Explainable artificial intelligence model to predict acute critical illness from electronic health records

Abstract

Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Early clinical prediction is typically based on manually calculated screening metrics that simply weigh these parameters, such as early warning scores (EWS). The predictive performance of EWSs yields a tradeoff between sensitivity and specificity that can lead to negative outcomes for the patient. Previous work on electronic health records (EHR) trained artificial intelligence (AI) systems offers promising results with high levels of predictive performance in relation to the early, real-time prediction of acute critical illness. However, without insight into the complex decisions by such system, clinical translation is hindered. Here, we present an explainable AI early warning score (xAI-EWS) system for early detection of acute critical illness. xAI-EWS potentiates clinical translation by accompanying a prediction with information on the EHR data explaining it.

Applying artificial intelligence in the microbiome for gastrointestinal diseases: A review

“…For example, the AI systems trained on EHRs exhibit substantial predictive performance in relation to real‐time early clinical prediction; however, their clinical translation is difficult because they provide less insight into systems' complex decisions. Recently, an xAI system provided an early prediction model to facilitate clinical translations, which can simultaneously use EHR data to explain model decisions 71 . On the other hand, in multicenter clinical trials, xAI could also support safe communication on different levels, including the study of basic mechanisms, clinical translation, privacy and the data sharing system, and the decisions made by collaborators and managers.…”

Machine Learning–Based Early Warning Systems for Clinical Deterioration: Systematic Scoping Review

“…Other explainability algorithms are model-agnostic, meaning they can be applied to any type of model, regardless of its mathematical basis [ 51 ]. In the study by Lauritsen et al [ 52 ], an explainable EWS was developed based on a temporal convolutional network, using a separate module for explanations. These methodologies are promising, but their application to health care, including to EWS, has been limited.…”

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

“…20(f) for one such explanation). In another work [106], the input time series is formed by EHRs sampled at a much lower rate, from which a DNN model can decide among a set of medical conditions. The medical condition can then be attributed to the different medical measurements.…”