Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores
<b>Background:</b> Mini-Mental State Examination (MMSE) is the most widely used tool in cognitive screening. Some individuals with normal MMSE scores have extensive cognitive impairment. Systematic neuropsychological assessment should be performed in these patients. This study aimed to o...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/12/1/37 |
| _version_ | 1797492834814656512 |
|---|---|
| author | Jie Wang Zhuo Wang Ning Liu Caiyan Liu Chenhui Mao Liling Dong Jie Li Xinying Huang Dan Lei Shanshan Chu Jianyong Wang Jing Gao |
| author_facet | Jie Wang Zhuo Wang Ning Liu Caiyan Liu Chenhui Mao Liling Dong Jie Li Xinying Huang Dan Lei Shanshan Chu Jianyong Wang Jing Gao |
| author_sort | Jie Wang |
| collection | DOAJ |
| description | <b>Background:</b> Mini-Mental State Examination (MMSE) is the most widely used tool in cognitive screening. Some individuals with normal MMSE scores have extensive cognitive impairment. Systematic neuropsychological assessment should be performed in these patients. This study aimed to optimize the systematic neuropsychological test battery (NTB) by machine learning and develop new classification models for distinguishing mild cognitive impairment (MCI) and dementia among individuals with MMSE ≥ 26. <b>Methods:</b> 375 participants with MMSE ≥ 26 were assigned a diagnosis of cognitively unimpaired (CU) (<i>n</i> = 67), MCI (<i>n</i> = 174), or dementia (<i>n</i> = 134). We compared the performance of five machine learning algorithms, including logistic regression, decision tree, SVM, XGBoost, and random forest (RF), in identifying MCI and dementia. <b>Results:</b> RF performed best in identifying MCI and dementia. Six neuropsychological subtests with high-importance features were selected to form a simplified NTB, and the test time was cut in half. The AUC of the RF model was 0.89 for distinguishing MCI from CU, and 0.84 for distinguishing dementia from nondementia. <b>Conclusions:</b> This simplified cognitive assessment model can be useful for the diagnosis of MCI and dementia in patients with normal MMSE. It not only optimizes the content of cognitive evaluation, but also improves diagnosis and reduces missed diagnosis. |
| first_indexed | 2024-03-10T01:10:23Z |
| format | Article |
| id | doaj.art-81982255f0274e1680daaf194de334b7 |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-10T01:10:23Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-81982255f0274e1680daaf194de334b72023-11-23T14:19:31ZengMDPI AGJournal of Personalized Medicine2075-44262022-01-011213710.3390/jpm12010037Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination ScoresJie Wang0Zhuo Wang1Ning Liu2Caiyan Liu3Chenhui Mao4Liling Dong5Jie Li6Xinying Huang7Dan Lei8Shanshan Chu9Jianyong Wang10Jing Gao11Department of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Computer Science and Technology, Tsinghua University, Beijing 100084, ChinaDepartment of Computer Science and Technology, Tsinghua University, Beijing 100084, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, ChinaDepartment of Computer Science and Technology, Tsinghua University, Beijing 100084, ChinaDepartment of Neurology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China<b>Background:</b> Mini-Mental State Examination (MMSE) is the most widely used tool in cognitive screening. Some individuals with normal MMSE scores have extensive cognitive impairment. Systematic neuropsychological assessment should be performed in these patients. This study aimed to optimize the systematic neuropsychological test battery (NTB) by machine learning and develop new classification models for distinguishing mild cognitive impairment (MCI) and dementia among individuals with MMSE ≥ 26. <b>Methods:</b> 375 participants with MMSE ≥ 26 were assigned a diagnosis of cognitively unimpaired (CU) (<i>n</i> = 67), MCI (<i>n</i> = 174), or dementia (<i>n</i> = 134). We compared the performance of five machine learning algorithms, including logistic regression, decision tree, SVM, XGBoost, and random forest (RF), in identifying MCI and dementia. <b>Results:</b> RF performed best in identifying MCI and dementia. Six neuropsychological subtests with high-importance features were selected to form a simplified NTB, and the test time was cut in half. The AUC of the RF model was 0.89 for distinguishing MCI from CU, and 0.84 for distinguishing dementia from nondementia. <b>Conclusions:</b> This simplified cognitive assessment model can be useful for the diagnosis of MCI and dementia in patients with normal MMSE. It not only optimizes the content of cognitive evaluation, but also improves diagnosis and reduces missed diagnosis.https://www.mdpi.com/2075-4426/12/1/37machine learningdementiacognitive dysfunctionneuropsychological testsmental status and dementia tests |
| spellingShingle | Jie Wang Zhuo Wang Ning Liu Caiyan Liu Chenhui Mao Liling Dong Jie Li Xinying Huang Dan Lei Shanshan Chu Jianyong Wang Jing Gao Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores Journal of Personalized Medicine machine learning dementia cognitive dysfunction neuropsychological tests mental status and dementia tests |
| title | Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores |
| title_full | Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores |
| title_fullStr | Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores |
| title_full_unstemmed | Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores |
| title_short | Random Forest Model in the Diagnosis of Dementia Patients with Normal Mini-Mental State Examination Scores |
| title_sort | random forest model in the diagnosis of dementia patients with normal mini mental state examination scores |
| topic | machine learning dementia cognitive dysfunction neuropsychological tests mental status and dementia tests |
| url | https://www.mdpi.com/2075-4426/12/1/37 |
| work_keys_str_mv | AT jiewang randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT zhuowang randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT ningliu randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT caiyanliu randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT chenhuimao randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT lilingdong randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT jieli randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT xinyinghuang randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT danlei randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT shanshanchu randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT jianyongwang randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores AT jinggao randomforestmodelinthediagnosisofdementiapatientswithnormalminimentalstateexaminationscores |