首页|Data on Machine Learning Reported by Jannatul Mawa Misti and Colleagues (Feature Contributions and Predictive Accuracy in Modeling Adolescent Daytime Sleepiness Using Machine Learning: The MeLiSA Study)
Data on Machine Learning Reported by Jannatul Mawa Misti and Colleagues (Feature Contributions and Predictive Accuracy in Modeling Adolescent Daytime Sleepiness Using Machine Learning: The MeLiSA Study)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-New research on Machine Learning is th e subject of a report. According to newsreporting out of Dhaka, Bangladesh, by NewsRx editors, research stated, "Excessive daytime sleepiness(EDS) among adole scents poses significant risks to academic performance, mental health, and overa llwell-being. This study examines the prevalence and risk factors of EDS in ado lescents in Bangladesh andutilizes machine learning approaches to predict the r isk of EDS."Funders for this research include University of South Asia, Princess Nourah bint Abdulrahman University.Our news journalists obtained a quote from the research, "A cross-sectional stud y was conductedamong 1496 adolescents using a structured questionnaire. Data we re collected through a two-stage stratified cluster sampling method. Chi-square tests and logistic regression analyses were performed usingSPSS. Machine learni ng models, including Categorical Boosting (CatBoost), Extreme Gradient Boosting(XGBoost), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), andGradient Boosting Machine (GBM), were employed to identify and predi ct EDS risk factors using Pythonand Google Colab. The prevalence of EDS in the cohort was 11.6%. SHAP values from the CatBoostmodel identified se lf-rated health status, gender, and depression as the most significant predictor s ofEDS. Among the models, GBM achieved the highest accuracy (90.15% ) and precision (88.81%), whileCatBoost had comparable accuracy (8 9.48%) and the lowest log loss (0.25). ROC-AUC analysis showedthat CatBoost and GBM performed robustly in distinguishing between EDS and non-EDS c ases, with AUCscores of 0.86. Both models demonstrated the superior predictive performance for EDS compared to others.The study emphasizes the role of health and demographic factors in predicting EDS among adolescentsin Bangladesh. Machi ne learning techniques offer valuable insights into the relative contribution of thesefactors, and can guide targeted interventions."
DhakaBangladeshAsiaCyborgsEmergi ng TechnologiesMachine LearningRisk and Prevention