Colin Walsh Leads New Grant from Military Suicide Research Consortium

December 15, 2017

Colin Walsh will serve as the Vanderbilt Principal Investigator of a new 3-year grant from the Military Suicide Research Consortium to apply the suicide risk prediction algorithms validated at Vanderbilt to primary care in the Navy in partnership with the Navy Medical Center, Portsmouth, and with Walsh’s longtime collaborators now at Florida State University, Jessica Ribeiro (MSRC/FSU PI) and Joseph Franklin (Co-PI). Laurie Novak, as Co-Investigator on the grant, will lead the study of qualitative research and clinical workflow in Naval primary care as a part of this work. The project will externally validate Vanderbilt’s algorithms of suicide risk prediction in the Naval cohort and will incorporate this risk prediction into novel decision support for use in the Electronic Health Record. The final aim of the project is to study the impact of this work on rates of suicidal behaviors and on clinical practice in primary care in a population of active duty servicemembers.

Daniel Fabbri Leads Grant to Build Electronic Medical Record System for Battlefield Scenarios

November 9, 2017

(From Vanderbilt University Medical Center Reporter)


Team seeks to build EMR system for battlefield scenarios

by Paul Govern

Daniel Fabbri, Ph.D., assistant professor of Biomedical Informatics and Computer Science, has been awarded a $1.7 million research grant from the U.S. Department of Defense to create an automated clinical documentation system for use in battlefield ambulances and helicopters.

Fabbri and his team will attempt to create a simple electronic medical record fed exclusively by data from video cameras installed in transport vehicles and motion sensors (accelerometers) worn by medics. In light of the noisy conditions that apply in battlefield patient transport, use of audio sensors and automated voice recognition is ruled out.

“We’re proposing to leverage a combination of off-the-shelf cameras and wearable sensors to capture motion signatures and report in real time not just the general level of activity among medics, but also specific patient interventions such as the duration of cardio-pulmonary resuscitation, how many IV bags were hung, whether a breathing tube or chest tube was placed,” Fabbri said. “We further propose using this type of passively gathered information to automatically generate a triage score indicating severity for each patient.”

Trauma teams in field hospitals are too often hobbled by lack of information about incoming wounded, according to one of the project’s co-investigators, U.S. Navy Medical Corps Commander and Afghan War veteran Jesse Ehrenfeld, M.D., MPH, professor of Anesthesiology, Health Policy and Surgery and associate professor of Biomedical Informatics.

During his tour as a combat anesthesiologist in Kandahar, Afghanistan, “Information I received about incoming casualties was limited to what might fit on a sticky note or be hastily scrawled with Magic Marker on a forehead or chest,” Ehrenfeld said.

“With this project we’re working toward automatically capturing events that are critically important to communicate upstream,” he added. “And whether it’s a patient being brought to Vanderbilt by ambulance or a service member being taken to a field hospital, similar challenges apply for communication. This project will have profound implications for both military and civilian patients and their care teams.”

Bradley Malin Appointed to European Medical Privacy Advisory Group

September 15, 2017

(From Vanderbilt University Medical Center Reporter)

Malin Appointed to European Medical Privacy Advisory Group

by Paul Govern 

Vanderbilt’s Bradley Malin, Ph.D., has been appointed to the Technical Anonymization Group, recently established by the European Medicines Agency to advise it regarding best practices for the anonymization of patient information used in research.  The European Medicines Agency is a European Union agency for the evaluation of drugs and other medical products.

To support patient privacy and dissemination of research data, the agency has adopted policies for the publication of clinical data gathered in medical products research.

Malin is professor of Biomedical Informatics and Computer Science and associate professor of Biostatistics, vice chair for research in the department of Biomedical Informatics, and founder and director of the Health Information Privacy Laboratory.

He co-directs the Health Data Science Center, the Center for Genetic Privacy and Identity in Community Settings, and the Big Biomedical Data Science Ph.D. program.

Joshua Denny Named to List of Top Experts in Health Information Technology

September 15, 2017

(From the Vanderbilt University Medical Center Reporter)


Denny named to list of top experts in health information technology

by Paul Govern 

Joshua Denny, M.D., M.S., professor of Biomedical Informatics and Medicine at Vanderbilt, has been named to an annual list of the 50 leading experts in health care information technology by Health Data Management, a trade news publication.

A profile in the publication notes that Denny has been named director of the Data and Research Support Center of the National Institutes of Health Precision Medicine Initiative, and states that “The job of acquiring, organizing and securing what will be one of the world’s largest and most diverse data sets for precision medicine research falls squarely on the shoulders of Vanderbilt University Medical Center in Nashville, Tennessee, and Denny will be leading that effort.”

Newsweek Article on Colin Walsh's Research in Predicting Suicide Risk

February 28, 2017

From Newsweek:


Machine-Learning Algorithms Can Predict Suicide Risk More Readily than Clinicians

by Matthew Hutson

Each year in the United States, more than 40,000 people die by suicide, and from 1999 to 2014, the suicide rate increased 24 percent. You might think that after generations of theories and data, we would be close to understanding how to prevent self-harm, or at least predict it. But a new study concludes that the science of suicide prediction is dismal, and the established warning signs about as accurate as tea leaves.

There is, however, some hope. New research shows that machine-learning algorithms can dramatically improve our predictive abilities on suicides. In a new survey in the February issue of Psychological Bulletin, researchers looked at 365 studies from the past 50 years that included 3,428 different measurements of risk factors, such as genes, mental illness and abuse.


Colin Walsh, an internist and data scientist at Vanderbilt University Medical Center, along with FSU’s Franklin and Ribeiro, looked at millions of anonymized health records and compared 3,250 clear cases of nonfatal suicide attempts with a random group of patients. To make their prediction method widely scalable, they restricted themselves to factors that would be documented in routine clinical encounters, such as demographics, medications, prior diagnoses and body mass index. Then they let a computer churn through the data and find patterns that would predict suicide attempts within various time frames, from a week to two years.

The accuracy score for each algorithm could range from 0.5 to 1, with 0.5 being no better than chance and 1 being perfect prediction. For comparison, the single factors from the meta-analysis achieved scores of about 0.58, little better than flipping a coin. The computer, however, achieved scores ranging from 0.86, when predicting whether someone would attempt suicide within two years, to 0.92, when looking ahead one week.


(Read the complete article here)