Mohammed Imran Basheer Ahmed
Using a convolutional neural network (CNN) integrated with AI, Large Language Models (LLMs), and image processing to analyze lung X-ray images, allowing medical specialists to have real-time conversations with a trained LLM model leveraging medical encyclopedia knowledge. Achieving an Area Under the Curve-Receiver Operating Characteristic (AUC-ROC) of 90%. The proposed approach aims to improve diagnostic accuracy, align with technological advancement goals, alleviate healthcare burdens, and enhance overall quality of life.
Given the growing challenges in healthcare diagnostics, the proposed research study aims to transform how we identify lung diseases. We aim to achieve this by integrating AI, Large Language Models (LLMs), and Image Processing with medical expertise. The main driving force behind the initiative is the need for more accurate diagnoses. In this regard, the primary focus is on using lung X-ray images to harness healthcare through image processing. Additionally, the research introduces a dimension in which medical specialists can have real-time conversations with a trained LLM model that leverages knowledge from a medical encyclopedia. This interactive feature enhances collaboration between AI and medical professionals, creating a platform for exchanging knowledge. A carefully designed convolutional neural network (CNN) was investigated, achieving an Area Under the Curve-Receiver Operating Characteristic (AUC-ROC) of 90%. By doing so, the study not only aligns with Saudi Arabia's vision for technological advancement in healthcare by 2030 but also aims to alleviate burdens on the healthcare sector and enhance overall quality of life. The proposed approach represents a collaboration that promises groundbreaking advancements in the diagnostic process.