A Multi-Modal Deep Learning System for Early Staging of Liver Fibrosis and Prediction of Diastolic Dysfunction Disease Risk

Author(s)	Mr. Sri Harsha Vardhan Dasari, Prof. Jacob Finny, Ms. Likitha Adireddi, Mr. Ramesh Gadamsetti
Country	India
Abstract	Left Ventricular Diastolic Dysfunction (DD) is an early indicator of Heart Failure with Preserved Ejection Fraction (HFpEF), yet traditional single-parameter diagnostics often yield ambiguous results. This study introduces an automated Clinical Decision Support System (CDSS) based on the Heart-Liver Axis hypothesis, which identifies liver fibrosis as a critical driver of cardiac deterioration. By integrating a tri-modal architecture—comprising Hepatic (EfficientNetB0), Cardiac (MobileNetV2-LSTM), and Clinical (XGBoost) modules—the system achieves a 93.74% balanced accuracy on a 2,000-sample population though dataset scarcity and dataset augmentation should be considered. To bridge the gap in clinical adoption, we have embedded Grad-CAM spatial explainability and an interactive AI Chatbot interface. This multi-organ diagnostic pipeline successfully reduces classification uncertainty, providing physicians with a robust, evidence-based tool for medical intervention.
Keywords	Diastolic Dysfunction, Liver Fibrosis, Clinical Decision Support System, Heart-Liver Axis, Multi-Modal Fusion, EfficientNetB0, MobileNetV2, Grad-CAM, Generative AI Chatbot, Deep Learning, METAVIR Staging
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-05

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research