AI systems in clinical practice

Decision support systems
Iliad
Expert system for internal medical diagnosis

developed by clinical domains keywords
University of Utah School of Medicine's Dept. of Medical Informatics Internal medicine, diagnosis Decision support system, Expert System, medical education
location commissioned status
Used widely Iliad v4.5 was commercially available - an update on CD-ROM with a library of digitized pictures.
description
At the University of Utah School of Medicine's Dept. of Medical Informatics, an Expert System program called Iliad has been under development for several years. Iliad uses Bayesian reasoning to calculate the posterior probabilities of various diagnoses under consideration, given the findings present in a case. Iliad which was developed primarily for diagnosis in Internal Medicine, now covers about 1500 diagnoses in this domain, based on several thousand findings. The Iliad shell has also been used to develop knowledge bases for diagnosis in other domains. Iliad was developed initially for the Apple Mac; a version for the PC-AT running windows has also been released. Current use: primarily as a teaching tool for medical students. Particular cases can be simulated thru' this program and the students have to "diagnose" the case (i.e. extract all relevant useful information to make the diagnosis from the computer in the most efficient manner possible). This helps the students sharpen their skill in differential diagnosis. It is anticipated that in the coming years, the Iliad program will become a widely used adjunct for clinical diagnosis and patient data documentation in the setting of the physician's office or clinic (at least in the USA).
references

Warner HR Jr, Bouhaddou O. Innovation review: Iliad--a medical diagnostic support program. Top Health Inf Manage. 1994 May;14(4):51-8.

[PubMed]   []

" An expert diagnostic system, iliad, can prove useful to a health care provider as a personal consultant. iliad can suggest relevant diagnoses, give advice regarding cost-effective workup strategies, and explain relationships of findings to diseases. Engineering medical knowledge to perform such tasks is now possible with the help of a personal computer, providing every physician's office with a new and exciting way to learn and practice medicine. "

Bouhaddou O, Frucci L, Cofrin K, Larsen D, Warner H Jr, Huber P, Sorenson D, Turner C, Warner H. Implementation of practice guidelines in a clinical setting using a computerized knowledge base (Iliad). Proc Annu Symp Comput Appl Med Care. 1993;:258-62.

[PubMed]   []

" We present the implementation of the indications for surgery for three surgical operations--cholecystectomy, cataract extraction, and knee arthroscopy--in a medical expert system, called Iliad. This implementation operates in the preauthorization service of IHC Health Plans (an insurance company in Salt Lake City) as a basis for reimbursement of services. Patient data collection forms, derived from Iliad knowledge base, were used by 13 participating surgeons to document the objective patient observations that justify the surgery and, then were faxed to IHC where a trained nurse input the data in Iliad. Iliad's decisions and reports on any deviations from guidelines are communicated back to the care provider. The study evaluates the impact of the computerized implementation on process, as measured by a questionnaire, and on outcome as measured by rate of approvals, documentation level, rate of requests, and average cost. The prospective implementation of the computerized guidelines has performed reliably, has been perceived as a preferred alternative to the old preauthorization system, and, most importantly, has enhanced significantly the level of documentation permitting evaluation and determination of appropriateness before surgery. "

Lincoln MJ, Turner CW, Haug PJ et al. Iliad training enhances medical students' diagnostic skills. J Med Syst. 1991 Feb;15(1):93-110.

[PubMed]  

" Iliad is a computerized, expert system for internal medical diagnosis. The system is designed to teach diagnostic skills by means of simulated patient case presentations. We report the results of a controlled trial in which junior students were randomly assigned to received Iliad training on one of two different simulated case mixes. Each group was subsequently tested in both their "trained" and "untrained" case domain. The testing consisted of computerized, simulated patient cases for which no training feedback was provided. Outcome variables were designed to measure the students' performance on these test cases. The results indicate that students made fewer diagnostic errors and more conclusively confirmed their diagnostic hypotheses when they were tested in their trained domain. We conclude that expert systems such as Iliad can effectively teach diagnostic skills by supplementing trainees' actual case experience with computerized simulations. "

Anderson JD, Jay SJ, Weng HC, Anderson MM. Studying the effect of clinical uncertainty on physicians' decision-making using ILIAD. Medinfo. 1995;8 Pt 2:869-72.

[PubMed]   []

" The influence of uncertainty on physicians' practice behavior is not well understood. In this research, ILIAD, a diagnostic expert system, has been used to study physicians' responses to uncertainty and how their responses affected clinical performance. The simulation mode of ILIAD was used to standardize the presentation and scoring of two cases to 46 residents in emergency medicine, internal medicine, family practice and transitional medicine at Methodist Hospital of Indiana. A questionnaire was used to collect additional data on how physicians respond to clinical uncertainty. A structural equation model was developed, estimated, and tested. The results indicate that stress that physicians experience in dealing with clinical uncertainty has a negative effect on their clinical performance. Moreover, the way that physicians respond to uncertainty has positive and negative effects on their performance. Open discussions with patients about clinical decisions and the use of practice guidelines improves performance. However, when the physician's clinical decisions are influenced by patient demands or their peers, their performance scores decline. "

contact links
&nbps;

 bullet  University of Utah, Dept. of Medical Informatics
acknowledgements

Archive of AI systems in clinical practice previously administered by Enrico Coiera. Used with permission. Maintained and extended since 2001 by OpenClinical.

Entry on archive: October 23 1995
Last main update: October 23 1995
Search this site
 

 

Privacy policy User agreement Copyright Feedback

Last modified:
© Copyright OpenClinical 2001-2007