Data Analytics with a Purpose

Improving Mental Health through Machine Learning

The Walsh Lab translates Healthcare Data to Action through Machine Learning and Decision Support for vulnerable populations like those with suicidality and mental illness.

Our research focuses on the application of data science to complex healthcare data to enable mental, behavioral, and population health. Our collaborators are internists, psychiatrists, psychologists, engineers, epidemiologists, statisticians, community case managers, mobile crisis teams, and more.

We translate our predictive algorithms through informatics and implementation science to the point-of-care. We have partnered with other research teams around the world to glean insights from these complex data to predict and prevent self-harm and to improve mental health.

Find out More


Opioid overdoses more readily preventable with ensemble learning

October 28, 2021

Read the Article

AI in Healthcare

The Undiscovered Country – Can Suicide Be Predicted? 

August 2021

Read the Article

Harper’s Magazine

Screening Algorithm Flags Patients At Risk of Suicide

March 22, 2021

Read the Article

Diagnostics World News

Artificial Intelligence System Calculates Suicide Attempt Risk – Here’s How It Performed

March 12, 2021

Read the Article


Guest on Informatics in the Round with Dr. Kevin B. Johnson — COVID and the Hidden Data Gap

February 6, 2021

Hear the Episode

Informatics in the Round

    Stay up to date with the latest developments in our work in The Walsh Lab.
    Carousel controls

    New Paper – Ensemble learning to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the state of Tennessee

    Read More

    New Project – Predicting and Preventing Suicide in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) in the COVID Era

    Read More

    Upcoming Panel – The Intersection of Value and AI: Where Machines Can Make a Difference, 5/13/21

    Read More

    New Paper: Prospective Validation of an Electronic Health Record–Based, Real-Time Suicide Risk Model

    Read More

    New Project — Improving probabilistic phenotyping of incident outcomes through enhanced ascertainment with natural language processing

    Read More

    Carrie Reale Honored with the Harriet H. Werley Award at the AMIA 2020 Virtual Annual Symposium

    Read More