Physical activity and the outcome of cognitive trajectory: a machine learning approach
Abstract Background Physical activity (PA) may have an impact on cognitive function. Machine learning (ML) techniques are increasingly used in dementia research, e.g., for diagnosis and risk stratification. Less is known about the value of ML for predicting cognitive decline in people with dementia...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | European Review of Aging and Physical Activity |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s11556-024-00367-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544890009255936 |
|---|---|
| author | Bettina Barisch-Fritz Jay Shah Jelena Krafft Yonas E. Geda Teresa Wu Alexander Woll Janina Krell-Roesch |
| author_facet | Bettina Barisch-Fritz Jay Shah Jelena Krafft Yonas E. Geda Teresa Wu Alexander Woll Janina Krell-Roesch |
| author_sort | Bettina Barisch-Fritz |
| collection | DOAJ |
| description | Abstract Background Physical activity (PA) may have an impact on cognitive function. Machine learning (ML) techniques are increasingly used in dementia research, e.g., for diagnosis and risk stratification. Less is known about the value of ML for predicting cognitive decline in people with dementia (PwD). The aim of this study was to use an ML approach to identify variables associated with a multimodal PA intervention that may impact cognitive changes in PwD, i.e., by distinguishing between cognitive decliners and non-decliners. Methods This is a secondary, exploratory analysis using data from a Randomized Controlled Trial that included a 16-week multimodal PA intervention for the intervention group (IG) and treatment as usual for the control group (CG) in nursing homes. Predictors included in the ML models were related to the intervention (e.g., adherence), physical performance (e.g., mobility, balance), and pertinent health-related variables (e.g., health status, dementia form and severity). Primary outcomes were global and domain-specific cognitive performance (i.e., attention/ executive function, language, visuospatial skills, memory) assessed by standardized tests. A Support Vector Machine model was used to perform the classification of each primary outcome into the two classes of decline and non-decline. GridSearchCV with fivefold cross-validation was used for model training, and area under the ROC curve (AUC) and accuracy were calculated to assess model performance. Results The study sample consisted of 319 PwD (IG, N = 161; CG, N = 158). The proportion of PwD experiencing cognitive decline, in the different domains measured, ranged from 27–48% in CG, and from 23–49% in IG, with no statistically significant differences and no time*group effects. ML models showed accuracy and AUC values ranging from 40.6–75.6. The strongest predictors of cognitive decline or non-decline were performance of activities of daily living in IG and CG, and adherence and mobility in IG. Conclusions ML models showed moderate performance, suggesting that the selected variables only had limited value for classification, with adherence and performance of activities of daily living appearing to be predictors of cognitive decline. While the study provides preliminary evidence of the potential use of ML approaches, larger studies are needed to confirm our observations and to include other variables in the prediction of cognitive decline, such as emotional health or biomarker abnormalities. |
| format | Article |
| id | doaj-art-65d05a45a3944a8aa97279652d2a79a4 |
| institution | Kabale University |
| issn | 1861-6909 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | European Review of Aging and Physical Activity |
| spelling | doaj-art-65d05a45a3944a8aa97279652d2a79a42025-01-12T12:11:49ZengBMCEuropean Review of Aging and Physical Activity1861-69092025-01-0122111310.1186/s11556-024-00367-2Physical activity and the outcome of cognitive trajectory: a machine learning approachBettina Barisch-Fritz0Jay Shah1Jelena Krafft2Yonas E. Geda3Teresa Wu4Alexander Woll5Janina Krell-Roesch6Karlsruhe Institute of TechnologyArizona State UniversityKarlsruhe Institute of TechnologyBarrow Neurological InstituteArizona State UniversityKarlsruhe Institute of TechnologyKarlsruhe Institute of TechnologyAbstract Background Physical activity (PA) may have an impact on cognitive function. Machine learning (ML) techniques are increasingly used in dementia research, e.g., for