Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Subject: search.filters.subject.healthcare analytics

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Neural Language Modeling of Unstructured Clinical Notes for Automated Patient Phenotyping
    (Institute of Electrical and Electronics Engineers Inc., 2022) Prabhakar, A.; Shidharth, S.; Kamath S․, S.
    The availability of huge volume and variety of healthcare data provides a wide scope for designing cutting-edge clinical decision support systems (CDSS) that can improve the quality of patient care. Identifying patients suffering from certain conditions/symptoms, commonly referred to as phenotyping, is a fundamental problem that can be addressed using the rich health-related data collected for generation of Electronic Health Records (EHRs). Phenotyping forms the foundation for translational research, effectiveness studies, and is used for analyzing population health using regularly collected EHR data. Also, determining if a patient has a particular medical condition is crucial for secondary analysis, such as in critical care situations to predict potential drug interactions and adverse events. In this paper, we consider all categories of unstructured clinical notes of patients, typically stored as part of EHRs in the raw form. The standard MIMIC-III dataset is considered for benchmark experiments for patient phenotyping. Experiments revealed that our proposed models outperformed state-of-the art works built on vanilla BERT ClinicalBERT models on the patient cohort considered, measured in terms of standard multi-label classification metrics like AUROC score (improvement by 6%), F1-score (by 4%), and Hamming Loss (by 17%) when we considered only patient discharge summaries and radiology notes. Further experiments with other note categories showed that using discharge summaries and physician notes yields significant improvements on the entire dataset giving 0.8 AUROC score, 0.72 F1 score, 0.09 Hamming loss. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Detection of Cardiac Arrhythmia Using Machine Learning Approaches
    (Institute of Electrical and Electronics Engineers Inc., 2022) Chittoria, J.; Kamath S․, S.; Mayya, V.
    Arrhythmia is a cardiovascular disease that alters the heart rate, resulting in too fast, too slow, or irregular rhythms. It is a life-threatening disease if left untreated. Traditionally, arrhythmia is diagnosed by a trained doctor, using an electrocardiogram to analyze irregular heartbeats. However, these methods are vulnerable to inadvertent misdiagnosis, especially during the early stages of the disease. In this paper, an approach for cardiac arrhythmia detection is presented, where the subjects or instances are first categorized as diseased or normal and then further graded into normal (non-diseased) or as distinct subtypes of cardiac arrhythmia. The dataset was obtained from the UCI Machine Learning Data Repository, and machine learning methods such as XGBoost, CatBoost, SVM, and Random Forest, were experimented with. Addition-ally, the mutual information-based feature selection approach, minimal redundancy maximum relevance (mRMR), is proposed to improve classification accuracy. Standard evaluation metrics such as accuracy, f1-score, precision, and recall are utilized for comparison of the obtained results. The experimental results demonstrated that accuracy of 81.48% was achieved for multi-class classification, while binary classification achieved up to 84% accuracy. © 2022 IEEE.