Summary

Behavioral characteristics should be used to characterize mental illnesses, according to this paper. This paper describes how digital behavioral data can be used to determine a patient’s diagnosis and customize treatment, thereby reducing the diagnosis rate of comorbidities.  It is this methodology that underpins the design of PREDICTIX.   

Abstract

Disorders of the mind are ambiguously defined and diagnosed. The established diagnosis technique, based on structured interviews, questionnaires and data reported subjectively by patients, leaves the mental health field behind other medical fields. We provide examples from major depressive disorder (MDD). In 2009, the National Institute of Mental Health (NIMH) launched the Research Domain Criteria (RDoC) project as a new framework for investigating psychiatric pathologies from a multidisciplinary perspective. This is a positive step. Psychiatry today views mental illnesses as disorders originating from the brain and manifesting as behavioral problems; therefore, we believe these syndromes should be mainly described by their behavior. Utilizing digital biomarkers of mental disorder symptoms, we propose using smartphones and wearable devices to passively collect quantified behavioral data from patients. Digital biomarkers of MDD symptoms have already been identified, and apps have been created to collect longitudinal behavioral data. Quantified data can be used to determine a patient’s diagnosis and treatment, minimizing the comorbidity diagnosis rate. Such a fluid and personalized approach is crucial when there is such a wide spectrum of human behavior.