Research Article
Influenza Diagnosis Deep Learning: Machine Learning Approach for Pharyngeal Image Infection
@ARTICLE{10.4108/eetpht.10.5613, author={Chetan Chaudhari and Sapana Fegade and Sasanko Sekhar Gantayat and Kumari Jugnu and Vikash Sawan}, title={Influenza Diagnosis Deep Learning: Machine Learning Approach for Pharyngeal Image Infection}, journal={EAI Endorsed Transactions on Pervasive Health and Technology}, volume={10}, number={1}, publisher={EAI}, journal_a={PHAT}, year={2024}, month={4}, keywords={Influenza, Deep Learning Model, Pharyngeal Image, AI Model, Heat Maps}, doi={10.4108/eetpht.10.5613} }
- Chetan Chaudhari
Sapana Fegade
Sasanko Sekhar Gantayat
Kumari Jugnu
Vikash Sawan
Year: 2024
Influenza Diagnosis Deep Learning: Machine Learning Approach for Pharyngeal Image Infection
PHAT
EAI
DOI: 10.4108/eetpht.10.5613
Abstract
INTRODUCTION: Annual influenza epidemics and rare pandemics represent a significant global health risk. Since the upper respiratory tract is the primary target of influenza, a diagnosis of influenza illness might be made using deep learning applied to pictures of the pharynx. Using pharyngeal imaging data and clinical information, the researcher created a deep-learning model for influenza diagnosis. People who sought medical attention for flu-like symptoms were the subjects included. METHODOLOGY: The study created a diagnostic and predicting Artificial Intelligence (AI) method using deep learning techniques to forecast clinical data and pharyngeal pictures for PCR confirmation of influenza. The accuracy of the AI method as a diagnostic tool was measured during the validation process. The extra research evaluated the AI model's diagnosis accuracy to that of three human doctors and explained the methodology using high-impact heat maps. In the training stage, a cohort of 8,000 patients was recruited from 70 hospitals. Subsequently, a subset of 700 patients, including 300 individuals with PCR-confirmed influenza, was selected from 15 hospitals during the validation stage. RESULTS: The AI model exhibited an operating receiver curve with an area of 1.01, surpassing the performance of three doctors by achieving a sensitivity of 80% and a specificity of 80%. The significance of heat maps lies in their ability to provide valuable insights. In AI models, particular attention is often directed towards analyzing follicles on the posterior pharynx wall. Researchers introduced a novel artificial intelligence model that can assist medical professionals in swiftly diagnosing influenza based on pharyngeal images.
Copyright © 2024 C. Chaudhari et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NCSA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.