EUVIMEDEUVIMED entdecken
Scoping ReviewOpen Access · CC BY 4.0

Use of artificial intelligence in the analysis of digital videos of invasive surgical procedures: scoping review

Einsatz künstlicher Intelligenz in der Analyse digitaler Videos invasiver chirurgischer Eingriffe: Scoping Review

Anni King iD, George E Fowler, Rhiannon C Macefield iD, Hamish Walker, Charlie Thomas, Sheraz Markar iD, Ethan Higgins, Jane M Blazeby, Natalie S Blencowe

BJS Open · 01.07.2025 · 9 (4)

DOI: 10.1093/bjsopen/zraf073 ↗

Auf einen Blick

Das Scoping Review fasste 122 Studien zur KI-gestützten Analyse von OP-Videos zusammen. Häufige Ziele waren Phasenerkennung, Instrumentenerkennung und verbesserte intraoperative Visualisierung.

Fragestellung

Wie wird künstliche Intelligenz zur Analyse von Videos chirurgischer Eingriffe eingesetzt, und welche Evidenzlücken bestehen?

Methode

Systematische Suche in Ovid MEDLINE und Embase; systematisches Scoping Review mit deskriptiver Zusammenfassung der Daten.

Ergebnisse

122 Studien. 75 Studien (61,5 %) zu gastrointestinalen Eingriffen, meist Cholezystektomie (47, 38,5 %). Häufigste Ziele: Phasenerkennung (40), Instrumentenerkennung (28), Visualisierung (23).

Einschränkungen

Oft fehlten Angaben zu Annotator:innen, deren Erfahrung sowie zu Trainings-, Test- und Validierungsprozessen. Häufig keine großen multizentrischen Datensätze.

Schlussfolgerung der Autor:innen

Viele Studien ließen wesentliche methodische Details der KI-Trainings-, Test- und Validierungsprozesse aus, was Interpretation und Replikation erschwert. Es fehlen große Datensätze aus mehreren Zentren und von mehreren Operateur:innen.

Kernaussagen

  • 122 Studien zur KI-Analyse von OP-Videos
  • Häufigste Ziele: Phasen-, Instrumenten- und Visualisierungserkennung
  • Viele methodische Angaben zu Annotation und Validierung fehlten

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Scoping Review in der Zeitschrift BJS Open, online erschienen am 17.07.2025. Verfasst von Anni King und 8 weiteren Autor:innen. Beteiligte Einrichtung: National Institute for Health Research Bristol Biomedical Research Centre (Surgical and Orthopeadic Innovation Theme), University of Bristol & Centre…. Hauptthemen laut MEDLINE: Artificial Intelligence, Video Recording, Surgical Procedures, Operative. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 157 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute for Health and Care Research, Biomedical Research Centre, University of Bristol.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Surgical videos are a valuable data source, offering detailed insights into surgical practice. However, video analysis requires specialist clinical knowledge and takes considerable time. Artificial intelligence (AI) has the potential to improve and streamline the interpretation of intraoperative video data. This systematic scoping review aimed to summarize the use of AI in the analysis of videos of surgical procedures and identify evidence gaps.

Methods

Systematic searches of Ovid MEDLINE and Embase were performed using search terms ‘artificial intelligence’, ‘video’, and ‘surgery’. Data extraction included reporting of general study characteristics; the overall objective of AI; descriptions of data sets, AI models, and training; methods of data annotation; and measures of accuracy. Data were summarized descriptively.

Results

In all, 122 studies were included. More than half focused on gastrointestinal procedures (75 studies, 61.5%), predominantly cholecystectomy (47, 38.5%). The most common objectives were surgical phase recognition (40 studies, 32.8%), surgical instrument recognition (28, 23.0%), and enhanced intraoperative visualization (23, 18.9%). Of the studies, 79.5% (97) used a single data set and most (92, 75.4%) used supervised machine learning techniques. There was considerable variation across the studies in terms of the number of videos, centres, and contributing surgeons. Forty-seven studies (38.5%) did not report the number of annotators, and details about their experience were frequently omitted (102, 83.6%). Most studies used multiple outcome measures (67, 54.9%), most commonly overall or best accuracy of the AI model (67, 54.9%).

Conclusion

This review found that many studies omitted essential methodological details of AI training, testing, data annotation, and validation processes, creating difficulties when interpreting and replicating these studies. Another key finding was the lack of large data sets from multiple centres and surgeons. Future research should focus on curating large, varied, open-access data sets from multiple centres, patients, and surgeons to facilitate accurate evaluation using real-world data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceVideo RecordingSurgical Procedures, OperativeHumans

Stichwörter der Autor:innen

artificial intelligenceoperativeproceduresreviewsurgeryvideo

Autor:innen und Institutionen

  • National Institute for Health Research Bristol Biomedical Research Centre (Surgical and Orthopeadic Innovation Theme), University of Bristol & Centre for Surgical Research, Bristol Medical School: Population Health Scie…
  • Nuffield Department of Surgical Sciences, Oxford University Hospitals, Oxford, UK.
  • School of Medicine, University of Sunderland, Sunderland, UK.

ORCID-Profile: Anni King, Rhiannon C Macefield, Sheraz Markar

Förderung

  • National Institute for Health and Care Research
  • Biomedical Research Centre
  • University of Bristol
  • NHS
  • NIHR
  • Royal College of Surgeons of England
  • Department of Health and Social Care
  • MRC Clinician Scientist Fellowship

Zitieren

APA

King, A., Fowler, G. E., Macefield, R. C., Walker, H., Thomas, C., Markar, S., Higgins, E., Blazeby, J. M., & Blencowe, N. S. (2025). Use of artificial intelligence in the analysis of digital videos of invasive surgical procedures: scoping review. BJS Open, 9(4). https://doi.org/10.1093/bjsopen/zraf073

Vancouver

King A, Fowler GE, Macefield RC, Walker H, Thomas C, Markar S, et al. Use of artificial intelligence in the analysis of digital videos of invasive surgical procedures: scoping review. BJS Open. 2025;9(4). doi:10.1093/bjsopen/zraf073

BibTeX
@article{King2025,
  author = {King, Anni and Fowler, George E and Macefield, Rhiannon C and Walker, Hamish and Thomas, Charlie and Markar, Sheraz and Higgins, Ethan and Blazeby, Jane M and Blencowe, Natalie S},
  title = {Use of artificial intelligence in the analysis of digital videos of invasive surgical procedures: scoping review},
  journal = {BJS Open},
  year = {2025},
  volume = {9},
  number = {4},
  doi = {10.1093/bjsopen/zraf073}
}
Kostenlos starten →