1
|
Hashemi N, Svendsen MBS, Bjerrum F, Rasmussen S, Tolsgaard MG, Friis ML. Acquisition and usage of robotic surgical data for machine learning analysis. Surg Endosc 2023:10.1007/s00464-023-10214-7. [PMID: 37389741 PMCID: PMC10338401 DOI: 10.1007/s00464-023-10214-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2023] [Accepted: 06/12/2023] [Indexed: 07/01/2023]
Abstract
BACKGROUND The increasing use of robot-assisted surgery (RAS) has led to the need for new methods of assessing whether new surgeons are qualified to perform RAS, without the resource-demanding process of having expert surgeons do the assessment. Computer-based automation and artificial intelligence (AI) are seen as promising alternatives to expert-based surgical assessment. However, no standard protocols or methods for preparing data and implementing AI are available for clinicians. This may be among the reasons for the impediment to the use of AI in the clinical setting. METHOD We tested our method on porcine models with both the da Vinci Si and the da Vinci Xi. We sought to capture raw video data from the surgical robots and 3D movement data from the surgeons and prepared the data for the use in AI by a structured guide to acquire and prepare video data using the following steps: 'Capturing image data from the surgical robot', 'Extracting event data', 'Capturing movement data of the surgeon', 'Annotation of image data'. RESULTS 15 participant (11 novices and 4 experienced) performed 10 different intraabdominal RAS procedures. Using this method we captured 188 videos (94 from the surgical robot, and 94 corresponding movement videos of the surgeons' arms and hands). Event data, movement data, and labels were extracted from the raw material and prepared for use in AI. CONCLUSION With our described methods, we could collect, prepare, and annotate images, events, and motion data from surgical robotic systems in preparation for its use in AI.
Collapse
Affiliation(s)
- Nasseh Hashemi
- Department of Clinical Medicine, Aalborg University Hospital, Aalborg, Denmark.
- Nordsim-Centre for Skills Training and Simulation, Aalborg, Denmark.
- ROCnord-Robot Centre, Aalborg University Hospital, Aalborg, Denmark.
- Department of Urology, Aalborg University Hospital, Aalborg, Denmark.
| | - Morten Bo Søndergaard Svendsen
- Copenhagen Academy for Medical Education and Simulation, Center for Human Resources and Education, Copenhagen, Denmark
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Flemming Bjerrum
- Copenhagen Academy for Medical Education and Simulation, Center for Human Resources and Education, Copenhagen, Denmark
- Department of Gastrointestinal and Hepatic Diseases, Copenhagen University Hospital - Herlev and Gentofte, Herlev, Denmark
| | - Sten Rasmussen
- Department of Clinical Medicine, Aalborg University Hospital, Aalborg, Denmark
| | - Martin G Tolsgaard
- Nordsim-Centre for Skills Training and Simulation, Aalborg, Denmark
- Copenhagen Academy for Medical Education and Simulation, Center for Human Resources and Education, Copenhagen, Denmark
| | - Mikkel Lønborg Friis
- Department of Clinical Medicine, Aalborg University Hospital, Aalborg, Denmark
- Nordsim-Centre for Skills Training and Simulation, Aalborg, Denmark
| |
Collapse
|
2
|
Lyman WB, Passeri MJ, Murphy K, Siddiqui IA, Khan AS, Iannitti DA, Martinie JB, Baker EH, Vrochides D. An objective approach to evaluate novice robotic surgeons using a combination of kinematics and stepwise cumulative sum (CUSUM) analyses. Surg Endosc 2020; 35:2765-2772. [PMID: 32556751 DOI: 10.1007/s00464-020-07708-z] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2020] [Accepted: 06/09/2020] [Indexed: 02/07/2023]
Abstract
BACKGROUND Current evaluation methods for robotic-assisted surgery (ARCS or GEARS) are limited to 5-point Likert scales which are inherently time-consuming and require a degree of subjective scoring. In this study, we demonstrate a method to break down complex robotic surgical procedures using a combination of an objective cumulative sum (CUSUM) analysis and kinematics data obtained from the da Vinci® Surgical System to evaluate the performance of novice robotic surgeons. METHODS Two HPB fellows performed 40 robotic-assisted hepaticojejunostomy reconstructions to model a portion of a Whipple procedure. Kinematics data from the da Vinci® system was recorded using the dV Logger® while CUSUM analyses were performed for each procedural