System for discriminating subtypes of parkinson's disease with mild cognitive impairment

Abstract

The present application relates to Parkinson disease subtype judgment technical field, specifically to the system for identifying Parkinson disease with mild cognitive impairment subtype, including: first data acquisition module, for generating first data table according to the scale data of overall cognitive function evaluation and the scale data of cognitive domain function test of first group of test personnel;Second data acquisition module, for generating second data table according to the scale data of overall cognitive function evaluation and the scale data of cognitive domain function test of second group of test personnel;Analysis module, for analyzing first data table and second data table, obtaining first score data and second score data;According to the preset Parkinson disease with mild cognitive impairment prediction strategy and subtype prediction strategy, the above data are processed, and the identification result of Parkinson disease with mild cognitive impairment subtype is obtained.The system provided by the present application provides data support for early evaluation and diagnosis of Parkinson disease with mild cognitive impairment patients.

Description

Technical Field

[0001] This invention relates to the field of Parkinson's disease subtype identification technology, specifically to a system for identifying Parkinson's disease subtypes with mild cognitive impairment. Background Technology

[0002] Previous research on Parkinson's Disease (PD) was limited to it being a simple motor disorder, characterized by the loss of dopaminergic neurons in the substantia nigra pars compacta of the midbrain and the formation of Lewy bodies (LB) within neurons. Clinical symptoms are mainly characterized by bradykinesia, resting tremor, rigidity, and postural and gait abnormalities, and levodopa treatment is effective. With further research, researchers have discovered cognitive decline and personality changes in Parkinson's patients. PD with mild cognitive impairment (PD-MCI) is one of the most common non-motor symptoms of Parkinson's disease. The cognitive decline in these patients has an insidious onset and a progressive course, often leading to neglect and delays in early intervention and treatment. This affects treatment outcomes, increases the burden on families and society, and severely harms the quality of life of Parkinson's patients. Studies have found that 33% of patients with primary Parkinson's disease exhibit PD-MCI symptoms, with the rate rising to 50% after a 5-year follow-up. PD-MCI is most common in the early stages of Parkinson's disease and serves as a transitional state towards Parkinson's disease with dementia (PD-D). However, unlike the symptom characteristics of PD-D, PD-MCI patients only exhibit mild cognitive impairment, experiencing only slight interference or difficulty in performing complex functional tasks, but without affecting functional independence.

[0003] Studies indicate that some patients with Parkinson's disease-associated mild cognitive impairment (PD-MCI) primarily experience executive function impairment, while others primarily experience attention impairment. Some patients exhibit severe memory impairment, mainly manifested as short-term or immediate recall impairment, while delayed recall impairment is less severe. Some patients show severe visuospatial impairment, which can also affect language, non-verbal, or visual cognitive functions. Language function impairment is relatively mild in patients with PD-MCI. It is evident that cognitive impairment in PD-MCI manifests as complex impairment in single or multiple cognitive domains, and this heterogeneity of cognitive dysfunction may be caused by different pathological changes. However, the specific characteristics and mechanisms of its cognitive impairment remain controversial, and no consensus has been reached.

[0004] Based on the number and type of impaired cognitive domains, PD-MCI can be further subdivided into different subtypes:

[0005] ① Single cognitive domain impairment PD-MCI (signal domain in PD-MCI-SD): Two neuropsychological tests show impairment in the same cognitive domain, while other cognitive domains are unaffected. ② Multiple cognitive domain impairment PD-MCI (multiple domains in PD-MCI-MD): At least one neuropsychological test shows impairment in at least two or more cognitive domains. Currently, some believe that the single cognitive domain impairment subtype is more common than the multi-domain impairment subtype, and among single cognitive domain impairments, the non-amnesic type is more common. Different cognitive domains are both affected individually and interconnected, and there is currently no consistent data to support the cognitive characteristics of the two subtypes, making the diagnosis and classification of PD-MCI more complex.

[0006] Clinically, the initial diagnosis of PD-MCI mainly relies on functional assessment using cognitive scales, which are divided into general assessment scales (MoCA, MMSE, etc.) and individual neuropsychological test scales (clock drawing test, line drawing test A / B, etc.). Although scale assessment is convenient, it also has many disadvantages. For example, there are many types of scales, and they interact with each other, resulting in low accuracy in identifying PD-MCI and its subtypes, and large errors in the identification results.

[0007] Existing technologies include products that utilize machine learning to process various data and provide disease feedback to patients and doctors. For example, patent application number CN202110782848.4 discloses an integrated K-nearest neighbor quantitative diagnostic system for Parkinson's disease based on plantar pressure. This system discloses the acquisition of pressure signal fragments from different locations on the sole of the foot, followed by training a K-nearest neighbor classification model—a multi-data processing approach—to diagnose Parkinson's disease. Patent application number CN202311198669.1 discloses an early prediction method, device, and system for Parkinson's disease, disclosing the acquisition of eye-tracking and walking data and the generation of disease prediction results through multiple model calculations. However, these products all involve a large number of complex calculations and extensive data processing steps. Therefore, developing a simpler and more accurate method for identifying Parkinson's subtypes remains an unsolved problem. Summary of the Invention

[0008] To overcome the shortcomings of existing scales for identifying subtypes of Parkinson's disease with mild cognitive impairment, this invention provides a system for identifying subtypes of Parkinson's disease with mild cognitive impairment.

[0009] To solve the above-mentioned technical problems, the present invention adopts the following technical solution.

[0010] A first aspect of the present invention provides a system for identifying a subtype of Parkinson's disease with mild cognitive impairment, comprising:

[0011] The first data acquisition module is used to generate a first data table based on the scale data of the overall cognitive function assessment and the scale data of the cognitive domain function test of the first group of test subjects; the first group of test subjects are the personnel to be identified.

[0012] The second data acquisition module is used to generate a second data table based on the scale data of the overall cognitive function assessment and the scale data of the cognitive domain function test of the second group of test subjects; the second group of test subjects are healthy individuals.

[0013] The analysis module is used to perform data analysis on the first data table and the second data table to obtain first score data and second score data; and to calculate the standard deviation of the second score data of the second group of testers according to the standard deviation calculation formula to obtain the standard deviation data of the second score data.

[0014] Based on the preset prediction strategies for Parkinson's disease with mild cognitive impairment and subtype prediction strategies, the first score data, the second score data, and the standard deviation data are processed to obtain the overall cognitive function impairment result and the cognitive domain function test impairment result corresponding to the first score data, and then the identification result of the Parkinson's disease with mild cognitive impairment subtype of the first group of test subjects is obtained.

[0015] In some technical solutions of this invention, the data analysis includes:

[0016] Add the scale data in the first data table to obtain the first rating data, and add the scale data in the second data table to obtain the second rating data;

[0017] The first scoring data includes the first overall cognitive function assessment scoring data and the first cognitive domain function test scoring data;

[0018] The second scoring data includes the second overall cognitive function assessment scoring data and the second cognitive domain function test scoring data.

[0019] In some technical solutions of the present invention, the preset prediction strategy for Parkinson's disease with mild cognitive impairment includes: comparing the first overall cognitive function assessment score data with the second overall cognitive function assessment score data; when the first overall cognitive function assessment score data is lower than 1.5 standard deviations below the average value of the second overall cognitive function assessment score data, it is considered that the overall cognitive function of the assessor corresponding to the first overall cognitive function assessment score data is impaired.

[0020] The scale data for the overall cognitive function assessment include: data from the Mini-Mental State Examination and data from the Montreal Cognitive Scale.

[0021] In some technical solutions of the present invention, the preset subtype prediction strategy includes: when there is impairment in overall cognitive function, comparing the first cognitive domain function test score data and the second cognitive domain function test score data; when the first cognitive domain function test score data is lower than 1.5 standard deviations below the average value of the second cognitive domain function test score data, it is considered that the cognitive domain function test corresponding to the first cognitive domain function test score data has impairment.

[0022] The cognitive domain function tests include: attention and working memory function tests, executive function tests, language function tests, memory function tests, and visuospatial function tests;

[0023] The Parkinson's disease subtype with mild cognitive impairment includes single cognitive domain impairment and multi-cognitive domain impairment.

[0024] In some technical solutions of this invention, in the analysis module, when the cognitive domain function test scale shows impairment, it is recorded as 1; when the cognitive domain function test scale does not show impairment, it is recorded as 0. Finally, the number of 0s and 1s is counted. When the number of 1s is greater than or equal to 2, it is determined that the test subject has a high risk of multiple cognitive domain impairment or multiple cognitive domain impairment; when the number of 1s is 1, it is determined that the test subject has a high risk of single cognitive domain impairment or single cognitive domain impairment.

[0025] In some technical solutions of the present invention, in the data acquisition module, each cognitive domain function test includes two tests; wherein,

[0026] The attention and working memory function tests include: digit span backwards test and connection test A;

[0027] The performance tests include: connection test B and autonomous clock drawing test;

[0028] The language function tests include: the Boston Naming Test and the Language Fluency Test;

[0029] The memory function test includes: an auditory language vocabulary learning test and a three-word recall test;

[0030] The visuospatial function tests include: the overlapping pentagram test and the imitation clock drawing test.

[0031] In some technical solutions of the present invention, the identification strategy for single cognitive domain impairment is as follows: when the test results of two tests in only one cognitive domain function test meet the preset subtype prediction strategy, it is considered that the scale of the cognitive domain function test has impairment, and it is judged that the test subject has a high risk of single cognitive domain impairment or has single cognitive domain impairment.

[0032] The identification strategy for multiple cognitive domain impairment is as follows: if the test result of at least one of the two tests in a cognitive domain function test meets the preset subtype prediction strategy, it is considered that the scale of the cognitive domain function test is impaired, and if there are at least two scales of the cognitive domain function test with impairment, then the test subject is judged to have a high risk of multiple cognitive domain impairment or multiple cognitive domain impairment.

[0033] In some technical solutions of the present invention, the data acquisition module is also used to collect the age, gender, education level, age at onset of symptoms, age at diagnosis, course of disease, Parkinson's disease HY stage, UPDRS III score, and the proportion of disease onset and motor impairment on the test subject.

[0034] In some technical solutions of the present invention, the system further includes an output module for outputting the judgment result of the judgment module.

[0035] A second aspect of the present invention provides a computer-readable storage medium for implementing the functions of the system, which stores a computer program.

[0036] A third aspect of the present invention provides an electronic device including a memory and a processor, the memory storing a computer program and the processor executing the computer program to implement the functions of the diagnostic system.

[0037] Compared with the prior art, the present invention has the following beneficial effects: The present invention aims to conduct a comprehensive cognitive function assessment of PD-MCI patients by collecting data from outpatients / inpatients and combining follow-up visits, analyzing their cognitive characteristics and effective assessment methods, and finally screening out a functional scale suitable for the subtyping diagnosis of PD-MCI patients. Using the screened scale, a system for identifying subtypes of Parkinson's disease with mild cognitive impairment was constructed, providing data support for the early assessment and diagnosis of PD-MCI patients.

[0038] The system provided in this invention for identifying subtypes of Parkinson's disease with mild cognitive impairment has an AUC value of 0.876, a sensitivity of 85.19%, and a specificity of 86.62% when used for the classification of PD-MCI patients.

