Diagnostic and Prognostic Decision-Making Systems: A Survey of Recent Developments in the United States
Over a decade ago, D. J.CROFT  wrote a review article, asking ‘Is Computerized Diagnosis Possible?’. His sentiments were echoed in a 1977 editorial by R.B. FRIEDMAN and D.H. GUSTAFSON  stating: ‘Successful applications in many other areas have been reported but the overall impact of computers on health care delivery has been less than was expected as recently as 5 years ago’. There are still no major successes to report in the realm of computerized diagnosis, but progress has been made. Two ‘second-generation’ artificial intelligence programs for medical diagnosis — ABEL and CADUCEUS — are reviewed below. Both are in the early stages of development. At this time, the prognosis for computerization remains unclear.
By contrast, two successful programs for computer-generated patient prognosis have been used regulary in a clinical setting. Both — ARAMIS and the Duke Cardiovascular Disease Databank — have assisted physicians in the management of individual patients, and resulted in useful general observations that have been published in the medical literature. A comparison between programs for patient prognosis and programs for medical diagnosis is made in this paper.
Unable to display preview. Download preview PDF.
- 2.Friedman, R.B., Gustafson D.H.: Computers in clinical medicine, a critical review. Comput. biomed. Res. (1977) 199–204.Google Scholar
- 7.Pople, H.E.: Heuristic methods for imposing structure on ill-structured problems: the structuring of medical diagnostics. In Szolovits, P. (Edit.): Artificial Intelligence in Medicine, pp. 119–190. ( AAAS Symposium Series). Boulder, Colo.: Westview Press 1982.Google Scholar
- 12.Rosati, R.A., McNeer, J.F., Starmer, C.F. et al.: A new information system for medical practice. Arch, intern. Med. 135 (1975) 1017–1024.Google Scholar
- 13.Rosati, R.A., Lee, K.L., Califf, R.M. et al.: Problems and advantages of an observational database, approach to evaluating the effect of therapy on outcome. Circulation 65 ( Suppl. II ) (1982) 27–32.Google Scholar
- 14.Lee, K.L.: Personal communication. Duke Cardiovascular Disease Databank, Sept. 1983.Google Scholar
- 15.Decker, J., McShane, D.J., Esdaile, J.M. et al.: The glossary for rheumatic disease. Amer. Rheum. Ass. 1. (1982) 1–95.Google Scholar
- 16.Follansbee, W.P., Steen, V.D., Gamble, W.H.: Cardiac involvement in progressive systemic sclerosis (pss) accessed by exercise and radionuclide technique. Abstract Arthr. Rheum. 25 (Suppl.) (1982) 5 ff.Google Scholar
- 18.Mitchell, D.M., Spitz, P.W., Young, D.Y.: Predictors of mortality in rheumatoid arthritis (ra). Arthr. Rheum. 25 (Suppl.) (1982) 5149 ff.Google Scholar
- 23.Ginzier, E.M., Diamond, H.S., Weiner, M.: A multicenter study of outcome in systemic lupus erythematosus: I. Entry variables as predictors of prognosis. Arthr. Rheum. 2J5 (1982) 601–611.Google Scholar
- 25.Fraker, T.D.Jr., Wagner, G.S., Rosati, R.A.: Extension of myocardial infarction: incidence and prognosis. Circulation 60 (1979) 1126–1129.Google Scholar
- 31.Miller, R.A., Kapoor, W.N., Peterson, J.: The use of relational databases as a tool for conducting clinical studies. Forthcoming Proceedings of the Seventh Annual Symposium on Computer Applications in Medical Care, Baltimore, MD. IEEE Computer Society, October, 1983.Google Scholar
- 32.Oleson, C.E.: Personal communication, NSABP project. Sept. 1983.Google Scholar
- 34.Shortliffe, E.H.: Computer-based medical consultations: MYCIN. New York: American Elsevier 1976.Google Scholar
- 36.Kulikowski, C.A., Weiss, S.: Representation of expert knowledge for consultation: the CASNET and EXPERT projects. In Szolovits, P. (Edit.): Artificial Intelligence in Medicine, pp. 21–25. ( AAAS Symposium Series). Boulder, Colo.: Westview Press 1982.Google Scholar
- 39.Silverman, H.B.: A Comparative Study of Computer-Aided Clinical Diagnosis of Birth Defects. Masters Thesis, Dept. of Electrical Engineering and Computer Science. Cambrigde, Mass.: MIT Laboratory for Computer Science, January, 1981.Google Scholar
- 40.Miller, R.A., Pople, H.E., Jr., Myers, J.D.: lnternist-1, an experimental computer-based diagnostic consultant for general internal medicine. New Engl. J. Med. 307 (1982) 468–476.Google Scholar
- 41.Patil, R.S., Szolovits, P., Schwartz, W.B.: Modeling knowledge of the patient in acid-base and electrolyte disorders. In Szolovits, P. (Edit.): Artificial Intelligence in Medicine, pp. 191–226 ( AAAS Symposium Series). Boulder, Colo.: Westview Press 1982.Google Scholar
- 42.Patil, R.S.: Causal Representation of Patient Illness for Electrolyte and Acid-Base Diagnosis. PhD Thesis, Dept. of Electrical Engineering and Computer Science. Cambridge, Mass.: MIT Laboratory for Computer Science, October, 1981.Google Scholar