Niyaz Ahmad Wani

IILM University, Greater Noida, India

Title: Synergizing fusion modelling for accurate cardiac prediction through explainable artificial intelligence

---

Biography

Niyaz Ahmad Wani is an accomplished academic and researcher in Computer Science and Engineering, currently an Assistant Professor at IILM University, Greater Noida. With a Ph.D. from Thapar Institute of Engineering and Technology, his research centers on Explainable Artificial Intelligence (XAI), machine learning, deep learning, and innovative healthcare systems. His doctoral thesis focused on developing efficient XAI models for cancer detection, reflecting his strong commitment to impactful healthcare innovation.

Wani is profilic author with 20 SCI publications in high impact Journals including Information Fusion, IEEE Transactions on Consumer Electronics, Nature (Scientific Reports). He has received multiple accolades, including Best Researcher Awards and Best Paper Awards for his work on interpretable AI models in oncology.

Abstract

Artificial Intelligence (AI) and Machine Learning (ML) are transforming modern healthcare by enabling the development of disruptive technologies that cater to consumer demands for accurate diagnostics and effective clinical decision-making. Their role becomes particularly vital in extracting actionable insights from complex healthcare datasets. In this context, we introduce “AC²” (Accurate Cardiac Classification), a novel hybrid deep learning framework designed to accurately detect cardiovascular disease (CVD) while providing interpretable outcomes. The AC² model seamlessly integrates Convolutional Neural Networks (CNN) with the Light Gradient Boosting Machine (Light GBM), combining the strengths of deep feature extraction and efficient classification. Trained on the CDC’s Behavioral Risk Factor Surveillance System (BRFSS) dataset—which offers comprehensive, state-level data on health behaviors and preventive care—the proposed model demonstrates superior performance across key metrics such as accuracy, precision, recall, and F1-score compared to existing approaches. To enhance trust and transparency, the AC² system incorporates Explainable AI (XAI) techniques, particularly SHAP (Shapley Additive explanations),to offer both local and global interpretability. These insights demystify the model's internal logic, making it more accessible to clinicians and healthcare stakeholders. As the need for reliable, data-driven healthcare solutions grows, the AC² model stands out for its high predictive accuracy and interpretability, positioning it as a valuable tool for improving diagnostic decisions and treatment planning in clinical practice.