Predicting Mortality of Hospital-Acquired Infections Using Data Mining Techniques

نوع: Type: Thesis

مقطع: Segment: masters

عنوان: Title: Predicting Mortality of Hospital-Acquired Infections Using Data Mining Techniques

ارائه دهنده: Provider: nila kazemi

اساتید راهنما: Supervisors: Hamidreza Dezfoulian

اساتید مشاور: Advisory Professors: Salman Khazaii

اساتید ممتحن یا داور: Examining professors or referees: Solymani & Aghazadeh

زمان و تاریخ ارائه: Time and date of presentation: 2026

مکان ارائه: Place of presentation: 61

چکیده: Abstract: Hospital-acquired infections (HAIs), also known as healthcare-associated infections, represent a major challenge for healthcare systems and significantly contribute to increased mortality rates, prolonged hospital stays, and rising healthcare costs. With the widespread adoption of health information systems, large volumes of clinical and laboratory data are generated in healthcare institutions. Proper analysis of these data can uncover hidden knowledge and support more effective clinical decision-making. The aim of this study is to develop a data mining–based model for predicting mortality associated with hospital-acquired infections and identifying infection patterns and key risk factors. In this research, data related to patients with HAIs were collected and preprocessed, and data mining techniques such as classification and clustering were applied to analyze the dataset. The results demonstrate that data mining techniques can effectively identify high-risk factors, detect high-risk hospital units, and predict mortality rates among patients with hospital-acquired infections. Implementing such predictive models can enhance infection surveillance and control systems, reduce mortality rates, improve the quality of healthcare services, and lower treatment-related costs in healthcare facilities.