[0039] The system for identifying subtypes of Parkinson's disease with mild cognitive impairment provided by this invention simplifies the existing methods for predicting or diagnosing Parkinson's disease. This invention can identify subtypes of Parkinson's disease with mild cognitive impairment using simple data processing. Attached Figure Description

[0040] Figure 1 This figure shows the comparison of demographic information and clinical characteristics of patients with PD-MCI and its subtypes.

[0041] Figure 2 The graph shows the results of various neuropsychological tests and assessments for PD-MCI and its subtypes.

[0042] Figure 3 This is a diagram showing the distribution of cognitive impairment in each subtype of PD-MCI; where AW represents simple attention deficit; E represents simple executive function deficit; M represents simple memory deficit; L represents simple language deficit; and V represents simple visuospatial deficit.

[0043] Figure 4 A graph showing the percentage of impairment in PD-MCI patients across different neuropsychological tests.

[0044] Figure 5 The AUC curve is shown for the PD-MCI patient subtype prediction system provided by this invention. Detailed Implementation

[0045] The present invention will be described in detail below with reference to specific embodiments, but should not be construed as limiting the present invention. Unless otherwise specified, the technical means used in the following embodiments are conventional means well known to those skilled in the art, and the materials, reagents, etc. used in the following embodiments can be obtained commercially unless otherwise specified.

[0046] I. Experimental Materials:

[0047] 1. Experimental blood samples: Blood samples were drawn from the research subjects (Parkinson's disease patients and healthy control groups), centrifuged at 2000×g for 15min, aliquoted and frozen at -80℃.

[0048] 2. Experimental reagents

[0049] The ELISA kit was purchased from EIAAB; 0.01 mol / L (1×) phosphate buffered saline (PBS) was purchased from KGI.

[0050] 3. Instruments and Consumables

[0051] Pipettes were purchased from Eppendorf GmbH, Germany; medical EDTA-K2 anticoagulant tubes were provided by the Affiliated Hospital of Xuzhou Medical University; medical separating gel coagulation tubes were provided by the Affiliated Hospital of Xuzhou Medical University; Eppendorf-5804R benchtop centrifuges were purchased from Eppendorf GmbH, Germany; microplate readers were purchased from BioTek Inc., USA; ice makers were purchased from SANYO Inc., Japan; HVE-50 autoclaves were purchased from Hirayama Inc.; Allegra 64R ultra-high-speed centrifuges were purchased from BECKMAN Inc., USA; and ultrapure water systems were purchased from ELGA LabWater Inc., UK.

[0052] 4. Research Subjects

[0053] This study included patients with primary Parkinson's disease (PD) who were admitted to the Department of Neurology at the Affiliated Hospital of Xuzhou Medical University between May 2016 and August 2017. Experienced neurologists collected detailed demographic information, disease course, treatment history, and assessed motor symptoms to establish a diagnosis. Cognitive function was assessed when patients were in good mental condition and cooperative. This clinical study was approved by the Ethics Committee of the Affiliated Hospital of Xuzhou Medical University (Ethics Approval No.: XYFY2017-KL047-01). All participants understood the trial and signed informed consent forms. Patient selection strictly adhered to the following inclusion and exclusion criteria.

[0054] Inclusion criteria: (1) Age 40-80 years; (2) Able to complete all cognitive tests under the guidance of a physician, with no difficulty in listening, comprehension and writing; (3) The diagnosis of Parkinson's disease must be independently diagnosed by two experienced neurologists according to the UK Brain Bank Parkinson's Disease Diagnosis Criteria.

[0055] Exclusion criteria: (1) All cases should undergo CT / MRI to exclude other neurological history besides PD: moderate or severe traumatic brain injury, stroke or vascular dementia, etc.; (2) Drug-induced, head trauma and vascular secondary Parkinson's syndromes; progressive supranuclear palsy, multiple system atrophy and other Parkinson's superimposed syndromes; (3) severe anxiety, depression and schizophrenia and other mental illnesses; (4) systemic diseases of the heart, liver, kidney and other diseases that may affect cognitive function.

[0056] PD-MCI group (70 cases): (1) Diagnostic and exclusion criteria for mild cognitive impairment of Parkinson's disease according to the 2012 International Movement Disorders Organization; (2) At least two neuropsychological test impairments, i.e., two test impairments in one cognitive area or at least one test impairment in each of the two cognitive areas. The standard for impairment is 1.5 SDs lower than the average of the normal control group, i.e. 1.5 standard deviations.

[0057] PD-MCI subtype:

[0058] (1) Single cognitive domain PD-MCI (PD-MCI-SD, 8 cases): two tests in a single cognitive domain (specific cognitive domain) were abnormal, while other cognitive domains were normal;

[0059] (2) Multi-domain PD-MCI (PD-MCI-MD, 62 cases): Abnormality in at least one test of two or more cognitive domains (specific cognitive domains).

[0060] Example 1: A system for identifying subtypes of Parkinson's disease with mild cognitive impairment

[0061] A system for identifying subtypes of Parkinson's disease with mild cognitive impairment, comprising:

[0062] The first data acquisition module is used to generate a first data table based on the scale data of the overall cognitive function assessment and the scale data of the cognitive domain function test of the first group of test subjects; the first group of test subjects are the personnel to be identified.

[0063] The second data acquisition module is used to generate a second data table based on the scale data of the overall cognitive function assessment and the scale data of the cognitive domain function test of the second group of test subjects; the second group of test subjects are healthy people.

[0064] The analysis module is used to perform data analysis on the first and second data tables to obtain the first and second score data; and to calculate the standard deviation of the second score data of the second group of testers according to the standard deviation calculation formula to obtain the standard deviation data of the second score data.

