Skip to content Skip to navigation

Strategies for Mental Health

Principal Investigator
Zhenan Bao, Professor of Department of Chemical Engineering, and by courtesy, Chemistry and Material Science and Engineering

Co-Principal Investigators
Keith Humphreys, Professor of Psychiatry and the Behavioral Sciences
Leanne Williams, Professor, Psychiatry and Behavioral Sciences
Boris Murmann, Professor of Electrical Engineering
James Landay, Professor of Computer Science
Jan Liphardt, Associate Professor of Bioengineering
Erin MacDonald, Assistant Professor of Mechanical Engineering

Grand Challenges
How do we achieve effective yet affordable healthcare everywhere?
How can we use our strength in computation and data analysis to drive innovation?
How do we create synergy between humans and engineered systems?

The global cost of mental health conditions in 2010 was estimated at $2.5 trillion, with the cost projected to surge to $6.0 trillion by 2030. Yet, while one in four people on Earth (1.8 billion people) will be affected by mental or neurological disorders, available resources and access to care scarcely begin to meet the need. When untreated, mental illness often leads to chronic disability and, too often, fatality.

The obstacles towards mental health care are multi-faceted: social stigma, high cost, and absence of local care all hinder the ability of those with mental health conditions to seek out and receive help. Furthermore, mental health care efficacy can be limited: there are significant challenges associated with diagnosis, effective treatment, and post-treatment recurrence. Hence, the problem of improving health outcomes necessitates a holistic approach. Within this context, a new generation of technologies coming out of Stanford’s SOE has the potential to change this global picture. Wearable devices can transform mental health care because of their ability to monitor behavior and biodata, and thus link patient and provider. The prevalence and continued expansion of mobile technology enables the possibility of remote care and, in conjunction with wearable devices, can allow discrete monitoring, potentially circumventing the stigma often associated with mental health treatment. The overarching goal of this project is to develop and use sensor data and analytics to characterize mental states quantitatively, and to use that capability to prevent and treat mental illness irrespective of local environment.

Our team will bring together the disciplines of engineering, human-computer interaction, psychology, psychiatry, global health, design, business, and communications. Our team represents five departments in the SOE and reaches into the Schools of Medicine, Law and Business.

Research and field-testing will be performed at Stanford, in East Palo Alto, and the East Bay, with the future aim to reach low-resource regions and underrepresented populations globally by leveraging our Center for Innovations for Global Health. We are proposing five intersecting efforts: (1) a “Think Tank” to engage stakeholders around the world, explore the current state of mental health technology-based innovations, and create an actionable plan for quantifiably improving the mental health of 100 million people by January 1, 2025, (2) a multidisciplinary team of engineers, scientists, and clinicians who will define quantifiable parameters to characterize mental states, (3) conceptualization and (4) design of wearable devices that continuously measure molecular, physiological and behavioral data, and (5) evaluation of the wearables for quantifying mental state.

This work will establish a highly interdisciplinary team to address one of the most pressing global health burdens. The general methodology for quantifying mental state will provide the foundation for our wearables design efforts and has the potential to benefit myriad other disciplines. For example, doctors and patients could use metrics to track progress, and drug researchers could use them to test the efficacy of different dosages and treatment regimens. Continuous biodata monitoring will enable early disease detection, more effective pharmacological treatment, and ease patient frustration with evidence of progress in their treatment.