The diagnosis of cancer is a daunting experience for patients as well as for physicians, especially in navigating the complex landscape of treatment options. From genetic mutations to medical histories, there are numerous factors to consider when making decisions about cancer care. However, artificial intelligence (AI) has the potential to transform cancer diagnosis and treatment by integrating and analyzing vast amounts of patient data from various sources.

A 2022 review paper by Acosta and colleagues highlights the multiple data modalities that AI can integrate to improve the quality and efficiency of decision-making for cancer care [1]. While AI cannot replace the medical care team, it can provide valuable insights by analyzing genetic data, histological information, wearable data, and medical history to inform the team about a patient's prognosis and care.

One promising application of AI in cancer care is the prediction of adverse drug reactions based on genetic polymorphisms in patients [2]. This approach has been effective in identifying potential drug–drug interactions, improving patient outcomes, and reducing adverse effects. Furthermore, AI provides a means of predicting drug reactions that are multifactorial in nature, enabling physicians to choose the best drug for a patient on the first try.

Another potential application of AI in cancer care is the selection of the most appropriate treatment for a patient. For example, a 2020 study by Howard used machine learning to guide adjuvant chemotherapy in patients with head and neck cancer [3]. By analyzing patient information, the researchers were able to predict which patients would benefit most from chemotherapy and minimize the risk of adverse effects. The use of AI-based tools is already translating to a clinical setting to provide risk-stratification and guide post-surgical treatments for patients in multiple disease sites. For example, Oncotype-Dx is a commercially available diagnostic tool that uses the genetic profile from a sample of cancer tissue to predict cancer recurrence and benefit of chemotherapy in breast cancer patients [4,5].

In conclusion, AI has the potential to revolutionize cancer care by integrating and analyzing vast amounts of patient data from various sources. By leveraging the power of AI we can improve precision medicine and oncology, unlocking the potential of constantly growing data to provide more tailored treatment options and improve outcomes. A future where cancer diagnosis and treatment are uniquely personalized to each patient based on a comprehensive analysis of patient data is within reach.

References

1. Acosta, J.N., Falcone, G.J., Rajpurkar, P. et al. Multimodal biomedical AI. Nat Med 28, 1773–1784 (2022). https://doi.org/10.1038/s41591-022-01981-2

2. Tod M, Nkoud-Mongo C, Gueyffier F. Impact of genetic polymorphism on drug-drug interactions mediated by cytochromes: a general approach. AAPS J. 2013 Oct;15(4):1242-52. doi: 10.1208/s12248-013-9530-2. Epub 2013 Sep 12. PMID: 24027036; PMCID: PMC3787231.

3. Howard FM, Kochanny S, Koshy M, Spiotto M, Pearson AT. Machine Learning–Guided Adjuvant Treatment of Head and Neck Cancer. JAMA Netw Open. 2020;3(11):e2025881. doi:10.1001/jamanetworkopen.2020.25881

4. You YN, Rustin RB, Sullivan JD. Oncotype DX(®) colon cancer assay for prediction of recurrence risk in patients with stage II and III colon cancer: A review of the evidence. Surg Oncol. 2015 Jun;24(2):61-6. doi: 10.1016/j.suronc.2015.02.001. Epub 2015 Feb 14. PMID: 25770397.

5. Zhang S, Fitzsimmons KC, Hurvitz SA. Oncotype DX Recurrence Score in premenopausal women. Ther Adv Med Oncol. 2022 Mar 10;14:17588359221081077. doi: 10.1177/17588359221081077. PMID: 35295864; PMCID: PMC8918761.