EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyseOpen Access

AI-Based Sepsis Prediction in Hospitalized Adults: Systematic Review, Subgroup Meta-Analysis, and Contextual Analysis of Clinical Burden

KI-basierte Sepsisvorhersage bei hospitalisierten Erwachsenen: systematische Übersicht, Subgruppen-Metaanalyse und kontextuelle Analyse der klinischen Belastung

Gyeong Min Lee, Joo-Yun Won, Eun Young Cho, Ji-Hyun Kim, Kwang Joon Kim, Yu Seung Lee, Hyun Jun Lee, Jae Hyun Kim

Journal of Medical Internet Research · 17.09.2026 · 28 · e95665-e95665

DOI: 10.2196/95665 ↗

Auf einen Blick

34 Studien zu ML- und DL-Modellen zeigten eine gute Diskrimination für die Sepsisvorhersage. Die Aussagekraft bleibt wegen Heterogenität, überlappender Datensätze und begrenzter prospektiver Evidenz unsicher.

Fragestellung

Wie gut sagen ML- und DL-Modelle Sepsis bei hospitalisierten Erwachsenen voraus, und wie hoch ist die sepsisbezogene Krankenhausbelastung in koreanischen Abrechnungsdaten?

Methode

Systematische Übersicht und Metaanalyse von ML- und DL-Modellen bei hospitalisierten Erwachsenen; Random-effects-Metaanalyse mit Hartung-Knapp-Sidik-Jonkman; zusätzlich Analyse koreanischer Krankenhaus-Abrechnungsdaten.

Ergebnisse

34 Studien. Gepoolte AUROC 0,913 (95 %-KI 0,887–0,933; 95 %-Prädiktionsintervall 0,660–0,983). Subgruppen: binnen 4 h 0,894 (0,829–0,936), >4 h 0,926 (0,897–0,948), unklar 0,858 (0,581–0,964).

Einschränkungen

Viele Studien waren retrospektiv; öffentliche Datensätze wurden wiederverwendet; 34 Berichte entsprachen nicht 34 unabhängigen Populationen.

Schlussfolgerung der Autor:innen

ML- und DL-Sepsismodelle zeigten in einzelnen Studiengattungen oft gute Diskrimination, die Performance in neuen klinischen Populationen bleibt aber unsicher. Subgruppenanalysen waren informativer als ein einzelner gepoolter AUROC.

Kernaussagen

  • Gepoolte AUROC: 0,913 (95 %-KI 0,887–0,933)
  • Subgruppen nach Vorhersagefenster zeigten unterschiedliche AUROCs
  • Koreanische Abrechnungsdaten zeigten längere Liegedauer und höhere Kosten

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Systematische Übersicht in der Zeitschrift Journal of Medical Internet Research, online erschienen am 17.09.2026. Verfasst von Gyeong Min Lee und 7 weiteren Autor:innen. Beteiligte Einrichtung: Research Institute for Healthcare Policy, Dankook University, Cheonan, Chungcheongnam-do, Republic of Korea. Hauptthemen laut MEDLINE: Sepsis, Hospitalization, Machine Learning, Artificial Intelligence. Die Arbeit nennt 85 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Machine learning (ML) and deep learning (DL) models have been developed for earlier recognition in hospitalized patients, but reported performance varies across datasets, prediction windows, care settings, and validation designs. Interpretation of a single pooled discrimination estimate is therefore uncertain, particularly because public datasets are often reused, and most evidence is retrospective.

Objective

This study aimed to synthesize the performance of ML- and DL-based sepsis prediction models in hospitalized adults, emphasizing prediction windows and validation maturity, and to separately describe sepsis-related health care burden using Korean national inpatient claims data.

