Abstract

The proposed research will continue our exploration of the critiquing approach to bringing artificial intelligence (AI) based advice to the practicing physician. To date, our research has primarily involved the implementation of several prototype critiquing systems in different medical domains. The proposed research will focus on one of these systems, HT-ATTENDING, which critiques the pharmacologic management of essential hypertension. 1. A Controlled Experiment A central component of the proposed project will involve a controlled experiment to help evaluate HT- ATTENDING in Yale's Primary Care Center. 2. An Experimental Period of Clinical Use Following the formal evaluation study, there will be a period of clinical use of HT- ATTENDING at the Primary Care Center. During this period, we will test various augmentations and modifications of the system. 3. Refining, Augmenting, and Updating HT-ATTENDING Throughout the proposed project, we will continually refine HT-ATTENDING and maintain the currency of its knowledge base. 4. Tools for Knowledge Inspection, Verification, and Updating We will continue to develop and refine computer-based tools to assist in the inspection, verification, and updating of HT-ATTENDING's knowledge base. 5. An External Validation of HT-ATTENDING's Knowledge He will perform an """"""""external"""""""" validation of HT-ATTENDING's knowledge by submitting 25 critiques of varying complexity to outside ypertension experts.

  Funding Agency

Agency
National Institute of Health (NIH)
Institute
National Library of Medicine (NLM)
Type
Research Project (R01)
Project #
5R01LM004336-04
Application #
3373632
Study Section
Biomedical Library Review Committee (BLR)
Project Start
1985-09-01
Project End
1991-02-28
Budget Start
1989-03-01
Budget End
1990-02-28
Support Year
4
Fiscal Year
1989
Total Cost
Indirect Cost

  Institution

Name
Yale University
Department
Type
Schools of Medicine
DUNS #
082359691
City
New Haven
State
CT
Country
United States
Zip Code
06520

  Publications

Norman, J (1994) Flow cytometry data analysis: comparing large multivariate data sets using classification trees. Proc Int Conf Intell Syst Mol Biol 2:310-3
Berman, L; Cullen, M; Miller, P L (1993) Automated integration of external databases: a knowledge-based approach to enhancing rule-based expert systems. Comput Biomed Res 26:230-41
Berman, L; Cullen, M R; Miller, P L (1992) Automated integration of external databases: a knowledge-based approach to enhancing rule-based expert systems. Proc Annu Symp Comput Appl Med Care :227-33
Miller, P L; Paton, J A; Clyman, J I et al. (1992) Prototyping an institutional IAIMS/UMLS information environment for an academic medical center. Bull Med Libr Assoc 80:281-7
Frohlich, M W; Miller, P L; Morrow, J S (1990) PATHMASTER: modelling differential diagnosis as ""dynamic competition"" between systematic analysis and disease-directed deduction. Comput Biomed Res 23:499-513
Rothschild, M A; Swett, H A; Fisher, P R et al. (1990) Exploring subjective vs. objective issues in the validation of computer-based critiquing advice. Comput Methods Programs Biomed 31:11-8
Sittig, D F; Factor, M (1990) Physiologic trend detection and artifact rejection: a parallel implementation of a multi-state Kalman filtering algorithm. Comput Methods Programs Biomed 31:1-10
Factor, M; Sittig, D F; Cohn, A I et al. (1990) A parallel software architecture for building intelligent medical monitors. Int J Clin Monit Comput 7:117-28
Cohn, A I; Miller, P L; Fisher, P R et al. (1990) Knowledge-based radiologic image retrieval using axes of clinical relevance. Comput Biomed Res 23:199-221
Cohn, A I; Rosenbaum, S; Factor, M et al. (1990) DYNASCENE: an approach to computer-based intelligent cardiovascular monitoring using sequential clinical ""scenes"". Methods Inf Med 29:122-31

Showing the most recent 10 out of 26 publications