AI-Driven Innovations for Early Sepsis Detection by Combining Predictive Accuracy With Blood Count Analysis in an Emergency Setting: Retrospective Study
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Background: Sepsis, a critical global health challenge, accounted for approximately 20% of worldwide deaths in 2017. Although the Sequential Organ Failure Assessment (SOFA) score standardizes the diagnosis of organ dysfunction, early sepsis detection remains challenging due to its insidious symptoms. Current diagnostic methods, including clinical assessments and laboratory tests, frequently lack the speed and specificity needed for timely intervention, particularly in vulnerable populations such as older adults, intensive care unit (ICU) patients, and those with compromised immune systems. While bacterial cultures remain vital, their time-consuming nature and susceptibility to false negatives limit their effectiveness. Even promising existing machine learning approaches are restricted by reliance on complex clinical factors that could delay results, underscoring the need for faster, simpler, and more reliable diagnostic strategies. Objective: This study introduces innovative machine learning models using complete blood count with differential (CBC+DIFF) data—a routine, minimally invasive test that assesses immune response through blood cell measurements, critical for sepsis identification. The primary objective was to implement this model within an artificial intelligence–clinical decision support system (AI-CDSS) to enhance early sepsis detection and management in critical care settings. Methods: This retrospective study at Tri-Service General Hospital (September to December 2023) analyzed 746 ICU patients with suspected pneumonia-induced sepsis (supported by radiographic evidence and a SOFA score increase of ≥2 points), alongside 746 stable outpatients as controls. Sepsis infection sources were confirmed through positive sputum, blood cultures, or FilmArray results. The dataset incorporated both basic hematological factors and advanced neutrophil characteristics (side scatter light intensity, cytoplasmic complexity, and neutrophil-to-lymphocyte ratio), with data from September to November used for training and data from December used for validation. Machine learning models, including light gradient boosting machine (LGBM), random forest classifier, and gradient boosting classifier, were developed using CBC+DIFF data and were assessed using metrics such as area under the curve, sensitivity, and specificity. The best-performing model was integrated into the AI-CDSS, with its implementation supported through workshops and training sessions. Results: Pathogen identification in ICU patients found 243 FilmArray-positive, 411 culture-positive, and 92 undetected cases, yielding a final dataset of 654 (43.8%) sepsis cases out of 1492 total cases. The machine learning models demonstrated high predictive accuracy, with LGBM achieving the highest area under the curve (0.90), followed by the random forest classifier (0.89) and gradient boosting classifier (0.88). The best-performing LGBM model was selected and integrated as the core of our AI-CDSS, which was built on a web interface to facilitate rapid sepsis risk assessment using CBC+DIFF data. Conclusions: This study demonstrates that by providing streamlined predictions using CBC+DIFF data without requiring extensive clinical parameters, the AI-CDSS can be seamlessly integrated into clinical workflows, enhancing rapid, accurate identification of sepsis and improving patient care and treatment timeliness.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
In the citing paper
“Intuitive SHAP visualisations also greatly assist clinicians in understanding the logic behind model predictions, thereby increasing their trust in decision support systems.21,43”
From Translational Potential and Explainability of Artificial Intelligence-Based Clinical Decision Support for Adults in Intensive Care: A Scoping Review (2026) · cites this paper as [43]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Fleischmann, C., Scherag, A., Adhikari, N. K. J., Hartog, C. S., Tsaganos, T., Schlattmann, P., Angus, D. C., & Reinhart, K. (2016) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.201504-0781oc · Cited by 3,548 · cited 1×
“The prevalence of sepsis, which is intensified by drug-resistant infections, highlights the need for more effective prevention and treatment methods [6] and rapid diagnostic strategies [7], particularly in optimizing their implementation in clinical settings [8].”
Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock 2021.
Evans, L., Rhodes, A., Alhazzani, W., Antonelli, M., Coopersmith, C. M., French, C., Machado, F. R., Mcintyre, L., Ostermann, M., Prescott, H. C., et al. (2021) · Critical Care Medicine · doi:10.1097/ccm.0000000000005337 · Cited by 2,935
Bauer, M., Gerlach, H., Vogelmann, T., Preissing, F., Stiefel, J., & Adam, D. (2020) · Critical Care · doi:10.1186/s13054-020-02950-2 · Cited by 867 · cited 2×
“The mortality rate for sepsis is alarmingly high at 32.2%, and it rises significantly to 38.5% for those who develop septic shock, as reported in a meta-analysis [4].”
InfluentialFleuren, L. M., Klausch, T. L. T., Zwager, C. L., Schoonmade, L. J., Guo, T., Roggeveen, L. F., Swart, E. L., Girbes, A. R. J., Thoral, P., Ercole, A., et al. (2020) · Intensive Care Medicine · doi:10.1007/s00134-019-05872-y · Cited by 755 · cited 4×
“The models’adoption is expected to enable early therapeutic intervention, thereby enhancing patient outcomes [15].”
InfluentialA targeted real-time early warning score (TREWScore) for septic shock.
Henry, K. E., Hager, D. N., Pronovost, P. J., & Saria, S. (2015) · Science Translational Medicine · doi:10.1126/scitranslmed.aab3719 · Cited by 598 · cited 3×
“Our sepsis prediction model based on CBC+DIFF data provides a streamlined and efficient approach compared to existing models that require numerous physiological and clinical parameters from laboratory profiles, electronic health records, vital signs, and monitoring devices [13,14,19].”
InfluentialMoor, M., Bennett, N., Plečko, D., Horn, M., Rieck, B., Meinshausen, N., Bühlmann, P., & Borgwardt, K. (2023) · eClinicalMedicine · doi:10.1016/j.eclinm.2023.102124 · Cited by 118
Aguirre, U., & Urrechaga, E. (2023) · Clinical Chemistry and Laboratory Medicine (CCLM) · doi:10.1515/cclm-2022-0713 · Cited by 17 · cited 1×
“Enhanced diagnostic accuracy can be achieved using new parameters that provide information on the morphological and functional characteristics of leukocytes, reflecting their activation and functional activity in response to infections [17].”
Research works printed but not linked: 15
- 10.1016/S0140-6736(19)32989-7 · DOI · Paper page
- 10.1001/jama.2016.0287 · DOI · Paper page
- 10.2196/31083 · DOI
- 10.2196/43486 · DOI
- 10.1016/j.ijid.2021.11.015 · DOI
- 10.1177/2050312119835043 · DOI · Paper page
- 10.1007/s10096-019-03529-8 · DOI
- 10.1097/01.ccm.0000217961.75225.e9 · DOI · Paper page
- 10.1007/s40121-021-00459-x · DOI
- 10.1109/JPROC.2015.2501978 · DOI · Paper page
- 10.1016/j.pmedr.2024.102841 · DOI
- 10.1016/j.ijid.2017.03.005 · DOI
- 10.1016/j.artmed.2020.101820 · DOI · Paper page
- 10.1016/S2214-109X(22)00043-2 · DOI · Paper page
- 10.1016/S1473-3099(09)70135-5 · DOI
Cited by
Ogut, E. (2025) · Clinics and Practice · doi:10.3390/clinpract15090169 · Cited by 107
Pranata, Y., Mirwanti, R., Bahtiar, Y. A., & Purwanti, H. (2026) · Journal of Multidisciplinary Healthcare · doi:10.2147/jmdh.s621469 · Cited by 1
Metadata
- Authors
- Lin, T.-H., Chung, H.-Y., Jian, M.-J., Chang, C.-K., Lin, H.-H., Yen, C.-T., Tang, S.-H., Pan, P.-C., Perng, C.-L., Chang, F.-Y., Chen, C.-W., & Shang, H.-S.
- ORCID
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2025-01-24
- Volume
- 27
- Pages
- e56155
- ISSN
- 1438-8871
- Cited by
- 29
- References
- 7
- Language
- en
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.