Background: Systematic and scoping literature searches are increasingly resource intensive. We present the results of a scoping review which combines the use of a novel artificial-intelligence-(AI)-assisted Medline search tool with two other ‘traditional’ literature search methods. We illustrate this novel approach with a case study to identify and map the range of conditions (clinical presentations, complications, coinfections and health problems) associatedwith gonorrhoea infection.
Methods: To fully characterize the range of health outcomes associated with gonorrhoea, we combined a high yield preliminary search with a traditional systematic search, then supplemented with the output of a novel AI-assisted Medline search tool based on natural language processing methods to identify eligible literature.
Results: We identified 189 health conditions associated with gonorrhoea infection of which: 53 were identified through the initial ‘high yield’ search; 99 through the systematic search; and 124 through the AI-assisted search. These were extracted from 107 unique references and 21 International Statistical Classification of Diseases and Related Health Problems Ninth and Tenth Revision (ICD 9/10) or Read codes. Health conditions were mapped to the urogenital tract (n = 86), anorectal tract (n = 6) oropharyngeal tract (n = 5) and the eye (n = 14); and other conditions such as systemic (n = 61) and neonatal conditions (n = 7), psychosocial associations (n = 3), and co-infections (n = 7). The 107 unique references attained a Scottish Intercollegiate Guidelines Network (SIGN) score of ≥ 2++ (n = 2), 2+ (14 [13%]), 2- (30 [28%]) and 3 (45 [42%]), respectively. The remaining papers (n = 16) were reviews.
Conclusions: Through AI screening of Medline, we captured – titles, abstracts, case reports and case series related to rare but serious health conditions related to gonorrhoea infection. These outcomes might otherwise have been missed during a systematic search. The AI-assisted search provided a useful addition to traditional/manual literature searches especially when rapid results are required in an exploratory setting.
(2021-09-07)
Additional file 2:
https://doi.org/10.6084/m9.figshare.16576113 Supplemental Fig. 1. Raw textual output listing a sample of representative words of one of the topics identified by the AI methods of the Papyrus tool from the corpus resulting from the search query ‘gonorrhea’. In this example, the most important topic-word (most frequently occurring) is ‘ectopic pregnancy’ followed by other words like ‘chlamydia trachomatis’ and ‘salpinx’. Supplementary Text 2.1. Public Health Websites accessed for the initial ‘high yield’ search. Supplementary Text 2.2. Seminal literature based on a review of key authors in the field. Supplementary Table 1. ICD9/ICD10 and Read (CPRD) codes. Supplementary Table 2. Read codes (level 3).
***This entry has been automatically imported via Datacite by LIST harvest scripts. Please refer to the above mentioned DOIs of the original and latest version of the datasets and data downloads*** (2026-03-25)