step. Each kinematic variable was modeled using machine learning to reflect the fellows' learning curves for each task. Statistically significant kinematics variables were then combined into a single formula to create the operative robotic index (ORI). RESULTS The inflection points of our overall CUSUM analysis showed improvement in technical performance beginning at trial 16. The derived ORI model showed a strong fit to our observed kinematics data (R2 = 0.796) with an ability to distinguish between novice and intermediate robotic performance with 89.3% overall accuracy. CONCLUSIONS In this study, we demonstrate a novel approach to objectively break down novice performance on the da Vinci® Surgical System. We identified kinematics variables associated with improved overall technical performance to create an objective ORI. This approach to robotic operative evaluation demonstrates a valuable method to break down complex surgical procedures in an objective, stepwise fashion. Continued research into objective methods of evaluation for robotic surgery will be invaluable for future training and clinical implementation of the robotic platform.
Collapse
Affiliation(s)
- William B Lyman
- Department of Surgery, Carolinas Medical Center, 1000 Blythe Blvd, MEB Suite 601, Charlotte, NC, 28203, USA.
| | - Michael J Passeri
- Division of HPB Surgery, Department of Surgery, Carolinas Medical Center, Charlotte, NC, USA
| | - Keith Murphy
- Division of HPB Surgery, Department of Surgery, Carolinas Medical Center, Charlotte, NC, USA
| | | | - Adeel S Khan
- Washington University School of Medicine, St. Louis, MO, USA
| | - David A Iannitti
- Division of HPB Surgery, Department of Surgery, Carolinas Medical Center, Charlotte, NC, USA
| | - John B Martinie
- Division of HPB Surgery, Department of Surgery, Carolinas Medical Center, Charlotte, NC, USA
| | - Erin H Baker
- Division of HPB Surgery, Department of Surgery, Carolinas Medical Center, Charlotte, NC, USA
| | - Dionisios Vrochides
- Division of HPB Surgery, Department of Surgery, Carolinas Medical Center, Charlotte, NC, USA
| |
Collapse
|
3
|
Shay SG, Chrin JD, Wang MB, Mendelsohn AH. Initial and Long-term Retention of Robotic Technical Skills in an Otolaryngology Residency Program. Laryngoscope 2018; 129:1380-1385. [PMID: 30098045 DOI: 10.1002/lary.27425] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2018] [Revised: 05/21/2018] [Accepted: 06/11/2018] [Indexed: 11/10/2022]
Abstract
OBJECTIVES/HYPOTHESIS To objectively assess the initial and long-term retention of robotic surgical skills of otolaryngology residents. STUDY DESIGN This study was performed in an academic otolaryngology residency training program. Between October 2015 and November 2016, residents were invited to complete a prospective, multiphase robotic surgical skills training course: 1) online da Vinci Surgical System Assessment and didactic, 2) faculty-supervised robotic simulator training, 3) robotic docking and draping training, 4) robotic dry-lab exercises. To optimize surgical skill retention, the training laboratory was repeated 2 weeks after the initial training session. METHODS Twenty otolaryngology residents were included. Primary outcome was measured as robotic skill assessment scores on three tasks: camera targeting, peg board, and needle targeting. Skill assessments were completed prior to training, between the two training sessions, and at 1 month and 6 months after training. Residents were also asked to complete a self-assessment questionnaire. RESULTS Camera targeting scores were improved at midtraining (P < .001) and 1-month posttraining (P = .010). Peg board scores were improved at 1 month training (P = .043). Needle targeting scores were improved at midtraining (P = .002), 1 month (P = .002), and 6 months posttraining (P < .001). Resident self-assessment scores demonstrating comfort with using the robotic console (P < .01) and docking/draping (P < .01) improved significantly following the training. CONCLUSIONS Following a multiphase robotic training program, otolaryngology residents demonstrated significant, objective skill acquisition and retention at 1 month and 6 months follow-up. Although the proposed training strategy may be considered an important step in otolaryngology residency training, additional innovations are being designed toward a formal robotic training curriculum. LEVEL OF EVIDENCE NA Laryngoscope, 129:1380-1385, 2019.
