Aim: Artificial intelligence (AI) has the potential to improve perioperative diagnosis and decision making. Despite promising study results, the majority of AI platforms in surgery currently remain in the research setting. Understanding the current knowledge and general attitude of surgeons toward AI applications in their surgical practice is essential and can contribute to the future development and uptake of AI in surgery.
Methods: In March 2021, a web-based survey was conducted among members of the Dutch Association of Surgery. The survey measured opinions on the existing knowledge, expectations, and concerns on AI among surgical residents and surgeons.
Results: A total of 313 respondents completed the survey. Overall, 85% of the respondents agreed that AI could be of value in the surgical field and 61% expected AI to improve their diagnostic ability. The outpatient clinic (35.8%) and operating room (39.6%) were stated as area of interest for the use of AI. Statistically, surgeons working in an academic hospital were more likely to be aware of the possibilities of AI (P = 0.01). The surgeons in this survey were not worried about job replacement, however they raised the greatest concerns on accountability issues (50.5%), loss of autonomy (46.6%), and risk of bias (43.5%).
Conclusion: This survey demonstrates that the majority of the surgeons show a positive and open attitude towards AI. Although various ethical issues and concerns arise, the expectations regarding the implementation of future surgical AI applications are high.
The recent development in the areas of deep learning and deep convolutional neural networks has significantly progressed and advanced the field of computer vision (CV) and image analysis and understanding. Complex tasks such as classifying and segmenting medical images and localising and recognising objects of interest have become much less challenging. This progress has the potential of accelerating research and deployment of multitudes of medical applications that utilise CV. However, in reality, there are limited practical examples being physically deployed into front-line health facilities. In this paper, we examine the current state of the art in CV as applied to the medical domain. We discuss the main challenges in CV and intelligent data-driven medical applications and suggest future directions to accelerate research, development, and deployment of CV applications in health practices. First, we critically review existing literature in the CV domain that addresses complex vision tasks, including: medical image classification; shape and object recognition from images; and medical segmentation. Second, we present an in-depth discussion of the various challenges that are considered barriers to accelerating research, development, and deployment of intelligent CV methods in real-life medical applications and hospitals. Finally, we conclude by discussing future directions.
Aim: Computer vision is a subset of machine learning (ML) technology that allows automated analysis of large operative video datasets. The aim of this study was to use a commercially available ML-driven platform to evaluate a subjective grading of operative difficulty in laparoscopic cholecystectomy (LC).
Methods: Patients undergoing LC prospectively consented, and their operations were recorded. The intra-operative findings were prospectively graded (1-4) based on intraoperative gallbladder appearance assessments. Deidentified videos were uploaded to Touch SurgeryTMand run through the platform’s algorithm, providing automated analytics including the total operative length and operative phase length. The rate of critical view of safety (CVS) achievement was also included in the analysis.
Results: 206 LC were included. 27 LC were excluded due to incomplete video recording and were therefore not amenable to the final data analysis. Grade 1 and 2 patients had significantly shorter operative time than grade 3 and 4 patients [17min and 53s (IQR 15min and 24s- 21min and 38s) vs. 25 min and 49s (IQR 20min and 12s-38min and 38s) (P < 0.010)]. The operative phases for each step were significantly longer in patients with gallbladders graded 3 or 4 compared to those patients graded 1 or 2 (P < 0.043). The CVS was achieved in 94% of grade 1 patients, 88% of grade 2 patients, 85% of grade 3 patients and 73% of grade 4 patients (P = 0.177).
Conclusion: Increased operative time and decreased ability to achieve the CVS with more difficult intraoperative findings supports the utility of the proposed grading system. ML in surgery is a nascent field, but this study demonstrates the potential of commercially available platforms for use in operative analytics, documentation, audit and training of future surgeons.