phone camera

Deep Phenotyping Could Help Solve the Mental Health Care Crisis

By Justin T. Baker

The United States faces a growing mental health crisis and offers insufficient means for individuals to access care.

Digital technologies — the phone in your pocket, the camera-enabled display on your desk, the “smart” watch on your wrist, and the smart speakers in your home — might offer a path forward.

Deploying technology ethically, while understanding the risks of moving too fast (or too slow) with it, could radically extend our limited toolkit for providing access to high-quality care for the many individuals affected by mental health issues for whom the current mental health system is either out of reach or otherwise failing to meet their need.

In 2016, my colleagues and I founded an institute at McLean Hospital to study the use of technology in psychiatry: not just the hope and hype, but also the impact of coming technologies and A.I. on society, public mental health, and the practice of psychiatry.

The challenges are less technical and more concerned with how to preserve core aspects of our clinical discipline while taking intentional risks with the capabilities afforded by the devices on which we increasingly rely to meet the needs of individuals in a digital age.

Preserving “The Moral Treatment” in a Digital Age

Just eight miles from the bleeding-edge technologies of MIT and Technology Square, McLean has retained its founding principles of “moral treatment.” Our committed clinicians (and in many cases, the individuals receiving care) harbor what I characterize as a healthy degree of apprehension for technologies or care-delivery models that could erode that human-first, mostly analog model.

But, if harnessed effectively, new tools will allow us to move past the false choice between precise and personalized psychiatry that has confounded the field and limited progress.

For the past five years, our group has investigated how traditional sources of truth (e.g., clinical observations) change relative to other sources of truth (e.g., signals from someone’s device or their self-report).

We believe that studying relationships between signals as they change over time will reveal new ways to recognize early warning signs of clinical decompensation in individuals with severe mental illness.

The primary goal of our project, “Robust Predictors of Mania and Psychosis,” is to identify biological, environmental, and social factors that trigger dangerous mental states, particularly mania and psychosis. This project leverages data obtained from individuals who have been diagnosed with a psychotic or affective condition to follow them through “a year in the life.”

In addition to data from smartphone and wrist actigraphy devices (similar to FitBits), we collect audio-visual (AV) data to document how individuals look and speak as they transition through phases of illness.

Unobtrusive, quantitative behavioral phenotyping strategies could transform our ability to infer causal relationships between illness fluctuations, contextual factors, and treatment interventions and radically reshape the discovery and development of novel therapeutics. Being able to derive contextualized signals — from sensors, self-reports, and clinician evaluations — will open up rich possibilities for closed-loop, personalized, targeted therapeutic strategies tailored to an individual’s unique illness expressions.

We anticipate these studies will allow us to develop and implement predictive models of illness manifestations, and that improved data collection and analysis methods may offer great opportunities to alleviate the burden of mental disorder.

We fully appreciate concerns about moving too quickly into the great digital beyond: how embracing technologies could distance clinicians from the people they care for, erode the already fragile “doctor-patient relationship,” or even exacerbate access issues for people at the fringe of traditional care systems.

As the National Institutes of Health has emphasized through a series of publications and workshops, technological advances must address unique ethical, legal, and societal implications (ELSI) when it comes to treating the brain. Indeed, the message is clear: “The time is now to give forethought to strong incentive structures to promote the safe and effective use of digital biomarkers.

And yet, given the immensity and urgency of the mental health access crisis — and the promise of technologies now so commonplace as to have changed nearly every other aspect of daily life — moving too slowly seems equally, if not more, problematic. The ethics of doing nothing, when so much promise is at our fingertips, requires deep and meaningful consideration, and, importantly, input from the many stakeholders affected by mental illness, not just those who have traditionally had a seat at the table.


Justin T. Baker, MD, PhD, is the scientific director of the McLean Institute for Technology in Psychiatry (ITP) and director of the Laboratory for Functional Neuroimaging and Bioinformatics at McLean Hospital.


This post is part of our Ethical, Legal, and Social Implications of Deep Phenotyping symposium. All contributions to the symposium are available here.

The Petrie-Flom Center Staff

The Petrie-Flom Center staff often posts updates, announcements, and guests posts on behalf of others.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.