Use of Artificial Intelligence for Medical Literature Search: Randomized Controlled Trial Using the Hackathon Format.
artificial intelligence
literature review
medical information technology
Journal
Interactive journal of medical research
ISSN: 1929-073X
Titre abrégé: Interact J Med Res
Pays: Canada
ID NLM: 101598421
Informations de publication
Date de publication:
30 Mar 2020
30 Mar 2020
Historique:
received:
08
10
2019
accepted:
15
12
2019
revised:
24
11
2019
entrez:
1
4
2020
pubmed:
1
4
2020
medline:
1
4
2020
Statut:
epublish
Résumé
Mapping out the research landscape around a project is often time consuming and difficult. This study evaluates a commercial artificial intelligence (AI) search engine (IRIS.AI) for its applicability in an automated literature search on a specific medical topic. To evaluate the AI search engine in a standardized manner, the concept of a science hackathon was applied. Three groups of researchers were tasked with performing a literature search on a clearly defined scientific project. All participants had a high level of expertise for this specific field of research. Two groups were given access to the AI search engine IRIS.AI. All groups were given the same amount of time for their search and were instructed to document their results. Search results were summarized and ranked according to a predetermined scoring system. The final scoring awarded 49 and 39 points out of 60 to AI groups 1 and 2, respectively, and the control group received 46 points. A total of 20 scientific studies with high relevance were identified, and 5 highly relevant studies ("spot on") were reported by each group. AI technology is a promising approach to facilitate literature searches and the management of medical libraries. In this study, however, the application of AI technology lead to a more focused literature search without a significant improvement in the number of results.
Sections du résumé
BACKGROUND
BACKGROUND
Mapping out the research landscape around a project is often time consuming and difficult.
OBJECTIVE
OBJECTIVE
This study evaluates a commercial artificial intelligence (AI) search engine (IRIS.AI) for its applicability in an automated literature search on a specific medical topic.
METHODS
METHODS
To evaluate the AI search engine in a standardized manner, the concept of a science hackathon was applied. Three groups of researchers were tasked with performing a literature search on a clearly defined scientific project. All participants had a high level of expertise for this specific field of research. Two groups were given access to the AI search engine IRIS.AI. All groups were given the same amount of time for their search and were instructed to document their results. Search results were summarized and ranked according to a predetermined scoring system.
RESULTS
RESULTS
The final scoring awarded 49 and 39 points out of 60 to AI groups 1 and 2, respectively, and the control group received 46 points. A total of 20 scientific studies with high relevance were identified, and 5 highly relevant studies ("spot on") were reported by each group.
CONCLUSIONS
CONCLUSIONS
AI technology is a promising approach to facilitate literature searches and the management of medical libraries. In this study, however, the application of AI technology lead to a more focused literature search without a significant improvement in the number of results.
Identifiants
pubmed: 32224481
pii: v9i1e16606
doi: 10.2196/16606
pmc: PMC7154940
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e16606Informations de copyright
©Dominik Schoeb, Rodrigo Suarez-Ibarrola, Simon Hein, Franz Friedrich Dressler, Fabian Adams, Daniel Schlager, Arkadiusz Miernik. Originally published in the Interactive Journal of Medical Research (http://www.i-jmr.org/), 30.03.2020.
Références
J Med Internet Res. 2013 Aug 15;15(8):e164
pubmed: 23948488
Int J High Risk Behav Addict. 2013 Winter;1(4):166-71
pubmed: 24971257
Stroke Vasc Neurol. 2017 Jun 21;2(4):230-243
pubmed: 29507784
Open Med. 2009;3(3):e123-30
pubmed: 21603045
Med Image Anal. 2014 Apr;18(3):579-90
pubmed: 24637155
Ann Transl Med. 2016 Dec;4(23):454
pubmed: 28090510
Respir Care. 2010 May;55(5):578-83
pubmed: 20420728
Med Image Anal. 2013 Dec;17(8):974-96
pubmed: 23837969
Comput Biol Med. 1995 Mar;25(2):127-37
pubmed: 7554831