

[0069] Step S130: Based on the characteristic variables related to the efficacy of STN-DBS, elastic network machine learning is used to construct a Parkinson's efficacy prediction model, wherein the Parkinson's efficacy prediction model is displayed in the form of a nomogram. The Parkinson's efficacy prediction model can be used to obtain the degree of influence of the characteristic variables related to the efficacy of STN-DBS treatment on the efficacy of STN-DBS treatment.

[0070] In one embodiment, step S130 may include:

[0071] The ROC curve was used to evaluate the prediction accuracy of the Parkinson's disease efficacy prediction model;

[0072] Calibration curves and multiple sampling comparisons were used to evaluate the prediction results of the Parkinson's disease efficacy prediction model and the probability of the actual surgical improvement rate to verify the accuracy and consistency index of the Parkinson's disease efficacy prediction model as conditions to determine whether the predicted effect of the Parkinson's disease efficacy prediction model on the improvement rate is consistent with the actual improvement rate.

[0073] In this embodiment, the disease duration, motor function score, levodopa drug improvement rate, and mood score of the target population are used as characteristic variables related to the efficacy of STN-DBS, and a training set and a validation set are divided. The Parkinson's efficacy prediction model is constructed through the elastic network in machine learning. The elastic network has high scalability and elasticity as well as a flexible network topology structure, which can ensure the prediction accuracy, high efficiency and stability of the performance, and rapid deployment capability of the Parkinson's efficacy prediction model. In the process of model construction, cross-validation, specificity and sensitivity tests are performed through the training set and the validation set, and the validity of the model is verified by using the calibration curve and the ROC curve (see Figure 2-5 ), in order to improve the prediction accuracy of the Parkinson's disease efficacy prediction model, and in this embodiment, the constructed Parkinson's disease efficacy prediction model is finally displayed in the form of a nomogram, such as Figure 6 shown.

[0074] The present invention provides a method for constructing a Parkinson's disease efficacy prediction model and an STN-DBS surgery decision-making support system. According to the clinical information, motor function scores, emotion scores, cognitive function scores and other data of the target group before and after STN-DBS treatment, combined with factor regression analysis, a high-precision Parkinson's disease efficacy prediction model is constructed, which can achieve accurate preoperative screening of Parkinson's disease patients undergoing subthalamic nucleus deep brain stimulation, and effectively improve the accuracy and efficiency of making individualized surgical decisions for Parkinson's disease patients with different clinical symptoms.

[0075] The Parkinson's efficacy prediction model obtained by the construction method of the Parkinson's efficacy prediction model provided by the present invention can be used to assist in STN-DBS surgical decision-making. The clinical information, motor function score, emotion score, cognitive function score, etc. of the subject before STN-DBS treatment are input into the Parkinson's efficacy prediction model. According to the degree of influence of characteristic variables related to STN-DBS efficacy obtained by the Parkinson's efficacy prediction model on the STN-DBS treatment efficacy, the degree of surgical improvement that the subject may obtain after STN-DBS treatment can be calculated according to the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment, so as to assist in deciding whether the subject needs to undergo STN-DBS treatment.

[0076] The following is a description of the system for constructing a Parkinson's disease efficacy prediction model provided by the present invention. The system for constructing a Parkinson's disease efficacy prediction model described below and the method for constructing a Parkinson's disease efficacy prediction model described above can be referred to each other.

[0077] The present invention provides a system for constructing a Parkinson's disease efficacy prediction model, which may include:

[0078] The data acquisition module is used to obtain clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, wherein the target group includes the Parkinson's disease patient group;

[0079] The preprocessing module is used to obtain characteristic variables related to the efficacy of STN-DBS based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group using factor regression analysis;

[0080] The construction module is used to: construct a Parkinson's disease efficacy prediction model through an elastic network based on characteristic variables related to STN-DBS efficacy.

[0081] See also Figure 7 The present invention also provides a STN-DBS surgery decision support system, which may include:

[0082] The data receiving module is used to: receive clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery;

[0083] A prediction module is used to: obtain a prediction result of whether the subject is suitable for STN-DBS surgery based on the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment and the Parkinson's efficacy prediction model obtained by any of the above-mentioned methods for constructing a Parkinson's efficacy prediction model;

[0084] The data output module is used to send the prediction result of whether the subject is suitable for STN-DBS surgery back to the at least one terminal.

[0085] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to perform the following steps:

[0086] Receiving clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery;

[0087] According to the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment, a Parkinson's disease efficacy prediction model is obtained by any of the above-mentioned methods for constructing a Parkinson's disease efficacy prediction model to obtain a prediction result of whether the subject is suitable for STN-DBS surgery;

[0088] The data output module is used to send the prediction result of whether the subject is suitable for STN-DBS surgery back to the at least one terminal.

[0089] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0090] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can perform the following steps:

[0091] Receiving clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery;

[0092] According to the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment, a Parkinson's disease efficacy prediction model is obtained by any of the above-mentioned methods for constructing a Parkinson's disease efficacy prediction model to obtain a prediction result of whether the subject is suitable for STN-DBS surgery;

[0093] The data output module is used to send the prediction result of whether the subject is suitable for STN-DBS surgery back to the at least one terminal.

[0094] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented to perform the following steps when executed by a processor:

[0095] Receiving clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery;

[0096] According to the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment, a Parkinson's disease efficacy prediction model is obtained by any of the above-mentioned methods for constructing a Parkinson's disease efficacy prediction model to obtain a prediction result of whether the subject is suitable for STN-DBS surgery;

[0097] The data output module is used to send the prediction result of whether the subject is suitable for STN-DBS surgery back to the at least one terminal.

[0098] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a Parkinson's disease efficacy prediction model, characterized in that: include: Obtain clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, where the target group includes Parkinson's disease patients; Based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, factor regression analysis was used to obtain characteristic variables related to the efficacy of STN-DBS. According to the characteristic variables related to the efficacy of STN-DBS, a Parkinson's disease efficacy prediction model was constructed through the elastic network.

2. The method for constructing a Parkinson's disease efficacy prediction model according to claim 1, characterized in that: Clinical information included any one of the following or any combination thereof: disease course, age at surgery, age at onset, levodopa equivalent dose, and levodopa medication improvement rate; motor function scores included motor function scores obtained by the Unified Parkinson's Disease Rating Scale; mood scores included the first mood score obtained by the Hamilton Anxiety Rating Scale and the second mood score obtained by the Hamilton Depression Rating Scale; cognitive function scores included the first cognitive function score obtained by the Mini-Mental State Examination and the second cognitive function score obtained by the Montreal Cognitive Assessment.

3. The method for constructing a Parkinson's disease efficacy prediction model according to claim 1 or 2, characterized in that: The factor regression analysis method includes univariate COX regression analysis and multivariate COX regression analysis. The factor regression analysis method is used to obtain characteristic variables related to the efficacy of STN-DBS based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, including: Based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, the first potential risk factor related to the efficacy of STN-DBS was obtained using univariate COX regression analysis; According to the first potential risk factor related to the efficacy of STN-DBS, the second potential risk factor related to the efficacy of STN-DBS was used as the characteristic variable related to the efficacy of STN-DBS using multivariate COX regression analysis.

4. The method for constructing a Parkinson's disease efficacy prediction model according to claim 3, characterized in that: According to the clinical information, motor function score, emotional score, and cognitive function score of the target group, the first potential risk factor related to the efficacy of STN-DBS was obtained by using the univariate COX regression analysis method, including: According to the clinical information, motor function score, emotional score, and cognitive function score of the target group, the univariate COX regression analysis method was used, and the factor corresponding to the probability value P1<0.05 in the univariate COX regression analysis results was taken as the first potential risk factor related to the efficacy of STN-DBS.

5. The method for constructing a Parkinson's disease efficacy prediction model according to claim 4, characterized in that: The second potential risk factor related to the efficacy of STN-DBS is analyzed by multivariate COX regression analysis based on the first potential risk factor related to the efficacy of STN-DBS, as a characteristic variable related to the efficacy of STN-DBS, including: According to the first potential risk factor related to the efficacy of STN-DBS, the multivariate COX regression analysis method was used, and the first potential risk factor corresponding to the probability value P2<0.05 in the multivariate COX regression analysis results was taken as the second potential risk factor related to the efficacy of STN-DBS, and at the same time as a characteristic variable related to the efficacy of STN-DBS.

6. The method for constructing a Parkinson's disease efficacy prediction model according to claim 1 or 2, characterized in that: The Parkinson's disease efficacy prediction model is constructed based on characteristic variables related to STN-DBS efficacy through an elastic network, including: According to the characteristic variables related to the efficacy of STN-DBS, a Parkinson's disease efficacy prediction model was constructed using the elastic network, where the Parkinson's disease efficacy prediction model was presented in the form of a nomogram.

7. A system for constructing a Parkinson's disease efficacy prediction model, characterized in that: include: The data acquisition module is used to obtain clinical information, motor function scores, emotional scores, and cognitive function scores of the target group before and after STN-DBS treatment, wherein the target group includes the Parkinson's disease patient group; The preprocessing module is used to obtain characteristic variables related to the efficacy of STN-DBS based on the clinical information, motor function scores, emotional scores, and cognitive function scores of the target group using factor regression analysis; A construction module is used to: construct a Parkinson's disease efficacy prediction model based on characteristic variables related to STN-DBS efficacy.

8. A STN-DBS surgery decision support system, characterized in that: include: The data receiving module is used to: receive clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery; A prediction module, used to: obtain a prediction result of whether the subject is suitable for STN-DBS surgery based on the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment and the Parkinson's efficacy prediction model obtained by the method for constructing a Parkinson's efficacy prediction model according to any one of claims 1 to 6; The data output module is used to send the prediction result of whether the subject is suitable for STN-DBS surgery back to the at least one terminal.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the following steps are implemented: Receiving clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery; A prediction module, used to: obtain a prediction result of whether the subject is suitable for STN-DBS surgery based on the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment and the Parkinson's efficacy prediction model obtained by the method for constructing a Parkinson's efficacy prediction model according to any one of claims 1 to 6; The prediction result of whether the subject is suitable for STN-DBS surgery is sent back to the at least one terminal.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the following steps are implemented: Receiving clinical information, motor function score, emotion score, and cognitive function score of a subject before STN-DBS treatment from at least one terminal, wherein the subject is a Parkinson's patient to be tested for whether he or she is suitable for STN-DBS surgery; A prediction module, used to: obtain a prediction result of whether the subject is suitable for STN-DBS surgery based on the clinical information, motor function score, emotion score, and cognitive function score of the subject before STN-DBS treatment and the Parkinson's efficacy prediction model obtained by the method for constructing a Parkinson's efficacy prediction model according to any one of claims 1 to 6; The prediction result of whether the subject is suitable for STN-DBS surgery is sent back to the at least one terminal.

Images