Logistic Regression for Personalized Hypertension Risk Profiling in Cloud-Integrated Healthcare Systems

• Published in: 2024 Asian Conference on Intelligent Technologies (ACOIT) pp. 1 - 6
• Main Authors: Saravanan, S., Ramya, S., Monikapreethi, S K, Kavididevi, Venkatesh, Kovarasan, Rajesh Kambattan, Sujatha, S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06.09.2024
• Subjects: Accuracy; Cloud Integration; Data models; Diseases; Healthcare Systems; Hypertension; Hypertension Risk; Logistic regression; Medical services; Personalized Medicine; Precision medicine; Predictive Modeling; Predictive models; Reliability; Risk management
• ISBN: 9798350374933
• DOI: 10.1109/ACOIT62457.2024.10939402

Advanced analytics for personalized chronic disease risk profiles are becoming possible as healthcare systems combine cloud-based technology. This work applies logistic regression (LR) models to cloud-integrated healthcare systems for personalized hypertension risk profiling. A large dataset of heterogeneous patient records was used to train and evaluate the LR model, including clinical characteristics and lifestyle variables. To assess the LR model's predictive accuracy in identifying high-risk hypertension patients and to provide a framework for personalized risk stratification that can be seamlessly integrated into cloud-based healthcare systems. The model's performance was rigorously cross-validated and compared to risk assessment methods. The LR approach predicted hypertension risk better than older techniques. Healthcare professionals and patients found the cloud integration of the personalized risk profiling system convenient, scalable, and accessible. It shows that cloud-based analytics may improve preventive healthcare by personalizing treatments to risk profiles. LR techniques can optimize personalized hypertension risk management in cloud-integrated systems, advancing data-driven healthcare.