Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis
IntroductionGait disorders and gait-related cognitive tests were recently linked to future Alzheimer’s Disease (AD) dementia diagnosis in amnestic Mild Cognitive Impairment (aMCI). This study aimed to evaluate the predictive power of gait disorders and gait-related neuropsychological performances fo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1328713/full |
| _version_ | 1797341240915656704 |
|---|---|
| author | Cosimo Tuena Chiara Pupillo Chiara Stramba-Badiale Marco Stramba-Badiale Giuseppe Riva Giuseppe Riva |
| author_facet | Cosimo Tuena Chiara Pupillo Chiara Stramba-Badiale Marco Stramba-Badiale Giuseppe Riva Giuseppe Riva |
| author_sort | Cosimo Tuena |
| collection | DOAJ |
| description | IntroductionGait disorders and gait-related cognitive tests were recently linked to future Alzheimer’s Disease (AD) dementia diagnosis in amnestic Mild Cognitive Impairment (aMCI). This study aimed to evaluate the predictive power of gait disorders and gait-related neuropsychological performances for future AD diagnosis in aMCI through machine learning (ML).MethodsA sample of 253 aMCI (stable, converter) individuals were included. We explored the predictive accuracy of four predictors (gait profile plus MMSE, DSST, and TMT-B) previously identified as critical for the conversion from aMCI to AD within a 36-month follow-up. Supervised ML algorithms (Support Vector Machine [SVM], Logistic Regression, and k-Nearest Neighbors) were trained on 70% of the dataset, and feature importance was evaluated for the best algorithm.ResultsThe SVM algorithm achieved the best performance. The optimized training set performance achieved an accuracy of 0.67 (sensitivity = 0.72; specificity = 0.60), improving to 0.70 on the test set (sensitivity = 0.79; specificity = 0.52). Feature importance revealed MMSE as the most important predictor in both training and testing, while gait type was important in the testing phase.DiscussionWe created a predictive ML model that is capable of identifying aMCI at high risk of AD dementia within 36 months. Our ML model could be used to quickly identify individuals at higher risk of AD, facilitating secondary prevention (e.g., cognitive and/or physical training), and serving as screening for more expansive and invasive tests. Lastly, our results point toward theoretically and practically sound evidence of mind and body interaction in AD. |
| first_indexed | 2024-03-08T10:14:59Z |
| format | Article |
| id | doaj.art-cc9126f8584c44aaa5dfe091b523e98a |
| institution | Directory Open Access Journal |
| issn | 1662-5161 |
| language | English |
| last_indexed | 2024-03-08T10:14:59Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj.art-cc9126f8584c44aaa5dfe091b523e98a2024-01-29T04:25:00ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612024-01-011710.3389/fnhum.2023.13287131328713Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysisCosimo Tuena0Chiara Pupillo1Chiara Stramba-Badiale2Marco Stramba-Badiale3Giuseppe Riva4Giuseppe Riva5Applied Technology for Neuro-Psychology Lab, IRCCS Istituto Auxologico Italiano, Milan, ItalyApplied Technology for Neuro-Psychology Lab, IRCCS Istituto Auxologico Italiano, Milan, ItalyApplied Technology for Neuro-Psychology Lab, IRCCS Istituto Auxologico Italiano, Milan, ItalyDepartment of Geriatrics and Cardiovascular Medicine, IRCCS Istituto Auxologico Italiano, Milan, ItalyApplied Technology for Neuro-Psychology Lab, IRCCS Istituto Auxologico Italiano, Milan, ItalyHumane Technology Lab, Università Cattolica del Sacro Cuore, Milan, ItalyIntroductionGait disorders and gait-related cognitive tests were recently linked to future Alzheimer’s Disease (AD) dementia diagnosis in amnestic Mild Cognitive Impairment (aMCI). This study aimed to evaluate the predictive power of gait disorders and gait-related neuropsychological performances for future AD diagnosis in aMCI through machine learning (ML).MethodsA sample of 253 aMCI (stable, converter) individuals were included. We explored the predictive accuracy of four predictors (gait profile plus MMSE, DSST, and TMT-B) previously identified as critical for the conversion from aMCI to AD within a 36-month follow-up. Supervised ML algorithms (Support Vector Machine [SVM], Logistic Regression, and k-Nearest Neighbors) were trained on 70% of the dataset, and feature importance was evaluated for the best algorithm.ResultsThe SVM algorithm achieved the best performance. The optimized training set performance achieved an accuracy of 0.67 (sensitivity = 0.72; specificity = 0.60), improving to 0.70 on the test set (sensitivity = 0.79; specificity = 0.52). Feature importance revealed MMSE as the most important predictor in both training and testing, while gait type was important in the testing phase.DiscussionWe created a predictive ML model that is capable of identifying aMCI at high risk of AD dementia within 36 months. Our ML model could be used to quickly identify individuals at higher risk of AD, facilitating secondary prevention (e.g., cognitive and/or physical training), and serving as screening for more expansive and invasive tests. Lastly, our results point toward theoretically and practically sound evidence of mind and body interaction in AD.https://www.frontiersin.org/articles/10.3389/fnhum.2023.1328713/fullamnestic mild cognitive impairmentgait abnormalitiescognitive dysfunctionAlzheimer’s diseaseartificial intelligencemotor system |
| spellingShingle | Cosimo Tuena Chiara Pupillo Chiara Stramba-Badiale Marco Stramba-Badiale Giuseppe Riva Giuseppe Riva Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis Frontiers in Human Neuroscience amnestic mild cognitive impairment gait abnormalities cognitive dysfunction Alzheimer’s disease artificial intelligence motor system |
| title | Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis |
| title_full | Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis |
| title_fullStr | Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis |
| title_full_unstemmed | Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis |
| title_short | Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis |
| title_sort | predictive power of gait and gait related cognitive measures in amnestic mild cognitive impairment a machine learning analysis |
| topic | amnestic mild cognitive impairment gait abnormalities cognitive dysfunction Alzheimer’s disease artificial intelligence motor system |
| url | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1328713/full |
| work_keys_str_mv | AT cosimotuena predictivepowerofgaitandgaitrelatedcognitivemeasuresinamnesticmildcognitiveimpairmentamachinelearninganalysis AT chiarapupillo predictivepowerofgaitandgaitrelatedcognitivemeasuresinamnesticmildcognitiveimpairmentamachinelearninganalysis AT chiarastrambabadiale predictivepowerofgaitandgaitrelatedcognitivemeasuresinamnesticmildcognitiveimpairmentamachinelearninganalysis AT marcostrambabadiale predictivepowerofgaitandgaitrelatedcognitivemeasuresinamnesticmildcognitiveimpairmentamachinelearninganalysis AT giusepperiva predictivepowerofgaitandgaitrelatedcognitivemeasuresinamnesticmildcognitiveimpairmentamachinelearninganalysis AT giusepperiva predictivepowerofgaitandgaitrelatedcognitivemeasuresinamnesticmildcognitiveimpairmentamachinelearninganalysis |