[0065] Based on the pre-set prediction strategies for Parkinson's disease with mild cognitive impairment and subtype prediction strategies, the first score data, the second score data, and the standard deviation data are processed to obtain the overall cognitive function impairment results and cognitive domain function test results corresponding to the first score data, and then to obtain the identification results of the Parkinson's disease with mild cognitive impairment subtype for the first group of test subjects.

[0066] In this embodiment, the data analysis includes: adding the scale data in the first data table to obtain the first rating data, and adding the scale data in the second data table to obtain the second rating data;

[0067] The first scoring data includes the first overall cognitive function assessment scoring data and the first cognitive domain function test scoring data;

[0068] The second scoring data includes the second overall cognitive function assessment scoring data and the second cognitive domain function test scoring data.

[0069] In this embodiment, the preset prediction strategy for Parkinson's disease with mild cognitive impairment includes: comparing the first overall cognitive function assessment score data with the second overall cognitive function assessment score data; when the first overall cognitive function assessment score data is lower than 1.5 standard deviations below the average of the second overall cognitive function assessment score data, it is considered that the overall cognitive function of the assessor corresponding to the first overall cognitive function assessment score data is impaired.

[0070] The scale data for the overall cognitive function assessment include: data from the Mini-Mental State Examination and data from the Montreal Cognitive Scale.

[0071] The pre-defined subtype prediction strategy includes: when there is impairment in overall cognitive function, comparing the score data of the first cognitive domain function test and the score data of the second cognitive domain function test; when the score data of the first cognitive domain function test is lower than 1.5 standard deviations below the average of the score data of the second cognitive domain function test, it is considered that there is impairment in the cognitive domain function test corresponding to the score data of the first cognitive domain function test.

[0072] Cognitive function tests include: attention and working memory function tests, executive function tests, language function tests, memory function tests, and visuospatial function tests;

[0073] Parkinson's disease with mild cognitive impairment subtypes include single cognitive domain impairment and multi-cognitive domain impairment.

[0074] In the analysis module, impairment on the cognitive domain function test scale is recorded as 1, and no impairment is recorded as 0. The final count of 0s and 1s is tallied. If the number of 1s is greater than or equal to 2, the individual is considered to have a high risk of multiple cognitive domain impairment or multiple cognitive domain impairment; if the number of 1s is 1, the individual is considered to have a high risk of single cognitive domain impairment or single cognitive domain impairment. A score of 1.5 SDs is an international diagnostic standard for Parkinson's disease with cognitive impairment; see references Litvan I, Goldman JG. AI,et al.Diagnostic criteria for mild cognitive impairment in Parkinson's disease.Movement DisordersOfficial Journal of the Movement Disorder Society,2012,27(3):349-356.

[0075] The system provided in this embodiment for identifying subtypes of Parkinson's disease with mild cognitive impairment includes two tests in each cognitive domain function test in the data acquisition module.

[0076] Attention and working memory function tests include: Digit span backwards test and connection test A;

[0077] The functional tests include: connectivity test B and autonomous clock drawing test;

[0078] Language function tests include: the Boston Naming Test and the Language Fluency Test;

[0079] The memory function test includes: an auditory language vocabulary learning test and a three-word recall test;

[0080] The visuospatial function test includes: the overlapping pentagram test and the imitation clock drawing test.

[0081] In this embodiment, the identification strategy for single cognitive domain impairment is as follows: when the test results of two tests in only one cognitive domain function test both meet the preset subtype prediction strategy, it is considered that the scale of that cognitive domain function test has impairment, and the test subject is judged to have a high risk of single cognitive domain impairment or single cognitive domain impairment. For example, when the test results of the connecting line test B and the self-drawing clock test both meet the preset subtype prediction strategy, it is considered that the executive function test has impairment; when only one test of the Boston naming test and the language fluency test meets the preset condition, the language function test has no impairment, and so on. If only the executive function test has impairment, then the test subject is judged to have single cognitive domain impairment.

[0082] The strategy for identifying multiple cognitive domain impairment is as follows: If at least one test result in a cognitive domain function test satisfies a pre-defined subtype prediction strategy, the scale of that cognitive domain function test is considered to have impairment. Furthermore, if at least two scales of the cognitive domain function test show impairment, the individual is judged to have a high risk of multiple cognitive domain impairment or to have multiple cognitive domain impairment. For example, if only one test in the performance function test (connecting line test B or self-drawing clock test) satisfies the pre-defined subtype prediction strategy, and only one test in the language function test (Boston naming test or language fluency test) satisfies the pre-defined subtype prediction strategy, then impairment is considered to exist in both the performance function test and the language fluency test, and the individual is judged to have multiple cognitive domain impairment.

[0083] The data acquisition module is also used to collect data on the test subjects' age, gender, education level, age at onset of symptoms, age at diagnosis, disease course, Parkinson's disease HY stage, UPDRS III score, and the proportion of disease onset and motor impairment.

[0084] In this embodiment, the system for identifying the subtype of Parkinson's disease with mild cognitive impairment further includes an output module for outputting the judgment result of the judgment module.

[0085] Example 2: Electronic device

[0086] This embodiment provides an electronic device, which can be represented in the form of a computing device (e.g., a server device), including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it can implement the steps of the method for identifying the subtype of Parkinson's disease with mild cognitive impairment in the system provided by this invention.

[0087] Example 3: Computer-readable storage medium

[0088] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for identifying a subtype of Parkinson's disease with mild cognitive impairment in the system provided by this invention.

[0089] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0090] Example 4: Differential Diagnosis of Parkinson's Disease with Mild Cognitive Impairment Subtype

[0091] 1. Predictive methods for the Parkinson's disease subtype with mild cognitive impairment are as follows:

[0092] 1.1 General Data Records

[0093] Record relevant information for all study subjects, including gender, age, education level, disease course, age of onset, medical history, medication history, family history, and accompanying symptoms.

