Mood disorders tend to have some of the highest prevalence rates among mental health disorders, and enact high personal, social and economic costs in our country and around the world, presenting a significant public health challenge. Patients often experience low rates of care, worsening their own outcomes. Cogito's mobile application Cogito Companion objectively measures behavioral biomarkers via mobile phone sensors and uses these patterns as inputs to predictive models, trained against clinical outcomes. The models predict mental state components of mood disorders. The primary goal of this proposal is to validate the ability of Cogito Companion to passively detect changes in mood disorders in order to improve diagnosis, predict relapse, and measure disease progression in a national sample. This proposal addresses the critical barrier of accurate, objective real-time information on individual mental health. This barrier has prevented individuals from tracking their own disease progression and relapse, from empowering patients to self-manage their chronic symptoms, and from allowing individuals to know when to reach out and access healthcare support. The validation described in this grant proposal will provide patients the ability to have objective, transparent, and continuous metrics of their own mental health. These metrics have never before been available to the patient, in real-time, and with no bias of self -report. Through an observational study of the PCORI-funded and Massachusetts General Hospital-administered Mood Patient Powered Research Network participants, results will be gathered on the relationship of the biomarkers to clinical outcomes. This validation will lead to a successful Phase III commercialization of the technology.
Mood disorders have an extremely high prevalence and are incredibly costly to both the individual and society; yet, little is known about how to use biomarkers to detect changes in these disorders. Cogito has developed a technology to objectively assess mood disorder symptomology via novel mobile phone data streams. It is uniquely prepared to provide a means to identify at-risk individuals, improve diagnosis, predict treatment response, and measure disease progression for patients with mood disorders. This Phase II application focuses on validating the ability of this technology to passively calculate episode onset, and symptom change, for those suffering a lifetime prevalence of mood disorders. The success of this project will lead to a Phase III commercial rollout.
| Gold, Alexandra K; Montana, Rebecca E; Sylvia, Louisa G et al. (2016) Cognitive Remediation and Bias Modification Strategies in Mood and Anxiety Disorders. Curr Behav Neurosci Rep 3:340-349 |
