@InProceedings{10.1007/978-3-032-28463-1_18,
author="Deshpande, Aprameya
and \textbf{Anandaswarup Vadapalli}
and Prahallad, Lavanya",
editor="Arabnia, Hamid R.
and Deligiannidis, Leonidas
and Shenavarmasouleh, Farzan
and Ghareh Mohammadi, Farid
and Amirian, Soheyla",
title="Predicting Hospital Readmission in Diabetic Patients Using Machine Learning Approaches",
booktitle="Emerging Trends in Health Informatics, Medical Devices, and Large Language Models",
year="2025",
publisher="Springer Nature Switzerland",
address="Cham",
pages="227--233",
abstract="Hospital readmission among diabetic patients remains a critical challenge in modern healthcare, reflecting both disease complexity and the quality of inpatient and post-discharge care. This study investigates the use of machine learning (ML) techniques to predict 30 day readmission risk and identify the most influential clinical factors contributing to it. Using the publicly available Diabetes Hospital Readmission Dataset from Kaggle, we trained and evaluated two predictive models, a Random Forest Decision Tree and a Deep Neural Network (DNN), after systematic data cleaning, normalization, and feature encoding.",
isbn="978-3-032-28463-1"
}