1
|
Chen Z, Yang D, Li A, Sun L, Zhao J, Liu J, Liu L, Zhou X, Chen Y, Cai Y, Wu Z, Cheng K, Cai H, Tang M, Peng B, Wang X. Decoding surgical skill: an objective and efficient algorithm for surgical skill classification based on surgical gesture features -experimental studies. Int J Surg 2024; 110:1441-1449. [PMID: 38079605 PMCID: PMC10942222 DOI: 10.1097/js9.0000000000000975] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2023] [Accepted: 11/21/2023] [Indexed: 03/16/2024]
Abstract
BACKGROUND Various surgical skills lead to differences in patient outcomes and identifying poorly skilled surgeons with constructive feedback contributes to surgical quality improvement. The aim of the study was to develop an algorithm for evaluating surgical skills in laparoscopic cholecystectomy based on the features of elementary functional surgical gestures (Surgestures). MATERIALS AND METHODS Seventy-five laparoscopic cholecystectomy videos were collected from 33 surgeons in five hospitals. The phase of mobilization hepatocystic triangle and gallbladder dissection from the liver bed of each video were annotated with 14 Surgestures. The videos were grouped into competent and incompetent based on the quantiles of modified global operative assessment of laparoscopic skills (mGOALS). Surgeon-related information, clinical data, and intraoperative events were analyzed. Sixty-three Surgesture features were extracted to develop the surgical skill classification algorithm. The area under the receiver operating characteristic curve of the classification and the top features were evaluated. RESULTS Correlation analysis revealed that most perioperative factors had no significant correlation with mGOALS scores. The incompetent group has a higher probability of cholecystic vascular injury compared to the competent group (30.8 vs 6.1%, P =0.004). The competent group demonstrated fewer inefficient Surgestures, lower shift frequency, and a larger dissection-exposure ratio of Surgestures during the procedure. The area under the receiver operating characteristic curve of the classification algorithm achieved 0.866. Different Surgesture features contributed variably to overall performance and specific skill items. CONCLUSION The computer algorithm accurately classified surgeons with different skill levels using objective Surgesture features, adding insight into designing automatic laparoscopic surgical skill assessment tools with technical feedback.
Collapse
Affiliation(s)
- Zixin Chen
- Department of General Surgery, Division of Pancreatic Surgery
- West China School of Medicine, West China Hospital of Sichuan University
| | - Dewei Yang
- Chongqing University of Posts and Telecommunications, School of Advanced Manufacturing Engineering, Chongqing
| | - Ang Li
- Department of General Surgery, Division of Pancreatic Surgery
- Guang’an People’s Hospital, Guang’an
| | - Louzong Sun
- Department of Hepatobiliary Surgery, Zigong First People’s Hospital, Zigong
| | - Jifan Zhao
- Chengdu Withai Innovations Technology Company, Chengdu
| | - Jie Liu
- Chengdu Withai Innovations Technology Company, Chengdu
| | - Linxun Liu
- Department of General Surgery, Qinghai Provincial People’s Hospital, Xining, People’s Republic of China
| | - Xiaobo Zhou
- School of Biomedical Informatics, McGovern Medical School, University of Texas Health Science Center, Houston, USA
| | - Yonghua Chen
- Department of General Surgery, Division of Pancreatic Surgery
| | - Yunqiang Cai
- Department of General Surgery, Division of Pancreatic Surgery
| | - Zhong Wu
- Department of General Surgery, Division of Pancreatic Surgery
| | - Ke Cheng
- Department of General Surgery, Division of Pancreatic Surgery
| | - He Cai
- Department of General Surgery, Division of Pancreatic Surgery
| | - Ming Tang
- Department of General Surgery, Division of Pancreatic Surgery
- West China School of Medicine, West China Hospital of Sichuan University
| | - Bing Peng
- Department of General Surgery, Division of Pancreatic Surgery
| | - Xin Wang
- Department of General Surgery, Division of Pancreatic Surgery
| |
Collapse
|
2
|
Cocchieri R, van de Wetering B, van Tuijl S, Mousavi I, Riezebos R, de Mol B. At the Crossroads of Minimally Invasive Mitral Valve Surgery—Benching Single Hospital Experience to a National Registry: A Plea for Risk Management Technology. J Cardiovasc Dev Dis 2022; 9:jcdd9080261. [PMID: 36005425 PMCID: PMC9410306 DOI: 10.3390/jcdd9080261] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Revised: 07/15/2022] [Accepted: 08/09/2022] [Indexed: 11/26/2022] Open
Abstract
Almost 30 years after the first endoscopic mitral valve repair, Minimally Invasive Mitral Valve Surgery (MIMVS) has become the standard at many institutions due to optimal clinical results and fast recovery. The question that arises is can already good results be further improved by an Institutional Risk Management Performance (IRMP) system in decreasing risks in minimally invasive mitral valve surgery (MIMVS)? As of yet, there are no reports on IRMP and learning systems in the literature. (2) Methods: We described and appraised our five-year single institutional experience with MIMVS in isolated valve surgery included in the Netherlands Heart Registry (NHR) and investigated root causes of high-impact complications. (3) Results: The 120-day and 12-month mortality were 1.1% and 1.9%, respectively, compared to the average of 4.3% and 5.3% reported in the NHR. The regurgitation rate was 1.4% compared to 5.2% nationwide. The few high-impact complications appeared not to be preventable. (4) Discussion: In MIMVS, freedom from major and minor complications is a strong indicator of an effective IRMP but remains concealed from physicians and patients, despite its relevance to shared decision making. Innovation adds to the complexity of MIMVS and challenges surgical competence. An IRMP system may detect and control new risks earlier. (5) Conclusion: An IRMP system contributes to an effective reduction of risks, pain and discomfort; provides relevant input for shared decision making; and warrants the safe introduction of new technology. Crossroads conclusions: investment in machine learning and AI for an effective IRMP system is recommended and the roles for commanding and operating surgeons should be considered.
Collapse
Affiliation(s)
- Riccardo Cocchieri
- Cardiothoracic Surgeon, OLVG Hospital, 1091 AC Amsterdam, The Netherlands
| | - Bertus van de Wetering
- Biomedical Engineer, LifeTec Group BV, 5611 ZS Eindhoven, The Netherlands
- Correspondence: (B.v.d.W.); (B.d.M.)
| | - Sjoerd van Tuijl
- Biomedical Engineer, LifeTec Group BV, 5611 ZS Eindhoven, The Netherlands
| | - Iman Mousavi
- Cardiothoracic Surgery Resident, OLVG Hospital, 1091 AC Amsterdam, The Netherlands
| | - Robert Riezebos
- Cardiologist, OLVG Hospital, 1091 AC Amsterdam, The Netherlands
| | - Bastian de Mol
- Department of Cardiothoracic Surgery, Amsterdam University Medical Center, 1105 AZ Amsterdam, The Netherlands
- Department of Biomedical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands
- Correspondence: (B.v.d.W.); (B.d.M.)
| |
Collapse
|
3
|
Daniel SJ, Bouchard MJ, Tremblay M. Rethinking Our Annual Congress-Meeting the Needs of Specialist Physicians by Partnering With Provincial Simulation Centers. THE JOURNAL OF CONTINUING EDUCATION IN THE HEALTH PROFESSIONS 2022; 42:e83-e87. [PMID: 34609357 PMCID: PMC8876424 DOI: 10.1097/ceh.0000000000000381] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
Canada's maintenance of certification programs for physicians has evolved to emphasize assessment activities. Our organization recognized the importance of offering more practice assessment opportunities to our members to enhance their practice and help them comply with a regulation from our provincial professional body related to ongoing continuing education. This led us to rethink our annual congress and enrich the program with a curriculum of interdisciplinary simulation sessions tailored to meet the needs of a broad audience of specialists. Our challenges are similar to those of many national specialty societies having limited access to simulation facilities, instructors, and simulation teams that can cover the breadth and scope of perceived and unperceived simulation needs for their specialty. Our innovative solution was to partner with local experts to develop 22 simulation sessions over the past three years. The response was very positive, drawing 867 participants. Over 95% of participants either agreed or strongly agreed that their simulation session (1) met their learning objectives, (2) was relevant for their practice, and (3) encouraged them to modify their practice. Narrative comments from a survey sent to the 2018 participants four months after their activity indicated several self-reported changes in their practice or patient outcomes. We were able to centralize offers from organizations that had previously worked in silo to develop simulation sessions meeting the needs of our members. Proposing simulation sessions allowed our organization to establish long-term partnerships and to expend our "educational toolbox" to address skill gaps not usually addressed during annual meetings.
Collapse
|
4
|
Moglia A, Georgiou K, Georgiou E, Satava RM, Cuschieri A. A systematic review on artificial intelligence in robot-assisted surgery. Int J Surg 2021; 95:106151. [PMID: 34695601 DOI: 10.1016/j.ijsu.2021.106151] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2021] [Revised: 10/04/2021] [Accepted: 10/19/2021] [Indexed: 12/12/2022]
Abstract
BACKGROUND Despite the extensive published literature on the significant potential of artificial intelligence (AI) there are no reports on its efficacy in improving patient safety in robot-assisted surgery (RAS). The purposes of this work are to systematically review the published literature on AI in RAS, and to identify and discuss current limitations and challenges. MATERIALS AND METHODS A literature search was conducted on PubMed, Web of Science, Scopus, and IEEExplore according to PRISMA 2020 statement. Eligible articles were peer-review studies published in English language from January 1, 2016 to December 31, 2020. Amstar 2 was used for quality assessment. Risk of bias was evaluated with the Newcastle Ottawa Quality assessment tool. Data of the studies were visually presented in tables using SPIDER tool. RESULTS Thirty-five publications, representing 3436 patients, met the search criteria and were included in the analysis. The selected reports concern: motion analysis (n = 17), urology (n = 12), gynecology (n = 1), other specialties (n = 1), training (n = 3), and tissue retraction (n = 1). Precision for surgical tools detection varied from 76.0% to 90.6%. Mean absolute error on prediction of urinary continence after robot-assisted radical prostatectomy (RARP) ranged from 85.9 to 134.7 days. Accuracy on prediction of length of stay after RARP was 88.5%. Accuracy on recognition of the next surgical task during robot-assisted partial nephrectomy (RAPN) achieved 75.7%. CONCLUSION The reviewed studies were of low quality. The findings are limited by the small size of the datasets. Comparison between studies on the same topic was restricted due to algorithms and datasets heterogeneity. There is no proof that currently AI can identify the critical tasks of RAS operations, which determine patient outcome. There is an urgent need for studies on large datasets and external validation of the AI algorithms used. Furthermore, the results should be transparent and meaningful to surgeons, enabling them to inform patients in layman's words. REGISTRATION Review Registry Unique Identifying Number: reviewregistry1225.
Collapse
Affiliation(s)
- Andrea Moglia
- EndoCAS, Center for Computer Assisted Surgery, University of Pisa, 56124, Pisa, Italy 1st Propaedeutic Surgical Unit, Hippocrateion Athens General Hospital, Athens Medical School, National and Kapodistrian University of Athens, Greece MPLSC, Athens Medical School, National and Kapodistrian University of Athens, Greece Department of Surgery, University of Washington Medical Center, Seattle, WA, United States Scuola Superiore Sant'Anna of Pisa, 56214, Pisa, Italy Institute for Medical Science and Technology, University of Dundee, Dundee, DD2 1FD, United Kingdom
| | | | | | | | | |
Collapse
|
5
|
Frazer A, Tanzer M. Hanging up the surgical cap: Assessing the competence of aging surgeons. World J Orthop 2021; 12:234-245. [PMID: 33959487 PMCID: PMC8082508 DOI: 10.5312/wjo.v12.i4.234] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/24/2020] [Revised: 01/28/2021] [Accepted: 04/05/2021] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND As the average age of surgeons continues to rise, determining when a surgeon should retire is an important public safety concern. AIM To investigate strategies used to determine competency in the industrial workplace that could be transferrable in the assessment of aging surgeons and to identify existing competency assessments of practicing surgeons. METHODS We searched websites describing non-medical professions within the United States where cognitive and physical competency are necessary for public safety. The mandatory age and certification process, including cognitive and physical requirements, were reported for each profession. Methods for determining surgical competency currently in use, and those existing in the literature, were also identified. RESULTS Four non-medical professions requiring mental and physical aptitude that involve public safety and have mandatory testing and/or retirement were identified: Airline pilots, air traffic controllers, firefighters, and United States State Judges. Nine late career practitioner policies designed to evaluate the ageing physician, including surgeons, were described. Six of these policies included subjective performance testing, 4 using peer assessment and 2 using dexterity testing. Six objective testing methods for evaluation of surgeon technical skill were identified in the literature. All were validated for surgical trainees. Only Objective Structured Assessment of Technical Skills (OSATS) was capable of distinguishing between surgeons of different skill level and showing a relationship between skill level and post-operative outcomes. CONCLUSION A surgeon should not be forced to hang up his/her surgical cap at a predetermined age, but should be able to practice for as long as his/her surgical skills are objectively maintained at the appropriate level of competency. The strategy of using skill-based simulations in evaluating non-medical professionals can be similarly used as part of the assessment of the ageing surgeons' surgical competency, showing who may require remediation or retirement.
