Conversational ontology operator: patient-centric vaccine dialogue management engine for spoken conversational agents

Muhammad Amith,Grace Xiong,Anna Zhu,Licong Cui,Hua Xu,Rebecca Z Lin,Kirk Roberts,Cui Tao,Dennis Wang

doi:10.1186/s12911-020-01267-y

Abstract

BackgroundPreviously, we introduced our Patient Health Information Dialogue Ontology (PHIDO) that manages the dialogue and contextual information of the session between an agent and a health consumer. In this study, we take the next step and introduce the Conversational Ontology Operator (COO), the software engine harnessing PHIDO. We also developed a question-answering subsystem called Frankenstein Ontology Question-Answering for User-centric Systems (FOQUS) to support the dialogue interaction.MethodsWe tested both the dialogue engine and the question-answering system using application-based competency questions and questions furnished from our previous Wizard of OZ simulation trials.ResultsOur results revealed that the dialogue engine is able to perform the core tasks of communicating health information and conversational flow. Inter-rater agreement and accuracy scores among four reviewers indicated perceived, acceptable responses to the questions asked by participants from the simulation studies, yet the composition of the responses was deemed mediocre by our evaluators.ConclusionsOverall, we present some preliminary evidence of a functioning ontology-based system to manage dialogue and consumer questions. Future plans for this work will involve deploying this system in a speech-enabled agent to assess its usage with potential health consumer users.

Highlights

We introduced our Patient Health Information Dialogue Ontology (PHIDO) that manages the dialogue and contextual information of the session between an agent and a health consumer
Overall, we present some preliminary evidence of a functioning ontology-based system to manage dialogue and consumer questions
This type of communication is helpful in personal interaction between the patient and provider when discussing the human papillomavirus (HPV) vaccine which mitigates cancers caused by the HPV virus in adulthood, and it has been reported to encourage vaccine uptake [4]

Summary

Introduction

We introduced our Patient Health Information Dialogue Ontology (PHIDO) that manages the dialogue and contextual information of the session between an agent and a health consumer. Face-to-face communication between a health providers and patients is an important factor in improving health outcomes This type of communication is helpful in personal interaction between the patient and provider when discussing the human papillomavirus (HPV) vaccine which mitigates cancers caused by the HPV virus in adulthood, and it has been reported to encourage vaccine uptake [4]. Despite the recommendations and benefits of the HPV vaccine, the vaccination rates are below the 80% coverage rate promoted by the Healthy People 2020 report [6] This is complicated with the limited time that health care providers have to discuss the HPV vaccine with health consumers, with just a third of the patients receiving a discussion about the HPV vaccine during their visit [4]. One experimental solution is our proposition for a speechenabled dialogue system embodied in a software agent that could facilitate the communication task of counseling on the HPV vaccine during the patients’ clinical visit

Objectives

Methods

Results

Discussion

Conclusion