AI Is Revolutionizing Oncology With a Quantum Leap in Cancer Treatment

Artificial intelligence (AI) has revolutionized cancer research and treatment by identifying intricate patterns in medical data and providing quantitative evaluations of clinical conditions.¹ In today’s complex terrain of available medical data, AI can play a crucial role in enhancing traditional data analysis methods. Through the use of AI algorithms in image analysis and radiology, oncology professionals can detect subtle nuances in medical images, leading to early cancer detection and accurate diagnoses.² AI also has ensured a data-driven methodology for evaluating eligibility criteria, facilitating more inclusive trial design while maintaining safeguards for patient safety.³

Image credit: Have a nice day | stock.adobe.com

Additionally, AI’s impact has extended to optimizing clinical trials and refining patient recruitment through alignment with trial criteria. Notably, precision medicine has become a worldwide trend. Precision medicine refers to a medical treatment selection process by which the most appropriate treatment for each patient is identified based on a vast amount of medical data, such as genome information.² Through real-time monitoring and integration of electronic health records, AI can support comprehensive patient management.

AI and Cancer Detection

Despite considerable scientific advances, early and accurate cancer detection has remained a challenge.⁴ With the use of AI, there is renewed hope in significantly enhancing cancer detection, as evidenced by the more than 20 FDA-approved AI models for mammography screening as of June 2023.⁵

The combination of technology and medicine has the potential to transform oncological treatment. The traditional approach to diagnosing cancer primarily revolved around biopsy, histological examinations under microscopes, and imaging tests such as MRI, CT, and PET scan.⁶ With these traditional approaches, the interpretation of imaging results could vary among professionals, and specific diagnostic procedures can be invasive or uncomfortable.⁷

However, AI systems, especially those using deep learning techniques, can analyze medical images with staggering accuracy. Trained on vast public domain cancer data sets, AI can detect minute anomalies often missed by the human eye, reducing false negatives. Using large sets of patient data, AI can potentially identify patients at higher risk for specific types of cancer, such as breast and skin cancer, because of family history, obesity, exposure to workplace hazards, or other health factors, allowing for early screenings.

AI has the potential to revolutionize cancer detection. Google’s DeepMind project, in collaboration with the United Kingdom’s National Health Service, created an AI system that surpasses human doctors in spotting more than 50 eye diseases using 3D scans.⁸ The implications for similar technology in spotting tumors in CT or MRI scans have been immense. Additionally, PathAI uses AI in pathology to aid in diagnosing diseases, including cancer. Its platform has helped pathologists identify patterns more effectively, ensuring everything that can be detected is detected.⁹

AI and Pharmacologic Treatment

AI and machine-based learning (MBL) are now able to predict which cancer treatments a patient might respond best to. A study by Gerdes et al verified this using data from 48 cell lines and validated it with 53 cancer cell models and 36 primary cases of acute myeloid leukemia.¹⁰ MBL can help prioritize drugs by supplementing clinical and mutational analysis.

The use of electronic systems for chemotherapy prescriptions has resulted in the accumulation of a significant amount of patient data for analysis. For example, MBL can predict individual risk of neutropenia. Holborow et al compared MBL to logistic regression and created a web app for associated risk prediction.¹¹

Li et al identified a set of drug pairs showing better results in treating breast cancer using advanced MBL techniques. This study offered valuable insights to guide efforts in developing drug combination treatments. This approach could be a promising solution to improve treatment outcomes and overcome drug resistance.12

A study by Manz et al involving 20,506 patients with cancer found that MBL interventions can improve cancer care delivery. The intervention led to a significant increase in serious illness conversations for highrisk patients and a decrease in end-of-life systemic therapy for outpatients with cancer.¹³

Challenges for AI and Cancer Treatment

The benefit of AI does not lie in the potential to use it to disregard human expertise. Health care providers possess valuable experience and intuition that AI cannot duplicate. An optimal situation involves a joint effort where AI assists physicians rather than taking their place.

However, there are concerns regarding the regulation of AI tools. According to Jaber’s research, more than 60 medical devices or algorithms that use AI received FDA approval in 2022.¹⁴ However, MBL algorithms have continued to change as they encounter new data, as noted by Benjamens et al in 2020.¹⁵ In response, the FDA established a monitoring framework for AI technologies that allowed for adoption in 2019.¹⁶

Regulatory challenges must be addressed to guarantee that AI is used safely and effectively in health care. The FDA’s attempt to establish monitoring frameworks for AI technologies is a positive step toward achieving this. By carefully addressing ethical and practical concerns, AI has the potential to become one of the most powerful tools in the battle against cancer.

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.

Monisha Gupta, PhD, is an assistant professor in the Marketing, Management Information Systems, and Entrepreneurship Division at the Lewis College of Business at Marshall University in Huntington, West Virginia.

Craig Kimble, PharmD, MBA, MS, BCACP, is director of experiential learning, manager of clinical support services, and associate professor in the Department of Pharmacy Practice, Administration, and Research at Marshall University School of Pharmacy in Huntington, West Virginia.

References

1. Huynh E, Hosny A, Guthier C, et al. Artificial intelligence in radiation oncology. Nat Rev Clin Oncol. 2020;17(12):771-781. doi:10.1038/s41571-020-0417-8

2. Hamamoto R, Suvarna K, Yamada M, et al. Application of artificial intelligence technology in oncology: towards the establishment of precision medicine. Cancers (Basel). 2020;12(12):3532. doi:10.3390/cancers12123532

3. Liu R, Rizzo S, Whipple S, et al. Evaluating eligibility criteria of oncology trials using real-world data and AI. Nature. 2021;592(7855):629-633. doi:10.1038/s41586-021-03430-5

4. Bi WL, Hosny A, Schabath MB, et al. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin. 2019;69(2):127-157. doi:10.3322/caac.21552

5. Taylor CR, Monga N, Johnson C, Hawley JR, Patel M. Artificial intelligence applications in breast imaging: current status and future directions. Diagnostics (Basel). 2023;13(12):2041. doi:10.3390/diagnostics13122041

6. How cancer is diagnosed. National Cancer Institute. Updated January 17, 2023. Accessed September 15, 2023. https://www.cancer.gov/about-cancer/diagnosis-staging/diagnosis

7. Waite S, Scott J, Colombo D. Narrowing the gap: imaging disparities in radiology. Radiology. 2021;299(1):27-35. doi:10.1148/radiol.2021203742

8. De Fauw J, Ledsam JR, Romera-Paredes B, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med. 2018;24(9):1342-1350. doi:10.1038/s41591-018-0107-6

9. Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A. Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology. Nat Rev Clin Oncol. 2019;16(11):703-715. doi:10.1038/s41571-019-0252-y

10. Gerdes H, Casado P, Dokal A, et al. Drug ranking using machine learning systematically predicts the efficacy of anti-cancer drugs. Nat Commun. 2021;12(1):1850. doi:10.1038/s41467-021-22170-8

11. Holborow A, Coupe B, Davies M, Zhou S. Machine learning methods in predicting chemotherapy-induced neutropenia in oncology patients using clinical data. Clin Med (Lond). 2019;19(suppl 3):89-90. doi:10.7861/clinmedicine.19-3s-s89

12. Li J, Zhou Z, Dong J, et al. Predicting breast cancer 5-year survival using machine learning: a systematic review. PLoS One. 2021;16(4):e0250370. doi:10.1371/journal.pone.0250370

13. Manz CR, Zhang Y, Chen K, et al. Long-term effect of machine learning-triggered behavioral nudges on serious illness conversations and end-of-life outcomes among patients with cancer: a randomized clinical trial. JAMA Oncol. 2023;9(3):414-418. doi:10.1001/jamaoncol.2022.6303

14. Jaber N. Can artificial intelligence help see cancer in new, and better, ways? National Cancer Institute. March 22, 2022. Accessed September 4, 2023. https://www.cancer.gov/news-events/cancer-currents-blog/2022/artificial-intelligence-cancer-imaging

15. Benjamens S, Dhunnoo P, Meskó B. The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database. NPJ Digit Med. 2020;3:118. doi:10.1038/s41746-020-00324-0

16. Artificial intelligence and machine learning (AI/ML)-enabled medical devices. FDA. Updated October 5, 2022. Accessed September 15, 2023. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices