Machine Learning-Based Prediction of Attention-Deficit/Hyperactivity Disorder and Sleep Problems With Wearable Data
Won-Pyo Kim1, Hyun-Jin Kim2, Seung Pil Pack3
1LumanLab Inc, R&D Center, Seoul, South Korea.
Insights
Machine learning models using wearable data show promise for early detection of attention-deficit/hyperactivity disorder (ADHD) and sleep problems in children. This digital phenotype approach offers a novel screening method to improve child mental health outcomes.
Area of Science:
- Child and Adolescent Psychiatry
- Digital Health
- Machine Learning in Healthcare
Background:
- Early detection of attention-deficit/hyperactivity disorder (ADHD) and sleep problems is crucial for children's mental well-being.
- Traditional interview-based diagnostic methods have limitations, highlighting the need for innovative evaluation techniques.
- Digital phenotypes derived from daily life activities offer a potential solution for objective assessment.
Purpose of the Study:
- To assess the predictive accuracy of machine learning (ML) models for identifying ADHD and sleep problems in children.
- To utilize data from personal digital devices (wearable data) as training features for ML models.
- To validate these models against established diagnostic criteria using the Kiddie Schedule for Affective Disorders and Schizophrenia (K-SADS).
Main Methods:
- The study employed data from the Adolescent Brain Cognitive Development (ABCD) study, including wearable sensor data and K-SADS diagnostic results.
- Circadian rhythm-based features were extracted from 21 days of wearable data collected from a large cohort of children.
- ML models were developed and trained using merged wearable and diagnostic data for ADHD and sleep problem prediction.
Main Results:
- ML models demonstrated reasonable predictive performance for ADHD (AUC: 0.798) and sleep problems (AUC: 0.737).
- Key performance metrics included sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for both conditions.
- Feature importance analysis using Shapley Additive Explanations identified significant predictors within the digital phenotype data.
Conclusions:
- An ML-based method using digital phenotypes from wearable devices was developed for early detection of ADHD and sleep problems in children.
- The findings support the potential of this approach for facilitating early screening and intervention.
- Further research and follow-up studies are recommended to enhance the performance and clinical utility of these ML models.
Importance:
Early detection of attention-deficit/hyperactivity disorder (ADHD) and sleep problems is paramount for children's mental health. Interview-based diagnostic approaches have drawbacks, necessitating the development of an evaluation method that uses digital phenotypes in daily life.
Objective:
To evaluate the predictive performance of machine learning (ML) models by setting the data obtained from personal digital devices comprising training features (ie, wearable data) and diagnostic results of ADHD and sleep problems by the Kiddie Schedule for Affective Disorders and Schizophrenia Present and Lifetime Version for Diagnostic and Statistical Manual of Mental Disorders, 5th edition (K-SADS) as a prediction class from the Adolescent Brain Cognitive Development (ABCD) study.
Design, Setting, And Participants:
In this diagnostic study, wearable data and K-SADS data were collected at 21 sites in the US in the ABCD study (release 3.0, November 2, 2020, analyzed October 11, 2021). Screening data from 6571 patients and 21 days of wearable data from 5725 patients collected at the 2-year follow-up were used, and circadian rhythm-based features were generated for each participant. A total of 12 348 wearable data for ADHD and 39 160 for sleep problems were merged for developing ML models.
Main Outcomes And Measures:
The average performance of the ML models was measured using an area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In addition, the Shapley Additive Explanations value was used to calculate the importance of features.
Results:
The final population consisted of 79 children with ADHD problems (mean [SD] age, 144.5 [8.1] months; 55 [69.6%] males) vs 1011 controls and 68 with sleep problems (mean [SD] age, 143.5 [7.5] months; 38 [55.9%] males) vs 3346 controls. The ML models showed reasonable predictive performance for ADHD (AUC, 0.798; sensitivity, 0.756; specificity, 0.716; PPV, 0.159; and NPV, 0.976) and sleep problems (AUC, 0.737; sensitivity, 0.743; specificity, 0.632; PPV, 0.036; and NPV, 0.992).
Conclusions And Relevance:
In this diagnostic study, an ML method for early detection or screening using digital phenotypes in children's daily lives was developed. The results support facilitating early detection in children; however, additional follow-up studies can improve its performance.
