Designing Interpretable ML System to Enhance Trustworthy AI in Healthcare: A Systematic Review of the Last Decade to A Proposed Robust Framework

AI-based medical technologies, including wearables, telemedicine, LLMs, and digital care twins, significantly impact healthcare. Ensuring AI results are accurate and interpretable is crucial, especially for clinicians. This paper reviews processes and challenges of interpretable ML (IML) and explainable AI (XAI) in healthcare. Objectives include reviewing XAI processes, methods, applications, and challenges, with a focus on quality control. The IML process is classified into data pre-processing interpretability, interpretable modeling, and post-processing interpretability. The paper aims to establish the importance of robust interpretability in healthcare through experimental results, providing insights for creating communicable clinician-AI tools. Research questions, eligibility criteria, and goals were identified following PRISMA and PICO methods. PubMed, Scopus, and Web of Science were systematically searched using specific strings. The survey introduces a step-by-step roadmap for implementing XAI in clinical applications, addressing existing gaps and acknowledging XAI model limitations.

AI Framework for Early Diagnosis of Coronary Artery Disease: An Integration of Borderline SMOTE, Autoencoders and Convolutional Neural Networks Approach

The accuracy of coronary artery disease (CAD) diagnosis is dependent on a variety of factors, including demographic, symptom, and medical examination, ECG, and echocardiography data, among others. In this context, artificial intelligence (AI) can help clinicians identify high-risk patients early in the diagnostic process, by synthesizing information from multiple factors. To this aim, Machine Learning algorithms are used to classify patients based on their CAD disease risk. In this study, we contribute to this research filed by developing a methodology for balancing and augmenting data for more accurate prediction when the data is imbalanced and the sample size is small. The methodology can be used in a variety of other situations, particularly when data collection is expensive and the sample size is small. The experimental results revealed that the average accuracy of our proposed method for CAD prediction was 95.36, and was higher than random forest (RF), decision tree (DT), support vector machine (SVM), logistic regression (LR), and artificial neural network (ANN).