Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/595918
Title: Context Aware Knowledge Discovery in Electronic Health Records
Researcher: Paliwal Gaurav
Guide(s): Bunglowala Aaquil and Kanthed Pravesh
Keywords: Electronic Health Records (EHR)
Engineering
Engineering and Technology
Engineering Electrical and Electronic
University: Narsee Monjee Institute of Management Studies
Completed Date: 2024
Abstract: Electronic Health Records (EHR) have gained widespread adoption in healthcare newlinesystems worldwide, promising to reshape patient care and streamline medical newlineprocesses. The primary objectives of this research included developing an enhanced newlineframework for optimizing EHR data usage, creating a context-based approach to newlinedeliver precise quotpoint of carequot services, and facilitating efficient, context-aware newlineknowledge discovery within healthcare records. newlineThe first objective involved crafting an innovative framework to maximize the newlineutilization of EHR data. The research introduced an EHR conceptual model that newlineoffered a structured framework for interpreting intricate healthcare data. The newlineimplementation of a six-tier system architecture laid the foundation for efficient data newlinemanagement and improved data accessibility. The establishment of an EHR newlinestandard was instrumental in promoting data standardization and interoperability. newlineThe incorporation of context parameters within healthcare records added depth and newlineprecision to patient data, enabling more informed decisions and personalized care. newlineThe second objective aimed at the development of a context-based approach to newlineprovide precise quotpoint of carequot services within healthcare settings. Employing newlineNatural Language Processing (NLP) and machine learning techniques, the research newlineextracted context from EHRs. The patient classification framework developed in newlinethis study exhibited remarkable performance, surpassing existing models in the newlinebiomedical NLP domain. It introduced a novel approach for creating composite newlinedatasets with minimal data loss (0.57%). This framework achieved an accuracy of newline82.86% and an F1 score of 0.89, underscoring its precision and reliability. newlineThe third objective involved the development of an Intelligent Knowledge newlineDiscovery Mechanism, harnessing advanced data analytics and artificial intelligence newlineto enable efficient, context-aware knowledge discovery within healthcare records. newline
Pagination: i-xxii;211p
URI: http://hdl.handle.net/10603/595918
Appears in Departments:Department of Electronic Engineering

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File91.5 kBAdobe PDFView/Open
02_prelim pages.pdf785.19 kBAdobe PDFView/Open
03_content.pdf67.86 kBAdobe PDFView/Open
04_abstract.pdf52.88 kBAdobe PDFView/Open
05_chapter 1.pdf357.01 kBAdobe PDFView/Open
06_chapter 2.pdf339.23 kBAdobe PDFView/Open
07_chapter 3.pdf106.68 kBAdobe PDFView/Open
08_chapter 4.pdf625.7 kBAdobe PDFView/Open
09_chapter 5.pdf466.83 kBAdobe PDFView/Open
10_chapter 6.pdf1.98 MBAdobe PDFView/Open
11_annexures.pdf297.87 kBAdobe PDFView/Open
80_recommendation.pdf115.84 kBAdobe PDFView/Open
Show full item record


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: