Optimizing Oncological Care: The Influence of AI on Insurance Approvals

Pharmacy Practice in Focus: OncologyApril 2024
Volume 6
Issue 3

Successful integration demands overcoming various hurdles.

Artificial intelligence -- Image credit: Shuo | stock.adobe.com

Image credit: Shuo | stock.adobe.com

About the Authors

Brian Cox, MBA, MSSF, FACHE, is the director of hospital operations and IT/CIT at Baptist Health System in New Albany, Indiana.

Alberto Coustasse, DrPH, MD, MBA, MPH, is a professor in the Health Informatics Program in the Management and Health Care Administrative Division at the Lewis College of Business at Marshall University in South Charleston, West Virginia.

Within the United States, oncological treatments represent a considerable portion of the health care landscape, in terms of both their prevalence and associated costs. The year 2022 witnessed 1.9 million new cancer cases and over 600,000 cancer-related deaths, signaling the pressing need for efficient strategies in managing and addressing challenges in oncology.1

The financial weight of cancer care is striking, with the total national expenditure on cancer care reaching approximately $208.9 billion in 2020. This substantial cost encompasses direct medical expenses and indirect costs such as productivity loss due to illness and premature death.2,3 These figures underscore the critical need to optimize oncological processes to ensure timely and accessible patient care.

Challenges in Oncological Treatment Authorization

Managing prior authorization (PA) and insurance approvals in oncology has always presented a considerable challenge. These intricate processes involve numerous stakeholders and can cause significant delays, ultimately impeding patients’ access to critical treatments.4 Studies have demonstrated that these delays have a considerable impact, with essential services such as imaging and chemotherapy experiencing an average delay of 2 weeks.4 Additionally, some reports have shown that patients may abandon their recommended treatment plans due to the time-consuming and often complicated PA process.5

Furthermore, specific treatments, such as proton beam therapy, encounter remarkably high initial denial rates, reaching up to 60%. These denials lead to prolonged waiting periods, with patients enduring delays of up to 4 months before receiving approval.6,7 The administrative intricacies associated with obtaining insurance authorization for such treatments profoundly affect patient care, which helps to emphasize the urgent need for streamlined and efficient processes.4,8

AI Intervention in Streamlining Authorization Processes

Recent strides in artificial intelligence (AI) offer promising solutions to expedite and enhance the PA and insurance approval processes. For example, Health Care Service Corporation (HCSC) implemented AI and observed a resulting 1400 times faster processing rate for PA requests in 2022. This breakthrough significantly reduced processing times and enabled more efficient triaging of requests.9,10 However, it should be noted that the AI tools at HCSC only approve or forward the PA to a hands-on clinician reviewer and never deny claims.9

Studies suggest that using AI-based systems to standardize clinical data submissions and integrate electronic health records using the Fast Healthcare Interoperability Resources data standard can optimize these processes further.10 Standardization initiatives aim to alleviate administrative burdens and expedite treatment access for patients with cancer. Strategies such as developing specialty-oriented, tool-based approaches and incorporating national clinical guidelines into decision-making processes can also improve the efficiency and effectiveness of the authorization process.4,8

Financial Implications and Administrative Burdens

The financial strain imposed on health care institutions by the PA process has been substantial, with estimates indicating an annual cost of nearly $500,000 per institution for obtaining PA for radiation treatment–related services.11 Administrative hurdles, especially those related to PA policies, have significantly impeded clinical access to specific therapies, resulting in financial constraints within the health care system.8

Addressing the challenges and optimizing AI integration in oncological treatment processes necessitates overcoming various hurdles. Ensuring AI systems’ seamless integration and interoperability with existing health care infrastructures is paramount to their effective operation. Additionally, comprehensive data standardization across health care facilities is crucial to unlocking the full potential of AI in streamlining authorization processes and ultimately enhancing patient care.12

Burnout among providers due to the PA process is also an expected outcome, even for providers in training. A study of 313 radiation and medical oncology trainees found that 71% reported a concern for the quality of care declining, and 77.1% also reported decreased enthusiasm for their chosen profession as a result of the PA process.13

The Path Forward: Addressing Challenges and Optimizing AI Integration

Ensuring fairness and accuracy in AI algorithms is crucial. To achieve this, national clinical leaders and patient representatives should evaluate and certify the algorithms. Additionally, including patient representatives in the review board guarantees that the AI algorithms effectively incorporate patient needs, concerns, and values. This rigorous process ensures that expert-level decisions are made transparently and fairly.10

The integration of AI has the potential to significantly improve traditional methods of analyzing medical data for cancer detection and treatment.14 Collaborative efforts among stakeholders, technology developers, and regulatory bodies are pivotal in accelerating standardized AI solutions in oncology. These concerted endeavors catalyze improved authorization processes, ultimately enhancing patient access to timely and effective treatments.


