QUANTIFYING EXPLAINABLE AI METHODS IN MEDICAL DIAGNOSIS: A STUDY IN SKIN CANCER

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 10, 2024

Abstract Deep learning models have shown substantial promise in assisting medical diagnosis, offering the potential to improve patient outcomes and reduce clinician workloads. However, widespread adoption of these clinical practice has been hindered by concerns surrounding their trustworthiness, transparency, interpretability. Addressing challenges requires not only development explainable AI (xAI) techniques but also quantitative metrics evaluate effectiveness. This study presents a comprehensive framework for training, explaining, quantitatively assessing deep skin cancer diagnosis. Leveraging HAM10000 dataset seven diagnostic lesion categories, multiple convolutional neural network architectures—including custom CNNs, DenseNet, MobileNet, ResNet—were trained optimized using augmentation, oversampling, hyperparameter tuning. Following model explainability such as SHAP, LIME, Integrated Gradients were deployed generate post hoc explanations. Critically, primary contribution this work is evaluation explanation methods related faithfulness, robustness, complexity. All code, models, results are publicly available, providing reproducible pathway toward more trustworthy, tools.

Language: Английский

Building Health Awareness: Analysis of the Relationship between Knowledge and Attitude with BSE Behavior in Public Health Science Students

Journal of Health Innovation and Environmental Education., Journal Year: 2024, Volume and Issue: 1(2), P. 53 - 59

Published: Dec. 31, 2024

Purpose of the study: The purpose this study was to determine relationship between knowledge and attitudes with BSE behavior in students Public Health Study Program, Jambi University. Methodology: This used a descriptive analytic research design cross sectional approach. sampling technique multistage random on 307 by filling an online questionnaire through Googleform. variables were knowledge, which analyzed using Chi-square test. Main Findings: Knowledge female good category is 73 people. Attitudes positive are 52 people, for 68 There no significant behavior, there behavior. Novelty/Originality results expected be useful as material developing scientific add literature breast cancer itself well policies regarding prevention non-communicable diseases, especially students.

Language: Английский