PROBABILISTIC DIAGNOSIS USING A REFORMULATION OF THE INTERNIST-1/QMR KNOWLEDGE BASE .1. THE PROBABILISTIC MODEL AND INFERENCE ALGORITHMS

被引:156
作者
SHWE, MA
MIDDLETON, B
HECKERMAN, DE
HENRION, M
HORVITZ, EJ
LEHMANN, HP
COOPER, GF
机构
[1] STANFORD UNIV, MED INFORMAT SECT, MED SCH OFF BLDG, X215, STANFORD, CA 94305 USA
[2] UNIV PITTSBURGH, MED INFORMAT SECT, PITTSBURGH, PA 15260 USA
关键词
EXPERT SYSTEMS; COMPUTER-AIDED DIAGNOSIS; PROBABILISTIC INFERENCE; BELIEF NETWORKS;
D O I
10.1055/s-0038-1634846
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In Part I of this two-part series, we report the design of a probabilistic reformulation of the Quick Medical Reference (QMR) diagnostic decision-support tool. We describe a two-level multiply connected belief-network representation of the QMR knowledge base of internal medicine. In the belief-network representation of the QMR knowledge base, we use probabilities derived from the QMR disease profiles, from QMR imports of findings, and from National Center for Health Statistics hospital-discharge statistics. We use a stochastic simulation algorithm for inference on the belief network. This algorithm computes estimates of the posterior marginal probabilities of diseases given a set of findings. In Part 11 of the series, we compare the performance of QMR to that of our probabilistic system on cases abstracted from continuing medical education materials from Scientific American Medicine. In addition, we analyze empirically several components of the probabilistic model and simulation algorithm.
引用
收藏
页码:241 / 255
页数:15
相关论文
共 42 条
[1]  
ANDERSEN SK, 1989, 11TH P INT JOINT C A, P1080
[2]   A COMPUTER-ASSISTED MEDICAL DIAGNOSTIC CONSULTATION SERVICE - IMPLEMENTATION AND PROSPECTIVE EVALUATION OF A PROTOTYPE [J].
BANKOWITZ, RA ;
MCNEIL, MA ;
CHALLINOR, SM ;
PARKER, RC ;
KAPOOR, WN ;
MILLER, RA .
ANNALS OF INTERNAL MEDICINE, 1989, 110 (10) :824-832
[3]  
CHAVEZ RM, 1990, COMPUT METH PROG BIO, V32, P5, DOI 10.1016/0169-2607(90)90081-J
[4]  
Cooper G. F., 1984, THESIS STANFORD U
[5]   THE COMPUTATIONAL-COMPLEXITY OF PROBABILISTIC INFERENCE USING BAYESIAN BELIEF NETWORKS [J].
COOPER, GF .
ARTIFICIAL INTELLIGENCE, 1990, 42 (2-3) :393-405
[6]  
Cooper GF, 1989, APPL STOCH MODEL BUS, V5, P39, DOI DOI 10.1002/ASM.3150050106
[7]   HUMAN AND COMPUTER-AIDED DIAGNOSIS OF ABDOMINAL-PAIN - FURTHER REPORT WITH EMPHASIS ON PERFORMANCE OF CLINICIANS [J].
DOMBAL, FTD ;
LEAPER, DJ ;
HORROCKS, JC ;
STANILAN.JR ;
MCCANN, AP .
BRITISH MEDICAL JOURNAL, 1974, 1 (5904) :376-380
[8]  
DONGARRA JJ, 1988, ANL23 TECHN MEM
[9]   QUICK (QUICK INDEX TO CADUCEUS KNOWLEDGE) - USING THE INTERNIST-1/CADUCEUS KNOWLEDGE BASE AS AN ELECTRONIC TEXTBOOK OF MEDICINE [J].
FIRST, MB ;
SOFFER, LJ ;
MILLER, RA .
COMPUTERS AND BIOMEDICAL RESEARCH, 1985, 18 (02) :137-165
[10]  
FUNG R, 1990, MACH INTELL, V5, P209