EUVIMEDEUVIMED entdecken
Crossref

Health Prediction Using Hybrid Deep Learning Models: A Transparent and Interpretable Approach

Garima Verma iD, Seema Yadav

The International Journal of Health Planning and Management · 2026-07 · 41 (4) · 640-657

DOI: 10.1002/hpm.70073 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Health Planning and Management, online erschienen am 08.04.2026. Verfasst von Garima Verma und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, DIT University, Dehradun, India. Hauptthemen laut MEDLINE: Deep Learning, Obesity. Die Arbeit nennt 44 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Obesity has become alarming globally, with mounting health emergencies related to a number of chronic conditions like cardiovascular disease, diabetes, and metabolic disorders. Despite growing global awareness, accurately categorising obesity remains challenging due to its multifactorial nature involving genetic, lifestyle, environmental, and psychological determinants. Traditional methods based on pristine Body Mass Index (BMI) fail to encapsulate the multifaceted biological and lifestyle variables responsible for weight gain, leading to misclassification and treatment unresponsiveness. To overcome the challenge of a precise obesity classification, this study proposes two hybrid Artificial Intelligence (AI) models—CNN + TabNet and Self‐Attention BiLSTM (SA‐BiLSTM) + TabNet—that conjointly employs deep characterisation learning and TabNet's sparse attention–mechanism feature selection. To ensure better comprehension, the proposed models use feature engineering, class‐balancing, and Explainable AI (XAI) tools, which include SHAP, LIME, and Integrated Gradients (IG). The performed experiments exhibit improved and better results over other conventional baselines. Viz. CNN + TabNet is 92% correct (recall 0.925, F1 0.917), while SA‐BiLSTM + TabNet is 94.1% correct (recall 0.93, F1 0.937). The novel approach of blending TabNet's dynamic sparse‐attention feature selection with CNN‐ and SA‐BiLSTM‐based deep characterisations enables the joint spatial‐temporal learning with interpretable and data‐efficient obesity prediction. Former hybrid approaches either combined generic deep networks (like CNN‐LSTM and DNN‐RF) or used TabNet on its own.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningObesityHumansPredictive Learning ModelsConvolutional Neural NetworksPrediction AlgorithmsLong Short Term MemoryClassification AlgorithmsArtificial Intelligence

Stichwörter der Autor:innen

SHAPdeep learningexplainable AIintegrated gradientsobesity classificationself‐attention LSTMtabnet

Autor:innen und Institutionen

  • School of Computing, DIT University, Dehradun, India.

ORCID-Profile: Garima Verma

Zitieren

APA

Verma, G., & Yadav, S. (2026). Health Prediction Using Hybrid Deep Learning Models: A Transparent and Interpretable Approach. The International Journal of Health Planning and Management, 41(4), 640-657. https://doi.org/10.1002/hpm.70073

Vancouver

Verma G, Yadav S. Health Prediction Using Hybrid Deep Learning Models: A Transparent and Interpretable Approach. The International Journal of Health Planning and Management. 2026;41(4):640-657. doi:10.1002/hpm.70073

BibTeX
@article{Verma2026,
  author = {Verma, Garima and Yadav, Seema},
  title = {Health Prediction Using Hybrid Deep Learning Models: A Transparent and Interpretable Approach},
  journal = {The International Journal of Health Planning and Management},
  year = {2026},
  volume = {41},
  number = {4},
  pages = {640--657},
  doi = {10.1002/hpm.70073}
}
Kostenlos starten →