INTERNIST-I properties: Representing common sense and good medical practice in a computerized medical knowledge base

Computers and Biomedical ResearchPublished 1 October 1985

Fred E. Masarie, Randolph A. Miller, Jack D. Myers

Citations46

TL;DR

This paper reviews the implementation and significance of properties in the INTERNIST-I knowledge representation scheme and finds that properties substantially influence the behavior of the INTERnist-I diagnostic program during case analyses.

Abstract

INTERNIST-I is an experimental diagnostic consultant program for use on clinically challenging cases in internal medicine. Properties are a part of the INTERNIST-I knowledge representation scheme which embody essential information about the medical facts contained in the knowledge base. Properties provide the INTERNIST-I program with a measure of common sense and encourage the program to follow good medical practice. Properties substantially influence the behavior of the INTERNIST-I diagnostic program during case analyses. This paper reviews the implementation and significance of properties.

Keywords

Computer ScienceHealth ProfessionsBiochemistry, Genetics and Molecular Biology

New England Journal of Medicine<i>Internist-I</i>, an Experimental Computer-Based Diagnostic Consultant for General Internal Medicine

1,103 Citations1982Randolph A. Miller, Harry E. Pople +1 more

It is demonstrated that the present form of the INTERNIST-I program is not sufficiently reliable for clinical applications and specific deficiencies that must be overcome include the program’s inability to reason anatomically or temporally, its inability to construct differential diagnoses spanning multiple problem areas, and its occasional attribution of findings to improper causes.

Artificial IntelligenceA model-based method for computer-aided medical decision-making

468 Citations1978Sholom M. Weiss, Casimir A. Kulikowski +2 more

A general method of computer-assisted medical decision-making based on causal-associational network (CASNET) models of disease based on observations of a patient, pathophysiological states, and disease classifications for diagnosis and treatment of the glaucomas has been developed.

The American Journal of MedicineTowards the simulation of clinical cognition

406 Citations1976Stephen G. Pauker, G. Anthony Gorry +2 more

It is suggested that the present experimental approach will facilitate accomplishment of the long-term goal of disseminating clinical expertise via the computer.

JAMAAntimicrobial Selection by a Computer

273 Citations1979Victor L. Yu

The evaluation of a computer-based consultation system called MYCIN compared its choice of antimicrobials with the choices of nine human prescribers for ten test cases of meningitis and found it never failed to cover a treatable pathogen while demonstrating efficiency in minimizing the number of antimicrobial prescribed.

Annals of Internal MedicineReadings in Medical Artificial Intelligence: The First Decade.

267 Citations1984

The chapter by Ralph Mann on sprinting and hurdling offers advice on how a knowledge of biomechanics can improve performance and could be improved with the addition of a set of recommendations for the coach and athlete.

Annals of Internal MedicineArtificial Intelligence in Medicine.

254 Citations1983

The feasibility of predicting the functional outcome for ischemic stroke patients and the usability of multimodal deep learning architectures for this purpose are demonstrated.

Computers and Biomedical ResearchQUICK (QUick Index to Caduceus Knowledge): Using the Internist-1/Caduceus knowledge base as an electronic textbook of medicine

42 Citations1985Michael B. First, Lynn J. Soffer +1 more

Using the INTERNIST-I knowledge base as an electronic textbook expands the project's intended audience by providing clinical support for a broad group of diagnostic problems.

Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)A Comparative Study of Computer-Aided Clinical Diagnosis of Birth Defects.

5 Citations1981Howard Bruce Sherman