Health Policy

Are We Ready in Radiation Oncology for an AI-enabled World?

For our August #radonc journal club, we will be doing something a little different. Diverting from our norm of clinical studies we will peer ahead to the (perhaps not so distant) future of articificial intelligence(AI)-enabled cancer care for radiation oncology:

Artificial intelligence in radiation oncology: A specialty-wide disruptive transformation?

(link: https://linkinghub.elsevier.com/retrieve/pii/S0167-8140(18)30289-5 )

Radiother Oncol 2018; In Press

Our guest tweeters are Dr. Reid Thompson (@thompson_lab), Dr. Sanjay Aneja, and Dr. James Yu (@jamesbyu).

Dr. Reid Thompson is an Assistant Professor of Radiation Oncology & Computational Biology at OHSU1 and chair of the American College of Radiology Data Science Institute’s (ACR DSI) Oncology Subspecialty Panel that is developing AI applications to help providers deliver improved medical care.2  Disclaimer:  Dr. Thompson’s views and statements are expressly his own and do not represent that of OHSU, the ACR, or the US government. Dr. Sanjay Aneja is an Instructor in the Department of Therapeutic Radiology at Yale and has published on health policy including geographic access to radiation therapy services, the distribution of the radiation oncologist workforce, and health economics in radiation oncology.3 Dr. James Yu is an Associate Professor of Therapeutic Radiology at Yale and has numerous publications on health policy, quality of life, and the effectiveness of treatments.4

Artificial Intelligence (AI) has already made gains in telecom, manufacturing, retail, and media. Historically conservative sectors such as the financial industry are now at the AI vanguard.5,6 Healthcare adoption has lagged, but there has been increasing attention over the last few years in media and medical journals with most applications focusing on cancer.7 Promises include improved efficiency and accuracy at interpreting medical images, triage, and diagnosis for higher value care. Big players include Google’s DeepMind that has partnered with the NHS to conduct studies and publish findings in peer-reviewed journals.8 Others such as IBM’s Watson have left review to the FDA and come under scrutiny for not sharing their results after reported adverse events including misdiagnosis and mistreatment.9,10

Despite the perils, many believe AI will eventually become an essential part of all clinical practice, perhaps especially for radiation oncology. Are we ready for it?

Please join us for our August #radonc journal club starting Saturday August 18th at 7AM Central Standard Time for the open chat. The structured one-hour live conversation with study authors will happen Sunday August 19th from 2-3 PM Central Standard Time (3-4pm EST).

Topics will include:

T1: What is artificial intelligence and why is it important in healthcare?

T2: What was the purpose and what were the methods used for this study?

T3: How is AI currently being used in Radiation Oncology? What are the benefits and risks?

T4: What will be the impact on patients, radiation oncologists, physicists, dosimetrists, therapists, nurses, and other stakeholders?

T5: How do we maximize the benefits and minimize the risks of AI to continue improving quality and value in cancer care?

Please join us this weekend!

  • Here are guidelines on how to sign up and participate
  • Read our disclaimer for ways to keep it rewarding and professional. If you’re not ready, just lurk and tune into the conversation.

Any suggestions? Leave a comment or tweet us at @Rad_Nation.

 

References

1 Reid F. Thompson, MD PhD. Oregon Health and Science University: https://www.ohsu.edu/xd/education/schools/school-of-medicine/departments/clinical-departments/radiation-medicine/about/faculty-staff/rfthompson.cfm

2 American College of Radiology Data Science Institute (ACR DSI)https://www.acrdsi.org/About-ACR-DSI

3 Sanjay Aneja, MD. Yale School of Medicine https://medicine.yale.edu/therapeuticradiology/people/faculty/sanjay_aneja-1.profile

4 James Yu, MD, MHS. Yale School of Medicine. https://medicine.yale.edu/therapeuticradiology/people/james_b_yu-1.profile

5 Marr, B. 27 Incredible Examples Of AI And Machine Learning In Practice. Forbes. April 30, 2018. https://www.forbes.com/sites/bernardmarr/2018/04/30/27-incredible-examples-of-ai-and-machine-learning-in-practice/#238722727502

6 Bughin, J. ARTIFICIAL INTELLIGENCE THE NEXT DIGITAL FRONTIER? McKinsey Global. 2017: https://www.mckinsey.com/~/media/McKinsey/Industries/Advanced%20Electronics/Our%20Insights/How%20artificial%20intelligence%20can%20deliver%20real%20value%20to%20companies/MGI-Artificial-Intelligence-Discussion-paper.ashx

7 Jiang, F. Artificial intelligence in healthcare: past, present and future. BMJ. 2017: https://svn.bmj.com/content/2/4/230

8 Fauw, J. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature. 2018: https://www.nature.com/articles/s41591-018-0107-6

9 Ross, C. IBM’s Watson supercomputer recommended ‘unsafe and incorrect’ cancer treatments, internal documents show. STAT. 2018: https://www.statnews.com/2018/07/25/ibm-watson-recommended-unsafe-incorrect-treatments/

10 Kahn, J. The Promise and Perils of AI Medical Care. Bloomberg. 2018: https://www.bloomberg.com/news/articles/2018-08-15/the-promise-and-perils-of-ai-medical-care

 

Add Comment

Click here to post a comment

Radiation Nation

Radiation Nation is dedicated to a collaborative approach to sharing for all involved in the use of radiation medicine.

Follow #radonc on Twitter