Explainable artificial intelligence for investigating the effect of lifestyle factors on obesity

•Investigating the use of machine learning classification to assess the effect of lifestyle factors on the obesity.•Using Explainable machine learning to interpret the results of the ML model in terms of how specific lifestyle factors influence the outcome of the classification. Obesity is a critica...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Intelligent systems with applications Ročník 23; s. 200427
Hlavní autoři: Khater, Tarek, Tawfik, Hissam, Singh, Balbir
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.09.2024
Elsevier
Témata:
Explainable artificial intelligence
Global explanations
Local explanations
Machine learning
Model-agnostic methods
Obesity
Explainable artificial intelligence
Obesity
Model-agnostic methods
Global explanations
Machine learning
Local explanations
ISSN:2667-3053, 2667-3053
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Investigating the use of machine learning classification to assess the effect of lifestyle factors on the obesity.•Using Explainable machine learning to interpret the results of the ML model in terms of how specific lifestyle factors influence the outcome of the classification. Obesity is a critical health issue associated with severe medical conditions. To enhance public health and well-being, early prediction of obesity risk is crucial. This study introduces an innovative approach to predicting obesity levels using explainable artificial intelligence, focusing on lifestyle factors rather than traditional BMI measures. Our best-performing machine learning model, free from BMI parameters, achieved 86.5% accuracy using the Random Forest algorithm. Explainability techniques, including SHAP, PDP and feature importance are employed to gain insights into lifestyle factors’ impact on obesity. Key findings indicate the importance of meal frequency and technology usage. This work demonstrates the significance of lifestyle factors in obesity risk and the power of model-agnostic methods to uncover these relationships.
ISSN:2667-3053
2667-3053
DOI:10.1016/j.iswa.2024.200427