Artificial intelligence research in radiation oncology: a practical guide for the clinician on concepts and methods
2024

A Practical Guide to Artificial Intelligence in Radiation Oncology

publication Evidence: moderate

Author Information

Author(s): Frank J P Hoebers, Leonard Wee, Jirapat Likitlersuang, Raymond H Mak, Danielle S Bitterman, Yanqi Huang, Andre Dekker, Hugo J W L Aerts, Benjamin H Kann

Primary Institution: Mass General Brigham, Harvard Medical School

Hypothesis

Improving clinicians’ AI-related knowledge and skills is necessary to enhance multidisciplinary collaboration between data scientists and physicians.

Conclusion

AI has great potential to improve efficiency in radiation oncology, but its clinical use in decision-making remains limited.

Supporting Evidence

  • AI can enhance efficiency in radiation oncology through applications like automatic segmentation and treatment planning.
  • Improving AI knowledge among clinicians may increase trust and acceptance of AI technologies.
  • AI models have shown promise in clinical decision support but require further validation for widespread use.

Takeaway

This study explains how doctors can use AI to help treat cancer better, but many doctors still need to learn more about it.

Methodology

The paper describes the processes involved in AI research and development, focusing on applications in radiation oncology.

Potential Biases

Potential biases in data could lead to biased results, disadvantaging certain patient groups.

Limitations

The limited clinical uptake of AI models may be due to a lack of understanding among clinicians.

Digital Object Identifier (DOI)

10.1093/bjro/tzae039

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication