Physiological markers of low-altitude exercise load for predicting acute mountain sickness: development of an interpretable machine learning model and research web calculator
Physiologische Marker der Belastung bei Training in niedriger Höhe zur Vorhersage der akuten Höhenkrankheit: Entwicklung eines interpretierbaren Machine-Learning-Modells und eines webbasierten Forschungsrechners
Frontiers in Public Health · 02.11.2026 · 14
DOI: 10.3389/fpubh.2026.1920845 ↗Auf einen Blick
Bei 171 gesunden Personen sagte ein fünfstelliger Modellansatz das Risiko für akute Höhenkrankheit anhand von Reaktionen auf Belastung in niedriger Höhe mit guter Trennschärfe voraus. In der externen Validierung blieb die Leistung ähnlich.
Fragestellung
Lassen sich physiologische Reaktionen auf körperliche Belastung in niedriger Höhe zur Vorhersage von akuter Höhenkrankheit nutzen?
Methode
Modellentwicklung mit nested cross-validation, LASSO-Variablenselektion und Auswahl des Algorithmus; Entwicklungskohorte und externe Validierungskohorte.
Ergebnisse
Entwicklungskohorte: AUC 0,866 (95 %-KI 0,791–0,929), AUPRC 0,842 (95 %-KI 0,748–0,932), Brier Score 0,148. Extern: AUC 0,834 (95 %-KI 0,723–0,929), AUPRC 0,867 (95 %-KI 0,758–0,946), Brier Score 0,152.
Einschränkungen
Das Modell benötigt weitere Entwicklung und Validierung in deutlich größeren Kohorten vor klinischem Einsatz.
Schlussfolgerung der Autor:innen
Die Befunde stützen einen Zusammenhang zwischen Belastungsreaktionen in niedriger Höhe und späterer akuter Höhenkrankheit.
Kernaussagen
- 5-Feature-Modell mit ΔSpO2, ΔCO, Sex, Rauch- und Trinkanamnese
- AUC 0,866 in der Entwicklung und 0,834 in der externen Validierung
- ΔSpO2 und ΔCO waren die einflussreichsten Prädiktoren
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Public Health, online erschienen am 02.11.2026. Verfasst von Fengbo Miao und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Information Engineering, Tiangong University, Tianjin, China. Hauptthemen laut MEDLINE: Altitude Sickness, Machine Learning, Altitude, Exercise. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Acute mountain sickness (AMS) poses a significant threat to individuals ascending to high-altitude regions, yet early identification of susceptible populations remains challenging. This study aimed to develop an interpretable machine learning model for estimating AMS risk from exercise-induced physiological responses measured at low altitude. A total of 171 healthy participants were included, with 111 participants (51 AMS events) comprising the development cohort and 60 participants (27 AMS events) forming an external validation cohort. Model development was repeated within a nested cross-validation framework, including LASSO feature selection and algorithm selection within the resampling process. The final locked five-feature model included changes in post-exercise pulse oxygen saturation (ΔSpO 2 ) and cardiac output (ΔCO), sex, smoking history, and drinking history, and combined logistic regression, support vector machine, and random forest by equal-weight soft voting. In the development cohort, pooled outer-fold predictions yielded an AUC of 0.866 (95% CI, 0.791–0.929), an AUPRC of 0.842 (95% CI, 0.748–0.932), and a Brier score of 0.148. The calibration intercept was −0.033 (95% CI, −0.504 to 0.527), the calibration slope was 0.931 (95% CI, 0.664–1.351) and the positive net benefit range was 0.078–0.840. In the external validation cohort, the locked model yielded an AUC of 0.834 (95% CI, 0.723–0.929), an AUPRC of 0.867 (95% CI, 0.758–0.946), and a Brier score of 0.152; the calibration intercept was −0.103 (95% CI, −0.834 to 0.531), the calibration slope was 1.013 (95% CI, 0.655–1.666) and a positive net benefit range of 0.200–0.953. Post-hoc SHAP analysis identified ΔSpO 2 and ΔCO as the two most influential predictors. These findings support an association between low-altitude exercise responses and subsequent AMS. However, the prediction model requires further development and validation in substantially larger cohorts before clinical deployment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Electronics and Information Engineering, Tiangong University, Tianjin, China.
- Department of Quality Control, The General Hospital of Northern Theater Command, Shenyang, China.
- Department of Oral and Maxillofacial Surgery, The General Hospital of Northern Theater Command, Shenyang, China.
- Department of Cardiology, The 967th Hospital of Joint Logistics Support Force of Chinese PLA, Dalian, China.
- Department of Critical Care Medicine, The 967th Hospital of Joint Logistics Support Force of Chinese PLA, Dalian, China.
- Department of Emergency, The 967th Hospital of Joint Logistics Support Force of Chinese PLA, Dalian, China.
Zitieren
APA
Miao, F., Yuan, Y., Wang, S., Tao, C., Liu, Y., Mao, Q., Zhang, H., Li, N., Chen, R., & Sui, J. (2026). Physiological markers of low-altitude exercise load for predicting acute mountain sickness: development of an interpretable machine learning model and research web calculator. Frontiers in Public Health, 14. https://doi.org/10.3389/fpubh.2026.1920845
Vancouver
Miao F, Yuan Y, Wang S, Tao C, Liu Y, Mao Q, et al. Physiological markers of low-altitude exercise load for predicting acute mountain sickness: development of an interpretable machine learning model and research web calculator. Frontiers in Public Health. 2026;14. doi:10.3389/fpubh.2026.1920845
BibTeX
@article{Miao2026,
author = {Miao, Fengbo and Yuan, Yi and Wang, Shuai and Tao, Chengli and Liu, Yupeng and Mao, Qi and Zhang, Hualin and Li, Ning and Chen, Renzheng and Sui, Jianfu},
title = {Physiological markers of low-altitude exercise load for predicting acute mountain sickness: development of an interpretable machine learning model and research web calculator},
journal = {Frontiers in Public Health},
year = {2026},
volume = {14},
doi = {10.3389/fpubh.2026.1920845}
}
EUVIMED