January 1, 2023Open Access

Enhancing Skill Assessment of Autonomous Robot-Assisted Minimally Invasive Surgery: A Comprehensive Analysis of Global and Gesture-Level Techniques applied on the JIGSAWS Dataset

Q: What is the clinical evidence from this study?

Study design: Other. Population: Robot-Assisted Minimally Invasive Surgery (RAMIS) skill assessment (n=8). Intervention: Machine learning classification algorithms (Decision Tree, k-NN, SVM, Logistic Regression, DTW, 1D CNN) vs. Global dataset assessment. Primary outcome: Classification accuracy of surgeon skill level (novice vs. experienced).

Q: What does this research mean for the field?

Gesture-level analysis using machine learning algorithms on kinematic data achieves 100% accuracy in classifying surgeons into novice and experienced groups for suturing, knot-tying, and needle-passing tasks. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Key Result

Gesture-level analysis using machine learning algorithms achieved 100% accuracy in classifying surgeons into novice and experienced groups for suturing, knot-tying, and needle-passing tasks.

Structured PICO

Population

8 right-handed participants with varying levels of surgical experience performing 3 different robotic surgical tasks (suturing, knot-tying, and needle-passing) from the JIGSAWS dataset

Intervention

Machine learning classification methods (Decision Tree, k-Nearest Neighbors, Support Vector Machines, Logistic Regression, Dynamic Time Warping, and 1D Convolutional Neural Network) applied to kinematic data

Outcome

Accuracy of classifying surgeons into novice and experienced groups

Machine learning algorithms applied to kinematic data from robot-assisted minimally invasive surgery can accurately classify surgeons' skill levels, particularly when analyzed at the gesture level.

Limitations

Small sample size of only 8 participants in the JIGSAWS dataset
Inconsistency in achieving the same accuracy when tests were rerun for non-time series classifiers
Lack of cross-validation in some DTW analyses could result in overly optimistic or pessimistic evaluations

Abstract

Improved surgical skills play a crucial role in ensuring optimal patient outcomes.Traditional methods for skill assessment include self-rating questionnaires and expert evaluations, but these approaches are prone to bias and require substantial qualified human resources.The emergence of Surgical Data Science (SDS) offers a promising avenue for automating skill assessment, leveraging data science techniques to capture, organize, analyze, and model surgical data.In this paper, kinematic data was employed from the JIGSAWS -which is the only skill-annotated Robot-Assisted Minimally Invasive Surgery (RAMIS) dataset -to classify surgeons into novice and experienced groups, using various classification methods (Decision Tree, k-Nearest Neighbors, Support Vector Machines, Logistic Regression, Dynamic Time Warping, and 1D Convolutional Neural Network).The research encompasses a thorough analysis of parameter tuning and dimensional reduction techniques with the aim of establishing a universal benchmark for data classification.The surgical training tasks of suturing, knot-tying and needle-passing consistently achieved 100 % accuracy.The accuracy attained during surgical gesture analysis often exceeded the overall accuracy of the global assessment of the dataset.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper

Cite This Study

Lukács et al. (Sun,) conducted a other in Robot-Assisted Minimally Invasive Surgery (RAMIS) skill assessment (n=8). Machine learning classification algorithms (Decision Tree, k-NN, SVM, Logistic Regression, DTW, 1D CNN) vs. Global dataset assessment was evaluated on Classification accuracy of surgeon skill level (novice vs. experienced). Gesture-level analysis using machine learning algorithms achieved 100% accuracy in classifying surgeons into novice and experienced groups for suturing, knot-tying, and needle-passing tasks.

synapsesocial.com/papers/6a1a2305ffd597a64136ff7c https://doi.org/https://doi.org/10.12700/aph.20.8.2023.8.8

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: