Developing an Artificial Intelligence-Based Representation of a Virtual Patient Model for Real-Time Diagnosis of Acute Respiratory Distress Syndrome

Abstract

Acute Respiratory Distress Syndrome (ARDS) is a condition that endangers the lives of many Intensive Care Unit patients through gradual reduction of lung function. Due to its heterogeneity, this condition has been difficult to diagnose and treat, although it has been the subject of continuous research, leading to the development of several tools for modeling disease progression on the one hand, and guidelines for diagnosis on the other, mainly the “Berlin Definition”. This paper describes the development of a deep learning-based surrogate model of one such tool for modeling ARDS onset in a virtual patient: the Nottingham Physiology Simulator. The model-development process takes advantage of current machine learning and data-analysis techniques, as well as efficient hyperparameter-tuning methods, within a high-performance computing-enabled data science platform. The lightweight models developed through this process present comparable accuracy to the original simulator (per-parameter R2 > 0.90). The experimental process described herein serves as a proof of concept for the rapid development and dissemination of specialised diagnosis support systems based on pre-existing generalised mechanistic models, making use of supercomputing infrastructure for the development and testing processes and supported by open-source software for streamlined implementation in clinical routines.

A systematic review of machine learning models for management, prediction and classification of ARDS

“…However, collecting patient data is meet with many difficulties in term of ethic and administrative control such as identifiability or patient consent. An interesting way to avoid this is by using virtual/simulated patients pioneered by Barakat [ 72 ]. However, whilst this method provided arbitrarily large, cleaned and complete database, the realistic of the virtual patients must be thoroughly tested and justified before being used for ML model development.…”

“…The largest data collection is from the National Trauma Data Bank from the US used by Pearl, et al, [26] with 1,438,035 patients. Barakat, et al, [72] used 1 million simulated patients based on MIMIC 3 database for their study. The simulation method was developed by Sharafutdinov [77].…”