Elham Nasarian

Elham Nasarian, Roohallah Alizadehsani, U. Rajendra Acharya et al.

This paper explores the significant impact of AI-based medical devices, including wearables, telemedicine, large language models, and digital twins, on clinical decision support systems. It emphasizes the importance of producing outcomes that are not only accurate but also interpretable and understandable to clinicians, addressing the risk that lack of interpretability poses in terms of mistrust and reluctance to adopt these technologies in healthcare. The paper reviews interpretable AI processes, methods, applications, and the challenges of implementation in healthcare, focusing on quality control to facilitate responsible communication between AI systems and clinicians. It breaks down the interpretability process into data pre-processing, model selection, and post-processing, aiming to foster a comprehensive understanding of the crucial role of a robust interpretability approach in healthcare and to guide future research in this area. with insights for creating responsible clinician-AI tools for healthcare, as well as to offer a deeper understanding of the challenges they might face. Our research questions, eligibility criteria and primary goals were identified using Preferred Reporting Items for Systematic reviews and Meta-Analyses guideline and PICO method; PubMed, Scopus and Web of Science databases were systematically searched using sensitive and specific search strings. In the end, 52 publications were selected for data extraction which included 8 existing reviews and 44 related experimental studies. The paper offers general concepts of interpretable AI in healthcare and discuss three-levels interpretability process. Additionally, it provides a comprehensive discussion of evaluating robust interpretability AI in healthcare. Moreover, this survey introduces a step-by-step roadmap for implementing responsible AI in healthcare.

Elham Nasarian, Danial Sharifrazi, Saman Mohsenirad et al.

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).

Elham Nasarian, Abhilash Neog, Kwok-Leung Tsui et al.

Integrating large language models (LLMs) into patient-facing healthcare systems offers significant potential to improve access to medical information. However, ensuring clinical safety and factual reliability remains a critical challenge. In practice, AI-generated responses may be conditionally correct yet medically inappropriate, as models often fail to interpret patient context and tend to produce agreeable responses rather than challenge unsafe assumptions. Unlike clinicians, who infer risk from incomplete information, LLMs frequently lack contextual awareness. Moreover, real-world patient interactions are open-ended and underspecified, unlike structured benchmark settings. We present CareGuardAI, a risk-aware safety framework for patient-facing medical question answering that addresses two key failure modes: clinical safety risk and hallucination risk. The framework introduces Clinical Safety Risk Assessment (SRA), inspired by ISO 14971, and Hallucination Risk Assessment (HRA) to evaluate medical risk and factual reliability. At inference time, CareGuardAI employs a multi-stage pipeline consisting of a controller agent, safety-constrained generation, and dual risk evaluation, followed by iterative refinement when necessary. Responses are released only when both SRA and HRA are less than or equal to 2, ensuring clinically acceptable outputs with bounded latency. We evaluate CareGuardAI on PatientSafeBench, MedSafetyBench, and MedHallu, covering both safety and hallucination detection. Across these benchmarks, the framework consistently outperforms strong baseline models, including GPT-4o-mini, demonstrating the importance of context-aware, risk-based, inference-time safety mechanisms for reliable deployment in healthcare.