From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults
Abstract Background This study aims to investigate the associations between signal-level physical activity (PA) features derived from wrist accelerometry data and cognitive status in older adults, and to evaluate their potential predictive value when combined with demographics. Methods We analyzed P...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | International Journal of Behavioral Nutrition and Physical Activity |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12966-025-01706-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585369882722304 |
|---|---|
| author | Ling-Jie Fan Feng-Yi Wang Jun-Han Zhao Jun-Jie Zhang Yang-An Li Jia Tang Tao Lin Quan Wei |
| author_facet | Ling-Jie Fan Feng-Yi Wang Jun-Han Zhao Jun-Jie Zhang Yang-An Li Jia Tang Tao Lin Quan Wei |
| author_sort | Ling-Jie Fan |
| collection | DOAJ |
| description | Abstract Background This study aims to investigate the associations between signal-level physical activity (PA) features derived from wrist accelerometry data and cognitive status in older adults, and to evaluate their potential predictive value when combined with demographics. Methods We analyzed PA data from 3,363 older adults (NHATS: n = 747; NHANES: n = 2,616), with each participant contributing a complete 3-day continuous activity sequence. We extracted the most relevant PA features associated with cognitive function using feature engineering and recursive feature elimination. Demographic characteristics were also incorporated, and multimodal data fusion was achieved through canonical correlation analysis. We then developed explainable machine learning models, primarily random forest, optimized with hyperparameters, to predict individual cognitive function status. Results Using recursive feature elimination, we identified the top 20 PA features from each dataset and combined them with demographic features for modeling. The models achieved AUCs of 0.84 and 0.80 for NHATS and NHANES. Change quantiles and FFT coefficients emerged as the consistently top-ranked PA features across datasets, ranking 1st and 2nd respectively in their predictive importance for cognitive function. Models based on the top 10 PA features common to both datasets, along with demographic features, achieved AUCs above 0.8. Conclusions This study identifies novel time-frequency domain features of physical activity that show robust associations with cognitive status across two independent cohorts. These features, particularly those capturing activity variability and rhythmicity, provide complementary information beyond traditional cumulative PA measures. Based on these findings, we developed a proof-of-concept application that demonstrates the feasibility of translating these PA analytics into practical monitoring tools in real-world settings. |
| format | Article |
| id | doaj-art-93999303531846208bd6073862156801 |
| institution | Kabale University |
| issn | 1479-5868 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | International Journal of Behavioral Nutrition and Physical Activity |
| spelling | doaj-art-93999303531846208bd60738621568012025-01-26T12:52:59ZengBMCInternational Journal of Behavioral Nutrition and Physical Activity1479-58682025-01-0122111510.1186/s12966-025-01706-xFrom physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adultsLing-Jie Fan0Feng-Yi Wang1Jun-Han Zhao2Jun-Jie Zhang3Yang-An Li4Jia Tang5Tao Lin6Quan Wei7College of Computer Science, Sichuan UniversityDepartment of Rehabilitation Medicine, West China Hospital of Sichuan UniversityDepartment of Biomedical Informatics, Harvard Medical SchoolCollege of Computer Science, Sichuan UniversityDepartment of Rehabilitation Medicine, West China Hospital of Sichuan UniversityCollege of Computer Science, Sichuan UniversityCollege of Computer Science, Sichuan UniversityDepartment of Rehabilitation Medicine, West China Hospital of Sichuan UniversityAbstract Background This study aims to investigate the associations between signal-level physical activity (PA) features derived from wrist accelerometry data and cognitive status in older adults, and to evaluate their potential predictive value when combined with demographics. Methods We analyzed PA data from 3,363 older adults (NHATS: n = 747; NHANES: n = 2,616), with each participant contributing a complete 3-day continuous activity sequence. We extracted the most relevant PA features associated with cognitive function using feature engineering and recursive feature elimination. Demographic characteristics were also incorporated, and multimodal data fusion was achieved through canonical correlation analysis. We then developed explainable machine learning models, primarily random forest, optimized with hyperparameters, to predict individual cognitive function status. Results Using recursive feature elimination, we identified the top 20 PA features from each dataset and combined them with demographic features for modeling. The models achieved AUCs of 0.84 and 0.80 for NHATS and NHANES. Change quantiles and FFT coefficients emerged as the consistently top-ranked PA features across datasets, ranking 1st and 2nd respectively in their predictive importance for cognitive function. Models based on the top 10 PA features common to both datasets, along with demographic features, achieved AUCs above 0.8. Conclusions This study identifies novel time-frequency domain features of physical activity that show robust associations with cognitive status across two independent cohorts. These features, particularly those capturing activity variability and rhythmicity, provide complementary information beyond traditional cumulative PA measures. Based on these findings, we developed a proof-of-concept application that demonstrates the feasibility of translating these PA analytics into practical monitoring tools in real-world settings.https://doi.org/10.1186/s12966-025-01706-xPhysical activityCognitive functionAccelerometerExplainable machine learning |
| spellingShingle | Ling-Jie Fan Feng-Yi Wang Jun-Han Zhao Jun-Jie Zhang Yang-An Li Jia Tang Tao Lin Quan Wei From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults International Journal of Behavioral Nutrition and Physical Activity Physical activity Cognitive function Accelerometer Explainable machine learning |
| title | From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults |
| title_full | From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults |
| title_fullStr | From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults |
| title_full_unstemmed | From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults |
| title_short | From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults |
| title_sort | from physical activity patterns to cognitive status development and validation of novel digital biomarkers for cognitive assessment in older adults |
| topic | Physical activity Cognitive function Accelerometer Explainable machine learning |
| url | https://doi.org/10.1186/s12966-025-01706-x |
| work_keys_str_mv | AT lingjiefan fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults AT fengyiwang fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults AT junhanzhao fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults AT junjiezhang fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults AT yanganli fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults AT jiatang fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults AT taolin fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults AT quanwei fromphysicalactivitypatternstocognitivestatusdevelopmentandvalidationofnoveldigitalbiomarkersforcognitiveassessmentinolderadults |