Massachusetts General Hospital develops AI model that predicts patient’s 12-year lung cancer risk 

Boston-based Massachusetts General Hospital scientists created an automatic deep learning design that can forecast a clients likelihood of establishing lung cancer within the next 12 years, according to a Sept. 1 study published in the Annals of Internal Medicine.

To establish the artificial intelligence-based technique, the research team utilized chest radiograph images and patient group data including age, sex and current smoking status that is readily available in EHRs. The model makes forecasts based on chest X-ray images from more than 41,000 people that took part in a multicenter trial of lung cancer screening with chest X-rays, called the Prostate, Lung, Colorectal and Ovarian Cancer Screening Trial..

More short articles on expert system: Penn State develops algorithm to alert users of illegitimate medications onlinePenn Medicine AI helps worldwide consortiums COVID-19 information design: 4 notesDefense Health Agency launches AI task for cancer detection.

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this material? View our policies by clicking here.

Jackie Drees –
Tuesday, September 1st, 2020
Print|Email.

Researchers validated the final model in 5,615 additional trial individuals and 5,493 individuals involved from a second trial, the National Lung Screening Trial. The deep knowing design exceeded the basic Medicare lung cancer screening requirements, which is the present scientific standard, and missed out on 30.7 percent less lung cancers while evaluating the same number of individuals.