Master clinical medical knowledge at certificated-doctor-level with deep learning model

被引:37
作者
Wu, Ji [1 ]
Liu, Xien [1 ]
Zhang, Xiao [1 ]
He, Zhiyang [2 ]
Lv, Ping [3 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
[2] iFlytek Co Ltd, Med Business Dept, Hefei 230088, Anhui, Peoples R China
[3] iFlytek Res, Tsinghua iFlytek Joint Lab, Beijing 100084, Peoples R China
关键词
WEB;
D O I
10.1038/s41467-018-06799-6
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
070301 [无机化学]; 070403 [天体物理学]; 070507 [自然资源与国土空间规划学]; 090105 [作物生产系统与生态工程];
摘要
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.
引用
收藏
页数:7
相关论文
共 36 条
[1]
[Anonymous], 2015, NEURAL NETWORK BASED
[2]
[Anonymous], 2011, P 20 ACM INT C INF K, DOI DOI 10.1145/2063576.2063676
[3]
DBpedia: A nucleus for a web of open data [J].
Auer, Soeren ;
Bizer, Christian ;
Kobilarov, Georgi ;
Lehmann, Jens ;
Cyganiak, Richard ;
Ives, Zachary .
SEMANTIC WEB, PROCEEDINGS, 2007, 4825 :722-+
[4]
Identifying implicit relationships [J].
Chu-Carroll, J. ;
Brown, E. W. ;
Lally, A. ;
Murdock, J. W. .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)
[5]
Finding needles in the haystack: Search and candidate generation [J].
Chu-Carroll, J. ;
Fan, J. ;
Boguraev, B. K. ;
Carmel, D. ;
Sheinwald, D. ;
Welty, C. .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)
[6]
Textual resource acquisition and engineering [J].
Chu-Carroll, J. ;
Fan, J. ;
Schlaefer, N. ;
Zadrozny, W. .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)
[7]
Making Watson fast [J].
Epstein, E. A. ;
Schor, M. I. ;
Iyer, B. S. ;
Lally, A. ;
Brown, E. W. ;
Cwiklik, J. .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)
[8]
Unsupervised named-entity extraction from the Web: An experimental study [J].
Etzioni, O ;
Cafarella, M ;
Downey, D ;
Popescu, AM ;
Shaked, T ;
Soderland, S ;
Weld, DS ;
Yates, A .
ARTIFICIAL INTELLIGENCE, 2005, 165 (01) :91-134
[9]
A framework for merging and ranking of answers in DeepQA [J].
Gondek, D. C. ;
Lally, A. ;
Kalyanpur, A. ;
Murdock, J. W. ;
Duboue, P. A. ;
Zhang, L. ;
Pan, Y. ;
Qiu, Z. M. ;
Welty, C. .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)
[10]
Hovy Dirk., 2012, P 13 C EUROPEAN CHAP, P185