Methods

We conducted a systematic review and meta-analysis of ML and DL models for sepsis prediction in hospitalized adults. The protocol was registered in PROSPERO. Random-effects meta-analysis used the Hartung-Knapp-Sidik-Jonkman approach, with 95% prediction intervals where sufficient studies were available. Interpretation focused on prediction-window subgroups and validation-maturity tiers rather than a single pooled area under the receiver operating characteristic curve (AUROC). Potential nonindependence from repeated use of Medical Information Mart for Intensive Care (MIMIC) and PhysioNet cohorts was examined through dataset-overlap assessment and sensitivity analysis. Separately, Korean Health Insurance Review and Assessment Service National Inpatient Sample data were used to describe length of stay, medical costs, and surgery counts by sepsis-related episode timing; this analysis did not validate an AI model.

Results

In total, 34 studies were included, most of which were retrospective model-development or validation studies. Several reused MIMIC- or PhysioNet-derived cohorts, so the 34 reports did not represent 34 fully independent patient populations. The pooled AUROC was 0.913 (95% CI 0.887‐0.933), with a 95% prediction interval of 0.660‐0.983. In exploratory subgroup analyses, pooled AUROCs were 0.894 (95% CI 0.829‐0.936) for models predicting sepsis within 4 hours, 0.926 (95% CI 0.897‐0.948) for models predicting more than 4 hours before onset, and 0.858 (95% CI 0.581‐0.964) for unclear or unreported prediction windows. Overlapping prediction intervals indicated substantial uncertainty and did not establish superiority of any prediction horizon. Prospective, randomized, and implementation studies were interpreted separately. In the Korean claims analysis, sepsis-related episode groups showed longer observed hospital stays and higher unadjusted medical costs than general inpatient episodes.

Conclusions

Reported ML and DL sepsis prediction models frequently demonstrated good discrimination within individual study settings, but performance in new clinical populations remains uncertain because of extreme heterogeneity, overlapping public data, inconsistent reporting, and limited prospective evaluation. Prediction-window and validation-maturity analyses were more clinically informative than a single pooled AUROC, although exploratory. The Korean claims analysis provided separate contextual evidence of disease burden and should not be interpreted as AI model validation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SepsisHospitalizationMachine LearningArtificial IntelligenceHumansAdultRepublic of KoreaPredictive Learning Models

Stichwörter der Autor:innen

AIclaims dataclinical burdendeep learningmachine learningmeta-analysisprediction modelsepsissystematic review

Autor:innen und Institutionen

  • Research Institute for Healthcare Policy, Dankook University, Cheonan, Chungcheongnam-do, Republic of Korea.
  • AITRICS Corp, Seoul, Republic of Korea.
  • Department of Health Administration, College of Public Health Sciences, Dankook University, Dongnam-gu, 119, Dandae-ro, Cheonan-si, Chungcheongnam-do, 31116, Republic of Korea, 82 10-8438-8353, 82 41-559-7934.

Zitieren

APA

Lee, G. M., Won, J. Y., Cho, E. Y., Kim, J. H., Kim, K. J., Lee, Y. S., Lee, H. J., & Kim, J. H. (2026). AI-Based Sepsis Prediction in Hospitalized Adults: Systematic Review, Subgroup Meta-Analysis, and Contextual Analysis of Clinical Burden. Journal of Medical Internet Research, 28, e95665-e95665. https://doi.org/10.2196/95665

Vancouver

Lee GM, Won JY, Cho EY, Kim JH, Kim KJ, Lee YS, et al. AI-Based Sepsis Prediction in Hospitalized Adults: Systematic Review, Subgroup Meta-Analysis, and Contextual Analysis of Clinical Burden. Journal of Medical Internet Research. 2026;28:e95665-e95665. doi:10.2196/95665

BibTeX
@article{Lee2026,
  author = {Lee, Gyeong Min and Won, Joo-Yun and Cho, Eun Young and Kim, Ji-Hyun and Kim, Kwang Joon and Lee, Yu Seung and Lee, Hyun Jun and Kim, Jae Hyun},
  title = {AI-Based Sepsis Prediction in Hospitalized Adults: Systematic Review, Subgroup Meta-Analysis, and Contextual Analysis of Clinical Burden},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e95665--e95665},
  doi = {10.2196/95665}
}
Kostenlos starten →