Year: 2024
Type: article
Abstract: Predictive analytics is increasingly recognized as a transformative tool in healthcare, offering the potential to enhance clinical decision-making, reduce hospital readmission rates, and improve overall patient outcomes. At the core of these advancements is machine learning (ML), which enables the development of predictive models capable of analyzing vast amounts of patient data to uncover patterns and forecast health trajectories. This paper explores the application of ML techniques in healthcare predictive analytics, providing an overview of commonly employed algorithms, evaluating their effectiveness, and outlining key challenges and directions for future research. To illustrate the practical application, we present a case study that employs supervised learning models to predict patient readmission rates using real-world healthcare datasets. The comparative analysis of model accuracy highlights the strengths and limitations of different approaches in real-world clinical contexts. Findings suggest that ML-driven predictive analytics can significantly improve healthcare efficiency, reduce operational costs, and enhance patient care through early intervention and proactive risk management strategies.
Authors: Rasmila Lama, Sen Sen Oo, Birbal Tamang, Jinnat Ara, Md Imran Khan, Md Nazmul Islam
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W7082439454
FWCI:
Cites:
Cited by:
Related to: