An adaptive two-tier menu approach to support on-line entry of diagnoses
We demonstrate how a task model derived from data mining techniques could be used to anticipate diagnosis codes from patient complaints for improved data entry efficiency. The anticipated diagnoses are presented to the user in a two-tier fashion with the first tier presenting the most likely diagnoses based upon the complaints which the second tier refines. A success rate of 70% was obtained in anticipating patient diagnosis.
Categoryknowledge acquisition & learning
Unable to display preview. Download preview PDF.
- 1.Canfield, K. (1995) Primary intelligent split menus with text corpora for computerised patient record data-entry. International J. Bio-Medical Computing, Vol. 39, 263–273.Google Scholar
- 2.Weed, L.L. (1969) Medical Records, Medical Education, and Patient Care. Press of the Case Western Reserve University.Google Scholar
- 3.Mudali, S.K., Warren, J.R., Spenceley, S.E., and Kirkwood, I (1996) Toward an Intelligent Interface for Clinical Data Capture: Probabilistic Analysis of the Subjective Component. Proceedings of the Fourth National Health Informatics Conference (HIC96), B. McGuiness and T. Leeder (eds), Melbourne, August 19–21, 57–62.Google Scholar
- 4.ICPC (1987) International Classification of Primary Care. H. Lamberts and M. Wood (eds.), Oxford University Press, Oxford.Google Scholar
- 5.Shortliffe, E.H. (1976) Computer-Based Medical Consultations: MYCIN. New York, Elsevier.Google Scholar