Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescents
BackgroundAttention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder with a complex etiology. The current diagnostic process for ADHD is often time-intensive and subjective. Recent advancements in machine learning offer new opportunities to improve ADHD diagnosis using d...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-05-01
|
| Series: | Frontiers in Child and Adolescent Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frcha.2025.1504323/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850154060085198848 |
|---|---|
| author | Muhammad Mahbubur Rahman Muhammad Mahbubur Rahman |
| author_facet | Muhammad Mahbubur Rahman Muhammad Mahbubur Rahman |
| author_sort | Muhammad Mahbubur Rahman |
| collection | DOAJ |
| description | BackgroundAttention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder with a complex etiology. The current diagnostic process for ADHD is often time-intensive and subjective. Recent advancements in machine learning offer new opportunities to improve ADHD diagnosis using diverse data sources. This study explores the potential of Fitbit-derived physical activity data to enhance ADHD diagnosis.MethodWe analyzed a sample of 450 participants from the Adolescent Brain Cognitive Development (ABCD) study (data release 5.0). Correlation analyses were conducted to examine associations between ADHD diagnosis and Fitbit-derived measurements, including sedentary time, resting heart rate, and energy expenditure. We then used multivariable logistic regression models to evaluate the predictive power of these measurements for ADHD diagnosis. Additionally, machine learning classifiers were trained to automatically classify individuals into ADHD+ and ADHD− groups.ResultsOur correlation analyses revealed statistically significant associations between ADHD diagnosis and Fitbit-derived physical activity data. The multivariable logistic regression models identified specific Fitbit measurements that significantly predicted ADHD diagnosis. Among the machine learning classifiers, the Random Forest outperformed others with cross-validation accuracy of 0.89, AUC of 0.95, precision of 0.88, recall of 0.90, F1-score of 0.89, and test accuracy of 0.88.ConclusionFitbit-derived measurements show promise for predicting ADHD diagnosis, with machine learning classifiers, particularly Random Forest, demonstrating high predictive accuracy. These findings suggest that wearable data may contribute to more objective and efficient methods for ADHD identification, potentially enhancing clinical practices for diagnosis and management. |
| format | Article |
| id | doaj-art-e6939b0cac0b4404aa60d33493956b00 |
| institution | OA Journals |
| issn | 2813-4540 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Child and Adolescent Psychiatry |
| spelling | doaj-art-e6939b0cac0b4404aa60d33493956b002025-08-20T02:25:33ZengFrontiers Media S.A.Frontiers in Child and Adolescent Psychiatry2813-45402025-05-01410.3389/frcha.2025.15043231504323Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescentsMuhammad Mahbubur Rahman0Muhammad Mahbubur Rahman1Center for Translational Research, Children’s National Hospital, Silver Spring, MD, United StatesPediatrics & Biostatistics and Bioinformatics, George Washington University, Washington, DC, United StatesBackgroundAttention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder with a complex etiology. The current diagnostic process for ADHD is often time-intensive and subjective. Recent advancements in machine learning offer new opportunities to improve ADHD diagnosis using diverse data sources. This study explores the potential of Fitbit-derived physical activity data to enhance ADHD diagnosis.MethodWe analyzed a sample of 450 participants from the Adolescent Brain Cognitive Development (ABCD) study (data release 5.0). Correlation analyses were conducted to examine associations between ADHD diagnosis and Fitbit-derived measurements, including sedentary time, resting heart rate, and energy expenditure. We then used multivariable logistic regression models to evaluate the predictive power of these measurements for ADHD diagnosis. Additionally, machine learning classifiers were trained to automatically classify individuals into ADHD+ and ADHD− groups.ResultsOur correlation analyses revealed statistically significant associations between ADHD diagnosis and Fitbit-derived physical activity data. The multivariable logistic regression models identified specific Fitbit measurements that significantly predicted ADHD diagnosis. Among the machine learning classifiers, the Random Forest outperformed others with cross-validation accuracy of 0.89, AUC of 0.95, precision of 0.88, recall of 0.90, F1-score of 0.89, and test accuracy of 0.88.ConclusionFitbit-derived measurements show promise for predicting ADHD diagnosis, with machine learning classifiers, particularly Random Forest, demonstrating high predictive accuracy. These findings suggest that wearable data may contribute to more objective and efficient methods for ADHD identification, potentially enhancing clinical practices for diagnosis and management.https://www.frontiersin.org/articles/10.3389/frcha.2025.1504323/fullADHDfitbit-derived physical activitywearable technologyadolescent mental healthmachine learning |
| spellingShingle | Muhammad Mahbubur Rahman Muhammad Mahbubur Rahman Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescents Frontiers in Child and Adolescent Psychiatry ADHD fitbit-derived physical activity wearable technology adolescent mental health machine learning |
| title | Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescents |
| title_full | Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescents |
| title_fullStr | Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescents |
| title_full_unstemmed | Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescents |
| title_short | Unlocking the potential of wearable technology: Fitbit-derived measures for predicting ADHD in adolescents |
| title_sort | unlocking the potential of wearable technology fitbit derived measures for predicting adhd in adolescents |
| topic | ADHD fitbit-derived physical activity wearable technology adolescent mental health machine learning |
| url | https://www.frontiersin.org/articles/10.3389/frcha.2025.1504323/full |
| work_keys_str_mv | AT muhammadmahbuburrahman unlockingthepotentialofwearabletechnologyfitbitderivedmeasuresforpredictingadhdinadolescents AT muhammadmahbuburrahman unlockingthepotentialofwearabletechnologyfitbitderivedmeasuresforpredictingadhdinadolescents |