Artificial intelligence as a diagnostic aid in cross-sectional radiological imaging of the abdominopelvic cavity: a protocol for a systematic review

A systematic scoping review protocol to summarise and appraise the use of artificial intelligence in the analysis of digital videos of invasive general surgical procedures

Background

Intraoperative video recordings are a valuable addition to operative written documentation. However, the review of these videos often requires surgical expertise and takes considerable time. While a large amount of work has been undertaken to understand the role of artificial intelligence (AI) in healthcare more generally, the application of these techniques to automate the analysis of surgical videos is currently unclear. In this systematic scoping review, we sought to give a contemporary overview of the use of AI research in the analysis of digital videos of invasive general surgical procedures. We will describe and summarise the study characteristics, purpose of the applications and stage of development, to ascertain how these techniques might be applied in future research and to identify gaps in current knowledge (e.g. uncertainties about the study methods).

Methods

Systematic searches will be conducted in OVID Medline and Embase, using terms related to 'artificial intelligence', 'surgery' and 'video' to identify all potentially relevant studies published since 1st January 2012. All primary studies where AI has been applied to the analysis of videos (recorded by conventional digital cameras or laparoscopic or robotic-assisted technology) of general surgical procedures will be included. Data extraction will include study characteristics, governance, details of video datasets and AI models, measures of accuracy, validation and any reported limitations.

Ethics and dissemination

No ethical approval is required as primary data will not be collected. The results will be disseminated at relevant conferences, on social media and published in a peer-reviewed journal.

Artificial intelligence as a diagnostic aid in cross-sectional radiological imaging of surgical pathology in the abdominopelvic cavity: a systematic review

OBJECTIVES

There is emerging use of artificial intelligence (AI) models to aid diagnostic imaging. This review examined and critically appraised the application of AI models to identify surgical pathology from radiological images of the abdominopelvic cavity, to identify current limitations and inform future research.

DESIGN

Systematic review.

DATA SOURCES

Systematic database searches (Medline, EMBASE, Cochrane Central Register of Controlled Trials) were performed. Date limitations (January 2012 to July 2021) were applied.

ELIGIBILITY CRITERIA

Primary research studies were considered for eligibility using the PIRT (participants, index test(s), reference standard and target condition) framework. Only publications in the English language were eligible for inclusion in the review.

DATA EXTRACTION AND SYNTHESIS

Study characteristics, descriptions of AI models and outcomes assessing diagnostic performance were extracted by independent reviewers. A narrative synthesis was performed in accordance with the Synthesis Without Meta-analysis guidelines. Risk of bias was assessed (Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2)).

RESULTS

Fifteen retrospective studies were included. Studies were diverse in surgical specialty, the intention of the AI applications and the models used. AI training and test sets comprised a median of 130 (range: 5-2440) and 37 (range: 10-1045) patients, respectively. Diagnostic performance of models varied (range: 70%-95% sensitivity, 53%-98% specificity). Only four studies compared the AI model with human performance. Reporting of studies was unstandardised and often lacking in detail. Most studies (n=14) were judged as having overall high risk of bias with concerns regarding applicability.

CONCLUSIONS

AI application in this field is diverse. Adherence to reporting guidelines is warranted. With finite healthcare resources, future endeavours may benefit from targeting areas where radiological expertise is in high demand to provide greater efficiency in clinical care. Translation to clinical practice and adoption of a multidisciplinary approach should be of high priority.

PROSPERO REGISTRATION NUMBER

CRD42021237249.