Preliminary Screening for Hereditary Breast and Ovarian Cancer Using a Chatbot Augmented Intelligence Genetic Counselor: Development and Feasibility Study.
IBM Watson
artificial intelligence
augmented intelligence
cancer
chatbot
familial cancer
feasibility
genetics
hereditary cancer
preliminary screening
screening
Journal
JMIR formative research
ISSN: 2561-326X
Titre abrégé: JMIR Form Res
Pays: Canada
ID NLM: 101726394
Informations de publication
Date de publication:
05 Feb 2021
05 Feb 2021
Historique:
received:
21
10
2020
accepted:
09
01
2021
revised:
29
12
2020
entrez:
5
2
2021
pubmed:
6
2
2021
medline:
6
2
2021
Statut:
epublish
Résumé
Breast cancer is the most common form of cancer in Japan; genetic background and hereditary breast and ovarian cancer (HBOC) are implicated. The key to HBOC diagnosis involves screening to identify high-risk individuals. However, genetic medicine is still developing; thus, many patients who may potentially benefit from genetic medicine have not yet been identified. This study's objective is to develop a chatbot system that uses augmented intelligence for HBOC screening to determine whether patients meet the National Comprehensive Cancer Network (NCCN) BRCA1/2 testing criteria. The system was evaluated by a doctor specializing in genetic medicine and certified genetic counselors. We prepared 3 scenarios and created a conversation with the chatbot to reflect each one. Then we evaluated chatbot feasibility, the required time, the medical accuracy of conversations and family history, and the final result. The times required for the conversation were 7 minutes for scenario 1, 15 minutes for scenario 2, and 16 minutes for scenario 3. Scenarios 1 and 2 met the BRCA1/2 testing criteria, but scenario 3 did not, and this result was consistent with the findings of 3 experts who retrospectively reviewed conversations with the chatbot according to the 3 scenarios. A family history comparison ascertained by the chatbot with the actual scenarios revealed that each result was consistent with each scenario. From a genetic medicine perspective, no errors were noted by the 3 experts. This study demonstrated that chatbot systems could be applied to preliminary genetic medicine screening for HBOC.
Sections du résumé
BACKGROUND
BACKGROUND
Breast cancer is the most common form of cancer in Japan; genetic background and hereditary breast and ovarian cancer (HBOC) are implicated. The key to HBOC diagnosis involves screening to identify high-risk individuals. However, genetic medicine is still developing; thus, many patients who may potentially benefit from genetic medicine have not yet been identified.
OBJECTIVE
OBJECTIVE
This study's objective is to develop a chatbot system that uses augmented intelligence for HBOC screening to determine whether patients meet the National Comprehensive Cancer Network (NCCN) BRCA1/2 testing criteria.
METHODS
METHODS
The system was evaluated by a doctor specializing in genetic medicine and certified genetic counselors. We prepared 3 scenarios and created a conversation with the chatbot to reflect each one. Then we evaluated chatbot feasibility, the required time, the medical accuracy of conversations and family history, and the final result.
RESULTS
RESULTS
The times required for the conversation were 7 minutes for scenario 1, 15 minutes for scenario 2, and 16 minutes for scenario 3. Scenarios 1 and 2 met the BRCA1/2 testing criteria, but scenario 3 did not, and this result was consistent with the findings of 3 experts who retrospectively reviewed conversations with the chatbot according to the 3 scenarios. A family history comparison ascertained by the chatbot with the actual scenarios revealed that each result was consistent with each scenario. From a genetic medicine perspective, no errors were noted by the 3 experts.
CONCLUSIONS
CONCLUSIONS
This study demonstrated that chatbot systems could be applied to preliminary genetic medicine screening for HBOC.
Identifiants
pubmed: 33544084
pii: v5i2e25184
doi: 10.2196/25184
pmc: PMC7895643
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e25184Informations de copyright
©Ann Sato, Eri Haneda, Nobuyasu Suganuma, Hiroto Narimatsu. Originally published in JMIR Formative Research (http://formative.jmir.org), 05.02.2021.
Références
J Clin Oncol. 2017 Dec 1;35(34):3800-3806
pubmed: 28820644
JAMA. 2017 Jun 20;317(23):2402-2416
pubmed: 28632866
Cancer. 2008 Nov 15;113(10):2627-37
pubmed: 18853415
Nat Commun. 2018 Oct 4;9(1):4083
pubmed: 30287823
J Clin Oncol. 2016 May 1;34(13):1460-8
pubmed: 26976419
Annu Rev Genomics Hum Genet. 2008;9:321-45
pubmed: 18544032
JMIR Cancer. 2019 May 02;5(1):e12856
pubmed: 31045505
JMIR Mhealth Uhealth. 2019 Oct 31;7(10):e15018
pubmed: 31674920
Int J Med Inform. 2019 Aug;128:18-23
pubmed: 31160007