DIGITAL PHENOTYPING TO UNDERSTAND HEALTH-RELATED OUTCOMES: A SCOPING REVIEW

Abstract Modeling passive data collected by smartphones, or digital phenotyping, may help detect the early signs of declines in daily health and lead to steps prevent declines. Health-related outcomes have been typically acquired through self-report measures, however this broad approach has several limitations, such as recall social desirability bias. A potential solution is phenotyping. Guided Arksey O’Malley methodological framework, aim scoping review was identify studies that modeled smartphone-sensor into behavioral markers correlate predict health-related outcomes. literature search peer-reviewed conference PubMed, Scopus, Compendex, HTA yielded 3,170 articles. 40 met inclusion criteria. Studies were organized assessed for their: 1) collection approaches (e.g., smartphone sensor questionnaire), 2) feature extraction converting bedtime wake time sleep), 3) analytics identifying accelerometer sleep patterns using machine learning), 4) markers, which observing activity pattern an extended period then modeling activities appropriate behaviors, 5) The findings study demonstrate how transform outcomes, could provide information more grounded predictive use successful implementation phenotyping future research.