Collapse
Affiliation(s)
- Abigail Frazer
- Department of Orthopaedic Surgery, McGill University, Montreal H3G 1A4, QC, Canada
| | - Michael Tanzer
- Department of Orthopaedic Surgery, McGill University, Montreal H3G 1A4, QC, Canada
| |
Collapse
|
6
|
Kanjilal D, Mahmud F, Sutkin G. Constructivist Grounded Theory to Establish the Relationship Between Technical Error and Adverse Patient Outcome: Modeling Technical Error and Adverse Outcomes. Am Surg 2020; 87:753-759. [PMID: 33170022 DOI: 10.1177/0003134820952837] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
BACKGROUND Preventable intraoperative errors have the potential to lead to adverse events. Our objective was to build a conceptual model of the relationship between minute technical errors performed by the surgeon and adverse patient outcomes. MATERIALS AND METHODS We used constructivist grounded theory methodology to build a model for the avoidance of technical errors. We used the Observational Clinical Human Reliability Assessment system, which categorizes granular, technical intraoperative errors, as our conceptual framework. We iteratively interviewed surgeons from multiple adult and pediatric surgical specialties, refined our semi-structured interview, and developed a conceptual model. Our model remained stable after interviewing 11 surgeons, and we reviewed it with earlier interviewed surgeons. RESULTS Our conceptual model helps us understand how technical errors can be associated with adverse outcomes and is applicable to a broad range of surgical steps. Each technical error is defined by a unique improper technical motion that without a compensatory response, it may lead to 1 or more discreet adverse outcomes. Our model includes 5 primary defenses against an adverse outcome, including perfect technique, recognizing imperfect technique, adequately correcting imperfect technique, recognizing an adverse event, and adequately compensating for an adverse event. It includes multiple examples of compensating for a technical error, resulting in a near miss. DISCUSSION Our conceptual model suggests that adverse patient outcomes can be related to minute technical deviations in surgical technique and provides a basis to study these preventable errors. Our model can also be used to develop intraoperative strategies to prevent these technical surgical errors.
Collapse
Affiliation(s)
- Debolina Kanjilal
- University of Missouri-Kansas City School of Medicine, Kansas City, MO, USA
| | - Fizza Mahmud
- University of Missouri-Kansas City School of Medicine, Kansas City, MO, USA
| | - Gary Sutkin
- University of Missouri-Kansas City School of Medicine, Kansas City, MO, USA
| |
Collapse
|
7
|
Non-technical skills in robotic surgery and impact on near-miss events: a multi-center study. Surg Endosc 2020; 35:5062-5071. [PMID: 32968920 DOI: 10.1007/s00464-020-07988-5] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Accepted: 09/14/2020] [Indexed: 12/27/2022]
Abstract
BACKGROUND Robotic surgery requires a set of non-technical skills (NTS), because of the complex environment. We aim to study relationship between NTS and near-miss events in robotic surgery. METHODS This is an observational study in five French centers. Three robotic procedures were observed and filmed by one of expert trainers in NTS. They established and scored a non-technical skills in robotic surgery (NTSRS) score, that included eight items, each scored from 1 to 5, to assess the whole surgical teams. The surgical teams also self-assessed their work. The number of near-miss events was recorded and classified as minor, or major but no harm incidents, independently by two surgeons. Correlations were Spearman coefficients. RESULTS Of the 26 procedures included, 15 were prostatectomy (58%), 9 nephrectomy (35%), and 2 pyeloplasty (7.7%). Half of procedures (n = 13) were performed by surgeons with extensive RS experience (more than 150 procedures). Per procedure, there was a median (quartiles) of 9 (7; 11) near-miss events. There was 1 (0; 2) major near-miss events, with no harm. The median NTSRS score was 18 (14; 21), out of 40. The number of near-miss events was strongly correlated with the NTSRS score (r = - 0.92, p < 0.001) but was not correlated with the surgeon's experience. The surgeons for fifteen (58%) procedures, and the bed-side surgeons for 11 (42%) procedures, felt that there was no need for an improvement in the quality of their NTS. None of the surgeons gave a negative self-evaluation for any procedure; in three procedures (12%), the bed-side surgeons self-assessed negatively, on ergonomics. CONCLUSION Occurrence of near-miss events was reduced in teams managing NTS. Specific NTS surgical team training is essential for robotic surgery as it may have a significant impact on risk management.
Collapse
|