Page 84 - Read Online

Page 42 McGivern et al. Art Int Surg 2023;3:27-47 https://dx.doi.org/10.20517/ais.2022.39

development: Transparent Reporting of a multivariable prediction model of Individual Prognosis Or
Diagnosis AI extension (TRIPOD-AI) and the Prediction model Risk Of Bias Assessment Tool (PROBAST-
[118]
AI) . These promise to provide standardization and assessment tools that will greatly increase the quality
of clinically-orientated AI study reporting.

Where should AI research in HPB be focussed? Most studies in this review concentrated on image analysis.
While this is an important area, there are many other challenges in HPB which could benefit from the
application of AI. Research prioritization in AI must be determined by broad stakeholder groups, led
primarily by the patient and public representatives, accounting for a range of viewpoints and actively
engaging non-technical individuals in the design and delivery of research studies. We found little mention
of engagement with stakeholder groups in included studies (e.g., patients, clinicians and the wider HPB
community), which is crucial if these complex interventions are to move into clinical practice successfully.
Moreover, included studies focused on the development of AI models rather than on the implementation of
AI systems. While this is understandable given the current stage of development, future work should focus
on how broader AI-driven systems can be implemented safely into clinical pathways and be clear about the
function they serve.

Our study has several limitations. First, there is significant heterogeneity in the content and outcomes of the
various studies included. While meaningful comparisons are challenging, a useful overview of common
issues and themes affecting AI research in HPB is provided. Second, as is the nature of a scoping review, it is
possible that studies meeting the inclusion criteria have been omitted, leading to an incomplete presentation
of the current literature. For example, papers focusing on NLP and the gallbladder were relatively poorly
represented in exploratory literature searches, possibly reflecting poor search descriptors and study labeling.
Finally, as AI and associated concepts are undergoing rapid development, study inclusion criteria are in
flux. Improving formal definitions in these emerging fields will help study classification and ease of
literature identification.

The use of AI and big data in HPB surgery and medicine, more generally, is rapidly expanding. AI promises
benefits in the delivery of clinical care and may result in future improvement of healthcare outcomes. This
review identifies crucial interlinking conceptual areas of AI as applied to HPB surgery. Future research must
address issues of bias, transparency, and explainability and ensure that innovation is representative of HPB
patient populations across the world.

DECLARATIONS
Authors’ contributions
Participated in the design of the study, data collection, screening, interpretation and presentation, writing of
the manuscript and submitted the manuscript: McGivern KG
Participated in the design of the study, data collection, screening, interpretation and presentation, and
critical evaluation of the manuscript: Knight SR
Participated in the writing and critical evaluation of the manuscript: Drake TM
Participated in data screening and presentation: Lucocq J
Participated in the critical evaluation of the manuscript: Bernabeu MO, Clark N, Fairfield C, Pius R, Shaw
C, Seth S
Participated in the design of the study and critical evaluation of the manuscript: Harrison EM
All authors approved the final version of the manuscript