Transforming patient care machine learning and biomedical data for adaptive and real-time healthcare solutions
| dc.contributor.author | Kumaran, S. | |
| dc.contributor.author | Murugan, P. Sundara Bala | |
| dc.contributor.author | Sathish, A. | |
| dc.contributor.author | Geetha, D. Mohana | |
| dc.contributor.author | Venkatesan, T. | |
| dc.contributor.author | Ali, Guma | |
| dc.date.accessioned | 2026-05-07T12:04:20Z | |
| dc.date.available | 2026-05-07T12:04:20Z | |
| dc.date.issued | 2026-02-22 | |
| dc.description | This research advances real time personalized healthcare through a hybrid deep learning model combining CNN and LSTM for biomedical signal analysis. It improves early disease detection, reduces diagnostic delays, lowers healthcare costs, and enhances patient outcomes. It supports SDG 3 on good health and Uganda NDP IV goals on digital transformation and efficient health service delivery. | |
| dc.description.abstract | Patient treatment is undergoing a revolution that is the fusion of ML and biomedical information, which facilitates adaptive and real-time healthcare. The existing healthcare systems exist in the form of non-responsive to dynamic patient status static models, which lead to diagnostic and therapeutic delays. This paper presents a novel hybrid DL algorithm that uses CNNs and LSTM networks to process real-time biomedical signals to provide individualized monitoring and early anomaly detection. The CNN element determines the spatial characteristics in biomedical signals, and LSTM module distinguishes the temporal dependencies to provide accurate predictions of trends. The new model is trained and self-updates in real-time using the principles of reinforcement learning and optimizes its pre-dictive quality as it gains new experience. Dataset based real-world assessments indicate high accuracy in anomaly detection, lower response times, and improved patient outcomes. This enhances the early detection of diseases, simplification of treatments, and reduction in healthcare costs by integrating ML-based predic-tive analytics with real-time observations, where the possibilities of intelligent, data-driven, personalized patient care. | |
| dc.identifier.citation | Kumaran, S., Murugan, P. S. B., Sathish, A., Geetha, D. M., Venkatesan, T., & Ali, G. (2025, September). Transforming Patient Care Machine Learning and Biomedical Data for Adaptive and Real-Time Healthcare Solutions. In Congress on Intelligent Systems (pp. 221-233). Cham: Springer Nature Switzerland. | |
| dc.identifier.isbn | 978-3-032-18140-4 | |
| dc.identifier.uri | https://dir.muni.ac.ug/handle/20.500.12260/973 | |
| dc.language.iso | en | |
| dc.publisher | Springer | |
| dc.subject | Machine Learning in Healthcare | |
| dc.subject | Biomedical Data Analysis | |
| dc.subject | Real-Time Patient Monitoring | |
| dc.subject | Adaptive Healthcare Systems | |
| dc.subject | Predictive Analytics in Medicine | |
| dc.title | Transforming patient care machine learning and biomedical data for adaptive and real-time healthcare solutions | |
| dc.type | Book chapter |