Graphical access to medical expert systems: iv. experiments to determine the role of spoken input
From Semantic Portal Wiki
{{#vardefine:category|Publication}}{{#vardefine:templatename|i.publication}}{{#vardefine:package|smwbp_instance_templates}}
| Edit |
Reference: {{#vardefine:pagename|graphical access to medical expert systems: iv. experiments to determine the role of spoken input }}
- [[]]
bibtex
{{#vardefine:pagename|Graphical access to medical expert systems: iv. experiments to determine the role of spoken input }}{{#vardefine:key| }}
abstract: Our goal is to design improved interfaces for medical expert systems. Wehave explored previously the use of graphical techniques to improve theacceptance by clinicians of the user interface. Now that devices that acceptspoken input are available, we wish to design interfaces that take advantageof this potentially more natural modality for interaction. To understand howclinicians might want to speak to a medical decision-support system, wecarried out an experiment that simulated the availability of a spokeninterface to the ONCOCIN medical expert system. ONCOCIN provides therapyadvice for patients on complex cancer therapy protocols based on a descriptionof the patient's current medical status and laboratory-test values. In theexperiment, we had oncologists present a clinical case while observing theONCOCIN flowsheet display. A project member listened to the presentation andfilled in values for the flowsheet, as well as introducing purposefulmisunderstandings of the input. The results suggest that each individualdeveloped a stereotypical grammar for communicating with the program. Ourexperience with the purposeful miscommunications suggests particular ways totailor requests for repetition based on which part of the utterance was notunderstood.
download:
- paper:
- slides:
| Abstract | Our goal is to design improved interfaces … Our goal is to design improved interfaces for medical expert systems. Wehave explored previously the use of graphical techniques to improve theacceptance by clinicians of the user interface. Now that devices that acceptspoken input are available, we wish to design interfaces that take advantageof this potentially more natural modality for interaction. To understand howclinicians might want to speak to a medical decision-support system, wecarried out an experiment that simulated the availability of a spokeninterface to the ONCOCIN medical expert system. ONCOCIN provides therapyadvice for patients on complex cancer therapy protocols based on a descriptionof the patient's current medical status and laboratory-test values. In theexperiment, we had oncologists present a clinical case while observing theONCOCIN flowsheet display. A project member listened to the presentation andfilled in values for the flowsheet, as well as introducing purposefulmisunderstandings of the input. The results suggest that each individualdeveloped a stereotypical grammar for communicating with the program. Ourexperience with the purposeful miscommunications suggests particular ways totailor requests for repetition based on which part of the utterance was notunderstood. h part of the utterance was notunderstood. |
| Author | Ellen Isaacs +, Carl E. Wulfman +, Janice Anne Rohn +, Christopher D. Lane +, and Lawrence M. Fagan + |
| Bibtype | techreport + |
| Institution | Knowledge Systems, AI Laboratory + |
| Key | KSL-90-69 + |
| Month | April + |
| Number | KSL-90-69 + |
| Tag | Computer science + |
| Title | Graphical Access to Medical Expert Systems: IV. Experiments to Determine the Role of Spoken Input + |
| Tr id | KSL-90-69 + |
| Year | 1993 + |