[0094] 1.2 Assessment of motor symptoms

[0095] All Parkinson's patients underwent motor assessment using Part III of the Unified Parkinson's Disease Rating Scale (UPDRS). The Hoehn-Yahr staging system (HY stage) was used to assess disease severity.

[0096] 1.3 Cognitive Assessment

[0097] Using the 2012 International Movement Disorders Association (IMA) diagnostic criteria for Level II mild cognitive impairment in Parkinson's disease, a comprehensive assessment of overall cognitive function and five cognitive areas (attention and working memory, executive function, language, memory, and visuospatial function) was conducted on all subjects. All assessments were performed in the "ON" state, with impairment considered to be 1.5 SD lower than that of the normal control group. In the "ON" state, patients' symptoms were effectively controlled, such as muscle numbness, weakness, and reduced tremor; while symptoms worsened in the "OFF" state.

[0098] 1.3.1 Overall cognitive function was assessed using the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA).

[0099] (1) The Mini-Mental State Examination (MMSE) includes the following seven aspects: orientation to time, orientation to place, immediate memory, attention and calculation, delayed memory, language, and visuospatial skills. There are 30 items in total. Each correct answer earns 1 point, and each incorrect answer or answer without knowledge earns 0 points. The total score ranges from 0 to 30. Test scores are closely related to literacy levels. The normal cutoff values ​​are: illiterate > 17 points, primary school > 20 points, junior high school and above > 24 points.

[0100] (2) The Montreal Cognitive Assessment (MoCA) is an assessment tool used for rapid screening of mild cognitive impairment. It assesses many different cognitive domains, including: attention and concentration, executive function, memory, language, visual-structural skills, abstract thinking, calculation, and orientation. One point is added if the number of years of schooling is ≤12 years, with a maximum score of 30. A score ≥26 is considered normal.

[0101] 1.3.2 Two neuropsychological tests were selected for each of the five cognitive areas:

[0102] (1) Assessment of attention and working memory abilities

[0103] The Digit Span Backward Test (DSB-T) is a fundamental algorithm for testing attention, used to assess attentional and working memory abilities. Digit Span Backward requires the patient to process and represent information without external verbal cues, thus primarily testing attentional and working memory abilities (dorsolateral prefrontal cortex). The test requires the subject to repeat numbers in reverse order, incrementing the number of digits by one each time, until two incorrect attempts are made on a sequence of the same number of digits.

[0104] Trail Making Test A (TMT-A): Assessing attention. The Trail Marking Test (TMT) was initially part of a military skills assessment scale (1944) and was later integrated into the Halstead-Reitan Test (1985). It consists of two parts: Trail Marking Test A (TMT-A) and Trail Marking Test B (TMT-B). Trail Marking Test A requires connecting numbers 1-25 in sequence. It primarily assesses the subject's perceptual processing and attention. Currently, the assessment of cognition is mainly based on the time taken to complete the test; a longer completion time indicates more severe attentional impairment.

[0105] (2) Performance evaluation

[0106] Trail Making Test B (TMT-B): Primarily assesses executive function (response inhibition, attention switching). Participants are required to alternately connect letters and numbers (e.g., 1, A, 2, B, 3, C, etc.). Professor Guo Qihao of Huashan Hospital in Shanghai, considering cultural differences and educational levels, developed a Chinese version of Trail Making Test B by incorporating the original numbers into both squares and circles. Participants are required to alternate between the two shapes when connecting the numbers. Cognitive assessment is primarily based on the time taken to complete the test; longer completion times indicate more severe executive function impairment.

[0107] Clock Drawing Test (CDT): This test primarily assesses executive functions such as planning, inhibitory control, and attention maintenance, as well as visual function. It is included in the MoCA test and requires the patient to draw a clock independently (please draw a clock showing "11:10"). Scoring criteria: 1 point for drawing a closed circle, 1 point for correctly placing the numbers, 1 point for drawing all 12 numbers without omission, and 1 point for correctly positioning the minute and hour hands. A score <4 is considered abnormal.

[0108] (3) Language function assessment

[0109] The Boston Naming Test (BNT): The BNT (Kaplan et al., 1983) is the most commonly used test for assessing naming in clinical neuropsychology practice. The BNT is often translated into other languages. The test effectively identifies naming impairments through visual stimuli combined with verbal responses. This invention uses the version from Huashan Hospital affiliated with Fudan University in Shanghai, which consists of 30 pictures arranged sequentially. Patients are asked to name the objects in the pictures one by one (spontaneous naming, semantically cued naming, and selective naming, requiring patients to choose an answer from "correct name, similar name, and morphologically similar name"). The 30 pictures are: tree, pen, scissors, flower, clothes hanger, camel, badminton racket, abacus, saw, mushroom, funnel, accordion, broom, wheelchair, stethoscope, compass, escalator, snail, pliers, harmonica, tripod, rhinoceros, flower shed, cactus, pyramid, protractor, harp, dart, seahorse, and igloo. The number of spontaneous names, semantically cued names, and selective names is recorded. The evaluation is primarily based on the number of spontaneously named entries.

[0110] The Semantic Fluency Test (SFT), also known as the Category Fluency Test (CFT), is primarily used to assess a participant's cognitive flexibility. We selected the Category Fluency Test (SFT) from the MoCA test, which is essentially the Semantic Fluency Test. Participants are required to name as many animals as possible within one minute. Each participant's score is the number of correctly named words.

