Browsing by Author "S, S.K."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Content-based medical retrieval systems with evidence-based diagnosis for enhanced clinical decision support
    (Elsevier Ltd, 2025) Karthik, K.; S, S.K.; Supreetha, S.; Katlam, A.
    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). © 2025 Elsevier Ltd
  • Thumbnail Image
    Item
    TAGS: Towards Automated Classification of Unstructured Clinical Nursing Notes
    (2019) Gangavarapu, T.; Jayasimha, A.; Krishnan, G.S.; S, S.K.
    Accurate risk management and disease prediction are vital in intensive care units to channel prompt care to patients in critical conditions and aid medical personnel in effective decision making. Clinical nursing notes document subjective assessments and crucial information of a patient�s state, which is mostly lost when transcribed into Electronic Medical Records (EMRs). The Clinical Decision Support Systems (CDSSs) in the existing body of literature are heavily dependent on the structured nature of EMRs. Moreover, works which aim at benchmarking deep learning models are limited. In this paper, we aim at leveraging the underutilized treasure-trove of patient-specific information present in the unstructured clinical nursing notes towards the development of CDSSs. We present a fuzzy token-based similarity approach to aggregate voluminous clinical documentations of a patient. To structure the free-text in the unstructured notes, vector space and coherence-based topic modeling approaches that capture the syntactic and latent semantic information are presented. Furthermore, we utilize the predictive capabilities of deep neural architectures for disease prediction as ICD-9 code group. Experimental validation revealed that the proposed Term weighting of nursing notes AGgregated using Similarity (TAGS) model outperformed the state-of-the-art model by 5% in AUPRC and 1.55% in AUROC. � 2019, Springer Nature Switzerland AG.