Content-based medical retrieval systems with evidence-based diagnosis for enhanced clinical decision support

• Published in: Expert systems with applications 2025-05, Vol.272, p.126678, Article 126678
• Main Authors: K, Karthik, S, Sowmya Kamath, R, Supreetha, Katlam, Ashish
• Format: Article
• Language: English
• Subjects: Clinical decision support system; Electronic health records; Evidence-based diagnosis; Healthcare analytics; Medical image retrieval
• ISSN: 0957-4174
• DOI: 10.1016/j.eswa.2025.126678

In the medical field, making accurate decisions during treatment is crucial. Incorrect decisions can lead to misdiagnoses, resulting in patient mismanagement and severe consequences. Clinical Decision Support Systems (CDSS) are essential in aiding doctors with critical medical decisions by providing precise and informative diagnostic recommendations. Despite the extensive availability of both textual and graphical electronic health records (EHR), current systems often fail to fully utilize all available data. Most systems rely predominantly on textual patient reports, while integrating findings from medical images is vital for accurate diagnoses. To address this gap, we propose an advanced system that incorporates medical image classification using a Content-Based Medical Image Retrieval (CBMIR) system in CDSSs, to enable evidence-based diagnosis. The proposed system leverages advanced AI algorithms to improve disease localization, recognition, and classification, of specific thoracic diseases using X-ray medical images that can be used for other imaging modalities like MRIs, and CT scans by the CDSS in future. The system also incorporates classification-based image filtering and tree-based similarity matching algorithms for optimized retrieval performance. The system achieved promising performance with a Mean Average Precision of 0.66−0.85 for Top-5 retrieval with time complexity of O(logn).