How Does AI Support Targeted Cancer Therapy Selection?

By Rasit Dinc

Introduction

Cancer remains a formidable challenge in modern medicine, with its treatment often complicated by the heterogeneity of tumors and the diverse responses of patients to therapies. Traditional cancer treatments, such as chemotherapy and radiation, have long been the standard of care, but their lack of specificity can lead to significant side effects and variable efficacy. The advent of targeted therapies has marked a paradigm shift in oncology, offering treatments that are directed at specific molecular targets on cancer cells. This approach has the potential to be more effective and less toxic than conventional therapies. However, the success of targeted therapy hinges on the accurate selection of patients who are most likely to benefit from it. This is where Artificial Intelligence (AI) is making a profound impact.

The Role of AI in Understanding Cancer

Artificial intelligence is revolutionizing our ability to comprehend the complexities of cancer. By analyzing vast and diverse datasets, AI algorithms can identify patterns and correlations that are not apparent to human researchers. This capability is particularly valuable in understanding the mechanisms of cancer progression, which is a multifaceted process involving genetic mutations, dysregulated cell signaling pathways, and evasion of the immune system [1].

AI-powered tools can analyze genomic, proteomic, and imaging data to create comprehensive models of tumors and their microenvironments. For instance, deep learning models, a subset of AI, can analyze histopathology images to identify tumor-infiltrating lymphocytes, which are a key indicator of the immune response to cancer. This information can be used to predict which patients are more likely to respond to immunotherapy [2]. By integrating data from multiple sources, AI can help to create a more complete picture of the tumor and its vulnerabilities, paving the way for more effective and personalized treatment strategies.

AI-Driven Targeted Therapy Selection

One of the most significant contributions of AI in oncology is its ability to guide the selection of targeted therapies. AI algorithms can analyze a patient's genomic data to identify specific mutations or biomarkers that are associated with a response to a particular drug. This process, known as biomarker discovery, is crucial for matching patients with the most effective treatments.

For example, machine learning models can be trained on large datasets of cancer patients to identify complex patterns that predict drug sensitivity. These models can integrate various types of data, including gene expression, DNA methylation, and protein levels, to create a highly accurate predictive model. This allows oncologists to move beyond a one-size-fits-all approach and select therapies that are tailored to the individual patient's tumor biology [3].

Furthermore, AI can help to identify novel drug targets. By analyzing the vast landscape of cancer genomics, AI algorithms can uncover new genes or pathways that are critical for cancer cell survival. This information can be used to develop new targeted therapies that are more effective and have fewer side effects than existing treatments.

Challenges and Future Directions

Despite the immense potential of AI in targeted cancer therapy, there are several challenges that need to be addressed before it can be widely implemented in clinical practice. One of the main challenges is the need for large, high-quality datasets to train AI models. The performance of AI algorithms is highly dependent on the quality and diversity of the data they are trained on. Therefore, it is crucial to have access to large, well-curated datasets that are representative of the patient population.

Another challenge is the "black box" nature of some AI models. Deep learning models, for example, can be very complex and difficult to interpret. This lack of transparency can be a barrier to their adoption in clinical practice, as clinicians need to be able to understand how the models are making their predictions. Therefore, there is a growing need for the development of explainable AI (XAI) models that can provide insights into their decision-making process.

Despite these challenges, the future of AI in targeted cancer therapy looks promising. As AI technology continues to evolve and more data becomes available, we can expect to see even more sophisticated AI-powered tools that can help to guide the selection of targeted therapies and improve patient outcomes. The integration of AI with other technologies, such as CRISPR-based gene editing, could open up new avenues for cancer treatment.

Conclusion

In conclusion, AI is poised to revolutionize the field of oncology by enabling a more personalized and effective approach to cancer treatment. By leveraging the power of AI, we can gain a deeper understanding of the complex biology of cancer and develop more targeted and effective therapies. While there are still challenges to overcome, the integration of AI into clinical practice has the potential to significantly improve the lives of cancer patients.

References

[1] Khorsandi, D., Farahani, A., Zarepour, A., Khosravi, A., Iravani, S., & Zarrabi, A. (2025). Bridging technology and medicine: artificial intelligence in targeted anticancer drug delivery. RSC Advances, 15(34), 27795–27815. https://doi.org/10.1039/d5ra03747f

[2] Bhushan, R., Rai, S., Jangra, P., Sonker, P., Singh, N., Lakshami, R., Philip, R. R., Gakhar, S., & Dakal, T. C. (2025). The role of artificial intelligence in predicting cancer immunotherapy response. Oral Oncology Reports, 16, 100767. https://doi.org/10.1016/j.oor.2025.100767

[3] Liao, J., Li, Y., & Wang, X. (2023). Artificial intelligence assists precision medicine in cancer treatment. Frontiers in Pharmacology, 14, 1126946. https://doi.org/10.3389/fphar.2023.1126946