Clinical Features and Physiological Signals Fusion Network for Mechanical Circulatory Support Need Prediction in Pediatric Cardiac ICU
Keywords: Convolutional Neural Networks, Deep Learning, Ensemble learning, Hemodynamics, Blood pressure, Heart Failure, Intensive Care Unit, Time series analysis
TL;DR: We present a novel multi-modal hemodynamic response deep learning system to predict Mechanical Circulatory Support need in advanced pediatric heart failure patients admitted to the ICU.
Abstract: We link the hemodynamic response to inotropic agents with outcomes related to Mechanical Circulatory Support (MCS) by analyzing physiological time series and clinical features using a Machine Learning/Deep Learning ensemble approach for multi-modal waveforms in
the pediatric cardiac intensive care setting of a quaternary-care hospital. Unlike existing studies that typically process a single feature type or focus on short-term diagnoses from physiological signals, our novel system processes minute-by-minute multi-sensor data to identify the need for MCS in patients admitted with Acute Decompensated Heart Failure. The data used includes tabular clinical features, time series from Intensive Care Unit monitors, and raw waveforms from electrocardiogram and arterial blood pressure signals. Our predictions facilitate early identification of high-risk patients after just two days of admission, with classification and feature importance results confirming the predictive ability of the early hemodynamic response to inotropic
agent administration, achieving an AUC of 0.88 in the prediction classification task. This is particularly significant in cases where clinical decisions are not straightforward, such as those in the cohort for this study.
Track: 4. AI-based clinical decision support systems
Registration Id: 5VNR6W6KLSN
Submission Number: 182
Loading