Collapse
Affiliation(s)
- Sophie G Shay
- Division of Pediatric Otolaryngology-Head and Neck Surgery, Ann and Robert Lurie Children's Hospital, Northwestern University Feinberg School of Medicine, Chicago, Illinois
| | - Jonathan D Chrin
- Center for Advanced Surgical and Interventional Technology, David Geffen School of Medicine, Ronald Reagan Medical Center, University of California Los Angeles, Los Angeles, California
| | - Marilene B Wang
- Department of Head and Neck Surgery, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California
| | - Abie H Mendelsohn
- Center for Advanced Surgical and Interventional Technology, David Geffen School of Medicine, Ronald Reagan Medical Center, University of California Los Angeles, Los Angeles, California.,Department of Head and Neck Surgery, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California
| |
Collapse
|
4
|
Abstract
Robotic technology currently offers some technical advantages in pelvic dissection compared with competing minimally invasive techniques, and adoption for the surgical treatment of rectal cancer is rapidly increasing worldwide. While there are some early data demonstrating modest improvement in patient outcomes, benefits in terms of long-term oncological outcomes, as well as potential improvements in surgeon-centered outcomes such as fatigue and repetitive stress injury are actively being investigated. Rapid innovation, with the impending release of several new robotic platforms, is likely to further expand the application of these technologies, improve on current limitations, and reduce capital and consumable costs. It is imperative that, as the technology develops and adoption increases further, clinician and research led programs drive safe implementation with a patient-first approach.
Collapse
Affiliation(s)
- Tarik Sammour
- Colorectal Unit, Department of Surgery, Royal Adelaide Hospital, Adelaide, Australia
| | - George J Chang
- Department of Surgical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA - .,Minimally Invasive and New Technologies in Oncologic Surgery (MINTOS) Program, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| |
Collapse
|
5
|
Robotic skills can be aided by laparoscopic training. Surg Endosc 2017; 32:2683-2688. [PMID: 29214515 DOI: 10.1007/s00464-017-5963-5] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2017] [Accepted: 10/23/2017] [Indexed: 10/18/2022]
Abstract
BACKGROUND General Surgery is currently the fastest growing specialty with regards to robotic surgical system utilization. Contrary to the experience in laparoscopy, simulator training for robotic surgery is not widely employed partly because robotic surgical simulators are expensive. We sought to determine the effect of a robotic simulation curriculum and whether robotic surgical skills could be derived from those psychomotor skills attained in laparoscopic training. METHODS Twenty-seven trainees with no prior robotic experience and limited laparoscopy exposure were randomly assigned to one of three training groups: no simulator training, training on a fundamentals of laparoscopic surgery (FLS™) standard box trainer, and training on a robotic computer based simulator (da Vinci Skills Simulator™). Baseline robotic surgical skills were assessed on the clinical robot docked to a standard FLS trainer box on two tasks-intracorporeal knot tying and peg transfer. Subjects subsequently underwent four 1-h long training sessions in their assigned training environment over a course of several weeks. Robotic surgical skills were reassessed on the robot on the same two tasks used to assess skills prior to training. RESULTS FLS training resulted in a greater score improvement than no training for both knot and peg scores. FLS training was also determined to result in greater score improvement than robotic simulator training for knot tying. There was no significant difference in peg transfer or knot tying scores when comparing robotic simulator training and no training. CONCLUSIONS Robotic surgical skills can be in part derived from psychomotor skills developed in a laparoscopic trainer, especially for complex skills such as intracorporeal knot tying. Acquisition of robotic surgical skills may be enhanced by practice on a laparoscopic simulator using the FLS curriculum. This may be especially helpful when a robotic simulator is not available or is poorly accessible.
