EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Analysis and implications of validation results for a clinical data-based early warning model for geriatric sepsis

Xuejie Ma, Xinyi Li, Xiaoqiang He, Xin Zou, Xiaowei Ma

Frontiers in Public Health · 15.07.2026 · 14

DOI: 10.3389/fpubh.2026.1833804 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Frontiers in Public Health, online erschienen am 15.07.2026. Verfasst von Xuejie Ma und 4 weiteren Autor:innen. Beteiligte Einrichtung: Intensive Care Unit, Cardiocerebral Vascular Disease Hospital, General Hospital of Ningxia Medical University, Yinchuan, Ningxia, China. Hauptthemen laut MEDLINE: Sepsis, Machine Learning, Early Warning Score, Geriatric Assessment. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Sepsis poses a serious threat to the health and lives of older adults and is difficult to identify accurately in its early stages. To address this issue, our team previously developed an early warning model for sepsis in older adults based on machine learning algorithms and conducted preliminary validation. To further validate the model’s performance for clinical use, we collected additional clinical data. In the process, we gained some insights.

Methods

We collected clinical data from patients aged 60 years or older admitted to the Emergency Department and Intensive Care Unit of the General Hospital of Ningxia Medical University. We conducted a secondary evaluation of the predictive and generalization capabilities of the geriatric sepsis sepsis early warning model using multiple metrics (including AUC, accuracy, sensitivity, specificity, precision, and F1 score), and analyzed the validation results.

Results

Eight hundred fourteen patients were included in the study, comprising 106 positive patients (sepsis patients) and 708 negative patients (non-sepsis patients). After validation, the model’s accuracy was 0.801, sensitivity was 0.764, and AUROC was 0.865.

Conclusion

In the study, although the AUROC of the further validation showed a slight decrease, the early warning model still performed well. The warning model is indeed helpful in identifying geriatric patients patients with sepsis earlier. The performance deviation observed during the validation phase may stem from multiple factors. Overall, machine learning models remain in a stage requiring continuous refinement and development. They are better suited as auxiliary tools in the medical field, necessitating long-term validation and adjustment rather than operating entirely independently.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SepsisMachine LearningEarly Warning ScoreGeriatric AssessmentHumansAgedMaleFemaleAged, 80 and overMiddle AgedIntensive Care UnitsEmergency Service, HospitalSensitivity and SpecificityReproducibility of ResultsPredictive Learning ModelsChina

Stichwörter der Autor:innen

artificial intelligence (AI)machine learning (ML)modelolder adultssepsisvalidation

Autor:innen und Institutionen

  • Intensive Care Unit, Cardiocerebral Vascular Disease Hospital, General Hospital of Ningxia Medical University, Yinchuan, Ningxia, China.
  • First Clinical College of Ningxia Medical University, Yinchuan, Ningxia, China.

Zitieren

APA

Ma, X., Li, X., He, X., Zou, X., & Ma, X. (2026). Analysis and implications of validation results for a clinical data-based early warning model for geriatric sepsis. Frontiers in Public Health, 14. https://doi.org/10.3389/fpubh.2026.1833804

Vancouver

Ma X, Li X, He X, Zou X, Ma X. Analysis and implications of validation results for a clinical data-based early warning model for geriatric sepsis. Frontiers in Public Health. 2026;14. doi:10.3389/fpubh.2026.1833804

BibTeX
@article{Ma2026,
  author = {Ma, Xuejie and Li, Xinyi and He, Xiaoqiang and Zou, Xin and Ma, Xiaowei},
  title = {Analysis and implications of validation results for a clinical data-based early warning model for geriatric sepsis},
  journal = {Frontiers in Public Health},
  year = {2026},
  volume = {14},
  doi = {10.3389/fpubh.2026.1833804}
}
Kostenlos starten →