Authors:
S. Rubin Bose, R. Vinoth, J. Angelin Jeba, Rahul Chauhan, C. Christina Angelin
Addresses:
Department of Computer Science Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communications Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Fitch Ratings, The Fitch Group, New York, United States of America. Department of Mathematics, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India.
Abstract:
AI and deep learning, which assess symptoms and diagnose, have improved healthcare. The paper intends to create AI-based symptom analysis systems using deep learning models for accurate, efficient, tailored medical insights. A differential diagnosis is made using advanced natural language processing NLP to assess user-reported symptoms, medical history, and other contextual information. Transformers, CNNS, and RNNs would be trained on big medical datasets. These models accurately identify complex symptom patterns and diseases. In tests, transformer-based structures like transformers identify rare diseases and complex symptom combinations with over 92% accuracy. The method handles overlapping symptoms using multi-label classification. The system's ability to process unstructured data from EHRs and patient reports to the Outcomes PRO is crucial. This permits thorough symptom extraction and analysis, reducing chart review and improving scalability. The system is also integrated into a simple web app that provides initial assessments and directs users to medical appointments. It is an AI-powered aid for patients and doctors, not a replacement. Earlier warning indications for dangerous illnesses and faster diagnostics could improve patient outcomes, lower healthcare costs, and boost medical decision-making efficiency. This is a major step toward AI-based tailored medicine.
Keywords: Deep Learning; Healthcare Diagnostics; Machine Learning; Natural Language Processing (NLP); Convolutional Neural Networks (CNN); Recurrent Neural Networks (RNN); Long Short-Term Memory (LSTM).
Received: 13/06/2024, Revised: 23/09/2024, Accepted: 01/11/2024, Published: 07/12/2024
AVE Trends in Intelligent Health Letters, 2024 Vol. 1 No. 4 , Pages: 243-254