Developing an Explainable Artificial Intelligence System for the Mobile-Based Diagnosis of Febrile Diseases Using Random Forest, LIME, and GPT
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: This study proposes a mobile-based explainable artificial intelligence (XAI) platform designed for diagnosing febrileillnesses. Methods: We integrated the interpretability offered by local interpretable model-agnostic explanations (LIME)and the explainability provided by generative pre-trained transformers (GPT) to bridge the gap in understanding and trustoften created by machine learning models in critical healthcare decision-making. The developed system employed randomforest for disease diagnosis, LIME for interpretation of the results, and GPT-3.5 for generating explanations in easy-to-understandlanguage. Results: Our model demonstrated robust performance in detecting malaria, achieving precision, recall, andF1-scores of 85%, 91%, and 88%, respectively. It performed moderately well in detecting urinary tract and respiratory tractinfections, with precision, recall, and F1-scores of 80%, 65%, and 72%, and 77%, 68%, and 72%, respectively, maintaining aneffective balance between sensitivity and specificity. However, the model exhibited limitations in detecting typhoid fever andhuman immunodeficiency virus/acquired immune deficiency syndrome, achieving lower precision, recall, and F1-scores of69%, 53%, and 60%, and 75%, 39%, and 51%, respectively. These results indicate missed true-positive cases, necessitatingfurther model fine-tuning. LIME and GPT-3.5 were integrated to enhance transparency and provide natural language explanations,thereby aiding decision-making and improving user comprehension of the diagnoses. Conclusions: The LIME plotsrevealed key symptoms influencing the diagnoses, with bitter taste in the mouth and fever showing the highest negative influenceon predictions, and GPT-3.5 provided natural language explanations that increased the reliability and trustworthiness ofthe system, promoting improved patient outcomes and reducing the healthcare burden.
Abstract
Objectives: This study proposes a mobile-based explainable artificial intelligence (XAI) platform designed for diagnosing febrileillnesses. Methods: We integrated the interpretability offered by local interpretable model-agnostic explanations (LIME)and the explainability provided by generative pre-trained transformers (GPT) to bridge the gap in understanding and trustoften created by machine learning models in critical healthcare decision-making. The developed system employed randomforest for disease diagnosis, LIME for interpretation of the results, and GPT-3.5 for generating explanations in easy-to-understandlanguage. Results: Our model demonstrated robust performance in detecting malaria, achieving precision, recall, andF1-scores of 85%, 91%, and 88%, respectively. It performed moderately well in detecting urinary tract and respiratory tractinfections, with precision, recall, and F1-scores of 80%, 65%, and 72%, and 77%, 68%, and 72%, respectively, maintaining aneffective balance between sensitivity and specificity. However, the model exhibited limitations in detecting typhoid fever andhuman immunodeficiency virus/acquired immune deficiency syndrome, achieving lower precision, recall, and F1-scores of69%, 53%, and 60%, and 75%, 39%, and 51%, respectively. These results indicate missed true-positive cases, necessitatingfurther model fine-tuning. LIME and GPT-3.5 were integrated to enhance transparency and provide natural language explanations,thereby aiding decision-making and improving user comprehension of the diagnoses. Conclusions: The LIME plotsrevealed key symptoms influencing the diagnoses, with bitter taste in the mouth and fever showing the highest negative influenceon predictions, and GPT-3.5 provided natural language explanations that increased the reliability and trustworthiness ofthe system, promoting improved patient outcomes and reducing the healthcare burden.