diagnosis and risk stratification. Less is known about the value of ML for predicting cognitive decline in people with dementia (PwD). The aim of this study was to use an ML approach to identify variables associated with a multimodal PA intervention that may impact cognitive changes in PwD, i.e., by distinguishing between cognitive decliners and non-decliners. Methods This is a secondary, exploratory analysis using data from a Randomized Controlled Trial that included a 16-week multimodal PA intervention for the intervention group (IG) and treatment as usual for the control group (CG) in nursing homes. Predictors included in the ML models were related to the intervention (e.g., adherence), physical performance (e.g., mobility, balance), and pertinent health-related variables (e.g., health status, dementia form and severity). Primary outcomes were global and domain-specific cognitive performance (i.e., attention/ executive function, language, visuospatial skills, memory) assessed by standardized tests. A Support Vector Machine model was used to perform the classification of each primary outcome into the two classes of decline and non-decline. GridSearchCV with fivefold cross-validation was used for model training, and area under the ROC curve (AUC) and accuracy were calculated to assess model performance. Results The study sample consisted of 319 PwD (IG, N = 161; CG, N = 158). The proportion of PwD experiencing cognitive decline, in the different domains measured, ranged from 27–48% in CG, and from 23–49% in IG, with no statistically significant differences and no time*group effects. ML models showed accuracy and AUC values ranging from 40.6–75.6. The strongest predictors of cognitive decline or non-decline were performance of activities of daily living in IG and CG, and adherence and mobility in IG. Conclusions ML models showed moderate performance, suggesting that the selected variables only had limited value for classification, with adherence and performance of activities of daily living appearing to be predictors of cognitive decline. While the study provides preliminary evidence of the potential use of ML approaches, larger studies are needed to confirm our observations and to include other variables in the prediction of cognitive decline, such as emotional health or biomarker abnormalities.https://doi.org/10.1186/s11556-024-00367-2Cognitive deteriorationAlzheimer's diseaseNeurodegenerative diseasesMachine learningPhysical activity interventionsArtificial intelligence analysis |
| spellingShingle | Bettina Barisch-Fritz Jay Shah Jelena Krafft Yonas E. Geda Teresa Wu Alexander Woll Janina Krell-Roesch Physical activity and the outcome of cognitive trajectory: a machine learning approach European Review of Aging and Physical Activity Cognitive deterioration Alzheimer's disease Neurodegenerative diseases Machine learning Physical activity interventions Artificial intelligence analysis |
| title | Physical activity and the outcome of cognitive trajectory: a machine learning approach |
| title_full | Physical activity and the outcome of cognitive trajectory: a machine learning approach |
| title_fullStr | Physical activity and the outcome of cognitive trajectory: a machine learning approach |
| title_full_unstemmed | Physical activity and the outcome of cognitive trajectory: a machine learning approach |
| title_short | Physical activity and the outcome of cognitive trajectory: a machine learning approach |
| title_sort | physical activity and the outcome of cognitive trajectory a machine learning approach |
| topic | Cognitive deterioration Alzheimer's disease Neurodegenerative diseases Machine learning Physical activity interventions Artificial intelligence analysis |
| url | https://doi.org/10.1186/s11556-024-00367-2 |
| work_keys_str_mv | AT bettinabarischfritz physicalactivityandtheoutcomeofcognitivetrajectoryamachinelearningapproach AT jayshah physicalactivityandtheoutcomeofcognitivetrajectoryamachinelearningapproach AT jelenakrafft physicalactivityandtheoutcomeofcognitivetrajectoryamachinelearningapproach AT yonasegeda physicalactivityandtheoutcomeofcognitivetrajectoryamachinelearningapproach AT teresawu physicalactivityandtheoutcomeofcognitivetrajectoryamachinelearningapproach AT alexanderwoll physicalactivityandtheoutcomeofcognitivetrajectoryamachinelearningapproach AT janinakrellroesch physicalactivityandtheoutcomeofcognitivetrajectoryamachinelearningapproach |