Applying the Deep Learning–Sector–Governance (DLSG) Framework to the U.S. Healthcare System: Opportunities, Deployment Pathways, and Policy‑Aligned Evaluation

Authors

1 College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, United States
2 School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, United States
3 Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA 30332, United States
4 Independent Researcher, Washington, DC 20004, United States
5 Tandon School of Engineering, New York University, Brooklyn, NY, 10012, United States
6 Computer and Information Science Department, Fordham University, Bronx, NY, 10458, United States
Corresponding author: ychen841@gatech.edu

DOI:

https://doi.org/10.63646/BCJZ4246

Keywords:

Deep Learning in Healthcare; AI Governance; Clinical Decision Support; Payment Integrity; Health System Evaluation; Digital Health Deployment

Abstract

The United States healthcare system faces persistent challenges in cost, access, quality, and administrative burden. Although deep learning (DL) has achieved strong performance in prediction and representation learning, real-world impact remains constrained by data heterogeneity, workflow integration, and regulatory and governance requirements. This paper adapts the Deep Learning–Sector–Governance (DLSG) framework to the U.S. healthcare context, positioning it as a deployment blueprint that aligns model design, sector workflows, and governance controls. We examine applications spanning clinical decision support, imaging triage, operations, administrative automation, and payment integrity, and outline evaluation strategies that prioritize safety, calibration, and policy-aligned outcomes over standalone accuracy metrics. Given the scale of documented improper payments and administrative burden in U.S. healthcare, governance-aligned efficiency and integrity gains could plausibly translate into about $30–60 billion in annual system-level savings, depending on adoption depth and sustained operational alignment. We argue that the primary contribution of DLSG is to improve in predictive accuracy and to increase the likelihood that algorithmic advances translate into measurable improvements in patient outcomes and system efficiency under real regulatory and operational constraints. In addition, this framework is in alignment with national health objectives such as those articulated in Healthy People 2030. 

How to Cite

Chen, Y., zhao, C., Zhong, Y., Wang, Z., Shi, J., & Zheng, W. (2025). Applying the Deep Learning–Sector–Governance (DLSG) Framework to the U.S. Healthcare System: Opportunities, Deployment Pathways, and Policy‑Aligned Evaluation. Journal of Technology Innovation and Society, 1(1), 95-109. https://doi.org/10.63646/BCJZ4246

References

Abràmoff, M. D., Lavin, P. T., Birch, M., Shah, N., & Folk, J. C. (2018). Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. NPJ Digital Medicine, 1(1). https://doi.org/10.1038/s41746-018-0040-6

American Medical Association. (2023). 2023 AMA prior authorization physician survey.

Bao, H., Deng, J., Xing, S., Zhong, Y., Shi, W., Marteau, B., Das, B., Shehata, B., Deshpande, S., & Wang, M. D. (2023). Rare heart transplant rejection classification using diffusion-based synthetic image augmentation. In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) (pp. 1–4). https://doi.org/10.1109/bhi58575.2023.10313377

Bodenheimer, T. (2005). High and rising health care costs. Part 1: Seeking an explanation. Annals of Internal Medicine, 142(10), 847–854. https://doi.org/10.7326/0003-4819-142-10-200505170-00010

Bodenheimer, T. (2005). High and rising health care costs. Part 2: Technologic innovation. Annals of Internal Medicine, 142(11), 932–937. https://doi.org/10.7326/0003-4819-142-11-200506070-00012

Centers for Disease Control and Prevention. (2022). CDC guideline for prescribing opioids for chronic pain. https://www.cdc.gov

Centers for Medicare & Medicaid Services. (2022). National health expenditures 2022 highlights. https://www.cms.gov/newsroom/fact-sheets/national-health-expenditures-2022-highlights

Centers for Medicare & Medicaid Services. (2023). Fiscal year 2023 improper payments fact sheet. https://www.cms.gov/newsroom/fact-sheets/fiscal-year-2023-improper-payments-fact-sheet

Centers for Medicare & Medicaid Services. (n.d.). Fraud prevention system (FPS). https://www.cms.gov

Chen, Y., Gao, Y., Yu, S., Zhao, C., & Lu, Y. (2026). Large language models in mental health: A systematic review of applications, innovations, and ethical challenges. Journal of Industrial Integration and Management, 1–33. https://doi.org/10.1142/s2424862225300042

Chen, Y., Zhao, C., & Gao, Y. (2025). Blockchain applications in health insurance: A review of applications, challenges, and prospects. Frontiers in Blockchain, 8. https://doi.org/10.3389/fbloc.2025.1699290

Chen, Y., Zhao, C., & Nie, C. (2025). Health insurance fraud detection: The role of feature engineering and preprocessing techniques. In Proceedings of the 2nd Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence (pp. 858–862). https://doi.org/10.1145/3745238.3745373

Chen, Y., Zhao, C., Xu, Y., Nie, C., & Zhang, Y. (2025). Deep learning in financial fraud detection: Innovations, challenges, and applications. Data Science and Management. https://doi.org/10.1016/j.dsm.2025.08.002

Chen, Z., Zhao, C., Zhao, M., Zhan, Q., Dong, Y., Zhao, S., Yu, S., Yao, C., Xie, Y., Dong, Z., Sun, Q., Liu, Y., Yu, C. H., Yang, H., & Wang, G. (2025). Rethinking subjective trust in LLM: Actualizing tangibility from uncertainty. https://doi.org/10.36227/techrxiv.176463545.53813864/v1

Cohen, J. P., Irvin, J., Ding, D., Kelly, K., & Rajpurkar, P. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv. https://arxiv.org/abs/1711.05225

De Fauw, J., Ledsam, J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., Askham, H., Glorot, X., O’Donoghue, B., Visentin, D., et al. (2018). Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature Medicine, 24(9), 1342–1350. https://doi.org/10.1038/s41591-018-0107-6

Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118. https://doi.org/10.1038/nature21056

Food and Drug Administration. (2018). FDA permits marketing of first medical device to use artificial intelligence to detect diabetic retinopathy. https://www.fda.gov/news-events/press-announcements/fda-permits-marketing-first-medical-device-use-artificial-intelligence-detect-diabetic

Food and Drug Administration. (2018). Software as a medical device (SaMD). https://www.fda.gov/medical-devices/digital-health-center-excellence/software-medical-device-samd

Food and Drug Administration. (2021). Artificial intelligence/machine learning (AI/ML)-based software as a medical device (SaMD) action plan. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-samd

Food and Drug Administration. (2025). 510(k) summary for Viz.ai LVO detection.

Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22), 2402. https://doi.org/10.1001/jama.2016.17216

Habib, A. R. (2025). Health care administrative costs. JAMA, 334(1), 89. https://doi.org/10.1001/jama.2025.3761

Himmelstein, D. U., Campbell, T., & Woolhandler, S. (2020). Health care administrative costs in the United States and Canada, 2017. Annals of Internal Medicine, 172(2), 134–142. https://doi.org/10.7326/m19-2818

Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L. W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Celi, L. A., & Mark, R. G. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3(1). https://doi.org/10.1038/sdata.2016.35

Levit, K. R., Freeland, M. S., & Waldo, D. R. (1990). National health care spending trends: 1988. Health Affairs, 9(2), 171–184. https://doi.org/10.1377/hlthaff.9.2.171

Li, E., Banerjee, S. S., Huang, S., Iyer, R. K., & Chen, D. (2021). Improved GPU implementations of the Pair-HMM forward algorithm for DNA sequence alignment. In Proceedings of the IEEE 39th International Conference on Computer Design (ICCD) (pp. 299–306). https://doi.org/10.1109/ICCD53106.2021.00055

Liao, R., Zhao, C., Li, J., Feng, W., Lyu, Y., Chen, B., & Yang, H. (2025). CATP: Cross-attention token pruning for accuracy-preserved multimodal model inference. In 2025 IEEE Conference on Artificial Intelligence (CAI) (pp. 1100–1104). https://doi.org/10.1109/cai64502.2025.00191

Lin, Z. (2025). Tax share analysis and prediction of kernel extreme learning machine optimized by vector weighted average algorithm. Advances in Economics, Management and Political Sciences, 194(1), 1–8. https://doi.org/10.54254/2754-1169/2025.24147

Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016). Deep patient: An unsupervised representation to predict the future of patients from electronic health records. Scientific Reports, 6. https://doi.org/10.1038/srep26094

Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019). Model cards for model reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency (pp. 220–229). https://doi.org/10.1145/3287560.3287596

Murff, H. J., FitzHenry, F., Matheny, M. E., Gentry, N., Kotter, K. L., Crimin, K., Dittus, R. S., Rosen, A. K., Elkin, P. L., Brown, S. H., & Speroff, T. (2011). Automated identification of postoperative complications within an electronic medical record using natural language processing. JAMA, 306(8). https://doi.org/10.1001/jama.2011.1204

Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. V. (2021). Federated learning for Internet of Things: A comprehensive survey. IEEE Communications Surveys & Tutorials, 23(3), 1622–1658. https://doi.org/10.1109/COMST.2021.3075439

Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447–453. https://doi.org/10.1126/science.aax2342

Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347–1358. https://doi.org/10.1056/NEJMra1814259

Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018). Scalable and accurate deep learning with electronic health records. npj Digital Medicine, 1(1). https://doi.org/10.1038/s41746-018-0029-1

Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C. P., et al. (2018). Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLOS Medicine, 15(11), e1002686. https://doi.org/10.1371/journal.pmed.1002686

Richman, B. D., Kaplan, R. S., Kohli, J., Purcell, D., Shah, M., Bonfrer, I., Golden, B., Hannam, R., Mitchell, W., Cehic, D., et al. (2022). Billing and insurance–related administrative costs: A cross-national analysis. Health Affairs, 41(8), 1098–1106. https://doi.org/10.1377/hlthaff.2022.00241

Tamo, J. B., Nnamdi, M. C., Lesbats, L., Shi, W., Zhong, Y., & Wang, M. D. (2023). Uncertainty-aware ensemble learning models for out-of-distribution medical imaging analysis. In IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 4243–4250). https://doi.org/10.1109/bibm58861.2023.10385418

Tomašev, N., Glorot, X., Rae, J. W., Zielinski, M., Askham, H., Saraiva, A., Mottram, A., Meyer, C., Ravuri, S., Protsyuk, I., et al. (2019). A clinically applicable approach to continuous prediction of future acute kidney injury. Nature, 572(7767), 116–119. https://doi.org/10.1038/s41586-019-1390-1

Topol, E. J. (2019). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 25(1), 44–56. https://doi.org/10.1038/s41591-018-0300-7

Tseng, P., Kaplan, R. S., Richman, B. D., Shah, M. A., & Schulman, K. A. (2018). Administrative costs associated with physician billing and insurance-related activities at an academic health care system. JAMA, 319(7), 691. https://doi.org/10.1001/jama.2017.19148

U.S. Congress. (2009). Health Information Technology for Economic and Clinical Health (HITECH) Act.

U.S. Department of Health and Human Services. (2013). HIPAA administrative simplification regulations: 45 CFR Parts 160, 162, and 164. https://www.hhs.gov/hipaa/for-professionals/privacy/laws-regulations/index.html

U.S. Department of Health and Human Services, Office of Disease Prevention and Health Promotion. (2024). Explore the new Healthy People 2030 leading health indicators infographics. https://odphp.health.gov/news/202412/explore-new-healthy-people-2030-leading-health-indicators-infographics

U.S. Department of Health and Human Services, Office of Inspector General. (2024). Health care fraud and abuse control program report, fiscal year 2023. https://oig.hhs.gov/reports

U.S. Department of Health and Human Services, Office of Inspector General. (2025). Medicaid program integrity and improper payments.

U.S. Government Accountability Office. (2024, April 16). Medicare and Medicaid: Additional actions needed to enhance program integrity and save billions (GAO-24-107487). https://www.gao.gov/products/gao-24-107487

Vickers, A. J., & Elkin, E. B. (2006). Decision curve analysis: A novel method for evaluating prediction models. Medical Decision Making, 26(6), 565–574. https://doi.org/10.1177/0272989X06295361

Wiens, J., Saria, S., Sendak, M., Ghassemi, M., Liu, V. X., Doshi-Velez, F., Jung, K., Heller, K., Kale, D., Saeed, M., et al. (2019). Do no harm: A roadmap for responsible machine learning for health care. Nature Medicine, 25(9), 1337–1340. https://doi.org/10.1038/s41591-019-0548-6

Wolff, R. F., Moons, K. G. M., Riley, R. D., Whiting, P. F., Westwood, M., Collins, G. S., Reitsma, J. B., Kleijnen, J., & Mallett, S. (2019). PROBAST: A tool to assess the risk of bias and applicability of prediction model studies. Annals of Internal Medicine, 170(1), 51–58. https://doi.org/10.7326/m18-1376

Wong, A., Otles, E., Donnelly, J. P., Krumm, A., McCullough, J., DeTroyer-Cooley, O., Pestrue, J., Phillips, M., Konye, J., Penoza, C., Ghous, M., & Singh, K. (2021). External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients. JAMA Internal Medicine. https://doi.org/10.1001/jamainternmed.2021.2626

Wynants, L., Van Calster, B., Collins, G. S., Riley, R. D., Heinze, G., Schuit, E., Albu, E., Arshi, B., Bellou, V., Bonten, M. M. J., et al. (2020). Prediction models for diagnosis and prognosis of COVID-19: Systematic review and critical appraisal. BMJ, m1328. https://doi.org/10.1136/bmj.m1328

Zhong, Y., Shi, W., Tamo, J. B., Nnamdi, M. C., Yuan, Y., & Wang, M. D. (2025). Multi-agent LLM reasoning for clinical procedure sequencing from high-granularity EHR data. In Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 1–12). https://doi.org/10.1145/3765612.3767238

Zhong, Y., Xu, J., Marteau, B., Tan, S. Q. Y., & Wang, M. D. (2025). Anatomically constrained near-eye gaze tracking and movement classification using transformer. In IEEE International Conference on Healthcare Informatics (ICHI) (pp. 280–287). https://doi.org/10.1109/ichi64645.2025.00040