[[HOPES Project Index]] **What is Digital Phenotyping?** - "moment-by-moment quantification of the individual-level human phenotype _[in situ](https://en.wikipedia.org/wiki/In_situ "In situ")_ using [data](https://en.wikipedia.org/wiki/Data "Data") from personal digital devices." [Digital phenotyping - Wikipedia](https://en.wikipedia.org/wiki/Digital_phenotyping) - [[Article - Technology and Mental Health. State of the Art for Assessment and Treatment]] **The first step to validate this method is to study the correlation between passive data, active data and patient-reported outcomes**. - "“Understanding how passive data relates to active data and patient reported outcomes is a first step in assessing the utility of these data.” (Henson, 2020, p. 2)" - source [[Article - Towards Clinically Actionable Digital Phenotyping Targets in Schizophrenia]] [[We should include a control group to compare healthy and patient digital phenotype data]] [[Passive Data are not always a direct proxy for symptoms. The use of digital phenotype data must be guided by theory]] **Ecological Momentary Assessment** - [[Ecological Momentary Assessments]] **Ecological Momentary Interventions** - [[Ecological Momentary Interventions]] - [[Use of Ecological Momentary Assessment and Intervention in Treatment With Adults]] **Science/Research related to Digital Phenotyping?** - [[Systematic Review of Digital Interventions Project]] **DP signals association with different symptoms, conditions, behaviour** _Association with Affective Symptoms_ - There are 85 different features - "A recent systematic review on studies that collected sensor data and depression symptoms identified 85 different features (e.g. amount of home stay, sleep duration, phone calls received) across 46 studies. While not all features showed consistent significance across studies, some features like sleep duration and distance travelled showed strong but opposite associations when comparing clinical and non-clinical populations." - (Rohani, D. A., Faurholt-Jepsen, M., Kessing, L. V. & Bardram, J. E. Correlations between objective behavioral features collected from mobile and wearable devices and depressive mood symptoms in patients with affective disorders: systematic review. JMIR mHealth uHealth. 6, e165 (2018).)- source [[Article - Towards Clinically Actionable Digital Phenotyping Targets in Schizophrenia]] - [[Digital Phenotype Signals associated with Anxiety]] - [[Digital Phenotype Signals associated with Bipolar Disorder]] - [[Digital Phenotype Signals associated with Psychosis]] - [[DP - Sleep]] - [[DP - Speech]] - [[DP - Phone calls]] - [[Sociability]] - [[DP - Geolocation]] - [[DP - Missing Data]] - [[DP - Accelerometry]] - [[DP - Text Messages]] - [[heart_Rate DP]] **Proponent to use digital tools in mental health** - [[Reinventing mental health care in youth through mobile approaches- Current status and future steps]] - [[Article - Relapse prediction in schizophrenia with smartphone digital phenotyping during COVID-19 - a prospective, three-site, two-country, longitudinal study]] **Opponent** - [[Can digital data diagnose mental health problems A sociological exploration of ‘digital phenotyping’]] - [[Can digital data diagnose mental health problems A sociological exploration of ‘digital phenotyping’]] **Standards, Frameworks** - [[The V3 framework for validating passive digital biomarkers]] - [[20230413 Designing Feedback Loop to improve system design]] **How is this aligned with the hospital vision?** - [[Strategy for Digital Transformation for the Hospital]] [[Clinical Constructs and Digital Phenotyping]]