Artificial intelligence-assisted occupational lung disease diagnosis.
Harber-P; McCoy-JM; Howard-K; Greer-D; Luo-J
Chest 1991 Aug; 100(2):340-346
The development and pilot application of an artificial intelligence expert system to help clinicians recognize occupational factors in lung disease were described. The system was operable on IBM PC compatible microcomputers. The method of integrating epidemiologic knowledge and clinical data was illustrated. Development of the system required explicitly determining the types of information and the process by which knowledge is used in establishing such diagnoses. The system used a knowledge representation scheme to capture relevant clinical knowledge into structures about specific objects and pairwise relations between objects. Quantifiers described both the closeness of association and risk, as well as the degree of belief in the validity of a fact. An independent inference engine used the knowledge, combining likelihoods and uncertainties to achieve estimates of likelihood factors for specific paths from work to illness. The system created a series of paths, linking work activities to disease outcomes. One path linked a single period of work to a single possible disease outcome. In a preliminary trial, the number of paths from job to possible disease averaged 18 per subject in a general population and averaged 25 per subject in an asthmatic population. The authors conclude that artificial intelligence methods hold promise in the future to facilitate diagnosis in pulmonary and occupational medicine.
NIOSH-Publication; NIOSH-Grant; Risk-factors; Occupational-exposure; Disease-incidence; Respiratory-system-disorders; Lung-disease; Diagnostic-techniques; Occupational-respiratory-disease
Medicine University of California School of Medicine Los Angeles, Calif 90024
University of California Los Angeles, Los Angeles, California