Page 70 - Read Online

Page 28 McGivern et al. Art Int Surg 2023;3:27-47 https://dx.doi.org/10.20517/ais.2022.39

Results: 98 studies were included. Most studies were performed in China or the USA (n = 45). Liver surgery was
the most common area studied (n = 51). Research into AI in HPB surgery has increased rapidly in recent years, with
almost two-thirds published since 2019 (61/98). Of these studies, 11 have focused on using “big data” to develop
and apply AI models. Nine of these studies came from the USA and nearly all focused on the application of Natural
Language Processing. We identified several critical conceptual areas where AI is under active development,
including improving preoperative optimization, image guidance and sensor fusion-assisted surgery, surgical
planning and simulation, natural language processing of clinical reports for deep phenotyping and prediction, and
image-based machine learning.

Conclusion: Applications of AI in HPB surgery primarily focus on image analysis and computer vision to address
diagnostic and prognostic uncertainties. Virtual 3D and augmented reality models to support complex HPB
interventions are also under active development and likely to be used in surgical planning and education. In
addition, natural language processing may be helpful in the annotation and phenotyping of disease, leading to new
scientific insights.

Keywords: Artificial Intelligence, big data, surgery, liver, pancreas, biliary

INTRODUCTION
Artificial Intelligence (AI) encompasses a range of computational approaches with the central aim of
developing algorithms to process and interpret information. AI methods can be applied to various input
data types ranging from tabular datasets and images to multimedia and text. Although termed
“intelligence”, these algorithms are in no sense conscious or able to employ “rational thought”, but in most
cases, reflect model parameters derived exclusively from input data. Within AI, there are three overlapping
fields that arguably have the most potential for HPB surgery: machine learning (ML), computer vision (CV)
and natural language processing (NLP). ML uses algorithms to learn, adapt, and draw inferences from
patterns in training data. CV allows for supervised or unsupervised image analysis, allowing for features of
interest in images to be identified and characterized. For text-based sources of data written as prose or in a
“human-readable” format (e.g., radiology or pathology reports), NLP allows computers to interpret human
[1-5]
text or spoken language communication .
The specific areas and applications of AI most likely to deliver a positive impact on patient care currently
need to be clarified, as are the barriers limiting the uptake of AI approaches into clinical practice. In 2021
Bari et al. described the applications of AI in hepatopancreatic and biliary (HPB) surgery, proposing the
framework of preoperative, intraoperative, and postoperative AI applications. We have adopted this
structure for this review .
[6]

With the increased availability of structured and unstructured healthcare datasets, the opportunity for AI-
based approaches widens. Policymakers, healthcare providers, and industry are exploring new AI
approaches, seeking to utilize data across a range of applications, including improving outcomes, optimizing
the patient experience, and providing cost-effectiveness in delivering care at the health system level . In
[7-9]
this review, we aim to outline the fundamental AI approaches to pressing questions in HPB surgery,
identifying where AI is most likely to have an impact in future patient care.

METHODS
This scoping review was performed in accordance with the PRISMA-ScR guidelines for scoping reviews .
[10]
The Medline database was searched systematically using the following Medical Subject Headings (MeSH)
search terms to ensure the identification of appropriate articles; “Algorithms.mp. or algorithm/” AND