Carter Cornelius
Pronouns: he/him
Research Mentor(s): Sardar Ansari
Research Mentor School/College/Department: Weil Institute for Critical Care Research and Innovation / Medicine
Program:
Authors:
Session: Session 2: 10:00 am – 10:50 am
Poster: 36
Abstract
In many cases, the diagnosis of a patient’s symptoms is invasive, may require several tests, and can take several days, if not weeks to correctly diagnose acute conditions. This study is part of a larger study that aims to find alternative ways to improve the accuracy in the prediction of various diseases by integrating features derived from sweat gas chromatography (GC) data and Electrocardiogram (ECG) data. ECG signals measure the electrical activity of the heart, and through ECGs, researchers and analysts can determine the Heart Rate Variability (HRV). HRV refers to the variation in the intervals between heart beats and is influenced by the parasympathetic and sympathetic nervous system. HRV features include: the measurement of mean of the RR intervals (the time between consecutive heartbeats) and RR50 (number of pairs of successive RR intervals that differ by more than 50 ms). Deviations in these features can indicate a change in the cardiovascular health or stress and mental health of a patient. In this specific study, a collection of patient ECGs will be annotated by identifying heartbeats, ectopic beats, and noisy portions of the signal. This is an important preprocessing step to properly identify HRV features. The HRV features from ECG data will be combined with data from patient sweat gas chromatography (GC) and other vitals to predict various diseases and to improve the accuracy of a diagnosis.
