Predicting Healthcare Service Quality Based on a Kalman-Optimized Bi-LSTM-Inspired Deep Learning Model

Mohammed K. Al-Khafaji, Software Dept., Information Technology College, University of Babylon, Hilla, Iraq,Follow
Eman S. Al-Shamery, Software Dept., Information Technology College, University of Babylon, Hilla, Iraq

Abstract

Health is one of the most important aspects of human well-being, and access to high-quality healthcare is essential for a good quality of life. Providing top-level health services at all times is crucial. However, the research in healthcare poses significant challenges due to the diversity and variations of medical practices across different hospitals. This paper aims to tackle the challenge of data missing and scattering during data collection. Then, the quality of services (QoS) offered by healthcare facilities will be analyzed and predicted from the patient's perspective. The model begins preprocessing data by data cleaning, handling missing values, and scattering data using clustering, similarity techniques, and collaborative filtering methods. Then, it focuses on predicting QoS using a structured structure for bidirectional long short-term memory (Bi-LSTM) networks. Finally, the model employs a Kalman filter method to optimize prediction by reducing the squared error between the model prediction and the actual prediction. In this study, two types of databases were used. The first data was from Iraqi hospitals in various geographical areas: Al-Hillah General Teaching Hospital in Babylon (H1), Al-Kafeel Hospital in Karbala (H2), Al-Yarmouk Hospital in Baghdad (H3), and Diwaniyah Women's and Children's Hospital in Diwaniyah (H4). The data was collected through questionnaires in both manual and electronic form. The second data was obtained from United States hospitals; it was collected by the Centers for Medicare and Medicaid Services (CMS). The model achieved an accuracy of 98.4%, precision of 98 %, recall of 97.7 %, and F1-measure of 97.6 % with the U.S. hospital databases, outperforming many models such as deep learning techniques (LSTM and Bi-LSTM), regression, and random forest.

Recommended Citation

Al-Khafaji, Mohammed K. and Al-Shamery, Eman S. (2025) "Predicting Healthcare Service Quality Based on a Kalman-Optimized Bi-LSTM-Inspired Deep Learning Model," Karbala International Journal of Modern Science: Vol. 11 : Iss. 2 , Article 6.
Available at: https://doi.org/10.33640/2405-609X.3403