Abstract
Mastering of medical knowledge to human is a lengthy process that typically involves several years of school study and residency training. Recently, deep learning algorithms have shown potential in solving medical problems. Here we demonstrate mastering clinical medical knowledge at certificated-doctor-level via a deep learning framework Med3R, which utilizes a human-like learning and reasoning process. Med3R becomes the first AI system that has successfully passed the written test of National Medical Licensing Examination in China 2017 with 456 scores, surpassing 96.3% human examinees. Med3R is further applied for providing aided clinical diagnosis service based on real electronic medical records. Compared to human experts and competitive baselines, our system can provide more accurate and consistent clinical diagnosis results. Med3R provides a potential possibility to alleviate the severe shortage of qualified doctors in countries and small cities of China by providing computer-aided medical care and health services for patients.
Highlights
Mastering of medical knowledge to human is a lengthy process that typically involves several years of school study and residency training
Med3R can be applied for providing aided clinical diagnosis service and the experimental results illustrate that the model can provide more accurate and consistent results compared to human experts and competitive baselines
Our study shows that deep learning techniques have potential abilities to master medical knowledge and provide accurate clinical diagnosis suggestions based on medical electronic records and that it provides a possibility to alleviate the severe shortage of qualified doctors in countries and small cities of the world
Summary
Mastering of medical knowledge to human is a lengthy process that typically involves several years of school study and residency training. The proposed model employs a human-like learning and reasoning framework that firstly captures primary medical knowledge from a large medical corpus with a “Free Reading” module, masters more precise knowledge via a “Guided Reading” phase, and makes inference/decision in a “Multi-layer Reasoning” fashion. Med3R can be applied for providing aided clinical diagnosis service and the experimental results illustrate that the model can provide more accurate and consistent results compared to human experts and competitive baselines. Our study shows that deep learning techniques have potential abilities to master medical knowledge and provide accurate clinical diagnosis suggestions based on medical electronic records and that it provides a possibility to alleviate the severe shortage of qualified doctors in countries and small cities of the world
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call