International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 02 | Feb 2025
p-ISSN: 2395-0072
www.irjet.net
Predicting the Impact on Re-admission Rates for Hospitalized Diabetic Patient Achala Harsha¹, Chethan Nazre S², Chethana M³, Hithaishi M´, Nithin Kµ ¹ Department of Information Science, Malnad College of Engineering, Hassan, Karnataka, India ² Department of Information Science, Malnad College of Engineering, Hassan, Karnataka, India ³ Department of Information Science, Malnad College of Engineering, Hassan, Karnataka, India ⁴ Department of Information Science, Malnad College of Engineering, Hassan, Karnataka, India ⁵Assistant Professor, Department of Information Science, Malnad College of Engineering, Hassan, Karnataka, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract — Hospital readmissions among diabetic patients
Addressing this critical issue involves the intensive data analysis throughout the research process. This study is a secondary analysis using machine learning methods. Our goal of the analysis is to find the determining factors that lead to higher readmission and correspondingly being able to predict which patients will get readmitted. Therefore, we proposed two research questions:
pose serious health risks and financial burdens. This study uses machine learning to predict 30-day readmissions, with XGBoost achieving the highest accuracy (94%). Key factors like inpatient visits, hospital stay duration, and diagnoses play a crucial role in readmission risk. These insights can help improve patient care and reduce unnecessary hospital visits.
1) What approaches can we utilize to effectively predict hospital readmission within this dataset?
Keywords— Hospital readmission, diabetes, machine learning, XGBoost, predictive modeling, inpatient visits, hospital stay duration, medication changes, healthcare analytics.
2) Which factors are the most significant indicators of hospital readmission among diabetic patients?
1. INTRODUCTION
The remainder of this paper is structured as follows: In Section 2, we provide a concise summary of previous research and highlight the existing gaps in the literature. Section 3 will detail the methodology employed in this study, encompassing the description of the dataset and the analytical procedures. This entails data processing, exploratory analysis, feature engineering, as well as modeling and evaluation. Section 4 presents the results and discussion in relation to each research question, followed by the conclusion and recommendations for future work in Section 5.
In the past decades, readmissions to the hospitals have become an aspect of the retrospectives and prospective research that sought to eliminate it from the hospitals [1]. A patient who gets readmitted in a hospital within a specified period after he or she was discharged from the same hospital is referred to as a hospital readmission. The occurrence of readmission to the hospital for some selected diseases in particular shows the standard of the hospital. In other word, it shows that the first admission did not give adequate care to the patient and hence the life of the patient is at risk. Furthermore, the cost of care is negatively affected by the increased rate of hospital revisits. More specifically, 30-day hospital readmission rates were relatively high among older and higher risk patients [2]. It stated that venting factors would cost the American hospitals more than $26 billion on average on each patient. Instead of Americans, patients with diabetes, they have a greater risk of incurring more costs. Out of all the expenses the US had on diabetic patients in 2011, $41 billion was incurred by patients who were readmitted within 30 days 4. Advocating for higher standards and minimizing unnecessary expenses, the United States congress enacted the Hospital Readmission Reduction Program (HRRP). Consequently, beginning in October 2012, the Centers for Medicare, and Medicaid Services (CMS) initiated policies that financially minimize repayment incapability hospitals.
© 2025, IRJET
|
Impact Factor value: 8.315
2. RELATED WORK Numerous prior investigations have examined the risk factors associated with readmission rates across various disease types. For instance, one study [6] conducted a broad analysis aimed at predicting hospital readmissions without concentrating on a specific illness. In the context of diabetic patients, other research efforts [7] [8] [9] have concentrated on subsets of the diabetic population and utilized smaller datasets. When assessing readmission rates, certain studies have emphasized the role of demographic and socioeconomic variables that may affect these rates [10]. For example, research by [11] highlighted age as a significant factor, revealing that both acute and chronic glycemic control impacted readmission risk for individuals aged 65 and older, based on data from 29,000 patients. Additionally, [12] investigated the correlation
|
ISO 9001:2008 Certified Journal
|
Page 320