AI-based solutions for predicting sepsis in ICUs

Le résumé fourni par la source

Artificial Intelligence (AI) advances in healthcare underpin timely and informed interventions that can elevate the quality of care for the benefit of the citizen. This can be especially beneficial for Intensive Care Unit (ICU) patients. The goal of this study is to develop an interoperable electronic health record (EHR) system, integrating reproducible AI-based algorithms for ICU services, linked with medical data and healthcare status visualizations, that will allow healthcare professionals to proceed to more informed diagnosis and targeted, personalized treatments. From a data science perspective, AI-based algorithms will first rely on the use of retrospective data via the openly available MIMIC dataset, investigating primarily the early prediction of Sepsis, and secondarily the length of ICU stay and rehospitalization probability. Emphasis will be given to explainability and ethical AI development. Within the context of the “HospAItal” project, real-life pilots will take place at the Nicosia General Hospital (NGH) of Cyprus, assessing the clinical impact of the proposed system while using prospective data to retrain and advance the precision of the developed algorithms.Clinical Relevance: The proposed AI-based system targets timely and informed healthcare interventions for ICU patients at risk of Sepsis, aspiring to increase the quality of care while contributing to more efficient ICU expenditures management.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.