Create Account | Sign In: Author or Forum

 
News  |  Journals  |  Conferences  |  Opinion  |  Articles  |  Forums  |  Twitter    
 
Category: Gynecology | Internal Medicine | Nursing | Oncology | Pathology | Pharmacy | Radiology | Surgery | Conference News

Back to Journal Articles

SABCS: Artificial Intelligence May Aid Doctors in Breast Cancer Care

Last Updated: December 09, 2016.

An artificially intelligent computer system, Watson Oncology, is making breast cancer treatment recommendations in concordance with those made by oncologists, according to a study presented at the annual San Antonio Breast Cancer Symposium, held from Dec. 6 to 10 in Texas.

 

'Watson Oncology' agreed with doctors 90 percent of the time in many cases, researchers find

Share |

Comments: (0)

Tell-a-Friend

 

  Advertisement

FRIDAY, Dec. 9, 2016 (HealthDay News) -- An artificially intelligent computer system, Watson Oncology, is making breast cancer treatment recommendations in concordance with those made by oncologists, according to a study presented at the annual San Antonio Breast Cancer Symposium, held from Dec. 6 to 10 in Texas.

In its oncology role, Watson processes a patient's medical history and current cancer data in under a minute. It then spends another minute reviewing all existing medical evidence regarding their particular form of cancer, study coauthor S.P. Somashekhar, M.B.B.S., chairman of the Manipal Comprehensive Cancer Center in Bengaluru, India, told HealthDay. The program then lists possible treatments in three categories -- recommended treatments, treatments worth considering, and therapies not recommended, Somashekhar said.

To test the program's effectiveness, Somashekhar and his colleagues studied the cases of 638 breast cancer patients who had been treated at Manipal Hospitals in India. The team entered data on the cases into the computer system, and compared Watson's recommendations to those produced by a group of 12 to 15 oncologists who meet weekly to review cases.

Overall, 90 percent of Watson's recommendations were consistent with the advice of the tumor board, the researchers reported. However, the degree of agreement varied depending on the type of breast cancer. The computer agreed with the human doctors nearly 80 percent of the time in cases where the breast cancer had not spread to other parts of the body, but only 45 percent of the time in metastatic cases. In cases of triple-negative breast cancer, Watson agreed with the oncologists 68 percent of the time. But in human epidermal growth factor receptor 2-negative cases, its recommendations matched the physicians' recommendations only 35 percent of the time.

Press Release
More Information

Copyright © 2016 HealthDay. All rights reserved.


Previous: SABCS: Scalp-Cooling System Can Reduce Chemo-Related Hair Loss Next: Duration of Estrogen Rx May Be Important Factor in Renal Health

Reader comments on this article are listed below. Review our comments policy.


Submit your opinion:

Name:

Email:

Location:

URL:

Remember my personal information

Notify me of follow-up comments?

 
     

Useful Sites
MediLexicon
  Tools & Services: Follow DoctorsLounge on Twitter Follow us on Twitter | RSS News | Newsletter | Contact us
Copyright © 2001-2017
Doctors Lounge.
All rights reserved.

Medical Reference:
Diseases | Symptoms
Drugs | Labs | Procedures
Software | Tutorials

Advertising
Links | Humor
Forum Archive
CME | Conferences

Privacy Statement
Terms & Conditions
Editorial Board
About us | Email

This website is certified by Health On the Net Foundation. Click to verify. This site complies with the HONcode standard for trustworthy health information:
verify here.