Treating Cancer with Artificial Intelligence: The Next Generation of Targeted Therapies

You are currently viewing Treating Cancer with Artificial Intelligence: The Next Generation of Targeted Therapies

Part 4 of an ongoing series

David Letsa, MD

Artificial intelligence (AI) is increasingly being used in healthcare to improve patient outcomes and streamline routine tasks. Some ways it is being applied include medical diagnosis, personalized medicine, and virtual healthcare.1,2 Introducing AI in the medical field has opened new opportunities in cancer care, especially for advanced practice providers (APPs), who are vital in managing patient care and treatment plans. Can AI be the key to the next generation of targeted cancer therapies and assist APPs?

Personalizing Patient Treatment

Each individual’s experience with cancer is different and can be affected by various factors such as genetics, lifestyle, and other medical conditions. AI’s application in cancer treatment can potentially transform this process. By utilizing machine learning and big data analytics, AI can help APPs with improved diagnostic capabilities, more precise forecasts of treatment results, and personalized treatment plans tailored to each patient’s unique needs.1,2

For example, AI algorithms can detect early signs of disease and help identify the most appropriate treatment. The Wisconsin Breast Cancer Center utilized a specific machine-learning algorithm that successfully diagnosed breast cancer with 98.53% accuracy.3

AI algorithms were designed to read mammograms for routine screenings and high-risk cases. These AI systems helped radiologists detect subtle signs that might indicate the early stages of breast cancer, thereby improving diagnostic accuracy and enabling timely interventions.3

Separately, an international team led by the University of Oxford and the University of Manchester applied AI to genomic data to identify 2 distinct subtypes of prostate cancer. This differentiation is based on the disease’s evolution and has significant implications for understanding disease progression and tailoring treatment strategies.4,5

By understanding a tumor’s specific genetic, cancer biomarkers, and molecular makeup, AI can help develop precision medicine treatments that target the particular vulnerabilities of the cancer cells. This can lead to more effective treatments with fewer side effects. Notably, these scientists revealed a new form of aggressive prostate cancer using AI, which could revolutionize diagnosis and treatment approaches.4,5

Also, AI can aid APPs by providing data-driven predictions from other institutions or physicians within the same institution when making treatment decisions. It can also predict cancer’s response to therapies by analyzing medical records and molecular data.5,6 However, one of the challenges to different AI systems in these healthcare domains is not whether the technologies will be capable enough to be helpful but rather ensuring their adoption in daily clinical practice.5,6

Studies show that AI can help determine which patients have the most potential to respond to certain chemotherapies or targeted therapies based on their health data and results. For instance, it was used to predict the survival of hepatocellular carcinoma, proving it could be a daily resource for APPs.7,8

AI in Identifying New Targets for Therapy

There are over 200 types of cancer, each unique based on their genetic profiles. Despite ongoing efforts to develop precision oncology treatments, persistent challenges remain since many cancers have a genetic basis.1,2,8

Much of the focus has been on developing genetic sequencing assays or analyses to identify and match those mutations with treatments that may work effectively against them. However, AI represents the next step in identifying new targets for cancer therapy as it can analyze complex biological data at an unprecedented scale, revealing novel targets that traditional biomarker tests and sequencing methods might overlook.2,8

AI algorithms can integrate various datasets—including genomic, proteomic, and clinical data—to uncover intricate patterns and interactions contributing to cancer progression and drug resistance. That enables the identification of previously unknown therapeutic targets and facilitates a more personalized and practical approach to cancer treatment.9,10

For example, AI-based tools are being explored to predict the mutational status of colorectal cancer, which can be crucial for treatment decisions. A review found that the AI model’s intense learning showed promising results in predicting mismatch repair deficiency status, with good performance in training cohorts. AI holds the potential to predict these crucial markers, but further research is needed to improve validation cohort performance, particularly for KRAS and BRAF mutations.11

AI in Predicting Response to Therapy

In another recent study published in Nature Cancer, researchers led by Sanju Sinha, PhD, Eytan Ruppin, MD, PhD, and Alejandro Schaffer, PhD, introduced a computational pipeline called PERCEPTION (Personalized Single-Cell Expression-Based Planning for Treatments in Oncology). This AI-based method utilizes transcriptomics to analyze the expression of transcription factors and messenger RNA molecules in single cells, providing valuable insights into patient response to cancer drugs.12

In the study discussed, the AI tool primarily focused on predicting patient responses to cancer drugs rather than identifying new therapeutic targets. The researchers utilized high-resolution gene expression data from individual tumor cells to enhance the predictive capability of PERCEPTION. Therefore, the AI’s principal application in this context was to match cancer drugs to patients more precisely based on their predicted therapeutic responses.12

The technology has already shown promising results in 3 clinical trials focusing on multiple myeloma, breast cancer, and lung cancer. Particularly noteworthy is the discovery made in the lung cancer trial, where PERCEPTION identified the development of drug resistance as the disease progressed, offering essential implications for future treatment strategies.12

Takeaway Points

Although understanding the genetic variants of cancer and their response to drugs and protocols has become complex for human clinicians, AI has the potential to revolutionize cancer treatment by providing personalized and precise treatment options through targeted therapies. The projected use of AI in clinical practice will become more extensive within the next 10 years.1,2,7

For AI systems to become widely adopted, regulators must first approve them. Furthermore, they need to be integrated with electronic health record (EHR) systems and standardized to a sufficient degree so that similar products work uniformly. Additionally, clinicians need to be trained in how to use these systems. Lastly, they must be paid for by public or private payer organizations and updated over time in the field.2,7

These challenges will eventually be overcome, but that will take much longer than it will for the technologies to mature. For APPs, integrating AI into cancer treatment translates to a tool that boosts their clinical acumen and saves time. AI’s promising potential to identify optimal targeted therapies, predict treatment responses, and suggest individualized dosing regimens can significantly enhance the care provided to cancer patients.1,7

As research progresses and AI becomes more integrated into clinical practice, APPs will find themselves at the forefront of using these cutting-edge technologies. Thus, staying informed about the latest developments in this field is essential. The intersection of AI and oncology is a dynamic and rapidly evolving area of medicine, with each breakthrough bringing new hope for patients battling cancer.

References

  1. Jallat F. (2023) How AI could dramatically improve cancer patients’ prognosis. December 24, 2023. The Conversation. https://theconversation.com/how-ai-could-dramatically-improve-cancer-patients-prognosis-216713
  1. Nia, N.G., Kaplanoglu, E., Nasab, A. (2023) Evaluation of artificial intelligence techniques in disease diagnosis and prediction. Discover Artificial Intelligence, 3. doi:10.1007/s44163-023-00049-5
  2. Aamir, S., Rahim, A., Aamir, Z., Abbasi, S. F., Khan, M. S., Alhaisoni, M., Khan, M. A., Khan, K., & Ahmad, J. (2022). Predicting Breast Cancer Leveraging Supervised Machine Learning Techniques. Computational and mathematical methods in medicine, 2022, 5869529. https://doi.org/10.1155/2022/5869529
  1. Woodcock, D. J., Sahli, A., Teslo, R., Bhandari, V., Gruber, A. J., Ziubroniewicz, A., Gundem, G., Xu, Y., Butler, A., Anokian, E., Pope, B. J., Jung, C. H., Tarabichi, M., Dentro, S. C., Farmery, J. H. R., CRUK ICGC Prostate Group, Van Loo, P., Warren, A. Y., Gnanapragasam, V., Hamdy, F. C., … Wedge, D. C. (2024). Genomic evolution shapes prostate cancer disease type. Cell genomics, 4(3), 100511. https://doi.org/10.1016/j.xgen.2024.100511
  2. Passaro, A., Al Bakir, M., Hamilton, E. G., Diehn, M., André, F., Roy-Chowdhuri, S., Mountzios, G., Wistuba, I. I., Swanton, C., & Peters, S. (2024). Cancer biomarkers: Emerging trends and clinical implications for personalized treatment. Cell, 187(7), 1617–1635. https://doi.org/10.1016/j.cell.2024.02.041
  3. Weerarathna, I. N., Kamble, A. R., & Luharia, A. (2023). Artificial Intelligence Applications for Biomedical Cancer Research: A Review. Cureus, 15(11), e48307. https://doi.org/10.7759/cureus.48307
  4. Lee, K. H., Choi, G. H., Yun, J., Choi, J., Goh, M. J., Sinn, D. H., Jin, Y. J., Kim, M. A., Yu, S. J., Jang, S., Lee, S. K., Jang, J. W., Lee, J. S., Kim, D. Y., Cho, Y. Y., Kim, H. J., Kim, S., Kim, J. H., Kim, N., & Kim, K. M. (2024). Machine learning-based clinical decision support system for treatment recommendation and overall survival prediction of hepatocellular carcinoma: a multi-center study. NPJ digital medicine, 7(1), 2. https://doi.org/10.1038/s41746-023-00976-8
  5. Davenport, T., & Kalakota, R. (2019). The potential for artificial intelligence in healthcare. Future healthcare journal, 6(2), 94–98. https://doi.org/10.7861/futurehosp.6-2-94
  6. You, Y., Lai, X., Pan, Y., Zheng, H., Vera, J., Liu, S., Deng, S., & Zhang, L. (2022). Artificial intelligence in cancer target identification and drug discovery. Signal transduction and targeted therapy, 7(1), 156. https://doi.org/10.1038/s41392-022-00994-0
  7. Perez-Lopez, R., Ghaffari Laleh, N., Mahmood, F., & Kather, J. N. (2024). A guide to artificial intelligence for cancer researchers. Nature reviews. Cancer, 24(6), 427–441. https://doi.org/10.1038/s41568-024-00694-7
  8. Guitton, T., Allaume, P., Rabilloud, N., Rioux-Leclercq, N., Henno, S., Turlin, B., Galibert-Anne, M. D., Lièvre, A., Lespagnol, A., Pécot, T., & Kammerer-Jacquet, S. F. (2023). Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review. Diagnostics (Basel, Switzerland), 14(1), 99. https://doi.org/10.3390/diagnostics14010099
  9. Sinha, S., Vegesna, R., Mukherjee, S., Kammula, A. V., Dhruba, S. R., Wu, W., Kerr, D. L., Nair, N. U., Jones, M. G., Yosef, N., Stroganov, O. V., Grishagin, I., Aldape, K. D., Blakely, C. M., Jiang, P., Thomas, C. J., Benes, C. H., Bivona, T. G., Schäffer, A. A., & Ruppin, E. (2024). PERCEPTION predicts patient response and resistance to treatment using single-cell transcriptomics of their tumors. Nature cancer, 10.1038/s43018-024-00756-7. Advance online publication. https://doi.org/10.1038/s43018-024-00756-7