Abstract
Continuous speech recognition systems have the potential to facilitate clinical data entry, but evaluating them rigorously is difficult. We describe a tool to aid evaluators of such systems. The tool is a HyperCard stack with stimuli consisting of pictures, sounds and the minimum of words to evoke 20 QMR physical findings. Despite using up to four different stimuli to communicate each finding and piloting the material on six subjects, eight test subjects made a total of 66 errors (42%) in interpreting the 20 sets of stimuli, of which 22 errors (14%) were serious. These results are relevant to those designing interfaces for decision-support, tutorial and student testing systems.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Lams P. M., Cocklin M. L. Spatial resolution requirements for digital chest radiographs: an ROC study of observer performance in selected cases. Radiology. 1986 Jan;158(1):11–19. doi: 10.1148/radiology.158.1.3940365. [DOI] [PubMed] [Google Scholar]
- Nathwani B. N., Heckerman D. E., Horvitz E. J., Lincoln T. L. Integrated expert systems and videodisc in surgical pathology: an overview. Hum Pathol. 1990 Jan;21(1):11–27. doi: 10.1016/0046-8177(90)90071-c. [DOI] [PubMed] [Google Scholar]
- Spiteri M. A., Cook D. G., Clarke S. W. Reliability of eliciting physical signs in examination of the chest. Lancet. 1988 Apr 16;1(8590):873–875. doi: 10.1016/s0140-6736(88)91613-3. [DOI] [PubMed] [Google Scholar]