TY - JOUR
T1 - Artificial Intelligent Virtual Assistant for Plastic Surgery Patient's Frequently Asked Questions
T2 - A Pilot Study
AU - Boczar, Daniel
AU - Sisti, Andrea
AU - Oliver, Jeremie D.
AU - Helmi, Haytham
AU - Restrepo, David J.
AU - Huayllani, Maria T.
AU - Spaulding, Aaron C.
AU - Carter, Rickey
AU - Rinker, Brian D.
AU - Forte, Antonio Jorge
N1 - Funding Information:
Conflicts of interest and sources of funding: This study was supported in part by the Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery. The authors have no conflicts of interest to declare.
Publisher Copyright:
© 2019 Wolters Kluwer Health, Inc. All rights reserved.
PY - 2020/4/1
Y1 - 2020/4/1
N2 - Background: Artificial Intelligent Virtual Assistants (AIVA) is a segment of artificial intelligence that is rapidly developing. However, its utilization to address patients' frequently asked questions remains unexplored. Methods: We developed an AIVA to answer questions related to 10 frequent topics asked by plastic surgery patients in our institution. Between July 27, 2018, and August 10 of 2018, we recruited subjects with administrative positions at our health care institution to chat with the virtual assistant. They asked, with their own words, 1 question for each topic and filled out a satisfaction questionnaire. Postsurvey analysis of questions and answers allowed assessment of the virtual assistant's accuracy. Results: Thirty participants completed the survey. The majority was female (70%), and the mean age was 27.76 years (SD, 8.68 [19-51] years). The overall accuracy of the plastic surgery AIVA was 92.3% (277/294 questions), and participants considered the answer correct in 83.3% of the time (250/294 answers). Most of the participants considered the AIVA easy to use, answered adequately, and could be helpful for patients. However, when asked if this technology could replace a human assistant, they stayed neutral.
AB - Background: Artificial Intelligent Virtual Assistants (AIVA) is a segment of artificial intelligence that is rapidly developing. However, its utilization to address patients' frequently asked questions remains unexplored. Methods: We developed an AIVA to answer questions related to 10 frequent topics asked by plastic surgery patients in our institution. Between July 27, 2018, and August 10 of 2018, we recruited subjects with administrative positions at our health care institution to chat with the virtual assistant. They asked, with their own words, 1 question for each topic and filled out a satisfaction questionnaire. Postsurvey analysis of questions and answers allowed assessment of the virtual assistant's accuracy. Results: Thirty participants completed the survey. The majority was female (70%), and the mean age was 27.76 years (SD, 8.68 [19-51] years). The overall accuracy of the plastic surgery AIVA was 92.3% (277/294 questions), and participants considered the answer correct in 83.3% of the time (250/294 answers). Most of the participants considered the AIVA easy to use, answered adequately, and could be helpful for patients. However, when asked if this technology could replace a human assistant, they stayed neutral.
KW - artificial intelligence
KW - conversational agents
KW - frequently asked questions
KW - plastic surgery
KW - virtual assistant
UR - http://www.scopus.com/inward/record.url?scp=85081944148&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081944148&partnerID=8YFLogxK
U2 - 10.1097/SAP.0000000000002252
DO - 10.1097/SAP.0000000000002252
M3 - Article
C2 - 32032120
AN - SCOPUS:85081944148
SN - 0148-7043
VL - 84
SP - E16-E21
JO - Annals of plastic surgery
JF - Annals of plastic surgery
IS - 4
ER -