Intelligent decision support in medicine: back to Bayes?

ABSTRACT

Decision Support Systems (DSSs) are proliferating at an increasingly rapid pace in many areas of human endeavor including clinical medicine and psychology. These DSSs are typically based on Artificial Neural Networks (ANNs), many of which have been shown to perform very well (e.g. Ennett, 2003). In this talk in which I am specifically concerned with medicine and e-health, I will attempt to show that Bayes' Theorem can offer an alternative and very effective approach to the design of DSSs. Bayesian models are highly adaptive in the sense that they are able to 'learn' iteratively from 'experience' without changing the underlying structure. This important feature enables customization of Bayesian models to individual users and thus to their changing needs. In e-learning contexts as well as in interventional e-health, particularly in clinical psychology, this is an important advantage, especially when courses or treatment plans are offering a range of different routes through, or different possible presentation modes of, the learning material.

REFERENCES

• 1: Briggs, K., & Myers, I. (1998). Myers-Briggs type indicator, Consulting Psychological Press, INC, Palo Alto, CA.
• 2: Colleen Michelle Ennett , Monique Frize, Imputation of missing values by integrating artificial neural networks and case-based reasoning, Carleton University, Ottawa, Ont., Canada, 2003
• 3: Furnham, A., Jackson, C., & Miller, T. (1999). Personality, learning style and work performance. Personality and Individual Differences, 27, 1113--1122.
• 4: Hughes, C. M., Phillips, J., Woodcock, J. (2000). How Many Deaths Are Due to Medical Errors?, Journal of the American Medical Association, 284, 2187--2189.
• 5: Jackson, C., & Lawty-Jones, M. (1996). Explaining the overlap between personality and learning style. Personality and Individual Differences, 20(3), 293--300.
• 6: Larsen, R., & Buss, D. (2002). Personality psychology: Domains of knowledge about human nature. New York: McGraw Hill.
• 7: Schiff, G. D., Kim, S., Abrams, R., Cosby, K., Lambert, B., Elstein, A. S., Hasler, S., Krosnjar, N., Odwazny, R., Wisniewski, M. A., & McNutt, R. A. (2006). Advances in patient safety, 2, 255--278.