Date of Submission
Fall 2023
Supervisor
Dr. Tariq Mahmood, Professor and Program Coordinator MS(CS) and MS(DS) Programs, School of Mathematics and Computer Science (SMCS)
Committee Member 1
Dr. Muhammad Rafi, Examiner – I, National University of Computer and Emerging Sciences (NUCES), Karachi
Committee Member 2
Dr. Umer Tariq, Examiner – II, Habib University, Karachi
Degree
Master of Science in Data Science
Department
Department of Computer Science
Faculty/ School
School of Mathematics and Computer Science (SMCS)
Keywords
PICU, Mortality Analysis, Fuzzy C-Means, Soft Clustering Framework, FCM
Abstract
Pediatric Intensive Care Units (PICUs) play a vital role in addressing the high mortality rate among children under five, with 5.4 million deaths annually (UNICEF, 2023). Children are particularly vulnerable to infections and critical conditions, necessitating specialized care due to their developing immune systems. However, the limited availability of PICUs and the high cost of medical equipment demands the need for optimizing resource use in these settings. The increasing volume of real-time data like vital signs, lab results, and clinical documentation creates complexity in decision-making, which requires advanced data analysis techniques for timely interventions and improved outcomes. This research introduces the PediatricCare PatternExplorer, a novel framework for mortality analysis in PICUs, employing Fuzzy C-Means clustering. Designed for Aga Khan University Hospital in Pakistan, the framework addresses key challenges such as data imputation, class imbalance, and feature selection, incorporating domain expertise to support clinicians in developing personalized care strategies. By evaluating clustering performance through metrics like the Xie-Beni index, this study aims to enhance the accuracy of risk stratification and improve care quality in PICUs. As the first comprehensive analysis of PICU mortality data in Pakistan, this research bridges a critical gap in local healthcare, offering a data-driven approach to improving pediatric critical care outcomes.
Document Type
Restricted Access
Submission Type
Thesis
Recommended Citation
Azam, S. (2023). PediatricCare PatternExplorer: A Fuzzy C-Means Based Framework for Mortality Analysis in the Pediatric ICU (Unpublished Unpublished graduate thesis). Retrieved from https://ir.iba.edu.pk/etd-ms-ds/3
