Page 71 - Read Online

McGivern et al. Art Int Surg 2023;3:27-47 https://dx.doi.org/10.20517/ais.2022.39 Page 29

“surgery/ or biliary tract surgery/ or liver surgery/ or pancreas surgery/”. Articles were limited to English
language and those published from 2012 onwards to provide contemporary studies that were likely
reflective of current approaches in AI. Further supplementary searches were performed using citation lists
th
and the Google Scholar database. The last search was conducted on 5 August 2022.

We defined “HPB surgery”, as the surgical management of benign and malignant diseases of the liver,
pancreas, gallbladder, and bile ducts. “Artificial intelligence” refers to the use of various algorithmic
methods which could be applied to interpret or process information. We further assessed the identified
papers for the element of AI primarily used i.e., machine/deep learning, computer vision or natural
language processing .
[1-5]

Following the literature search, article titles and abstracts were screened by three reviewers (KMcG, SRK, JL)
and those meeting the inclusion criteria underwent full-text review. Any disagreements were resolved by
consensus within the group. References from included articles were searched to identify any other relevant
articles. Conference abstracts were screened to assist in identifying related full-text articles before inclusion.
Where more than one article was published from a single data set, the article analyzing the largest cohort of
patients was included.

Data were extracted independently using a standardized pro forma. This included the aim of the study,
methodology, year of publication, countries represented, the primary organ of focus, AI methods employed,
and the number of patients (where applicable). Identified publications were further interrogated to find a
shared focus on diagnostics, prognostics, or intervention, allowing further subdivision of the presented
research. We then undertook a conceptual mapping exercise to identify areas of crucial importance.

We used a pragmatic approach to further select studies with a sample size equal to or greater than five
thousand that satisfied the “velocity, volume and variety” of data points needed to be considered as “big
data”. A similar approach used previously, albeit with smaller datasets, acted as a benchmark [7-9,11] . Any
disagreements on the selection of these papers were resolved by group consensus.

The Covidence online toolkit was used throughout the data collection and extraction stages of this scoping
[12]
review .

RESULTS
Scoping search results
The search identified 5,221 articles, of which 134 were fully assessed for eligibility. A further 63 articles were
identified from article citation lists or by the supplementary search of the Google Scholar database
[Figure 1]. Following assessment, 98 studies [13-110] were included in this review, with most studies excluded
due to being in conference abstract form only (n = 84).

Characteristics of included studies
Identified studies had a wide geographical distribution, coming from a total of 24 countries, with the
majority from China or the USA (45/98). No papers identified originated from the African continent
[Figure 2]. Studies on the use of AI in surgical conditions of the liver predominated (n = 51). Research on
pancreatic and biliary conditions (n = 23) was included at a comparable frequency to one another. We
noted a rapid increase in the number of studies published over the past three years, with almost two-thirds
of the identified papers (n = 61) published since 2019 [Figure 3].