Summaries of Must-Read Clinical Literature, Guidelines, and FDA Actions

Oncologists Agree With AI Treatment Decisions About Half the Time

Publish date:: September 5, 2019

Key clinical point: The Watson for Oncology artificial intelligence advisory tool provides the same treatment recommendations as oncologists about half the time.

Major finding: Concordance between oncologists and intelligence advisory tool treatment recommendations was 56%.

Study details: A cross-sectional, observational study involving 10 Chinese oncologists and 1,977 cases of breast cancer.

Disclosures: The study was funded by Zefei Jiang. The investigators reported affiliations with IBM Watson Health, Pharmaceutical Manufacturer Institution, Merck, and others.

Citation:

Xu F et al. JCO Clin Cancer Inform. 2019 Aug 16. doi: 10.1200/CCI.18.00159.

This Week's Must Reads

Younger adults present with more advanced esophageal adenocarcinoma,

PDAC: Tumor reduction after neoadjuvant therapy may predict postsurgical survival,

Mortality risks rise with age, infections, but not inhibitor status in persons with non-severe hemophilia A,

‘Impressive’ local control with MRI-guided brachytherapy in cervical cancer,

U.S. mothers underestimate role breastfeeding plays in curbing breast cancer,

Must Reads in Breast Cancer

U.S. mothers underestimate role breastfeeding plays in curbing breast cancer,

Study: Doctors underreport side effects of breast irradiation,

No edge for anastrozole over tamoxifen in DCIS,

Long-term APBI cosmetic, toxicity data reported WBI has the edge Practice-confirming results,

Omitting postop radiotherapy doesn’t affect survival in older breast cancer patients,