Imaging for Quality Control: Comparison of Systematic Video Recording to the Operative Note in Colorectal Cancer Surgery. A Pilot Study

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.

A comparison between real-time intraoperative voice dictation and the operative report in laparoscopic cholecystectomy: a multicenter prospective observational study

PURPOSE

The current operative report often inadequately reflects events occurring during laparoscopic cholecystectomy (LC). The addition of intraoperative video recording to the operative report has already proven to add important information. It was hypothesized that real-time intraoperative voice dictation (RIVD) can provide an equal or more complete overview of the operative procedure compared to the narrative operative report (NR) produced postoperatively.

METHODS

SONAR is a multicenter prospective observational trial, conducted at four surgical centers in the Netherlands. Elective LCs of patients aged 18 years and older were included. Participating surgeons were requested to dictate the essential steps of LC during surgery. RIVDs and NRs were reviewed according to the stepwise LC guideline of the Dutch Society for Surgery. The cumulative adequacy rates for RIVDs were compared with those of the postoperatively written NR.

RESULTS

79 of 90 cases were eligible for inclusion and available for further analysis. RIVD resulted in a significantly higher adequacy rate compared to NR for the circumferential dissection of the cystic duct and artery (NR 32.5% vs. RIVD 61.0%, P = 0.016). NR had higher adequacy rates in reporting the transection of the cystic duct (NR 100% vs. RIVD 77.9%, P =  < 0.001) and the removal of the gallbladder from the liver bed (NR 98.7% vs. RIVD 68.8%, P < 0.001). The total adequacy was not significantly different between the two reporting methods (NR 78.0% vs. RIVD 76.4%, P = 1.00).

CONCLUSION

Overall, the adequacy of RIVD is comparable to the postoperatively written NR in reporting surgical steps in LC. However, the most essential surgical step, the circumferential dissection of the cystic duct and artery, was reported more adequately in RIVD.

Association of Video Completed by Audio in Laparoscopic Cholecystectomy With Improvements in Operative Reporting

Importance

All events that transpire during laparoscopic cholecystectomy (LC) cannot be adequately reproduced in the operative note. Video recording is already known to add important information regarding this operation.

Objective

It is hypothesized that additional audio recordings can provide an even better procedural understanding by capturing the surgeons' considerations.

Design, Setting, and Participants

The Simultaneous Video and Audio Recording of Laparoscopic Cholecystectomy Procedures (SONAR) trial is a multicenter prospective observational trial conducted in the Netherlands in which operators were requested to dictate essential steps of LC. Elective LCs of patients 18 years and older were eligible for inclusion. Data collection occurred from September 18, 2018, to November 13, 2018.

Main Outcomes and Measures

Adequacy rates for video recordings and operative note were compared. Adequacy was defined as the competent depiction of a surgical step and expressed as the number of adequate steps divided by the total applicable steps for all cases. In case of discrepancies, in which a step was adequately observed in the video recording but inadequately reported in the operative note, an expert panel analyzed the added value of the audio recording to resolve the discrepancy.

Results

A total of 79 patients (49 women [62.0%]; mean [SD] age, 54.3 [15.9] years) were included. Video recordings resulted in higher adequacy for the inspection of the gallbladder (note, 39 of 79 cases [49.4%] vs video, 79 of 79 cases [100%]; P < .001), the inspection of the liver condition (note, 17 of 79 [21.5%] vs video, 78 of 79 cases [98.7%]; P < .001), and the circumferential dissection of the cystic duct and the cystic artery (note, 25 of 77 [32.5%] vs video, 62 of 77 [80.5%]; P < .001). The total adequacy was higher for the video recordings (note, 849 of 1089 observations [78.0%] vs video, 1005 of 1089 observations [92.3%]; P < .001). In the cases of discrepancies between video and note, additional audio recordings lowered discrepancy rates for the inspection of the gallbladder (without audio, 40 of 79 cases [50.6%] vs with audio, 17 of 79 cases [21.5%]; P < .001), the inspection of the liver condition (without audio, 61 of 79 [77.2%] vs with audio, 37 of 79 [46.8%]; P < .001), the circumferential dissection of the cystic duct and the cystic artery (without audio, 43 of 77 cases [55.8%] vs with audio, 17 of 77 cases [22.1%]; P < .001), and similarly for the removal of the first accessory trocar (without audio, 27 of 79 [34.2%] vs with audio, 16 of 79 [20.3%]; P = .02), the second accessory trocar (without audio, 24 of 79 [30.4%] vs with audio, 11 of 79 [13.9%]; P < .001), and the third accessory trocar (without audio, 27 of 79 [34.2%] vs with audio, 14 of 79 [17.7%]; P < .001). The total discrepancy was lower with audio adjustment (without audio, 254 of 1089 observations [23.3%] vs with audio, 128 of 1089 observations [11.8%]; P < .001).

Conclusions and Relevance

Audio recording during LC significantly improves the adequacy of depicting essential surgical steps and exhibits lower discrepancies between video and operative note.

Current perspectives on video and audio recording inside the surgical operating room: results of a cross-disciplinary survey

The availability of intraoperative multimedia recording is increasing. Considering the growing call for physicians’ accountability, it is inevitable that multimedia will play an important role in aiding quality control by improving the adequacy of operative reporting. However, the perspectives of medical professionals on this matter are poorly known. In this cross-disciplinary survey, we aimed to investigate the current viewpoints concerning the use of multimedia recording in the operating room. We conducted an electronic survey among all affiliated members of the Association of Surgeons of the Netherlands, the Dutch Urological Association and the Dutch Society of Obstetrics and Gynecology containing questions regarding current use of intraoperative recording and the level of likelihood or objection for certain scenarios. The response rate was 27.8%. The survey encompasses 370 (54.5%) surgeons, 71 (10.5%) urologists, 80 (11.8%) gynecologists, and 158 (23.3%) residents in training. 52.4% of respondents feel that the currently used operative report is insufficient for future quality requirements. 58.5% think it is unlikely they would behave differently during surgery when intra-operative video recording is applied. 82.8% think it is unlikely that their surgical methods would be altered. 63.8% of respondents preferred only video registration when intraoperative recording is implemented. The majority of respondents agree that the current method of operative reporting is insufficient for future quality requirements. There is support for intraoperative video recording, however, legal transparency is needed before either intraoperative video or audio recording could be implemented to protect not only the patients, but also the healthcare providers.

Comparison of Systematic Video Documentation With Narrative Operative Report in Colorectal Cancer Surgery

Importance

Despite ongoing advances in the field of colorectal surgery, the quality of surgical treatment is still variable. As an intrinsic part of surgical quality, the technical information regarding the surgical procedure is reflected only by the narrative operative report (NR), which has been found to be subjective and regularly omits important information.

Objective

To investigate systematic video recording (SVR) as a potential improvement in quality and safety with regard to important information in colorectal cancer surgery.

Design, Setting, and Participants

The Imaging for Quality Control Trial was a prospective, observational cohort study conducted between January 12, 2016, and October 30, 2017, at 3 centers in the Netherlands. The study group consisted of 113 patients 18 years or older undergoing elective laparoscopic surgery for colorectal cancer. These patients were case matched and compared with cases from a historical cohort that received only an NR.

Interventions

Among study cases, participating surgeons were requested to systematically capture predefined key steps of the surgical procedure intraoperatively on video in short clips.

Main Outcomes and Measures

The SVRs and NRs were analyzed for adequacy with respect to the availability of important information regarding the predefined key steps. Adequacy of the reported information was defined as the proportion of key steps with available and sufficient information in the report. Adequacy of the SVR and NR was compared between the study and control groups, with the SVR alone and as an adjunct to the NR in the study group vs NR alone in the control group.

Results

Of the 113 study patients, 69 women (61.1%) were included; mean (SD) age was 66.3 (9.8) years. In the control group, a mean (SD) of 52.5% (18.3%) of 631 steps were adequately described in the NR. In the study group, the adequacy of both the SVR (78.5% [16.5%], P < .001) and a combination of the SVR with NR (85.1% [14.6%], P < .001) was significantly superior to NR alone. The only significant difference between the study and historical control groups regarding postoperative and pathologic outcomes was a shorter postoperative mean (SD) length of stay in favor of the study group (8.0 [7.7] vs 8.6 [6.8] days; P = .03).

Conclusions and Relevance

Use of SVR in laparoscopic colorectal cancer surgery as an adjunct to the NR might be superior in documenting important steps of the operation compared with NR alone, adding to the overall availability of necessary intraoperative information and contributing to quality control and objectivity.

Creation of a universal language for surgical procedures using the step-by-step framework

Background

Learning of surgical procedures is traditionally based on a master–apprentice model. Segmenting procedures into steps is commonly used to achieve an efficient manner of learning. Existing methods of segmenting procedures into steps, however, are procedure‐specific and not standardized, hampering their application across different specialties and thus worldwide uptake. The aim of this study was to establish consensus on the step‐by‐step framework for standardizing the segmentation of surgical procedures into steps.

Methods

An international expert panel consisting of general, gastrointestinal and oncological surgeons was approached to establish consensus on the preciseness, novelty, usefulness and applicability of the proposed step‐by‐step framework through a Delphi technique. All statements were rated on a five‐point Likert scale. A statement was accepted when the lower confidence limit was 3·00 or more. Qualitative comments were requested when a score of 3 or less was given.

Results

In round one, 20 of 49 experts participated. Eighteen of 19 statements were accepted; the ‘novelty’ statement needed further exploration (mean 3·05, 95 per cent c.i. 2·45 to 3·65). Based on the qualitative comments of round one, five clarifying statements were formulated for more specific statements in round two. Twenty‐two experts participated and accepted all statements.

Conclusion

The international expert panel consisting of general, gastrointestinal and oncological surgeons supported the preciseness, usefulness and applicability of the step‐by‐step framework. This framework creates a universal language by standardizing the segmentation of surgical procedures into step‐by‐step descriptions based on anatomical structures, and may facilitate education, communication and assessment.

The American Society of Colon and Rectal Surgeons Clinical Practice Guidelines for the Treatment of Colon Cancer

The American Society of Colon and Rectal Surgeons is dedicated to ensuring high-quality patient care by advancing the science, prevention, and management of disorders and diseases of the colon, rectum, and anus. The Clinical Practice Guidelines Committee is composed of society members who are chosen because they have demonstrated expertise in the specialty of colon and rectal surgery. This committee was created to lead international efforts in defining quality care for conditions related to the colon, rectum, and anus. This is accompanied by developing Clinical Practice Guidelines based on the best available evidence. These guidelines are inclusive and not prescriptive. Their purpose is to provide information on which decisions can be made, rather than to dictate a specific form of treatment. These guidelines are intended for the use of all practitioners, health care workers, and patients who desire information about the management of the conditions addressed by the topics covered in these guidelines. It should be recognized that these guidelines should not be deemed inclusive of all proper methods of care or exclusive of methods of care reasonably directed to obtaining the same results. The ultimate judgment regarding the propriety of any specific procedure must be made by the physician in light of all the circumstances presented by the individual patient.