0
0
A groundbreaking study led by researchers from Moffitt Cancer Center, in collaboration with investigators from the University of Michigan, has found that artificial intelligence (AI) can significantly improve cancer treatment decisions. However, it also underscores the challenges of integrating AI into clinical practice and highlights the irreplaceable role of human expertise in patient care.
The study, published in Nature Communications, focused on AI-assisted radiotherapy for non-small cell lung cancer and hepatocellular carcinoma (liver cancer). Researchers explored the use of knowledge-based response-adaptive radiotherapy (KBR-ART), a technique that utilizes AI to optimize treatment by suggesting adjustments based on a patient’s response to therapy.
AI Enhances Consistency, But Human Judgment Prevails
Radiotherapy, a widely used cancer treatment, relies on high-energy radiation to shrink or eliminate tumors. The study found that when doctors used AI to assist in determining the best treatment plan, they demonstrated greater consistency in their decisions, minimizing variability in treatment approaches. However, the AI system did not always influence clinical decisions. Some doctors chose to rely on their own judgment, prioritizing their experience and their patients’ unique needs over AI-generated recommendations.
To test AI’s impact, doctors were first asked to make treatment decisions independently. Then, they were provided with AI-generated recommendations based on patient data, including medical imaging and test results. While many found AI suggestions beneficial, some opted to follow their own medical expertise instead.
“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 Department at Moffitt Cancer Center. “Every patient is unique, and doctors must make decisions based on both AI recommendations and their own clinical judgment.”
Trust in AI: A Key Factor in Adoption
One of the study’s key findings was that doctors were more likely to follow AI recommendations when they trusted the system’s accuracy. “Our research shows that AI can be a powerful tool for doctors,” said Dipesh Niraula, Ph.D., an applied research scientist at Moffitt. “But it’s important to recognize that AI works best when used as a support, not a replacement, for human expertise. Doctors bring experience and intuition, while AI provides data-driven insights. Together, they can create more effective treatment plans, but trust and clear communication are essential.”
The study’s authors hope their findings will encourage better integration of AI tools in clinical settings, fostering collaboration between AI systems and medical professionals. They also plan to investigate AI’s potential applications in other areas of medicine.
For more details, the study can be accessed in Nature Communications: Dipesh Niraula et al., Intricacies of human–AI interaction in dynamic decision-making for precision oncology, Nature Communications (2025). DOI: 10.1038/s41467-024-55259-x.
Disclaimer:
While AI has shown promise in enhancing cancer treatment, it is not a substitute for professional medical advice. Patients should consult their healthcare providers for personalized treatment plans. The findings in this study represent ongoing research and should not be interpreted as definitive clinical guidelines.
