Faculty Publications

Now showing 1 - 3 of 3

Ensemble deep neural models for automated abnormality detection and classification in precision care applications
(Elsevier, 2023) Karthik, K.; Mayya, V.; Kamath S․, S.
Radiological imaging is one of the most relied upon modalities in the clinical diagnosis and treatment planning process. Conventional diagnosis involves the manual analysis of radiology images by experienced radiologists, which is often a time-consuming and labor-intensive process. The scarcity of experienced radiologists and necessity of large-scale X-rays image analysis given the huge diagnosis workload at most hospitals stresses the need for automated clinical diagnosis systems capable of fast and accurate identification of abnormalities, disease characteristic identification, disease classification, and others. Such automated methods are thus a fundamental requirement in clinical workflow management applications. In this work, we present an approach for multitask clinical objectives such as disease classification and detection of abnormalities. The proposed model leverages the predictive power of deep neural models for enabling evidence-based diagnosis. During validation experiments, the model achieved an accuracy of 89.58% along with sensitivity and specificity of 85.83% and 90.83%, respectively, with an AUC (area under the ROC curve) of 95.84% for normal/no findings versus COVID-19 chest radiograph classification and an accuracy of 73.19% for upper extremity musculoskeletal images. The performance of the model for the classification and abnormality identification tasks, when benchmarked over multiple standard datasets, emphasizes its suitability and adaptability in real-world clinical settings, with significant improvements in radiology-based diagnosis workflow and patient care. © 2023 Elsevier Inc. All rights reserved.
Multi-channel, convolutional attention based neural model for automated diagnostic coding of unstructured patient discharge summaries
(Elsevier B.V., 2021) Mayya, V.; Kamath S?, S.S.; S. Krishnan, G.S.; Gangavarapu, T.
Effective coding of patient records in hospitals is an essential requirement for epidemiology, billing, and managing insurance claims. The prevalent practice of manual coding, carried out by trained medical coders, is error-prone and time-consuming. Mitigating this labor-intensive process by developing diagnostic coding systems built on patients’ Electronic Medical Records (EMRs) is vital. However, developing nations with low digitization rates have limited availability of structured EMRs, thereby necessitating a need for systems that leverage unstructured data sources. Despite the rich clinical information available in such unstructured data, modeling them is complex, owing to the variety and sparseness of diagnostic codes, complex structural and temporal nature of summaries, and prolific use of medical jargon. This work proposes a context-attentive network to facilitate automatic diagnostic code assignment as a multi-label classification problem. The proposed model facilitates information aggregation across a patient's discharge summary via multi-channel, variable-sized convolutional filters to extract multi-granular snippets. The attention mechanism enables selecting vital segments in those snippets that map to the clinical codes. The model's superior performance underscores its effectiveness compared to the state-of-the-art on the MIMIC-III database. Additionally, experimental validation using the CodiEsp dataset exhibited the model's interpretability and explainability. © 2021 Elsevier B.V.
An empirical study of preprocessing techniques with convolutional neural networks for accurate detection of chronic ocular diseases using fundus images
(Springer, 2023) Mayya, V.; Kamath S․, S.K.; Kulkarni, U.; Surya, D.K.; Acharya, U.R.
Chronic Ocular Diseases (COD) such as myopia, diabetic retinopathy, age-related macular degeneration, glaucoma, and cataract can affect the eye and may even lead to severe vision impairment or blindness. According to a recent World Health Organization (WHO) report on vision, at least 2.2 billion individuals worldwide suffer from vision impairment. Often, overt signs indicative of COD do not manifest until the disease has progressed to an advanced stage. However, if COD is detected early, vision impairment can be avoided by early intervention and cost-effective treatment. Ophthalmologists are trained to detect COD by examining certain minute changes in the retina, such as microaneurysms, macular edema, hemorrhages, and alterations in the blood vessels. The range of eye conditions is diverse, and each of these conditions requires a unique patient-specific treatment. Convolutional neural networks (CNNs) have demonstrated significant potential in multi-disciplinary fields, including the detection of a variety of eye diseases. In this study, we combined several preprocessing approaches with convolutional neural networks to accurately detect COD in eye fundus images. To the best of our knowledge, this is the first work that provides a qualitative analysis of preprocessing approaches for COD classification using CNN models. Experimental results demonstrate that CNNs trained on the region of interest segmented images outperform the models trained on the original input images by a substantial margin. Additionally, an ensemble of three preprocessing techniques outperformed other state-of-the-art approaches by 30% and 3%, in terms of Kappa and F1 scores, respectively. The developed prototype has been extensively tested and can be evaluated on more comprehensive COD datasets for deployment in the clinical setup. © 2022, The Author(s).

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results