[0111] (4) Memory assessment

[0112] The Auditory Verbal Learning Test (AVLT) – Huashan Version: Primarily assesses memory abilities (language memory, learning ability, resistance to interference, and recognition memory). The most classic Rey Auditory Verbal Learning Test (RAVLT; Rey, 1958) is an episodic memory test that involves the test-taker's participation in the vocabulary learning process. There are many versions of the Auditory Verbal Learning Test; we have chosen the version from Huashan Hospital affiliated with Fudan University (Auditory Verbal Learning Test-Huashan, AVLT-H, compiled with reference to CVLT and HKVLT, 12 words). The 12 selected words can be divided into 3 categories, with 4 words in each category.

[0113] Category 1: Overcoat, trousers, headscarf, gloves; Category 2: Driver, carpenter, soldier, lawyer; Category 3: Crabapple, wintersweet, lily, magnolia. The examiner reads the words aloud at a rate of one word per second, requiring the subject to learn and recall them three times consecutively. One point is awarded for each correct answer. After a 5-minute interval between non-verbal tests, a fourth recall (short-delay recall) is conducted. After a 20-minute interval, a fifth recall (long-delay recall) is conducted. The sixth recall is recognition. The examiner reads 24 words and asks the subject to identify which ones they have previously learned (these 24 words are from the following categories: Category 1: Overcoat, jacket, long johns, trousers, headscarf, towel, gloves, mask; Category 2: Driver, craftsman, carpenter, worker, soldier, officer, lawyer, judge; Category 3: Crabapple, rose, wintersweet, plum blossom, lily, daffodil, magnolia, spider plant). The statistics include scores for short-term memory (the sum of the first three free recalls), short-delay recall, long-delay recall, and recognition.

[0114] MMSE 3-word recall test: See MMSE test for method details.

[0115] (5) Visual space function assessment

[0116] Clock Copying Test (CCT): Primarily assesses visuospatial function. Subjects are asked to copy a clock drawn beforehand. Scoring criteria: 1 point for drawing a closed circle, 1 point for correct digit placement, 1 point for all 12 digits present, 1 point for correct minute and hour hands, <4 points indicates abnormality.

[0117] MMSE Overlapping Pentagon: See MMSE Test for details.

[0118] 2.2.4 Depression assessment: The Geriatric Depression Scale-30 (GD-30) with a score of 30 was used for assessment.

[0119] This is a depression screening scale specifically for older adults, not a diagnostic tool for depression. Professor Williams suggests that the GDS-30 may be the most effective screening scale for depression in Parkinson's disease patients. A score of 0-10 is considered normal, indicating no depression; 11-20 indicates mild depression; and 21-30 indicates moderate to severe depression.

[0120] 3. Statistical Analysis Methods

[0121] Data analysis and processing were performed using SPSS 16.0 software. For continuous variables, normality was tested; data satisfying normality were expressed as mean ± standard deviation (x ± s), and non-normal data were expressed as median (interquartile range). For parametric tests, analysis of variance was used, with further pairwise comparisons using the LSD method (or Bonferroni method). For tests not satisfying parametric tests, the Kruskal-Wallis test was used for multiple group comparisons, with further pairwise comparisons using the rank-transformed LSD method. Chi-square analysis was performed on binary variables. The predict function of R was used to assess the sensitivity of the scale combinations, and the AUC was calculated. A two-sided p-value < 0.05 was considered statistically significant.

[0122] 4. Results

[0123] (1) Analysis of demographic information and clinical characteristics of PD-MCI and its subtypes

[0124] Based on the diagnostic and subtype classification criteria for PD-MCI, a total of 70 cases of PD-MCI were selected, including 8 cases of PD-MCI-SD and 62 cases of PD-MCI-MD. Analysis of demographic information, clinically relevant motor scores, cognitive scores, and biochemical indicators for each group showed (e.g.) Figure 1 As shown in the figure: There were no significant differences among the total PD-MCI group, PD-MCI-SD group, and PD-MCI-MD group in terms of age, sex, education level, age at symptom onset, age at diagnosis, disease duration, HY stage, UPDRS III score, and the proportion of disease onset and motor impairment (P>0.05). The MMSE and MOCA scores of the total PD-MCI group were lower than those of the PD-MCI-SD group (P=0.034, P=0.04), while the MMSE and MOCA scores of the PD-MCI-MD group were lower than those of the total PD-MCI group (P=0.04, P=0.02) and the PD-MCI-SD group (P=0.037, P=0.019), and the differences were statistically significant.

[0125] (2) Analysis of various neuropsychological tests for PD-MCI and its subtypes

[0126] The impairments in attention and working memory, executive function, memory, language function, and visuospatial function were assessed using individual neuropsychological tests in the total PD-MCI group, PD-MCI-SD group, and PD-MCI-MD group. Results are as follows: Figure 2 As shown in the figure. The assessment results of the Digit Span Recall Test, Connect-the-Dots Test B, and Self-Drawing Clock Test showed statistically significant differences among the three groups (P<0.001). The scores of the Auditory Language Word Learning Test in the PD-MCI-SD and PD-MCI-MD groups were significantly lower than the overall PD-MCI group scores (P<0.001), but there was no significant difference in the Auditory Language Word Learning Test scores between the PD-MCI-SD and PD-MCI-MD groups. The assessment results of other neuropsychological tests showed no statistically significant differences among the groups (P>0.05).

[0127] (3) Analysis of the characteristics of cognitive impairment in each subtype of PD-MCI

[0128] Statistical analysis of the distribution of cognitive impairment in various cognitive domains within the PD-MCI subtype showed (e.g.) Figure 3 As shown in the figure: 8 patients (12%) with PD-MCI-SD had significantly fewer cases than 62 patients (88%) with PD-MCI-MD; among them, the most common type was simple memory impairment (M) (4 cases, 6%), followed by simple attention impairment (AW) and simple executive function impairment (E). Further analysis of the distribution of cognitive domain impairment in PD-MCI-MD patients showed that executive / memory impairment (E+M) was the most common (9 cases, 13%), followed by attention + executive + memory impairment (AW+E+M, 7 cases, 10%), attention + executive + memory + language impairment (AW+E+M+L, 7 cases, 10%), and executive + memory impairment (AW+M, 6 cases, 9%). The results suggest that regardless of whether there is impairment in a single cognitive domain or multiple cognitive domains, executive function and memory impairment are the most common, followed by attention and language impairment, while visuospatial function impairment accounts for a relatively small proportion.

