Modeling Predictive Pathways for Chronic Disease Progression Using Temporal Data from Integrated Healthcare Information Networks
Keywords:
Chronic disease, predictive modeling, temporal data, healthcare networks, disease progression, machine learning, EHR, longitudinal dataAbstract
The increasing prevalence of chronic diseases necessitates predictive systems that can anticipate disease progression using large-scale temporal health data. Integrated healthcare information networks, aggregating patient-level data across time, offer a promising avenue for machine learning models to identify patterns in disease evolution. This study proposes a temporal modeling approach that utilizes sequential patient data to predict chronic disease pathways. Key findings demonstrate that temporal deep learning architectures outperform classical models, especially when embedded within clinical event-aware frameworks. The analysis draws from publicly available integrated data, revealing patterns in cardiovascular, diabetes, and renal disease trajectories.
References
Estiri, H., Strasser, Z.H., Murphy, S.N. (2021). High-throughput phenotyping with temporal sequences. JAMIA Open, 4(2), ooab030.
Choi, E., Bahadori, M.T., Schuetz, A., Stewart, W.F., Sun, J. (2016). RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism. NeurIPS.
Miotto, R., Li, L., Kidd, B.A., Dudley, J.T. (2016). Deep Patient: An unsupervised representation to predict the future of patients from the electronic health records. Scientific Reports, 6, 26094.
Nguyen, P., Tran, T., Wickramasinghe, N., Venkatesh, S. (2022). Predicting chronic disease using temporal deep learning models: A survey. ACM Computing Surveys, 55(3), 1–35.
Shickel, B., Tighe, P.J., Bihorac, A., Rashidi, P. (2018). Deep EHR: A survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE Journal of Biomedical and Health Informatics, 22(5), 1589–1604.
Zhang, Z., Liu, X., Wang, D., Li, Z. (2020). Dynamic progression modeling of CKD with LSTM networks. Journal of Biomedical Informatics, 103, 103381.
Lin, C., Karlson, E.W., Dligach, D., Miller, T., et al. (2019). Time-aware predictive modeling for healthcare using recurrent networks. Journal of Biomedical Informatics, 95, 103117.
Baytas, I.M., Xiao, C., Zhang, X., Wang, F., Jain, A.K., Zhou, J. (2017). Patient subtyping via time-aware LSTM networks. KDD, 65–74.
Zhao, J., Papapetrou, P., Asker, L., Boström, H. (2017). Learning from heterogeneous temporal data in EHRs for early detection of heart failure. BMC Med Informatics Decis Mak, 17(1), 112.
Rajkomar, A., Dean, J., Kohane, I. (2019). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347–1358.
Futoma, J., Hariharan, S., Heller, K., et al. (2017). Learning to detect sepsis with a multitask Gaussian process RNN classifier. MLHC.
Liu, F., Wang, Y., Zhang, Z., et al. (2018). Clinically interpretable and explainable medical predictions using attention-based neural networks. Bioinformatics, 34(8), 1366–1374.
Chen, R., Stewart, W.F., Sun, J. (2019). Leveraging EHR data for predictive modeling in chronic disease: Challenges and solutions. JMIR Medical Informatics, 7(4), e14244.
Razavian, N., Blecker, S., Schmidt, A.M., Smith-McLallen, A., et al. (2016). Population-level prediction of diabetes progression. Machine Learning for Healthcare Conference, 73–88.
Johnson, A.E.W., Pollard, T.J., Shen, L., Lehman, L.W.H., et al. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035.
