EUVIMEDEUVIMED entdecken
Open Access

Development of Machine Learning–Based Risk Prediction Models to Predict Rapid Weight Gain in Infants: Analysis of Seven Cohorts

Miaobing Zheng iD, Yuxin Zhang iD, Rachel A Laws iD, Peter Vuillermin iD, Jodie Dodd iD, Li Ming Wen iD, Louise A Baur iD, Rachael Taylor iD, Rebecca Byrne iD, Anne-Louise Ponsonby iD, Kylie D Hesketh iD

JMIR Public Health and Surveillance · 2025

DOI: 10.2196/69220 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Public Health and Surveillance, 2025. Verfasst von Miaobing Zheng und 10 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Physical Activity and Nutrition, School of Exercise and Nutrition Sciences, Deakin University, Geelong, Australia. Hauptthemen laut MEDLINE: Machine Learning, Weight Gain. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Rapid weight gain (RWG) during infancy, defined as an upward crossing of one centile line on a weight growth chart, is highly predictive of subsequent obesity risk. Identification of infant RWG could facilitate obesity risk assessment from infancy.

Objective

Leveraging machine learning (ML) algorithms, this study aimed to develop and validate risk prediction models to identify infant RWG by the age of 1 year.

Methods

Data from 7 Australian and New Zealand cohorts were pooled for risk model development and validation (n=5233). A total of 8 ML algorithms predicted infant RWG using routinely available prenatal and early postnatal factors, including maternal prepregnancy weight status, maternal smoking during pregnancy, gestational age, parity, infant sex, birth weight, any breastfeeding and timing of solids introduction at the age of 6 months. Pooled data were randomly split into a training dataset (70%) and a test dataset (30%) for model training and validation, respectively. Model consistency was evaluated using 5-fold cross-validation. Model predictive performance was evaluated by area under the receiver operating characteristic (ROC) curve (AUC), accuracy, precision, sensitivity, specificity, and Cohen κ.

Results

The average prevalence of infant RWG was 27%. In the training dataset, all ML algorithms showed acceptable to excellent discrimination with AUCs ranging from 0.75 to 0.86. Accuracy, which indicates the overall correctness of the model, ranged from 0.69 to 0.78. Precision, which measures the model’s ability to avoid false positives, ranged from 0.68 to 0.77. The spread of sensitivity, specificity, and Cohen κ of all models was 0.68‐0.80, 0.65‐0.78, and 0.38‐0.56, respectively. Of the 8 algorithms, the Gradient Boosting model showed the most favorable predictive accuracy. Validation of the Gradient Boosting model in the testing dataset exhibited excellent discrimination (AUC 0.3‐0.6) and good ability to make accurate predictions, particularly true positive cases (with accuracy and sensitivity>0.75), but modest performance for precision (0.57‐0.60) and Cohen κ (0.47‐0.52).

Conclusions

This study developed the first set of ML-based risk prediction models to identify infants’ risk of experiencing RWG by the age of 1 year with acceptable accuracy. The models could be feasibly integrated into routine child growth monitoring and may facilitate population-wide early obesity risk assessment in primary health care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningWeight GainHumansInfantFemaleMaleRisk AssessmentNew ZealandAustraliaCohort StudiesInfant, Newborn

Stichwörter der Autor:innen

childhood obesityinfantsmachine learningpooled analysisrapid weight gainrisk prediction

Autor:innen und Institutionen

  • Institute for Physical Activity and Nutrition, School of Exercise and Nutrition Sciences, Deakin University, Geelong, Australia.
  • School of Health Sciences, Faculty of Health & Medicine, UNSW Sydney, Wallace Wurth Building, Kensington, 2330, Australia, 61 0290659337.
  • Barwon Health, Geelong, Australia.
  • Discipline of Obstetrics and Gynaecology, The Robinson Research Institute, The University of Adelaide, Adelaide, Australia.
  • School of Public Health and Sydney Medical School, The University of Sydney, Sydney, Australia.
  • Department of Medicine, University of Otago, Dunedin, New Zealand.

ORCID-Profile: Miaobing Zheng, Yuxin Zhang, Rachel A Laws, Peter Vuillermin, Jodie Dodd, Li Ming Wen, Louise A Baur, Rachael Taylor, Rebecca Byrne, Anne-Louise Ponsonby, Kylie D Hesketh

Zitieren

APA

Zheng, M., Zhang, Y., Laws, R. A., Vuillermin, P., Dodd, J., Wen, L. M., Baur, L. A., Taylor, R., Byrne, R., Ponsonby, A. L., & Hesketh, K. D. (2025). Development of Machine Learning–Based Risk Prediction Models to Predict Rapid Weight Gain in Infants: Analysis of Seven Cohorts. JMIR Public Health and Surveillance. https://doi.org/10.2196/69220

Vancouver

Zheng M, Zhang Y, Laws RA, Vuillermin P, Dodd J, Wen LM, et al. Development of Machine Learning–Based Risk Prediction Models to Predict Rapid Weight Gain in Infants: Analysis of Seven Cohorts. JMIR Public Health and Surveillance. 2025. doi:10.2196/69220

BibTeX
@article{Zheng2025,
  author = {Zheng, Miaobing and Zhang, Yuxin and Laws, Rachel A and Vuillermin, Peter and Dodd, Jodie and Wen, Li Ming and Baur, Louise A and Taylor, Rachael and Byrne, Rebecca and Ponsonby, Anne-Louise and Hesketh, Kylie D},
  title = {Development of Machine Learning–Based Risk Prediction Models to Predict Rapid Weight Gain in Infants: Analysis of Seven Cohorts},
  journal = {JMIR Public Health and Surveillance},
  year = {2025},
  doi = {10.2196/69220}
}
Kostenlos starten →