Generating synthetic data with a mechanism-based Critical Illness Digital Twin: Demonstration for Post Traumatic Acute Respiratory Distress Syndrome

Abstract

Machine learning (ML) and Artificial Intelligence (AI) approaches are increasingly applied to predicting the development of sepsis and multiple organ failure. While there has been success in demonstrating the clinical utility of such systems in terms of affecting various outcomes, there are fundamental challenges to the ML/AI approach in terms of improving the actual predictive performance and future robustness of such systems. Given that one of the primary proposed avenues for improving algorithmic performance is the addition of molecular/biomarker/genetic features to the data used to train these systems, the overall sparsity of such available data suggests the need to generate synthetic data to aid in training, as has been the case in numerous other ML/AI tasks, such as image recognition/generation and text analysis/generation. We propose the need to generate synthetic molecular/mediator time series data coincides with the advent of the concept of medical digital twins, specifically related to interpretations of medical digital twins that hew closely to the original description and use of industrial digital twins, which involve simulating multiple individual twins from a common computational model specification. Herein we present an example of generating synthetic time series data of a panel of pro- and anti-inflammatory cytokines using the Critical Illness Digital Twin (CIDT) regarding the development of post-traumatic acute respiratory distress syndrome.