Using physiological data such as heart rate variability from seriously ill COVID-19 patients, Dr. Buchman is working with Rishikesan Kamaleswaran, PhD, Ofer Sadan, MD, Prem Kandiah, MD, and Jim Blum, MD, to harness the power of artificial intelligence to predict poor outcomes for ICU patients with the disease. The researchers have drawn information from a variety of sources, including patient monitors at ICUs across the Emory hospital system, to identify early signs of deterioration.
Data was generated for 25 critically ill COVID-19 patients and then the forecasts were validated among 150 patients. This presents opportunities for novel, life-saving interventions and can further the understanding of high-risk biomarkers. The goal is to create an algorithm that can then be used in the ER — and potentially in homes — to spot early signs of patients in distress.
Following strict privacy safeguards, Dr. Patzer and Justin Schrager, MD, are using the symptom checker app launched at Emory to create a nationwide cohort of 60,000 people who reported COVID-19 symptoms. They will then use this cohort to determine whether the symptom tracker reduced healthcare utilization, to clarify transmission patterns and explore how these patterns relate to outcomes and health care resources, and to create a repository of data for Emory researchers to use for future grant submissions.