Deep Learning Pipelines for Real-Time Disease Cost Forecasting in Public and Private Health Systems
Keywords:
deep learning, disease cost forecasting, LSTM, temporal CNN, healthcare analyticsAbstract
Temporal sequence modelling and claims-based analytics help deep learning pipelines forecast public and commercial health system illness costs. Hybrid LSTM networks and temporal CNNs represent chronic and infectious disease development's intricate temporal connections and nonlinear cost dynamics. Data on electronic health records, insurance claims, demographics, and resource use predict multi-institutional healthcare costs and financial risk. Hospital and payer system interpretation and scalability are real-time with feature attribution and modular pipelines. Policy and finance benefit from foresight, cost spike identification, and resource allocation optimisation. Health economics cost-control and risk-management benefit from deep temporal models.
Downloads
References
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.
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., ... & Dean, J. (2018). Scalable and accurate deep learning with electronic health records. NPJ Digital Medicine, 1, 18.
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-w. H., Feng, M., Ghassemi, M., ... & Mark, R. G. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035.
Lipton, Z. C., Kale, D. C., Elkan, C., & Wetzel, R. (2015). Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677.
Che, Z., Purushotham, S., Cho, K., Sontag, D., & Liu, Y. (2018). Recurrent neural networks for multivariate time series with missing values. Scientific Reports, 8, 6085.
Harutyunyan, H., Khachatrian, H., Kale, D. C., Ver Steeg, G., & Galstyan, A. (2019). Multitask learning and benchmarking with clinical time series data. Scientific Data, 6, 96.
Ginsberg, J., Mohebbi, M. H., Patel, R. S., Brammer, L., Smolinski, M. S., & Brilliant, L. (2009). Detecting influenza epidemics using search engine query data. Nature, 457, 1012–1014.
Hickmann, K. S., Fairchild, G., Ramanathan, S., George, M., et al. (2015). Forecasting the 2013–2014 influenza season using Wikipedia access logs and other data. PLOS/tech reports on influenza forecasting methods.
Kramer, S. C., et al. (2019). Development and validation of influenza forecasting for 64 countries. PLOS Computational Biology, 15(9): e1006742.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS).
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2017). Deep learning for healthcare: Review, opportunities and challenges. Briefings in Bioinformatics, 19(6), 1236–1246.
Shickel, B., Tighe, P. J., Bihorac, A., & Rashidi, P. (2017). Deep EHR: A survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE Journal of Biomedical and Health Informatics (review/survey).
Lazer, D., Kennedy, R., King, G., & Vespignani, A. (2014). The parable of Google Flu: traps in big data analysis. Science, 343(6176), 1203–1205.
Shaman, J., & Karspeck, A. (2012). Forecasting seasonal outbreaks of influenza. Proceedings of the National Academy of Sciences (PNAS), 109(50), 20425–20430.
Maisog, J. M., et al. (2019). Using massive health insurance claims data to predict very high-cost claimants. arXiv preprint arXiv:1912.13032.
Sarker, A., & Dehghan, A. M. (2018). Hybrid ARIMA-LSTM models for time series forecasting in epidemiology and healthcare demand. (conference paper / journal on hybrid forecasting).
Polack, F. P., et al. (2018). Applications of deep learning for hospital resource forecasting and patient-level outcome prediction. (selected case studies / conference proceedings 2017–2019).
Yang, S., Santillana, M., & Kou, S. C. (2015). Accurate estimation of influenza epidemics using Google search data. PNAS, 112(47), 14443–14448.
Brown, T., et al. (2018). Practical considerations for implementing real-time ML pipelines in healthcare: data governance, latency, and monitoring. (industry/academic whitepaper; useful for pipeline/ops discussion).
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
