Feature Contributions and Predictive Accuracy in Modeling Adolescent Daytime Sleepiness Using Machine Learning: The
Mohammed A Mamun1,2,3, Jannatul Mawa Misti1, Md Emran Hasan1,4
1CHINTA Research Bangladesh, Dhaka 1342, Bangladesh.
Brain Sciences
|October 25, 2024
Summary
Excessive daytime sleepiness (EDS) affects 11.6% of adolescents in Bangladesh. Machine learning models identified self-rated health, gender, and depression as key risk factors, enabling better prediction and intervention strategies.
Area of Science:
- Public Health
- Computational Medicine
- Adolescent Health
Background:
- Excessive daytime sleepiness (EDS) in adolescents is linked to poor academic performance, mental health issues, and reduced well-being.
- Understanding EDS prevalence and risk factors in diverse populations like Bangladesh is crucial for targeted interventions.
Purpose of the Study:
- To determine the prevalence and identify risk factors of EDS in Bangladeshi adolescents.
- To apply machine learning (ML) models for predicting EDS risk in this population.
Main Methods:
- A cross-sectional study involving 1496 adolescents using a structured questionnaire and two-stage stratified cluster sampling.
- Statistical analyses (Chi-square, logistic regression) and ML models (CatBoost, XGBoost, SVM, RF, KNN, GBM) were utilized for risk factor identification and prediction.
- SHAP values were used to interpret the significance of predictors in the CatBoost model.
Main Results:
- The prevalence of EDS was found to be 11.6% among the surveyed adolescents.
- Self-rated health status, gender, and depression emerged as the most significant predictors of EDS, as identified by SHAP values.
- Gradient Boosting Machine (GBM) and Categorical Boosting (CatBoost) models demonstrated high accuracy (90.15% and 89.48% respectively) and robust predictive performance (AUC of 0.86).
Conclusions:
- Health status and demographic factors significantly predict EDS in Bangladeshi adolescents.
- Machine learning models effectively identify EDS risk factors and offer superior predictive capabilities for targeted interventions.
- Further longitudinal and interventional studies are recommended to enhance generalizability and develop effective EDS management strategies.
More Related Videos
Related Concept Videos
01:07Narcolepsy
92
Narcolepsy is a chronic sleep disorder characterized by pervasive, uncontrolled sleepiness and other sleep disturbances. One of its hallmark symptoms is an abrupt transition to REM sleep upon falling asleep, which causes symptoms typically associated with this phase to occur unexpectedly during wakefulness. These include the following symptoms, which typically last from a minute or two to half an hour.
92
01:13Insufficient Sleep and Sleep Deprivation
134
Insufficient sleep refers to not getting the recommended amount of sleep for optimal functioning, even if it's just slightly less than needed. Sleep insufficiency may occur due to lifestyle choices, such as staying up late for social events or work, resulting in routinely getting less sleep than required. For example, consistently sleeping 6 hours when the body needs 7-9 hours can lead to cumulative effects on health and well-being.
Sleep deprivation is a more severe form of sleep loss...
Sleep deprivation is a more severe form of sleep loss...
134
01:11Understanding Sleep
220
Sleep, an essential biological state, involves significant reductions in physical activity, sensory awareness, and interaction with the environment. This complex physiological process is primarily regulated by specific brain regions, notably the hypothalamus and pons, which govern the sleep-wake cycle or circadian rhythm.
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
220