Artificial Intelligence: Bayesian versus Heuristic Method for Diagnostic Decision Support

Evoking strength is one of the important contributions of the field of Biomedical Informatics to the discipline of Artificial Intelligence. The University at Buffalo's Orthopedics Department wanted to create an expert system to assist patients with self-diagnosis of knee problems and to thereby facilitate referral to the right orthopedic subspecialist. They had two independent sports medicine physicians review 469 cases. A board-certified orthopedic sports medicine practitioner, L.B., reviewed any disagreements until a gold standard diagnosis was reached. For each case, the patients entered 126 potential answers to 26 questions into a Web interface. These were modeled by an expert sports medicine physician and the answers were reviewed by L.B. For each finding, the clinician specified the sensitivity (term frequency) and both specificity (Sp) and the heuristic evoking strength (ES). Heuristics are methods of reasoning with only partial evidence. An expert system was constructed that reflected the posttest odds of disease-ranked list for each case. We compare the accuracy of using Sp to that of using ES (original model, p < 0.0008; term importance * disease importance [DItimesTI] model, p < 0.0001: Wilcoxon ranked sum test). For patient referral assignment, Sp in the DItimesTI model was superior to the use of ES. By the fifth diagnosis, the advantage was lost and so there is no difference between the techniques when serving as a reminder system.

[1]  Peter L. Elkin,et al.  Evolution of DXplain: A Decision Support System , 1989 .

[2]  W Michalowski,et al.  Comparing predictions made by a prediction model, clinical score, and physicians , 2013, Applied Clinical Informatics.

[3]  S. G. Axline,et al.  Computer-based consultations in clinical therapeutics: explanation and rule acquisition capabilities of the MYCIN system. , 1975, Computers and biomedical research, an international journal.

[4]  F E Masarie,et al.  Quick medical reference (QMR) for diagnostic assistance. , 1986, M.D.Computing.

[5]  Ledley Rs,et al.  The role of computers in medical diagnosis. , 1961 .

[6]  G. Barnett,et al.  DXplain. An evolving diagnostic decision-support system. , 1987, JAMA.

[7]  S. Magid,et al.  Electronic Ordering System Improves Postoperative Pain Management after Total Knee or Hip Arthroplasty , 2015, Applied Clinical Informatics.

[8]  Zhan Ye,et al.  SparkText: Biomedical Text Mining on Big Data Framework , 2016, PloS one.

[9]  Peter L. Elkin,et al.  DXplain-Important Issues in the Development of a Computer-Based Decision Support System. , 1990 .

[10]  M G Kahn,et al.  ASTM E31.15 on health knowledge representation: the Arden Syntax. , 1993, Studies in health technology and informatics.

[11]  R A Miller,et al.  A tool for the computer-assisted creation of QMR medical knowledge base disease profiles. , 1991, Proceedings. Symposium on Computer Applications in Medical Care.

[12]  Bronson Dl,et al.  Patients who read their hospital charts. , 1980 .

[13]  Peter L. Elkin,et al.  Automated Batch Searching of MEDLINE for DXplain , 1989 .

[14]  G. Octo Barnett,et al.  DXplain on the Internet , 1998, AMIA.

[15]  Hang Joon Jo,et al.  Multiclass Classification for the Differential Diagnosis on the ADHD Subtypes Using Recursive Feature Elimination and Hierarchical Extreme Learning Machine: Structural MRI Study , 2016, PloS one.

[16]  H. R. Warner,et al.  The HELP system , 1982, Journal of Medical Systems.

[17]  O Bouhaddou,et al.  An interactive patient information and education system (Medical HouseCall) based on a physician expert system (Iliad). , 1995, Medinfo. MEDINFO.

[18]  H. Warner,et al.  HELP--a program for medical decision-making. , 1972, Computers and biomedical research, an international journal.

[19]  S. G. Axline,et al.  An artificial intelligence program to advise physicians regarding antimicrobial therapy. , 1973, Computers and biomedical research, an international journal.

[20]  W. Kapoor,et al.  A computer-assisted medical diagnostic consultation service. Implementation and prospective evaluation of a prototype. , 1989, Annals of internal medicine.

[21]  C. Sudlow,et al.  Defining Disease Phenotypes in Primary Care Electronic Health Records by a Machine Learning Approach: A Case Study in Identifying Rheumatoid Arthritis , 2016, PloS one.

[22]  Peter L. Elkin,et al.  Closing the Loop on Diagnostic Decision Support Systems. , 1990 .

[23]  T A Pryor,et al.  The use of medical logic modules at LDS hospital. , 1994, Computers in biology and medicine.

[24]  T D Dombal,et al.  Computer training for doctors and students , 1994, BMJ.