CoChat

AI-Driven Innovations for Early Sepsis Detection by Combining Predictive Accuracy With Blood Count Analysis in an Emergency Setting: Retrospective Study

Lin, Tai-Han, Chung, Hsing-Yi, Jian, Ming-Jr, Chang, Chih-Kai, Lin, Hung-Hsin, Yen, Chiung-Tzu, Tang, Sheng-Hui, Pan, Pin-Ching, Perng, Cherng-Lih, Chang, Feng-Yee, Chen, Chien-Wen, Shang, Hung-Sheng · 2025 · Journal of Medical Internet Research
Cited by 29

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2196/56155

Cites

7 of 7 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 7 references

Research works printed but not linked: 15

  1. 10.1016/S0140-6736(19)32989-7 · DOI · Paper page
  2. 10.1001/jama.2016.0287 · DOI · Paper page
  3. 10.2196/31083 · DOI
  4. 10.2196/43486 · DOI
  5. 10.1016/j.ijid.2021.11.015 · DOI
  6. 10.1177/2050312119835043 · DOI · Paper page
  7. 10.1007/s10096-019-03529-8 · DOI
  8. 10.1097/01.ccm.0000217961.75225.e9 · DOI · Paper page
  9. 10.1007/s40121-021-00459-x · DOI
  10. 10.1109/JPROC.2015.2501978 · DOI · Paper page
  11. 10.1016/j.pmedr.2024.102841 · DOI
  12. 10.1016/j.ijid.2017.03.005 · DOI
  13. 10.1016/j.artmed.2020.101820 · DOI · Paper page
  14. 10.1016/S2214-109X(22)00043-2 · DOI · Paper page
  15. 10.1016/S1473-3099(09)70135-5 · DOI

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.
Venue
Journal of Medical Internet Research
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.