Predictive Modeling of Future Trends in US Healthcare Data and Outcomes


Authors : Joseph Kobi; Amida Nchaw Nchaw; Dr. Brian Otieno

Volume/Issue : Volume 9 - 2024, Issue 7 - July

Google Scholar : https://tinyurl.com/ye2azj7y

Scribd : https://tinyurl.com/rwv2452d

DOI : https://doi.org/10.38124/ijisrt/IJISRT24JUL665

Abstract : Predictive modeling has great potential to help guide healthcare policymaking and planning through forecasting future trends in domains such as disease prevalence, resource utilization, and costs. However, past research in this area has been limited by mostly examining small, narrow datasets that only captured specific illnesses or geographic regions. This study aimed to leverage more sophisticated predictive analytics to generate informed estimations of the most consequential healthcare trends anticipated in the United States throughout the next decade. The analysis drew upon an extensive collection of over 50 million longitudinal electronic health records spanning a 5-year timeframe, comprehensive national public health statistics from the same period, and Medicare claims encompassing 72 million beneficiaries. Advanced machine learning techniques, including neural networks and Bayesian additive regression trees, were applied to identify nonlinear relationships and temporal patterns across 500 variables related to patient demographics, medical diagnoses, therapeutic procedures, reimbursement amounts, and clinical outcomes. Models were trained using data from 2010 to 2015 then utilized to project trends and forecasts for the years 2020 to 2025. Five-fold cross-validation testing was conducted to evaluate the accuracy and generalizability of the predictive models. The model projections indicate that chronic disease prevalence nationwide will rise by approximately 40% by the conclusion of 2025, primarily fueled by growing epidemics of obesity and an increasingly aging American population. Additionally, heart disease and stroke are estimated to maintain their positioning as leading causes of death, but cases of dementia and Alzheimer's disease specifically are projected to climb even more sharply at over a 50% increase. Healthcare costs on the whole are anticipated to rise on average between 4-6% annually, and costs may potentially double for elderly patients presenting with multiple morbidities. As outpatient and home-based care options expand further, inpatient hospital facility utilization may drop marginally between 10-15%. Improved management of chronic medical conditions within local community settings could reduce preventable hospital readmissions from 25-30%. Primary care, nursing, and mental healthcare roles are likely to face looming staffing shortages as well. Telehealth adoption is forecasted to surge by approximately 45% as virtual visit formats help address access obstacles. By 2025, biologics and gene therapies could account for over 25% of total drug spending pertaining to oncology and rare disease treatment. Larger Medicaid, Medicare, and ACA commercial coverage markets may motivate higher rates of health insurance enrollment over the next few years.

Keywords : Predictive Modeling, Predictive Analytics, Machine Learning, Artificial Intelligence, Future Trends, Healthcare Forecasting, Healthcare Policy, US Healthcare System.

References :

