Related Experiment Video
Updated: Aug 16, 2025
07:44
Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis
Published on: March 23, 2019
17.8K
Surgical gestures as a method to quantify surgical performance and predict patient outcomes
Runzhuo Ma1, Ashwin Ramaswamy2, Jiashu Xu3
1Center for Robotic Simulation & Education, Catherine & Joseph Aresty Department of Urology, USC Institute of Urology, University of Southern California, Los Angeles, CA, USA.
NPJ Digital Medicine
|December 22, 2022
Summary
Analyzing surgical gestures in robot-assisted radical prostatectomies reveals specific movements linked to better erectile function recovery. This objective approach can improve surgical performance and patient outcomes.
Area of Science:
- Robotics in Surgery
- Surgical Performance Analysis
- Urological Surgery Outcomes
Background:
- Objective quantification of surgical performance is crucial for patient outcomes but remains challenging.
- Deconstructing procedures into instrument-tissue "gestures" offers a novel approach to surgical analysis.
- Nerve-sparing robot-assisted radical prostatectomy is a procedure where surgical technique critically impacts patient recovery, particularly erectile function.
Purpose of the Study:
- To identify specific surgical gestures associated with improved 1-year erectile function (EF) recovery after robot-assisted radical prostatectomy.
- To investigate the interaction between surgeon experience and gesture selection on EF recovery.
- To validate a gesture-based framework for predicting surgical outcomes using machine learning.
Main Methods:
- Identification and classification of 34,323 individual surgical gestures from 80 nerve-sparing robot-assisted radical prostatectomies.
- Statistical analysis to correlate specific gestures (e.g., "hot cut," "peel/push") with 1-year EF recovery.
- Development and comparison of machine learning models using surgical gesture sequences versus traditional clinical features to predict 1-year EF recovery.
Main Results:
- Reduced use of "hot cut" and increased use of "peel/push" gestures were statistically associated with a higher likelihood of 1-year EF recovery.
- Surgeon experience significantly modulated the impact of gesture selection on EF recovery.
- Machine learning models based on gesture sequences demonstrated superior prediction of 1-year EF recovery (AUCs ranging from 0.68 to 0.77) compared to models using traditional clinical features (AUCs ranging from 0.65 to 0.69).
Conclusions:
- Surgical gestures provide a granular, objective metric for assessing surgical performance and predicting patient outcomes.
- This gesture-based framework has the potential to guide surgical training and improve patient recovery in radical prostatectomy.
- The methodology can be extended to other surgical procedures to uncover performance-outcome relationships and enhance surgical quality.
