AI boosts efficacy of cancer treatment, but doctors remain key

Radiotherapy is a common treatment for cancer that uses high-energy radiation to kill or shrink tumors. The study looked at a treatment approach known as knowledge-based response-adaptive radiotherapy (KBR-ART). This method uses AI to optimize treatment outcomes by suggesting treatment adjustments based on how well the patient responds to the therapy.

The study found that when doctors used AI to help decide the best treatment plan, they made more consistent choices, reducing differences between doctors' decisions. However, the technology didn't always change doctors' minds. In some cases, doctors disagreed with the AI suggested and made treatment decisions based on their experience and patient needs.

Doctors were asked to make treatment decisions for cancer patients, first without any technological assistance, and then with the help of AI. The AI system developed by the researchers uses patient data like medical imaging and test results to recommend changes in radiation doses. While some doctors found the suggestions helpful, others preferred to rely on their own judgment.

"While AI offers insights based on complex data, the human touch remains crucial in cancer care," said Issam El Naqa, Ph.D., chair of the Machine Learning Dept. at Moffitt. "Every patient is unique, and doctors must make decisions based on both AI recommendations and their own clinical judgment."

The researchers noted that while AI can be a helpful tool, doctors need to trust it for it to work well. Their study found that doctors were more likely to follow AI suggestions when they felt confident in its recommendations. "Our research shows that AI can be a powerful tool for doctors," said Dipesh Niraula, Ph.D., an applied research scientist in Moffitt's Machine Learning Department. "But it's important to recognize that AI works best when it's used as a support, not a replacement, for human expertise. Doctors bring their expertise and experience to the table, while AI provides data-driven insights. Together, they can make better treatment plans, but it requires trust and clear communication."

The study's authors hope that their findings can lead to better integration of AI tools and collaborative relationships that doctors can use to make more personalized treatment decisions for cancer patients. They also plan to further investigate how AI can support doctors in other medical fields.

This study was supported by the National Institutes of Health (R01-CA233487).