  1. Agirre, A., Begazo, M. J., Montejo, R., & Kubat, M. (2020). Clustering techniques for precision medicine: A survey. Computer methods and programs in biomedicine, 189, 105338. https://doi.org/10.1016/j.cmpb.2020.105338
  2. Ahmed, A. E., Al Zobidi, M., Tun, K. W., Mekala, D. M., & Alfuraih, A. A. (2020). Machine learning in healthcare: an updated overview. Yearbook of medical informatics, 29(1), e18-e29. https://doi.org/10.1055/s-0040-1708452
  3. Al Khalifa, S. (2021). Explainable AI readiness in healthcare: A multistakeholder perspective study. Journal of Biomedical Informatics, 114, 103693. https://doi.org/10.1016/j.jbi.2020.103693
  4. Alex Paul Kamson, L. N. Sharma, S. Dandapat, “Multi- Centroid Diastolic Duration Distribution based HSMM for Heart Sound Segmentation”, Biomedical Signal Processing and Control, ELSEVIER, ScienceDirect, vol 48, pp. 265-272, February 2019.
  5. Antonis S. Billis and Panagiotis D. Bamidis, “Employing Time-Series Forecasting to Historical Medical Data: An Application Towards Early Prognosis within Elderly Health Monitoring Environments”, Proceedings of the 3rd International Conference on Artificial Intelligence and Assistive Medicine AIAM’14, August 18th, 2014, Aachen, Germany, vol.1213, pp 31-35, 2014.
  6. Attia, Z. I., Njie, G., Lokoth, R., Krishnan, S., Samin, A., Henry, M., & Olajide, D. (2019). An overview of data mining techniques for predictive healthcare modeling. Data, 4(2), 64. https://doi.org/10.3390/data4020064
  7. Bhat, S., Chaudhary, K., Chaudhari, N. S., Dixit, P., & Jain, M. (2011). Application of data mining techniques in healthcare sector. International Journal of Scientific & Engineering Research, 2(4), 1-7.
  8. Billis, A. S., & Bamidis, P. D. (2014). Soft computing for clinical medicine: the road ahead. Studies in health technology and informatics, 205, 1066-1070.
  9. Cheng, R. C., & Nguyen, L. T. M. (2022). AI-based prediction in healthcare: a systematic literature review. Artificial Intelligence in Medicine, 121, 102263. https://doi.org/10.1016/j.artmed.2021.102263
  10. Crockett, J. (2017). Machine learning and medicine: What’s next? Computer, 50(11), 72-76. https://doi.org/10.1109/MC.2017.4121226 
  11. David Crockett, “Using Predictive Analytics in Healthcare: Technology Hype vs Reality”, An Executive Report in Health Catalyst, 2017.
  12. Dr Marc Siegel, “Brain Implants: Will they be used to Heal or for Control?”, Opinion, The Hill, 22/10/2018, 2019 Capitol Hill Publishing Corp., A Subsidiary of News Communications, Inc, 2019.
  13. Elnagar, A., & Güler, M. E. (2020). Healthcare predictive modeling and clinical decision support systems: A survey. International Journal of Computational Intelligence Systems, 13(1), 703-723. https://doi.org/10.2991/ijcis.d.200817.001
  14. Eskandari, M., Hashemi, S., Ghasem-Aghaee, N., & Hofmann, M. (2021). Soft computing for health informatics: A survey. Applied Soft Computing, 103, 107210. https://doi.org/10.1016/j.asoc.2021.107210
  15. Fevrier Valdez, Patricia Melin and Oscar Castillo, “A Survey on Nature-Inspired Optimization Algorithms with Fuzzy Logic for Dynamic Parameter Adaptation”, Expert Systems with Applications, Elsevier, ScienceDirect, vol.41, no. 14, pp 6459-6466, 15 October 2014.
  16. Ghassemi, M., Naumann, T., Doshi-Velez, F., Brimmer, N., Joshi, R., Rumshisky, A., & Ozair, S. (2019). Opportunities in machine learning for healthcare. arXiv preprint arXiv:1909.09251.
  17. Ho, T. K., Nguyen, T. T., Le, H. D., & Ho, M. T. (2020). Healthcare predictive analytics for risk profiling in chronic disease management—A real-world study of diabetic patients. IEEE Journal of Biomedical and Health Informatics, 24(8), 2316-2324. https://doi.org/10.1109/JBHI.2020.2970368
  18. Jiang, X., Huang, Z., & He, D. (2020). Healthcare data mining and medical knowledge graph. Annual Global Health and Nursing Colloquium, Hong Kong Polytechnic University. https://doi.org/10.13140/RG.2.2.17747.31760
  19. Jimmy Ming-Tai Wu, Meng-Hsiun Tsai, Yong Zhi Huang, SK Hafizul Islam, Mohammad Mehedi Hassan, Abdulhameed Alelaiwi, Giancarlo Fortino, “Applying an Ensemble Convolutional Neural Network with Savitzk-Golay Filter to Construct a Phonocardiogram Prediction Model”, Applied Soft Computing, ELSEVIER, ScienceDirect, vol 78, pp 29-40, May 2019.
  20. Maged Nasser, Naomie Salim, Hentabli Hamza, and Faisal Saeed, “Deep Belief Network for Molecular Feature Selection in Ligand-Based Virtual Screening”, Data Science, AI and IoT Trends for the Fourth Industrial Revolution, International Conference of Reliable Information and Communication Technology, Kuala Lumpur, Malaysia, on July 23–24, 2018. Advances in Intelligent Systems and Computing, Springer Nature Switzerland AG 2019, vol. 843, pp 3-14, 2019.
  21. Marathe, V. V., Tripathi, S., Wani, T. A., & Lagoo, J. (2021). Predictive modeling for healthcare: challenges and opportunities. International Journal of Medical Informatics, 153, 104542. https://doi.org/10.1016/j.ijmedinf.2021.104542
  22. Meeting Abstracts, BMC Complementary and Alternative Medicine, World Congress Integrative Medicine & Health, Berlin, Germany, 3–5 May 2017, vol 17(Suppl 1):322, pp 1-
  23. Moore, C. G., Carter, R. E., Nietert, P. J., & Stewart, P. W. (2011). Recommendations for planning pilot studies in clinical and translational research. Clinical and translational science, 4(5), 332-337. https://doi.org/10.1111/j.1752-8062.2011.00347.x
  24. Narayanan, C. K., Wai, C. L. J., & Chong, J. W. (2018). A novel genetic algorithm approach to optimize fuzzy logic control system parameters. Cogent Engineering, 5(1), 1526286. https://doi.org/10.1080/23311916.2018.1526286
  25. Qiang Yang and Xindong Wu, “10 Challenging Problems in Data Mining Research”, International Journal of Information Technology & Decision Making, vol. 05, No. 04, pp. 597-604, 2006.
  26. Ren, K., Zeng, Y., Yang, Y., Xiang, W., & Choo, K. K. R. (2022). Blockchain meets healthcare: A survey. Computers, 11(1), 10. https://doi.org/10.3390/computers11010010
  27. Thompson, M. J. A., White, C. C., Koeser, L., & Downing, N. L. (2019). Ethics of artificial intelligence in clinical medicine. Current problems in pediatric and adolescent health care, 49(10), 100627. https://doi.org/10.1016/j.cppeds.2019.100627  
  28. Tripathi, S., Del Fiol, G., Leo-Gura, G., & Saripalli, A. (2017). Natural language processing and public health: Analyzing text to improve population health. Yearbook of medical informatics, 26(1), 126-134. https://doi.org/10.15265/IY-2017-028
  29. Veena H Bhat, Prasanth Rao, Shiva Krishna, P. Deepa Shenoy, Venugopal K R, and Lalit M Patnaik, “An Efficient Framework for Prediction in Healthcare Data Using Soft Computing Techniques”, Proceedings of Advances in Computing and Communications - First International Conference, ACC 2011, Part III, July 22-24, 2011, Kochi, India, & Communications in Computer and Information Science, vol. 192, pp.522-532, July 2011.
  30. Wan Muhamad Taufik Wan Ahmad, Nur Laila Ab Ghani and Sulfeeza Mohd Drus, “Data Mining Techniques for Disease Risk Prediction Model: A Systematic Literature Review”, Data Science, AI and IoT Trends for the Fourth Industrial Revolution, International Conference of Reliable Information and Communication Technology, Kuala Lumpur, Malaysia, on July 23–24, 2018. Advances in Intelligent Systems and Computing, Springer Nature Switzerland AG 2019, vol. 843, pp 40-46, 2019.
  31. Yap, Bee Wah, Mohamed, Azlinah H, Berry, Michael W. (Eds.), Proceedings 4th IEEE International Conference on Soft Computing in Data Science SCDS 2018, August 15th-16th 2018, Bangkok, Thailand. Communications in Computer and Information Science, 2019 Springer Nature Switzerland AG, 2019

Predictive modeling has great potential to help guide healthcare policymaking and planning through forecasting future trends in domains such as disease prevalence, resource utilization, and costs. However, past research in this area has been limited by mostly examining small, narrow datasets that only captured specific illnesses or geographic regions. This study aimed to leverage more sophisticated predictive analytics to generate informed estimations of the most consequential healthcare trends anticipated in the United States throughout the next decade. The analysis drew upon an extensive collection of over 50 million longitudinal electronic health records spanning a 5-year timeframe, comprehensive national public health statistics from the same period, and Medicare claims encompassing 72 million beneficiaries. Advanced machine learning techniques, including neural networks and Bayesian additive regression trees, were applied to identify nonlinear relationships and temporal patterns across 500 variables related to patient demographics, medical diagnoses, therapeutic procedures, reimbursement amounts, and clinical outcomes. Models were trained using data from 2010 to 2015 then utilized to project trends and forecasts for the years 2020 to 2025. Five-fold cross-validation testing was conducted to evaluate the accuracy and generalizability of the predictive models. The model projections indicate that chronic disease prevalence nationwide will rise by approximately 40% by the conclusion of 2025, primarily fueled by growing epidemics of obesity and an increasingly aging American population. Additionally, heart disease and stroke are estimated to maintain their positioning as leading causes of death, but cases of dementia and Alzheimer's disease specifically are projected to climb even more sharply at over a 50% increase. Healthcare costs on the whole are anticipated to rise on average between 4-6% annually, and costs may potentially double for elderly patients presenting with multiple morbidities. As outpatient and home-based care options expand further, inpatient hospital facility utilization may drop marginally between 10-15%. Improved management of chronic medical conditions within local community settings could reduce preventable hospital readmissions from 25-30%. Primary care, nursing, and mental healthcare roles are likely to face looming staffing shortages as well. Telehealth adoption is forecasted to surge by approximately 45% as virtual visit formats help address access obstacles. By 2025, biologics and gene therapies could account for over 25% of total drug spending pertaining to oncology and rare disease treatment. Larger Medicaid, Medicare, and ACA commercial coverage markets may motivate higher rates of health insurance enrollment over the next few years.

Keywords : Predictive Modeling, Predictive Analytics, Machine Learning, Artificial Intelligence, Future Trends, Healthcare Forecasting, Healthcare Policy, US Healthcare System.

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe