Artificial Intelligence in Surgery: Promises and Perils

Hashimoto, Daniel A.; Rosman, Guy; Rus, Daniela; Meireles, Ozanan R.

doi:10.1097/sla.0000000000002693

Cited by 845 publications

(619 citation statements)

References 55 publications

Supporting

Mentioning

598

Contrasting

Unclassified

Order By: Relevance

“…Equally important, the review highlights the current limitations of OCHRA including its labor-intensive nature involving human factors scientists using established criteria to identify and categorize errors from unedited videos of operations [15,16,. In this respect, the OCHRA will eventually benefit by progress in AI and ML [50]. This development is considered essential for the wider uptake of OCHRA.…”

Section: Discussionmentioning

confidence: 99%

Objective assessment of surgical operative performance by observational clinical human reliability analysis (OCHRA): a systematic review

Tang

Cuschieri

2020

Surg Endosc

View full text Add to dashboard Cite

Background Both morbidity and mortality data (MMD) and learning curves (LCs) do not provide information on the nature of intraoperative errors and their mechanisms when these adversely impact on patient outcome. OCHRA was developed specifically to address the unmet surgical need for an objective assessment technique of the quality of technical execution of operations at individual operator level. The aim of this systematic review was to review of OCHRA as a method of objective assessment of surgical operative performance. Methods Systematic review based on searching 4 databases for articles published from January 1998 to January 2019. The review complies with Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines and includes original publications on surgical task performance based on technical errors during operations across several surgical specialties. Results Only 26 published studies met the search criteria, indicating that the uptake of OCHRA during the study period has been low. In 31% of reported studies, the operations were performed by fully qualified consultant/attending surgeons and by surgical trainees in 69% in approved training programs. OCHRA identified 7869 consequential errors (CE) during the conduct of 719 clinical operations (mean = 11 CEs). It also identified 'hazard zones' of operations and proficiency-gain curves (P-GCs) that confirm attainment of persistent competent execution of specific operations by individual trainee surgeons. P-GCs are both surgeon and operation specific. Conclusions Increased OCHRA use has the potential to improve patient outcome after surgery, but this is a contingent progress towards automatic assessment of unedited videos of operations. The low uptake of OCHRA is attributed to its laborintensive nature involving human factors (cognitive engineering) expertise. Aside from faster and more objective peer-based assessment, this development should accelerate increased clinical uptake and use of the technique in both routine surgical practice and surgical training. Keywords Observational clinical human reliability analysis (OCHRA) • Objective assessment of surgical operative performance • Technical error • Task performance • Hazard zones of operations • Proficiency-gain curves

show abstract

Section: Discussionmentioning

confidence: 99%

Objective assessment of surgical operative performance by observational clinical human reliability analysis (OCHRA): a systematic review

Tang

Cuschieri

2020

Surg Endosc

View full text Add to dashboard Cite

show abstract

“…To disseminate and improve the quality of global surgical care, consolidating results for the robotic console in accomplishing surgeries independently without complex assistive procedures might be the key for reproducibility through AI on the basis of the robotic platform. Although truly autonomous robotic surgery will remain out of reach for the meantime, synergy across fields will likely accelerate the capabilities of AI in augmenting surgical care . Our experience helped to develop a protocol for liver resection with a fully robotic approach and without an assistant surgeon or any additional MIS procedures.…”

Section: Discussionmentioning

confidence: 99%

Toward a fully robotic surgery: Performing robotic major liver resection with no table‐side surgeon

Chen

Liang

et al. 2019

Robotics Computer Surgery

View full text Add to dashboard Cite

Background: Evidence has suggested that robotic system helps perform more major liver resections. However, the required table-side surgeon has remained a concern because of the uncertain performance and the incomplete control of console surgeon.Methods: Data were reviewed for consecutive 333 robotic liver resections, of which 56 patients underwent left liver resection with the usual setting, and 35 with no table-side surgeon.Results: No conversion was required in the setting with no table-side surgeon. The group without the table-side surgeon had similar complication rates, blood loss, and operative time compared with that of the normal settings, as well as focused analysis on major left hemihepatectomy.Conclusion: Our data suggest that performing robotic major liver resection without the presence of the table-side surgeon is safe and feasible. The concise performance of robotic platforms might accelerate the machine learning process along with the ability to predict patterns of future autonomous surgery.

show abstract

“…These algorithms can be trained for predictive tasks ( Figure ). The process to detect structures in data without labels is called unsupervised learning . Therefore, ML require hand‐engineered feature extraction from inputs.…”

Section: Concepts Of Ai ML and Dlmentioning

confidence: 99%

Radiomics and Machine Learning in Oral Healthcare

Leite

Vasconcelos

Willems

et al. 2020

Proteomics Clinical Apps

View full text Add to dashboard Cite

The increasing storage of information, data, and forms of knowledge has led to the development of new technologies that can help to accomplish complex tasks in different areas, such as in dentistry. In this context, the role of computational methods, such as radiomics and Artificial Intelligence (AI) applications, has been progressing remarkably for dentomaxillofacial radiology (DMFR). These tools bring new perspectives for diagnosis, classification, and prediction of oral diseases, treatment planning, and for the evaluation and prediction of outcomes, minimizing the possibilities of human errors. A comprehensive review of the state-of-the-art of using radiomics and machine learning (ML) for imaging in oral healthcare is presented in this paper. Although the number of published studies is still relatively low, the preliminary results are very promising and in a near future, an augmented dentomaxillofacial radiology (ADMFR) will combine the use of radiomics-based and AI-based analyses with the radiologist's evaluation. In addition to the opportunities and possibilities, some challenges and limitations have also been discussed for further investigations.

show abstract

Artificial Intelligence in Surgery: Promises and Perils

Cited by 845 publications

References 55 publications

Objective assessment of surgical operative performance by observational clinical human reliability analysis (OCHRA): a systematic review

Objective assessment of surgical operative performance by observational clinical human reliability analysis (OCHRA): a systematic review

Toward a fully robotic surgery: Performing robotic major liver resection with no table‐side surgeon

Radiomics and Machine Learning in Oral Healthcare

Contact Info

Product

Resources

About