首页|Ulm University Reports Findings in Machine Learning (The predictive value of sup ervised machine learning models for insomnia symptoms through smartphone usage b ehavior)
Ulm University Reports Findings in Machine Learning (The predictive value of sup ervised machine learning models for insomnia symptoms through smartphone usage b ehavior)
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 Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news originating from Ulm, Germany, by NewsR x correspondents, research stated, “Digital phenotyping can be an innovative and unobtrusive way to improve the detection of insomnia. This study explores the c orrelations between smartphone usage features (SUF) and insomnia symptoms and th eir predictive value for detecting insomnia symptoms.” Our news journalists obtained a quote from the research from Ulm University, “In an observational study of a German convenience sample, the Insomnia Severity In dex (ISI) and smartphone usage data (e.g., time the screen was active, longest t ime the screen was inactive in the night) for the previous 7 days were obtained. SUF (e.g., min, mean) were calculated from the smartphone usage data. Correlati on analyses between the ISI and SUF were conducted. For the specification of the machine learning models (ML), 80 % of the data was allocated to t raining, 20 % to testing, and five-fold cross-validation was used. Six algorithms (support vector machine, XGBoost, Random Forest, k-Nearest-Neigh bor, Naive Bayes, and Logistic Regressions) were specified to predict ISI scores 15. 752 participants (51.1 % female, mean ISI = 10.23, mean age = 41.92) were included in the analyses. Small correlations between some of the SU F and insomnia symptoms were found. In the ML models, sensitivity was low, rangi ng from 0.05 to 0.27 in the testing subsample. Random Forest and Naive Bayes wer e the best-performing algorithms. Yet, their AUCs (0.57, 0.58 respectively) in t he testing subsample indicated a low discrimination capacity. Given the small ma gnitude of the correlations and low discrimination capacity of the ML models, SU Fs, as measured in this study, do not appear to be sufficient for detecting inso mnia symptoms.”
NETL
NSTL
