A.I. Shows Promise as a Physician Assistant

“These A.I. tools have a real chance to make a difference,” said Eric Topol, a cardiologist in addition to geneticist with Scripps Research in San Diego, in addition to the author of a forthcoming book on the use of machine learning in health care, who was not involved inside the research. “however in which can be going to take a while.”

Using neural-network technology, Dr. Zhang has built systems in which can analyze eye scans for hemorrhages, lesions in addition to additional signs of diabetic blindness. Ideally, such systems would likely serve as a first line of defense, screening patients in addition to pinpointing those who need further attention.

Dr. Zhang in addition to his colleagues right now have created a system in which can diagnose an even wider range of conditions, by recognizing patterns in text, not just in medical images. The completely new system analyzed the electronic medical records of nearly 0,000 patients at the Guangzhou Women in addition to Children’s Medical Center, a hospital in southern China.

First, a group of trained physicians annotated the Guangzhou records, adding labels in which identified information related to certain medical conditions. The system then analyzed the labeled data. When in which was done, in addition to was presented with completely new data — a patient’s symptoms determined during a physical examination — in which was able to make connections on its own.

When tested on unlabeled data, the system could rival the performance of experienced physicians. in which was more than 0 percent accurate at diagnosing asthma; the accuracy of physicians inside the study ranged through 80 to 94 percent. In diagnosing gastrointestinal disease, the system was 87 percent accurate, compared to the physicians’s accuracy of 82 to 0 percent.

Experts said extensive clinical trials are right now needed, particularly given the difficulty of interpreting decisions made by neural networks.

“Medicine can be a slow-moving field,” said Ben Shickel, a researcher at the University of Florida who specializes inside the use of deep learning for health care. “No one can be just going to deploy one of these techniques without rigorous testing in which shows exactly what can be going on.”