17 August 2016
A new study has offered evidence that computers could be used to predict the type and severity of a person's lung cancer more effectively than a human pathologist.
Carried out by Stanford University Medical Center, the research compared a machine-learning approach to identifying critical disease-related features in lung cancer cells to the standard approach of pathologists classifying tumors by grade and stage.
It was shown that the machine-learning approach accurately differentiated between two types of lung cancers and predicted patient survival times better than the manual method, as it helps to eliminate some of the inconsistency that subjective judgement can cause.
Whereas two skilled pathologists assessing the same slide might agree only about 60 percent of the time, a computer software program can identify many more cancer-specific characteristics than can be detected by the human eye, making it potentially much more accurate.
Dr Michael Snyder, professor and chair of genetics at Stanford University School of Medicine, said: "This brings cancer pathology into the 21st century and has the potential to be an awesome thing for patients and their clinicians."
Posted by Philip Briggs
Health News is provided by Axonn Media in collaboration with Spire Healthcare. Please note that all copy above is ©Axonn Media and does not reflect views or opinions of Spire Healthcare unless explicitly stated. Additional comments on the page from individual Spire consultants do not necessarily reflect the views or opinions of other consultants or Spire Healthcare.