Downloads: 1 | Views: 31 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1
Analysis Study Research Paper | Computer Science and Information Technology | United States of America | Volume 13 Issue 4, April 2024
Deciphering the Dynamics of Hospital Readmissions Patterns Using Supervised Machine Learning
Nithin Narayan Koranchirath [3]
Abstract: The challenge of reducing patient readmissions remains a pivotal concern within the healthcare sector, especially for elderly, given its implications for patient outcomes and healthcare economics. This study introduces an innovative approach, leveraging Linear regression model (LRM) and machine learning models, to dissect and predict the complex patterns of patient readmissions. This research is anchored in a robust methodology that encompasses the collection and preprocessing of data, application of LRM to distill the data into principal components, and the deployment of machine learning models on the transformed datasets. The core of this approach is the simplification of the multifaceted nature of healthcare data, enabling a deeper exploration of the determinants of readmissions. The findings of this research carry significant implications across several domains of healthcare, from clinical practice to policy formulation and resource management. By enabling more accurate patient risk stratification, healthcare providers can allocate interventions more effectively, concentrating efforts and resources on high-risk patients. Moreover, the insights derived from the analysis provide a strong evidence base for policymaking, aimed at addressing the underlying causes of readmissions. This facilitates the development of policies that can significantly impact patient care and healthcare system sustainability. A key outcome of this study is the advancement of personalized patient care. Through the identification of specific factors associated with readmissions, healthcare providers can create personalized care plans, reflecting a shift towards personalized medicine and improving patient satisfaction and outcomes. Furthermore, the continuous refinement of the analytical models promotes a culture of improvement, ensuring that healthcare services can adapt to emerging insights and maintain the relevance and accuracy of predictive models.
Keywords: Healthcare, Linear Regression Model (LRM), Supervised Machine Learning, Hospital Readmissions, Computer - Assisted Identification, population health management, big data; advanced analytics, personalized patient care, elderly care
Edition: Volume 13 Issue 4, April 2024,
Pages: 715 - 725