The problem with the problem list
Apr. 10, 2023—Algorithms to infer missing problems and suggest that they be added to electronic health records improved problem list completeness, with benefits for clinical care, patient comprehension of health conditions and population health.
Machine learning predicts delirium
Jan. 23, 2023—Using machine learning based on electronic health records of ICU patients predicted new-onset delirium with 82% sensitivity, Vanderbilt researchers found.
Study to search EHR for undiagnosed genetic diseases
Oct. 13, 2022—A team at Vanderbilt University Medical Center will explore computational solutions to help address the problem of missed or delayed diagnosis for patients with rare genetic diseases.
Counting steps can reduce disease risk: study
Oct. 10, 2022—A Vanderbilt study found that using a wearable activity tracker to count and increase the number and intensity of steps taken daily can reduce the risk of several common, chronic diseases.
BMI genetics influence heart function
Jun. 16, 2022—Vanderbilt researchers have discovered that a genetic predisposition to elevated body mass index increases the risk of diastolic dysfunction — a cardiac condition that can lead to heart failure.
Pushing (anti-overdose) drugs
May. 23, 2022—An automated alert to encourage clinicians to coprescribe naloxone for patients at risk of opioid overdose increased naloxone prescriptions per opioid prescription 16-fold.
Autism and sleep problems
May. 10, 2022—Vanderbilt researchers developed a framework for using de-identified medical records to characterize sleep in people on the autism spectrum — a framework that should also be useful for studying other neurodevelopmental disorders.
Gene network linked to Type 2 diabetes
May. 5, 2022—Vanderbilt researchers used a novel analytical approach to identify a network of genes associated with Type 2 diabetes, including 31 genes that had not previously been associated with the disease.
Smartphone app supports EHR efforts in low-income countries
Jan. 26, 2022—A smartphone app developed at Vanderbilt is assisting health care efforts in low- and middle-income countries.
AI predicts 24-hour hospital discharge
Nov. 16, 2021—Vanderbilt researchers used a machine learning algorithm and data from more than 26,000 hospital stays to predict who would and would not be discharged over the next 24 hours.
Medical diagnoses in musicians
Sep. 6, 2021—Vanderbilt researchers mined electronic health records to find medical diagnoses that are more or less prevalent among musicians, who are present in large numbers in “Music City.”
Using billing codes to count cancers
Sep. 2, 2021—The billing codes in electronic health records are useful for counting skin cancers over time — an important metric for cancer risk assessment and prevention.