A framework for intelligent speech-based self-care health information and disease diagnosis systems.
No Thumbnail Available
Date
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Description
Self-care health information obtained from the Internet is largely
delivered in text form, and therefore inadequate for the needs of
the blind, the visually impaired and the computer illiterates.
Existing speech-based disease screening systems also lack
reasoning capability expected of disease diagnosis systems. In this
work, we have designed and developed SSDDeS that makes
possible, speech-based access to self-care health information. The
system also diagnoses diseases using rule-based reasoning
technique. Selected number of fever rampant in Africa is
diagnosed by the system. Health information for the types of fever
diagnosed by the system and information about how these
diseases are diagnosed was obtained from the American Medical
Library Association recommended websites and doctors.
VoiceObjects Desktop for Eclipse was used to develop, test and
deploy the prototype application. Voxeo Prophecy was used as the
media platform, and server-side Javascript was used to specify the
rules using script objects. Logic objects were used to control the
logic of the dialog flow. VoiceObjects embedded database was
used to store the context of the problem domain, while the inbuilt
rule engine within VoiceObjects determines which rule gets fired.
X-Lite soft phone was used to call the application. This initiative
makes web-based health information available through speech and
takes care of the needs of the estimated 180,000,000 visually
impaired and blind people worldwide as well as the computer
illiterates that cannot access websites. It also incorporates
reasoning, which existing systems lack, into speech-based disease
screening systems to enable them diagnose more than one disease.
Keywords
QA75 Electronic computers. Computer science