External validation of a machine learning model for classifying hospitalization outcomes in Asian elephants across three elephant hospitals in Thailand
Externe Validierung eines Machine-Learning-Modells zur Klassifikation von Hospitalisierungsoutcomes bei asiatischen Elefanten in drei Elefantenkrankenhäusern in Thailand
PLOS One · 11.11.2026 · 21 (11) · e0362469
DOI: 10.1371/journal.pone.0362469 ↗Auf einen Blick
Ein Random-Forest-Modell wurde an 237 Hospitalisierungsereignissen von 215 asiatischen Elefanten validiert. Die Gesamtgenauigkeit lag bei 0,793 und nur knapp über einem Mehrheitsklassen-Modell.
Fragestellung
Wie gut klassifiziert ein zuvor entwickeltes Random-Forest-Modell Hospitalisierungsoutcomes bei asiatischen Elefanten in drei Elefantenkrankenhäusern in Thailand?
Methode
Externe Validierung mit zeitlich getrennten 2025-Daten aus 3 Krankenhäusern; temporale Validierung am Entwicklungszentrum und institutionelle Validierung an 2 weiteren Kliniken.
Ergebnisse
Die Validierung umfasste 237 Hospitalisierungsereignisse von 215 Elefanten. Gesamtgenauigkeit 0,793; macro-averaged balanced accuracy 0,732; AUC 0,854; multiclass log loss 0,617.
Einschränkungen
Wenige Todesfälle führten zu erheblicher Unsicherheit bei Mortalitäts- und Kalibrierungsmaßen.
Schlussfolgerung der Autor:innen
Das Modell behielt diskriminative Information, zeigte aber nur einen geringen Vorteil gegenüber der Mehrheitsklasse; die schwächere Leistung für Todesfälle und die Abhängigkeit von Aufenthaltsdauer erfordern Vorsicht.
Kernaussagen
- 237 Hospitalisierungsereignisse von 215 Elefanten
- Gesamtgenauigkeit 0,793; AUC 0,854
- Schwächere Klassifikation für Todesfälle; Vorsicht bei der Anwendung
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Validierungsstudie in der Zeitschrift PLOS One, online erschienen am 11.11.2026. Verfasst von Worapong Kosaruk und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Veterinary Medicine, Chiang Mai University, Chiang Mai, Thailand. Hauptthemen laut MEDLINE: Elephants, Machine Learning, Hospitalization, Hospitals, Animal. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chiang Mai University.
Abstract (Originalsprache)
Classification of hospitalization outcomes in wildlife hospitals may support clinical assessment and resource planning, but model performance can vary across institutions with different case profiles and care practices. This study evaluated a previously developed random forest model for classifying hospitalization outcomes in Asian elephants using temporally distinct 2025 data from three elephant hospitals in Thailand. The validation comprised temporal validation at the original development center and institutional validation at two additional hospitals. Because length of stay was included as a predictor, the model was evaluated as a hospitalization-course classification model rather than as an admission-time prognostic tool. The final validation cohort comprised 237 hospitalization episodes contributed by 215 elephants, including 17 deceased, 36 ongoing, and 184 recovered episodes. Overall accuracy was 0.793, compared with 0.776 for a recovered-only majority-class classifier. Macro-averaged balanced accuracy was 0.732, the prevalence-weighted one-vs-rest area under the receiver operating characteristic curve (AUC) was 0.854, and multiclass log loss was 0.617. Classification performance was stronger for ongoing and recovered episodes than for deceased episodes. The limited number of deceased episodes resulted in substantial uncertainty around mortality-focused performance and calibration estimates. Calibration patterns differed across outcome classes, with an overall multiclass Brier score of 0.323. In the binary deceased-versus-recovered sensitivity analysis, the AUC was 0.726 (95% confidence interval, 0.585–0.839), indicating moderate but imprecise discrimination. Overall, the model retained discriminatory information across the validation cohort, but its modest improvement over the majority-class benchmark, weaker deceased-class performance, and reliance on hospitalization-duration information warrant cautious interpretation. Further prospective evaluation is needed before routine clinical application.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Faculty of Veterinary Medicine, Chiang Mai University, Chiang Mai, Thailand.
- Elephant, Wildlife and Companion Animals Research Group, Chiang Mai University, Chiang Mai, Thailand.
- National Elephant Institute, Elephant Hospital, Thai Elephant Conservation Center, Forest Industry Organization, Ministry of Natural Resources and Environment, Lampang, Thailand.
- National Institute of Elephant Research and Health Service, Division of Animal Welfare and Veterinary Service, Department of Livestock Development, Surin, Thailand.
ORCID-Profile: Worapong Kosaruk
Förderung
- Chiang Mai University
Zitieren
APA
Kosaruk, W., Ueangpaibool, P., Hirannithithamrong, N., Kaew-Ek, J., & Angkawanish, T. (2026). External validation of a machine learning model for classifying hospitalization outcomes in Asian elephants across three elephant hospitals in Thailand. PLOS One, 21(11), e0362469. https://doi.org/10.1371/journal.pone.0362469
Vancouver
Kosaruk W, Ueangpaibool P, Hirannithithamrong N, Kaew-Ek J, Angkawanish T. External validation of a machine learning model for classifying hospitalization outcomes in Asian elephants across three elephant hospitals in Thailand. PLOS One. 2026;21(11):e0362469. doi:10.1371/journal.pone.0362469
BibTeX
@article{Kosaruk2026,
author = {Kosaruk, Worapong and Ueangpaibool, Pichamon and Hirannithithamrong, Nawapa and Kaew-Ek, Janjeera and Angkawanish, Taweepoke},
title = {External validation of a machine learning model for classifying hospitalization outcomes in Asian elephants across three elephant hospitals in Thailand},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0362469},
doi = {10.1371/journal.pone.0362469}
}
EUVIMED