Artificial Intelligence(AI) methods are rapidly being adopted for risk assessment and prediction of outcomes of medical events in medicine. Improving the interpretability and transparency of machine learning(ML) models is a fundamental goal of applying AI techniques in the healthcare sector. Explainable AI(XAI) is a phenomenon that arises from the use of AI in the healthcare business through several tactics such as interpretation, fairness, validation, and performance assessment of the model. The work focuses on once such XAI model named, C3 PW - A novel ML method for assessing Percutaneous Transvenous Mitral Commissurotomy(PTMC) Outcome in patients with Mitral Stenosis. Patients with symptomatic moderate to severe mitral stenosis(MS) with pliable valves are indicated for PTMC typically over a valve replacement based on favourable anatomic characteristics. Currently, this decision is arrived based on Wilkins' echocardiographic score which is considered to be a simplistic estimate often. The AI model takes into account demographic, clinical, and pre-procedural echocardiographic variables pertaining to patients with moderate to severe mitral stenosis without significant mitral regurgitation(MR). The success of the procedure was defined by four different post-procedural variables such as the final Mitral valve area(MVA), MR, Left Atrial Pressure(LA), and Right Ventricular Systolic Pressure(RVSP). Cover Coefficient Clustering Power as Weights(C3PW), a novel problem transformation technique which deals with the multi-label classes was adopted to correctly classify the patients having successful PTMC procedure. Extreme gradient boosting(XGB) an ML technique gave the best performance (accuracy: 0.79; F-score: 0.87) on the transformed single-label problem. Application of association rule mining revealed that a combination of the parameters such as ‘initial MVA' less than 1 sqcm, ‘RVSP’ less than 50 mmHg, 'valvular calcification' score less than or equal to 2, 'leaflet mobility' score less than or equal to 2 and ‘normal sinus rhythm’ plays a crucial role in determining the success of the PTMC procedure. The outcome takes into RVSP, regurgitation, and the rhythm apart from calcification and mobility which are part of Wilkins's score. The ML framework also includes the prediction of post-PTMC MR indicating that this methodology is more comprehensive than Wilkins' score. This AI model could serve as an alternative to Wilkins's score to select patients for a successful PTMC procedure. Thus, a systematically analyzed ML framework that yields highly interpretable and conclusive findings with high confidence can be considered to be a useful tool in clinical decision-making

Subramaniyan Mani has completed his M.Tech in Computer Science and active researcher from Sri Sathya Sai Institute of Higher Learning (Deemed University), India. He is the head of Patient Welfare & Telemedicine Services and Software lead at department of Management Information Systems at Sri Sathya Sai Institute of Higher Medical Sciences, a tertiary care teaching hospital in Bangalore, India. He has led several projects of development and implementation of electronic medical records and enterprise resource planning at the hospital. He is a practicing professor and workgroup member for Healthcare IT, analytics, and research initiatives at the university. He was a key member of the organizing committee for 2 international Health IT conferences in the institute.