[0129] (4) Comparative analysis of the evaluation effects of various neuropsychological test scales

[0130] To analyze the assessment effectiveness of various neuropsychological testing scales, we compared the indications of cognitive impairment in PD-MCI patients using different neuropsychological testing scales (e.g., Figure 4As shown in the figure, the most frequently indicating impairments were the Digit Span Reversal Test (32%), the Auditory-Language Vocabulary Learning Test (25%), and the Boston Naming Test (20%). In assessing attention and executive function impairments, the Digit Span Reversal Test showed a significant sensitivity advantage, followed by the Connect-the-Dots A / B Test. For assessing memory impairments, the Auditory-Language Vocabulary Learning Test and the 3-word recall test in the MMSE all showed good sensitivity. In assessing language function, the Boston Naming Test was more effective. This provides guidance for the selection of subsequent cognitive function assessment tools.

[0131] Previous demographic analyses and clinical studies on Parkinson's disease (PD) patients with cognitive impairment have yielded inconsistent conclusions. Some studies suggest a positive correlation between age and the severity of cognitive impairment in PD, and a negative correlation with education level; others indicate that male PD patients experience more severe cognitive decline, while female PD patients suffer more severe memory impairment; still others suggest that age, education level, and gender are not associated with PD-associated cognitive impairment. However, multiple studies have found significant correlations between age of onset, disease duration, UPDRS score, and HY stage and the severity of PD-associated cognitive impairment, with these factors exhibiting an additive effect during cognitive decline. These studies focus on Parkinson's patients as a whole. This study found no significant differences in age, sex, education level, age at symptom onset, age at diagnosis, disease duration, HY stage, UPDRS III, and the proportion of disease onset and motor impairment among all PD-MCI patients and their subtypes (PD-MCI-SD and PD-MCI-MD). This suggests that the main differences between PD-MCI and its subtypes do not lie in the severity of cognitive impairment, and these factors may play a supporting role in the development of PD-MCI and its subtypes, rather than being the dominant factors.

[0132] Studies on motor symptoms of Parkinson's disease (PD) have found that asymmetry in the degree of neurodegeneration in the cerebral hemispheres is the main reason for the lateralization of motor symptoms. This study found that these asymmetric motor symptoms are not correlated with the occurrence and development of PD-MCI or its subtypes, suggesting that the dopamine neural circuit in the substantia nigra pars compacta, which mainly affects motor symptoms, is not the only neural circuit influencing cognitive impairment; it may also involve the participation of multiple neurotransmitters / pathways such as acetylcholine and norepinephrine.

[0133] As comprehensive cognitive assessment scales, the MMSE and MOCA, although containing sub-item tests, have low sensitivity. Therefore, while the MMSE and MOCA results show significant differences among the three groups, further evaluation with individual neuropsychological tests is needed.

[0134] This study assessed the overall PD-MCI group and two subtypes using various individual neuropsychological tests. Significant differences were found among the three groups in the digit span backwards test, the line-connecting test (B), and the clock drawing test, suggesting that cognitive impairment in PD-MCI patients and their subtypes is primarily characterized by attention and executive function impairment. The reasons for this are: 1. Decreased executive function and attention may appear earlier in PD-MCI patients and are more prevalent; 2. The three individual neuropsychological tests have overlap in their assessment of cognitive function; 3. The digit span backwards test has high sensitivity and effectiveness.

[0135] Auditory-verbal vocabulary learning tests primarily assess memory capacity, showing good sensitivity, especially in assessing areas of recognition impairment. Significant differences were found in auditory-verbal vocabulary learning test results between the PD-MCI group and its subtypes, but no differences were observed within the PD-MCI-SD and PD-MCI-MD subtypes, suggesting a significant difference in memory impairment between the overall PD-MCI group and its subtypes, primarily in recognition impairment. Studies indicate that memory impairment in PD patients is categorized into many types, such as retrieval impairment, encoding and information storage impairment, and recognition memory impairment. In severe dementia patients, comprehensive impairment of free recall and recognition memory is observed, but the relationship between recognition memory impairment and the severity of PD remains controversial.

[0136] There were no significant differences in language and visuospatial tests among the three groups, suggesting that patients in the PD stage with mild cognitive impairment have relatively preserved language function, which may be related to the neural pathways controlling language function. Executive function and working memory are mainly controlled by the substantia nigra-striatal dopaminergic pathway, while impairment of language and visuospatial functions is mainly caused by damage to the posterior cortical acetylcholinergic pathway. Moreover, abnormalities in the posterior cortical acetylcholinergic pathway have a significantly greater impact on the degree of cognitive impairment than those in the substantia nigra-striatal dopaminergic pathway, which may explain why language function impairment is not significant in the same area of ​​mild cognitive impairment.

[0137] This study comprehensively investigated the cognitive impairment characteristics of two PD-MCI subtypes, finding that PD-MCI-SD patients (12%) had significantly fewer cases than PD-MCI-MD patients (88%). The most common subtype was isolated memory impairment, followed by isolated attention impairment and isolated executive function impairment. Further analysis of PD-MCI-MD patient types revealed that executive / memory impairment was the most prevalent, followed by attention + executive + memory impairment, attention + executive + memory + language impairment, and executive + memory impairment. Cognitive impairment in each PD-MCI subtype also exhibited significant heterogeneity, with both single-domain and multi-domain impairments. Regardless of whether single or multi-domain impairment was observed, executive function and memory impairment were the most common, followed by attention and language impairment, while visuospatial function impairment was relatively less common. This suggests that the substantia nigra-striatal pathway and the posterior cortical acetylcholine pathway are simultaneously involved in the development and progression of PD-MCI subtypes, providing a theoretical basis for further mechanistic research.