1. Cancer facts & figures 2022. American Cancer Society. Accessed December 14, 2023. https://www.cancer.org/research/cancer-facts-statistics/all-cancer-facts-figures/cancer-facts-figures-2022.html
2. Mariotto AB, Enewold L, Zhao J, Zeruto CA, Yabroff KR. Medical care costs associated with cancer survivorship in the United States. Cancer Epidemiol Biomarkers Prev. 2020;29(7):1304-1312. doi:10.1158/1055-9965.EPI-19-1534
3. Financial burden of cancer care. National Cancer Institute. Updated August 2023. Accessed December 14, 2023. https://progressreport.cancer.gov/after/economic_burden
4. Chino F, Baez A, Elkins IB, Aviki EM, Ghazal LV, Thom B. The patient experience of prior authorization for cancer care. JAMA Netw Open. 2023;6(10):e2338182. doi:10.1001/jamanetworkopen.2023.38182
5. Smith AJB, Mulugeta-Gordon L, Pena D, et al. Prior authorization in gynecologic oncology: an analysis of clinical impact. Gynecol Oncol. 2022;167(3):519-522. doi:10.1016/j.ygyno.2022.10.002
6. Yu NY, Sio TT, Mohindra P, et al. The insurance approval process for proton beam therapy must change: prior authorization is crippling access to appropriate health care. Int J Radiat Oncol Biol Phys. 2019;104(4):737-739. doi:10.1016/j.ijrobp.2019.04.007
7. Chiang JS, Yu NY, Daniels TB, Liu W, Schild SE, Sio TT. Proton beam radiotherapy for patients with early-stage and advanced lung cancer: a narrative review with contemporary clinical recommendations. J Thorac Dis. 2021;13(2):1270-1285. doi:10.21037/jtd-20-2501
8. Gupta A, Khan AJ, Goyal S, et al. Insurance approval for proton beam therapy and its impact on delays in treatment. Int J Radiat Oncol Biol Phys. 2019;104(4):714-723. doi:10.1016/j.ijrobp.2018.12.021
9. Diamond F. How HCSC is using AI to speed up prior authorization. Fierce Healthcare. July 17, 2023. Accessed December 14, 2023. https://www.fiercehealthcare.com/payers/hcsc-using-augmented-and-artificial-intelligence-quicken-speed-prior-authorization
10. Lenert LA, Lane S, Wehbe R. Could an artificial intelligence approach to prior authorization be more human?. J Am Med Inform Assoc. 2023;30(5):989-994. doi:10.1093/jamia/ocad016
11. Bingham B, Chennupati S, Osmundson EC. Estimating the practice-level and national cost burden of treatment-related prior authorization for academic radiation oncology practices. JCO Oncol Pract. 2022;18(6):e974-e987. doi:10.1200/OP.21.00644
12. Williams E, Kienast M, Medawar E, et al. A standardized clinical data harmonization pipeline for scalable AI application deployment (FHIR-DHP): validation and usability study. JMIR Med Inform. 2023;11:e43847. doi:10.2196/43847
13. Kim H, Srivastava A, Gabani P, Kim E, Lee H, Pedersen KS. Oncology trainee perceptions of the prior authorization process: a national survey. Adv Radiat Oncol. 2021;7(2):100861. doi:10.1016/j.adro.2021.100861
14. Cox B, Coustasse A, Gupta M, Kimble C. AI is revolutionizing oncology with a quantum leap in cancer treatment. Pharmacy Times®. October 16, 2023. Accessed December 14, 2023. https://www.pharmacytimes.com/view/ai-is-revolutionizing-oncology-with-a-quantum-leap-in-cancer-treatment
Related Videos
pharmacy oncology, Image Credit: © Konstantin Yuganov - stock.adobe.com
Mayo Clinic oncology pharmacy
Therapy session -- Image credit: pressmaster | stock.adobe.com
Testicular cancer and prostate cancer concept. | Image Credit: kenchiro168 - stock.adobe.com
Multiple myeloma awareness -- Image credit: Fauzi | stock.adobe.com
© 2024 MJH Life Sciences

All rights reserved.