The DOI matches its Crossref record.
AI-based solutions for predicting sepsis in ICUs
Abstract
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Machine learning and deep learning models can leverage large ICU datasets, including MIMIC-IV, to detect patterns and predict sepsis onset more accurately than traditional scoring methods.
“Machine learning (ML) and deep learning (DL) models can leverage large ICU datasets, including Medical Information Mart for Intensive Care, Version IV (MIMIC-IV) [10], to detect patterns and predict sepsis onset more accurately than traditional scoring methods [11, 12].”
From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [11]
Explainable AI addresses the need for interpretable predictive systems by providing human-interpretable outputs and highlighting clinically important features that drive model decisions.
“Explainable AI addresses this need by providing human-interpretable outputs and highlighting clinically important features that drive model decisions [4–6, 11–13].”
From Explainable AI for critical care: a systematic review of interpretable models for sepsis and ICU mortality prediction (2026) · cites this paper as [11]
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 5
- 10.1109/e-Science58273.2023.10254863 · DOI
- 10.1109/JBHI.2020.2991043 · DOI · Paper page
- Gupta, An Extensive Data Processing Pipeline for MIMIC-IV, 193, 311
- Johnson, 2021, MIMIC-IV (version 1.0)
- 10.1109/EHB55594.2022.9991445 · DOI
Cited by
Sorted by citations
Athukorala, V. S., & Ilmini, W. M. K. S. (2026) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-026-03344-0 · Cited by 10
“While machine learning (ML) and deep learning (DL) models have shown significant potential in predicting sepsis onset and patient outcomes [11–17], many of these systems function as “black boxes,” generating predictions without providing explanations for their reasoning.”
Influential
Metadata
- Authors
- Stylianides, C., Alexandropoulou, C.-A., Sulaiman, W., Panagiotopoulos, I., Kleanthous, S., Dimitrakopoulos, G., Constantinou, I., Vassiliou, S., Garcia, F., Politi, E., Ntalaperas, D., Papageorgiou, X., Ioannides, N., Palazis, L., Pattichis, C. S., & Panayides, A. S.
- Affiliations
- CYENS CoE,Cyprus
- Harokopio University of Athens (GR)
- University of Cyprus (CY)
- 3aHealth,Research & Development Department,Cyprus
- UBITECH Limited,Cyprus
- State Health Services Organization,Cyprus
- ORCID
- Venue
- 2023 IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, Medicine and Biology
- Publisher
- IEEE
- Published
- 2023-12-07
- Pages
- 163-164
- OpenAlex
- W4391306720
- Cited by
- 5
- References
- 0
- Citations by year
- 2026: 3 · 2025: 1 · 2024: 1
- FWCI
- 0.88
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, Medicine and Biology (publishedVersion)
- Kypseli (submittedVersion)
- Funders
- Research and Innovation Foundation
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Sepsis Diagnosis and Treatment
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- sepsis prediction, intensive care unit, electronic health records, MIMIC dataset, ICU length of stay, explainable AI, ethical AI, interoperability, clinical decision support, personalized treatment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