[0138] (5) The results above show that the Digit Span Reverse Memorization Test, TMT-B, Auditory-Language Vocabulary Learning Test, and Boston Naming Test have significant sensitivity advantages in assessing attention and working memory function, executive ability, memory, and language function, respectively. To verify this result, this study collected 40 outpatients diagnosed with PD and used two different combinations of neuropsychological test scales (Group 1 and Group 2) to test their cognitive function, evaluate the sensitivity of the two groups, and predict the ROC curve.

[0139] Group 1: A combination of digital span recitation test + TMT-B + auditory language vocabulary learning test + Boston naming test; Group 2: Four other corresponding functional test scales were randomly selected for evaluation, namely: TMT-A + self-drawing clock test + 3-word recall test + language fluency test.

[0140] The results are as follows Figure 5 As shown, the detection results for group 1 were: AUC = 0.876, 95% CI: 0.836-0.939, sensitivity 85.19%, specificity 86.62%; and the detection results for group 2 were: AUC = 0.637, 95% CI: 0.602-0.839, sensitivity 70.57%, specificity 69.39%.

[0141] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0142] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A system for identifying subtypes of Parkinson's disease with mild cognitive impairment, characterized in that, include: The first data acquisition module is used to generate the first data table based on the scale data of the overall cognitive function assessment and the scale data of the cognitive domain function test of the first group of testers. The first group of testers are the individuals to be identified; The second data acquisition module is used to generate a second data table based on the scale data of the overall cognitive function assessment and the scale data of the cognitive domain function test of the second group of test subjects; the second group of test subjects are healthy individuals. The analysis module is used to perform data analysis on the first data table and the second data table to obtain the first score data and the second score data; The standard deviation of the second score data of the second group of testers is calculated according to the standard deviation calculation formula to obtain the standard deviation data of the second score data; Based on the preset prediction strategies for Parkinson's disease with mild cognitive impairment and subtype prediction strategies, the first score data, the second score data, and the standard deviation data are processed to obtain the overall cognitive function impairment result and the cognitive domain function test impairment result corresponding to the first score data, and then the identification result of the Parkinson's disease with mild cognitive impairment subtype of the first group of test subjects is obtained.

2. The system as described in claim 1, characterized in that, The data analysis includes: Add the scale data in the first data table to obtain the first rating data, and add the scale data in the second data table to obtain the second rating data; The first scoring data includes the first overall cognitive function assessment scoring data and the first cognitive domain function test scoring data; The second scoring data includes the second overall cognitive function assessment scoring data and the second cognitive domain function test scoring data.

3. The system as described in claim 2, characterized in that, The pre-defined prediction strategy for Parkinson's disease with mild cognitive impairment includes: comparing the first overall cognitive function assessment score data with the second overall cognitive function assessment score data; when the first overall cognitive function assessment score data is lower than 1.5 standard deviations below the average of the second overall cognitive function assessment score data, it is considered that the overall cognitive function of the assessor corresponding to the first overall cognitive function assessment score data is impaired. The scale data for the overall cognitive function assessment include: data from the Mini-Mental State Examination and data from the Montreal Cognitive Scale.

4. The system as described in claim 3, characterized in that, The preset subtype prediction strategy includes: when there is impairment in overall cognitive function, comparing the first cognitive domain function test score data and the second cognitive domain function test score data; when the first cognitive domain function test score data is lower than 1.5 standard deviations below the average value of the second cognitive domain function test score data, it is considered that the cognitive domain function test corresponding to the first cognitive domain function test score data has impairment. The cognitive domain function tests include: attention and working memory function tests, executive function tests, language function tests, memory function tests, and visuospatial function tests; The Parkinson's disease subtype with mild cognitive impairment includes single cognitive domain impairment and multi-cognitive domain impairment.

5. The system as described in claim 4, characterized in that, In the analysis module, when the cognitive domain function test scale shows impairment, it is recorded as 1; when the cognitive domain function test scale does not show impairment, it is recorded as 0. Finally, the number of 0s and 1s is counted. When the number of 1s is greater than or equal to 2, it is judged that the test subject has a high risk of multiple cognitive domain impairment or multiple cognitive domain impairment; when the number of 1s is 1, it is judged that the test subject has a high risk of single cognitive domain impairment or single cognitive domain impairment.

6. The system as described in claim 5, characterized in that, In the data acquisition module, each cognitive domain function test includes two tests; wherein, The attention and working memory function tests include: digit span backwards test and connection test A; The performance tests include: connection test B and autonomous clock drawing test; The language function tests include: the Boston Naming Test and the Language Fluency Test; The memory function test includes: an auditory language vocabulary learning test and a three-word recall test; The visuospatial function tests include: the overlapping pentagram test and the imitation clock drawing test.

7. The system as described in claim 1, characterized in that, The data acquisition module is also used to collect the age, gender, education level, age at onset of symptoms, age at diagnosis, course of disease, Parkinson's disease HY stage, UPDRS III score, and the proportion of disease onset and motor impairment on the test subjects.

8. The system as described in claim 1, characterized in that, The system also includes an output module for outputting the judgment result of the judgment module.

9. A computer-readable storage medium for implementing the functions of the system as claimed in any one of claims 1-8, wherein a computer program is stored.

10. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor is used to execute the computer program to implement the functions of the diagnostic system as described in any one of claims 1-8.

Images