Sleepless, Overheated, Sugar-charged and Broken-hearted: Predictive Models for Improving Performance and Assessing Risk
Predictive Models for Individualized Medicine
Jaques Reifman, PhD, Senior Research Scientist, DoD Biotechnology High-Performance Computing Software Applications Institute, Telemedicine and Advanced Technology Research Center, U.S. Army Medical Research and Materiel Command, Ft. Detrick, Maryland
The U.S. Army Medical Research and Materiel Command, Ft. Detrick, Maryland has developed a suite of bio-mathematical predictive models for on-line estimation of an individual’s physiological state. Dr. Reifman will outline the requirements for developing individual-specific, field-deployable models based on both first-principles and data-driven approaches. He will demonstrate models for:
(1) improving the management of cognitive performance impairment due to sleep loss,
(2) avoiding undesirable hypo- and hyperglycemic episodes for patients with type 1 and type 2 diabetes
(3) reducing the risk of heat illnesses by predicting body core temperature.
A Novel Non-invasive ECG-based Method for Predicting Adverse Cardiovascular Outcomes
Collin M. Stultz, MD, PhD, Principal Investigator, Research Laboratory of Electronics and W. M. Keck Associate Professor of Biomedical Engineering, MIT
An important goal of clinical cardiology is to accurately identify patients who are at high risk of adverse cardiovascular events. Such high risk individuals may benefit from aggressive interventions. Risk assessment methods utilizing non-invasive physiologic signals are of particular interest. We have developed a novel risk assessment metric, called morphologic variability (MV), which measures subtle beat-to-beat changes in the shape of ECG signals. Unlike other ECG-based metrics, morphologic variability uses information from the entire ECG signal and does not focus on any specific segment of the ECG. Our results suggest that MV adequately predicts mortality in patients who are at high risk of casualty 90 days after admission for an unstable coronary syndrome (e.g., heart attack). MV may be clinically effective in identifying high risk patients that would benefit from more intense monitoring and therapy.
CIMIT blog is a publication of the Center for Integration of Medicine and Innovative Technology (CIMIT)
Comments