Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 8, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Obesity prediction using an explainable deep learning framework based on LSTM-LIME with integrated visualization.

Norah S Alsulami^1,2, Muhammad Sher Ramzan³, Bander A Alzahrani³

¹Department of Information Systems, Faculty of Computer Science and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia. nalsulami0391@stu.kau.edu.sa.

Scientific Reports

|December 21, 2025

Summary

Related Concept Videos

Obesity

Obesity

The Body Mass Index (BMI) is a numerical value derived from a person's weight and height, used to categorize individuals into weight ranges. It is calculated using the formula: weight in kilograms divided by height in meters squared. Obesity is a health condition characterized by excessive accumulation of adipose tissue that poses health risks, often diagnosed with a BMI ≥ 30. This excess fat storage occurs when surplus dietary calories are converted into triglycerides and stored in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

XMedFuse: An Explainable Multimodal Feature Fusion Framework for Healthcare Diagnostics.

IEEE journal of biomedical and health informatics·2026

Same author

Knowledge of hypoglycemia and awareness of diabetes complications among diabetic patients: A cross-sectional study.

Saudi medical journal·2025

Same author

Knowledge, attitude, and practice of breastfeeding among mothers attending King Abdulaziz University Hospital, Jeddah, Saudi Arabia.

Journal of family medicine and primary care·2025

Same author

Translation and validation of the Arabic version of the Chronic Illness Anticipated Stigma Scale in Saudi patients with multiple sclerosis.

Frontiers in psychiatry·2025

Same author

Novel graph-based machine-learning technique for viral infectious diseases: application to influenza and hepatitis diseases.

Annals of medicine·2024

Same author

Effect of Ramadan Fasting on Blood Glucose Level in Pregnant Women with Gestational and Type 2 Diabetes.

Diabetes, metabolic syndrome and obesity : targets and therapy·2023

Same journal

Integrated multi-assessment and structural performance index framework for stacking-sequence optimisation of natural fibre reinforced laminates.

Scientific reports·2026

Same journal

SuperiorGAT: graph attention networks for sparse LiDAR point cloud reconstruction in autonomous systems.

Scientific reports·2026

Same journal

The effect of stretching the pectoralis major, sternocleidomastoid, and iliopsoas muscles on 800 m swimming performance in master swimmers.

Scientific reports·2026

Same journal

ISNR-PQC: isometry noise resilience post quantum cryptography primitive.

Scientific reports·2026

Same journal

Identification of high-yielding and stable genotypes of barley in the cold climate of Iran using AMMI and GGE biplot models.

Scientific reports·2026

Same journal

Bayesian negative binomial modelling of spatial and temporal patterns of road traffic deaths in Ghana.

Scientific reports·2026

See all related articles

This summary is machine-generated.

This study developed an explainable deep learning model for obesity prediction using Saudi data. The Bidirectional Long Short-Term Memory (Bi-LSTM) model achieved 96% accuracy, offering interpretable insights into obesity risk factors.

Area of Science:

Health Informatics
Artificial Intelligence in Medicine
Public Health

Background:

Obesity presents a significant global health challenge, necessitating advanced risk assessment tools.
Accurate and interpretable models are crucial for effective early detection and prevention of obesity.
Existing models often lack cultural specificity and transparency in factor identification.

Purpose of the Study:

To introduce a novel explainable deep learning framework for multiclass obesity prediction.
To develop and evaluate models using a unique Saudi-specific dataset integrating diverse health factors.
To enhance transparency in obesity risk assessment through interpretable AI.

Main Methods:

Evaluation of six deep learning models: LSTM, Bi-LSTM, RNN, DNN (MLP), TabNet, and Autoencoder.

Keywords:

Deep Learning Explainable AI Interactive Interface LIME Visualization LSTM Obesity Level Prediction

Related Experiment Videos

Last Updated: Jan 8, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Utilized a Saudi-specific dataset comprising anthropometric, lifestyle, and dietary data.

Integrated Local Interpretable Model-Agnostic Explanations (LIME) with Bi-LSTM for interpretability.

Main Results:

The Bidirectional LSTM (Bi-LSTM) model demonstrated superior performance with 96% accuracy, 0.96 macro recall, and 0.95 macro F1-score.
Regression metrics (MAE, RMSE, R²) were used for model calibration and ordinal misclassification assessment.
The developed framework provides accurate predictions and transparent visualization of obesity risk factors.

Conclusions:

The Bi-LSTM model offers a highly accurate and interpretable solution for multiclass obesity prediction in the Saudi population.
This research establishes the first culturally specific Saudi multiclass obesity dataset for AI-driven health applications.
The integration of explainable AI with region-specific data advances precision public health strategies.