News

PhD Defense, 9/30: Kevin "KJ" Krause

Below is this week's PhD student defense. See details below:  FRIDAY, SEPTEMBER 30, 2022 at 9:00 AM CT Kevin "KJ" Krause PhD Student, DBMI Title: "Applying Network Analysis and Supervised Learning to Electronic Clinical Notes to Improve Operational Suicide Risk Prevention at an Academic Medical Center"

Voice as a Biomarker of Health Project (Led by Toufeeq Ahmed) Seeks to Use Patients’ Voices to Help Diagnose Disease

A national databank of de-identified voices, combined with artificial intelligence, could lead to diagnosing and treating cancer, depression, autism, Alzheimer’s disease and voice disorders. Vanderbilt University Medical Center is partnering with 11 institutions on a $14 million NIH-funded project led by the University of South Florida and Weill Cornell Medicine that aims to establish voice as a biomarker used in clinical care.

Faculty Position Opportunity in VCLIC—Apply Now!

VCLIC FACULTY POSITION Faculty Position Opening: The Vanderbilt Clinical Informatics Center (VCLIC), Department of Biomedical Informatics, School of Medicine, Vanderbilt University Medical Center 

PheWAS Reveals Post-COVID-19 Diagnoses

A high-throughput informatics technique developed at Vanderbilt University Medical Center that reveals associations between genetic variations and medical conditions in the electronic health record (EHR) also can identify new “post-COVID” diagnoses, according to a report in the Journal of the American Medical Informatics Association. 

VUMC's Dan Roden Leads Effort to Map Heart Disease-Causing Genetic Variations

One in 100 people have genetic variations that can cause potentially life-threatening heart conditions, including high cholesterol (lipid disorders), heart muscle disease (cardiomyopathies), and abnormal heart rhythms (arrhythmias). Yet the functional impact of most of these cardiovascular genetic variants — whether they disrupt normal function or are harmless — is unknown. That is about to change.

NATURE: Cosmin Adi Bejan uses Natural Language Processing (NLP) to improve how well we identify (“ascertain”) suicidal thoughts and behaviors in healthcare data.

Methods relying on diagnostic codes to identify suicidal ideation and suicide attempt in Electronic Health Records (EHRs) at scale are suboptimal because suicide-related outcomes are heavily under-coded. We propose to improve the ascertainment of suicidal outcomes using natural language processing (NLP). We developed information retrieval methodologies to search over 200 million notes from the Vanderbilt EHR. Suicide query terms were extracted using word2vec. A weakly supervised approach was designed to label cases of suicidal outcomes.