ML-Based Risk Stratification of Patients Using Real-Time Clinical Streams on Cloud
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V1I2P105Keywords:
Machine Learning, Risk Stratification, Real-Time Clinical Streams, Predictive Modeling, MIMIC-III, LSTM, EHRAbstract
Current health care systems are struggling with many issues to provide temporal and customized services to sick patients. The inability to stratify real-time and precise patient-level risk is one of the burning issues regarding the rapid expansion of the volume of clinical information, which includes the use of wearable devices, bedside monitors, and Electronic Health Records (EHRs). Cloud computing solutions can be readily integrated into existing Machine Learning (ML) algorithms to provide promising risk stratification solutions, enabling scalable and real-time analytics. In this paper, an entire framework is provided to support real-time risk stratification to fulfil the original quest of using ML on real-time clinical data streams to stratify yet unidentified patients using a cloud framework. The suggested method can absorb heterogeneous health data, preprocess it, select meaningful features, and then utilise predictive models to assess risks in real-time. By the use of Apache Kafka, Spark Streaming, and ML libraries, like TensorFlow and Scikit-learn, the system is scalable and has a low-latency processing rate. In the methodology section, the exact procedure of data collection, data preprocessing, feature engineering, and model training in ICU conditions is described. The models, such as Random Forests, Gradient Boosting Machines (GBM) and Long Short-Term Memory (LSTM) networks, were trained on publicly available datasets, namely MIMIC-III, and validated based on accuracy, precision, recall, and F1-score. In comparison with others, LSTM models are the most accurate because they are temporally sensitive to a patient's vital signs. The findings underscore a significant increase in the early identification of patient deterioration, providing healthcare workers with a real-time decision-making system. Future implications are described by model explainability, expanding patient privacy, and connecting with the hospital information system
Downloads
References
[1] Knaus, W. A., Draper, E. A., Wagner, D. P., & Zimmerman, J. E. (1985). APACHE II: a severity of disease classification system. Critical care medicine, 13(10), 818-829.
[2] Vincent, J. L., Moreno, R., Takala, J., Willatts, S., De Mendonça, A., Bruining, H., ... & Thijs, L. G. (1996). The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure: On behalf of the Working Group on Sepsis-Related Problems of the European Society of Intensive Care Medicine (see contributors to the project in the appendix).
[3] Moody, G. B., & Mark, R. G. (2001). The impact of the MIT-BIH arrhythmia database. IEEE engineering in medicine and biology magazine, 20(3), 45-50.
[4] Goldberger, A. L., Amaral, L. A., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation, 101(23), e215-e220.
[5] Plourde, J., Arney, D., & Goldman, J. M. (2014, April). Openice: An open, interoperable platform for medical cyber-physical systems. In 2014 ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS) (pp. 221-221). IEEE.
[6] Johnson, A. E., Ghassemi, M. M., Nemati, S., Niehaus, K. E., Clifton, D. A., & Clifford, G. D. (2016). Machine learning and decision support in critical care. Proceedings of the IEEE, 104(2), 444-466.
[7] Liu, Y., Zhang, L., Yang, Y., Zhou, L., Ren, L., Wang, F., ... & Deen, M. J. (2019). A novel cloud-based framework for elderly healthcare services using a digital twin. IEEE Access, 7, 49088-49101.
[8] Kuo, M. H. (2011). Opportunities and challenges of cloud computing to improve health care services. Journal of Medical Internet Research, 13(3), e1867.
[9] Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018). Deep learning for healthcare: review, opportunities and challenges. Briefings in bioinformatics, 19(6), 1236-1246.
[10] Dueñas-Espín, I., Vela, E., Pauws, S., Bescos, C., Cano, I., Cleries, M., ... & Roca, J. (2016). Proposals for enhanced health risk assessment and stratification in an integrated care scenario. BMJ open, 6(4), e010301.
[11] Liyanage, H., Liaw, S. T., Jonnagaddala, J., Schreiber, R., Kuziemsky, C., Terry, A. L., & de Lusignan, S. (2019). Artificial intelligence in primary health care: perceptions, issues, and challenges. Yearbook of medical informatics, 28(01), 041-046.
[12] Lau, A. Y., & Staccini, P. (2019). Artificial intelligence in health: new opportunities, challenges, and practical implications. Yearbook of medical informatics, 28(01), 174-178.
[13] Zhao, X. H., Ma, S. N., Long, H., Yuan, H., Tang, C. Y., Cheng, P. K., & Tsang, Y. H. (2018). Multifunctional sensor based on porous carbon derived from metal–organic frameworks for real-time health monitoring. ACS applied materials & interfaces, 10(4), 3986-3993.
[14] Tokognon, C. A., Gao, B., Tian, G. Y., & Yan, Y. (2017). Structural health monitoring framework based on Internet of Things: A survey. IEEE Internet of Things Journal, 4(3), 619-635.]
[15] Ajerla, D., Mahfuz, S., & Zulkernine, F. (2019). A real‐time patient monitoring framework for fall detection. Wireless Communications and Mobile Computing, 2019(1), 9507938.
[16] AbuKhousa, E., Mohamed, N., & Al-Jaroodi, J. (2012). e-Health cloud: opportunities and challenges. Future Internet, 4(3), 621-645.
[17] Alexandru, A., Alexandru, C., Coardos, D., & Tudora, E. (2016). Healthcare, big data and cloud computing. WSEAS transactions on computer research, 4, 123-131.
[18] Morykwas, M. J., Simpson, J., Punger, K., Argenta, A., Kremers, L., & Argenta, J. (2006). Vacuum-assisted closure: state of basic research and physiologic foundation. Plastic and reconstructive surgery, 117(7S), 121S-126S.
[19] Gohil, I., Vilensky, J. A., & Weber, E. C. (2014). Vacuum phenomenon: clinical relevance. Clinical Anatomy, 27(3), 455-462.
[20] Lee, I. N., Liao, S. C., & Embrechts, M. (2000). Data mining techniques applied to medical information. Medical informatics and the Internet in medicine, 25(2), 81-102.
[21] Rosati, R. A., McNeer, J. F., Starmer, C. F., Mittler, B. S., Morris, J. J., & Wallace, A. G. (1975). A new information system for medical practice. Archives of Internal Medicine, 135(8), 1017-1024.