Collapse
|
6
|
Yang K, Zhen H, Hubert N, Perez M, Wang XH, Hubert J. From dV-Trainer to Real Robotic Console: The Limitations of Robotic Skill Training. JOURNAL OF SURGICAL EDUCATION 2017; 74:1074-1080. [PMID: 28462814 DOI: 10.1016/j.jsurg.2017.03.006] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/22/2016] [Revised: 02/05/2017] [Accepted: 03/21/2017] [Indexed: 06/07/2023]
Abstract
OBJECTIVES To investigate operators' performance quality, mental stress, and ergonomic habits through a training curriculum on robotic simulators. DESIGN Forty volunteers without robotic surgery experience were recruited to practice 2 exercises on a dV-Trainer (dVT) for 14 hours. The simulator software (M-scorea) provided an automatic evaluation of the overall score for the surgeons' performance. Each participant provided a subjective difficulty score (validity to be proven) for each exercise. Their ergonomic habits were evaluated based on the workspace range and armrest load-validated criteria for evaluating the proficiency of using the armrest. They then repeated the same tasks on a da Vinci Surgical Skill Simulator for a final-level test. Their final scores were compared with their initial scores and the scores of 5 experts on the da Vinci Surgical Skill Simulator. RESULTS A total of 14 hours of training on the dVT significantly improved the surgeons' performance scores to the expert level with a significantly reduced workload, but their ergonomic score was still far from the expert level. CONCLUSION Sufficient training on the dVT improves novices' performance, reduces psychological stress, and inculcates better ergonomic habits. Among the evaluated criteria, novices had the most difficulty in achieving expert levels of ergonomic skills. The training benefits of robotic surgery simulators should be determined with quantified variables. The detection of the limitations during robotic training curricula could guide the targeted training and improve the training effect.
Collapse
Affiliation(s)
- Kun Yang
- Department of Urology, Zhongnan Hospital, Wuhan University, Wuhan, China; IADI/Inserm U947, Lorraine University, Nancy, France; Department of Emergency and General Surgery, CHU Nancy, Nancy, France
| | - Hang Zhen
- Department of Urology, Zhongnan Hospital, Wuhan University, Wuhan, China
| | - Nicolas Hubert
- IADI/Inserm U947, Lorraine University, Nancy, France; Department of Urology, CHU Nancy, Nancy, France
| | - Manuela Perez
- IADI/Inserm U947, Lorraine University, Nancy, France; Department of Emergency and General Surgery, CHU Nancy, Nancy, France
| | | | - Jacques Hubert
- IADI/Inserm U947, Lorraine University, Nancy, France; Department of Emergency and General Surgery, CHU Nancy, Nancy, France.
| |
Collapse
|
7
|
Evans CH, Schenarts KD. Evolving Educational Techniques in Surgical Training. Surg Clin North Am 2016; 96:71-88. [DOI: 10.1016/j.suc.2015.09.005] [Citation(s) in RCA: 68] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
8
|
Vetter MH, Green I, Martino M, Fowler J, Salani R. Incorporating resident/fellow training into a robotic surgery program. J Surg Oncol 2015; 112:684-9. [PMID: 26289120 DOI: 10.1002/jso.24006] [Citation(s) in RCA: 25] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2015] [Accepted: 07/27/2015] [Indexed: 01/09/2023]
Abstract
With the rapid uptake of the robotic approach in gynecologic surgery, a thorough understanding of the technology, including its uses and limitations, is critical to maximize patient outcomes and safety. This review discusses the role of training modalities and development of curricula for robotic surgery. Furthermore, methods for incorporating the entire surgical team and the process of credentialing/maintaining privileges are described.
Collapse
Affiliation(s)
| | | | - Martin Martino
- University of South Florida, Allentown, Pennsylvania
- Lehigh Valley Health Network, Allentown, Pennsylvania
| | | | | |
Collapse
|