Utilizing Digital Phenotyping to Discriminate Unipolar Depression and Bipolar Disorder: A Systematic Review (Preprint)

Differentiating bipolar disorder (BD) from unipolar depression (UD) is essential, as these conditions differ greatly in their progression and treatment approaches. Digital phenotyping, which involves using data from smartphones or other digital devices to assess mental health, has emerged as a promising tool for distinguishing between these two disorders. This systematic review aims to summarize the findings of existing studies that assess the use of digital devices in distinguishing between UD and BD. Additionally, it seeks to identify gaps in the current research and suggest directions for future studies. A comprehensive search was conducted in Scopus, IEEE Xplore, PubMed, and EMBASE databases until 20/9/2024. The search was focused on studies evaluating the use of digital tools, such as smartphone apps, wearable devices, audio/video recordings, and multimodal technologies, for patients with UD and BD. The review protocol was registered in PROSPERO (CRD42024624202). We identified 18 studies involving 732 participants with UD and 590 participants with BD. Among the included studies, 4 utilized smartphone apps, 3 employed wearable devices, 10 analyzed audio/video recordings, and 1 used multimodal technologies. Importantly, 9 studies directly focused on differentiating between UD and BD, excluding healthy controls or other mental health conditions from their classifications. Digital phenotyping offers significant promise in distinguishing between UD and BD, with ongoing advances in technology. However, challenges such as data privacy, security concerns, and equitable access must be addressed to fully harness the potential of digital tools for inclusive mental health care. Further research should focus on overcoming these challenges and refining digital phenotyping methodologies to ensure broader applicability in clinical settings.