Dataset Information

Ensemble deep learning for the prediction of proficiency at a virtual simulator for robot-assisted surgery.

ABSTRACT:

Background

Artificial intelligence (AI) has the potential to enhance patient safety in surgery, and all its aspects, including education and training, will derive considerable benefit from AI. In the present study, deep-learning models were used to predict the rates of proficiency acquisition in robot-assisted surgery (RAS), thereby providing surgical programs directors information on the levels of the innate ability of trainees to facilitate the implementation of flexible personalized training.

Methods

176 medical students, without prior experience with surgical simulators, were trained to reach proficiency in five tasks on a virtual simulator for RAS. Ensemble deep neural networks (DNN) models were developed and compared with other ensemble AI algorithms, i.e., random forests and gradient boosted regression trees (GBRT).

Results

DNN models achieved a higher accuracy than random forests and GBRT in predicting time to proficiency, 0.84 vs. 0.70 and 0.77, respectively (Peg board 2), 0.83 vs. 0.79 and 0.78 (Ring walk 2), 0.81 vs 0.81 and 0.80 (Match board 1), 0.79 vs. 0.75 and 0.71 (Ring and rail 2), and 0.87 vs. 0.86 and 0.84 (Thread the rings 2). Ensemble DNN models outperformed random forests and GBRT in predicting number of attempts to proficiency, with an accuracy of 0.87 vs. 0.86 and 0.83, respectively (Peg board 2), 0.89 vs. 0.88 and 0.89 (Ring walk 2), 0.91 vs. 0.89 and 0.89 (Match board 1), 0.89 vs. 0.87 and 0.83 (Ring and rail 2), and 0.96 vs. 0.94 and 0.94 (Thread the rings 2).

Conclusions

Ensemble DNN models can identify at an early stage the acquisition rates of surgical technical proficiency of trainees and identify those struggling to reach the required expected proficiency level.

SUBMITTER: Moglia A

PROVIDER: S-EPMC9402513 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Ensemble deep learning for the prediction of proficiency at a virtual simulator for robot-assisted surgery.

Moglia Andrea A Morelli Luca L D'Ischia Roberto R Fatucchi Lorenzo Maria LM Pucci Valentina V Berchiolli Raffaella R Ferrari Mauro M Cuschieri Alfred A

Surgical endoscopy 20220112 9

<h4>Background</h4>Artificial intelligence (AI) has the potential to enhance patient safety in surgery, and all its aspects, including education and training, will derive considerable benefit from AI. In the present study, deep-learning models were used to predict the rates of proficiency acquisition in robot-assisted surgery (RAS), thereby providing surgical programs directors information on the levels of the innate ability of trainees to facilitate the implementation of flexible personalized t ...[more]

PMID: 35020053

Similar Datasets

Project description:BackgroundRobot assisted surgery has expanded considerably in the past years. Compared to conventional open or laparoscopic surgery, virtual reality (VR) training is an essential component in learning robot assisted surgery. However, for tasks to be implemented in a curriculum, the levels of validity should be studied for proficiency-based training. Therefore, this study was aimed to assess the validity evidence of advanced suturing tasks on a robot assisted VR simulator.MethodParticipants were voluntary recruited and divided in the robotic experienced, laparoscopic experienced or novice group, based on self-reported surgical experience. Subsequently, a questionnaire on a five-point Likert scale was completed to assess the content validity. Three component tasks of complex suturing were performed on the RobotiX simulator (Task1: tilted plane needle transfer, Task: 2 intracorporal suturing, Task 3: anastomosis needle transfer). Accordingly, the outcome of the parameters was used to assess construct validity between robotic experienced and novice participants. Composite scores (0-100) were calculated from the construct parameters and corresponding pass/fail scores with false positive (FP) and false negative (FN) percentages.ResultsFifteen robotic experienced, 26 laparoscopic experienced and 29 novices were recruited. Overall content validity outcomes were scored positively on the realism (mean 3.7), didactic value (mean 4.0) and usability (mean 4.2). Robotic experienced participants significantly outperformed novices and laparoscopic experienced participants on multiple parameters on all three tasks of complex suturing. Parameters showing construct validity mainly consisted of movement parameters, needle precision and task completion time. Calculated composite pass/fail scores between robotic experienced and novice participants resulted for Task 1 in 73/100 (FP 21%, FN 5%), Task 2 in 85/100 (FP 28%, FN 4%) and Task 3 in 64/100 (FP 49%, FN 22%).ConclusionThis study assessed the validity evidence on multiple levels of the three studied tasks. The participants score the RobotiX good on the content validity level. The composite pass/fail scores of Tasks 1 and 2 allow for proficiency-based training and could be implemented in a robot assisted surgery training curriculum.

Project description:BackgroundWe recently reported the importance of deep learning (DL) of pelvic magnetic resonance imaging in predicting the degree of urinary incontinence (UI) following robot-assisted radical prostatectomy (RARP). However, our results were limited because the prediction accuracy was approximately 70%.AimTo develop a more precise prediction model that can inform patients about UI recovery post-RARP surgery using a DL model based on intraoperative video images.Methods and resultsThe study cohort comprised of 101 patients with localized prostate cancer undergoing RARP. Three snapshots from intraoperative video recordings showing the pelvic cavity (prior to bladder neck incision, immediately following prostate removal, and after vesicourethral anastomosis) were evaluated, including pre- and intraoperative parameters. We evaluated the DL model plus simple or ensemble machine learning (ML), and the area under the receiver operating characteristic curve (AUC) was analyzed through sensitivity and specificity. Of 101, 64 and 37 patients demonstrated "early continence (using 0 or 1 safety pad at 3 months post-RARP)" and "late continence (others)," respectively, at 3 months postoperatively. The combination of DL and simple ML using intraoperative video snapshots with clinicopathological parameters had a notably high performance (AUC, 0.683-0.749) to predict early recovery from UI after surgery. Furthermore, combining DL with ensemble artificial neural network using intraoperative video snapshots had the highest performance (AUC, 0.882; sensitivity, 92.2%; specificity, 78.4%; overall accuracy, 85.3%) to predict early recovery from post-RARP incontinence, with similar results by internal validation. The addition of clinicopathological parameters showed no additive effects for each analysis using DL, EL and simple ML.ConclusionOur findings suggest that the DL algorithm with intraoperative video imaging is a reliable method for informing patients about the severity of their recovery from UI after RARP, although it is not clear if our methods are reproducible for predicting long-term UI and pad-free continence.

Dataset Information

Ensemble deep learning for the prediction of proficiency at a virtual simulator for robot-assisted surgery.

Background

Methods

Results

Conclusions

Publications

Ensemble deep learning for the prediction of proficiency at a virtual simulator for robot-assisted surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets