EUVIMEDEUVIMED entdecken
Crossref

Tidal breathing flow‐volume loop for early asthma identification in young children: An uncertainty‐aware machine learning approach

Henglin Zeng, Deping Yu iD, Xiangdong He iD, Ke Tian, Hua Luo, Lina Chen, Hanmin Liu iD

Pediatric Allergy and Immunology · 2026-11 · 37 (11)

DOI: 10.1111/pai.70548 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Allergy and Immunology, online erschienen am 09.11.2026. Verfasst von Henglin Zeng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatric Pulmonology and Immunology, West China Clinical Medical College, West China Second University Hospital, Sichuan University, C…. Hauptthemen laut MEDLINE: Asthma, Machine Learning, Tidal Volume. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Noncommunicable Chronic Diseases-National Science and Technology Major Project, Science and Technology Projects of Xizang Autonomous Region, Medical Interdisciplinary Research Key Project of Sichuan University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Conventional tidal breathing parameters are often insensitive to mild early airway obstruction. In addition, existing artificial intelligence (AI) models may generate overconfident errors in clinically heterogeneous cases.

Methods

This retrospective study (2022–2025) included 1121 children aged 1–3 years from West China Second University Hospital, Sichuan University. Data from the Jinjiang campus were used for model development ( n = 805) and data from the Huaxi campus served as an independent spatial validation cohort ( n = 316). We extracted novel geometric morphological and derived functional features from TBFVL and used machine learning model to evaluate a conventional‐feature baseline model versus an enhanced model incorporating novel features. We further proposed and evaluated the Adaptive Conformal Three‐way Decision framework (ACT‐Decision) to separate high‐uncertainty cases from automatic decision‐making.

Results

The final feature set comprised 20 newly derived features, 8 conventional parameters and 1 demographic variable. In the Huaxi validation cohort, the enhanced model using combined features outperformed the baseline model using only conventional features, achieving an accuracy of 0.788 (95% CI: 0.741, 0.829), ROC‐AUC of 0.867 (95% CI: 0.827, 0.902) and F1‐score of 0.798 (95% CI: 0.744, 0.841). SHAP analysis confirmed contributions from both conventional and newly derived features. In the Huaxi test subset, ACT‐Decision automatically classified 74.78% of children with an accuracy of 0.849 (95% CI: 0.787, 0.896).

Conclusions

TBFVL‐derived features improved discrimination between children aged 1–3 years with clinically diagnosed asthma and healthy controls. ACT‐Decision framework enabled selective deferral of higher‐uncertainty predictions for clinician review. image

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AsthmaMachine LearningTidal VolumeHumansChild, PreschoolRetrospective StudiesInfantFemaleMaleUncertaintyROC CurveEarly DiagnosisChina

Stichwörter der Autor:innen

machine learningpediatric asthmatidal breathinguncertainty quantification

Autor:innen und Institutionen

  • Department of Pediatric Pulmonology and Immunology, West China Clinical Medical College, West China Second University Hospital, Sichuan University, Chengdu, China.
  • School of Mechanical Engineering, Sichuan University, Chengdu, China.
  • Department of Pediatric Pulmonology and Immunology, Frontiers Science Center for Disease-Related-Molecular Network, West China Second University Hospital, Sichuan University, Chengdu, China.
  • Department of Pediatric Pulmonology, West China Second University Hospital, Sichuan University, Chengdu, China.
  • Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, Chengdu, China.
  • NHC Key Laboratory of Chronobiology (Sichuan University), Chengdu, China.

ORCID-Profile: Deping Yu, Xiangdong He, Hanmin Liu

Förderung

  • Noncommunicable Chronic Diseases-National Science and Technology Major Project
  • Science and Technology Projects of Xizang Autonomous Region
  • Medical Interdisciplinary Research Key Project of Sichuan University
  • Transformation Foundation of Tianfu Jincheng Laboratory

Zitieren

APA

Zeng, H., Yu, D., He, X., Tian, K., Luo, H., Chen, L., & Liu, H. (2026). Tidal breathing flow‐volume loop for early asthma identification in young children: An uncertainty‐aware machine learning approach. Pediatric Allergy and Immunology, 37(11). https://doi.org/10.1111/pai.70548

Vancouver

Zeng H, Yu D, He X, Tian K, Luo H, Chen L, et al. Tidal breathing flow‐volume loop for early asthma identification in young children: An uncertainty‐aware machine learning approach. Pediatric Allergy and Immunology. 2026;37(11). doi:10.1111/pai.70548

BibTeX
@article{Zeng2026,
  author = {Zeng, Henglin and Yu, Deping and He, Xiangdong and Tian, Ke and Luo, Hua and Chen, Lina and Liu, Hanmin},
  title = {Tidal breathing flow‐volume loop for early asthma identification in young children: An uncertainty‐aware machine learning approach},
  journal = {Pediatric Allergy and Immunology},
  year = {2026},
  volume = {37},
  number = {11},
  doi = {10.1111/pai.70548}
}
Kostenlos starten →