Using digital phenotyping for the classification of bipolar disorder and unipolar disorder: findings from machine learning models

Using digital phenotyping for the classification of bipolar disorder and unipolar disorder: findings from machine learning models

During this session we will look into two aspects of using digital phenotyping in bipolar disorder.

First, distinguishing between bipolar disorder type I and II constitutes a significant clinical challenge that relies on retrospective patient recall. Misclassification carries risks of inappropriate pharmacological management. Digital phenotyping offers a potential objective solution by monitoring behavioral biomarkers via smartphones. During this session data from new studies using digital phenotyping whether passive sensing data can distinguish between bipolar disorder type I and II at the population level versus the individual level.

Second, dysregulation in circadian rhythms, including sleep abnormalities, is a central feature in bipolar disorder during all illness phases. Data from exploratory analyses will be presented. These analyses investigated the association between variation in sleep and instability in mood based on day-to-day patient-reported smartphone-based data in patients with bipolar disorder.