Data analytics interrogates robotic surgical performance using a microsurgery-specific haptic device.

Area of Science:

• Robotics in Surgery
• Surgical Skill Assessment
• Haptic Technology

Background:

• Robot-assisted surgery is increasing, necessitating objective measures for surgeon proficiency.
• Evaluating surgeon dexterity is critical for training and patient safety.

Purpose of the Study:

• To assess a new haptic device, neuroArmPLUS^HD, for its effectiveness in robotic surgery.
• To quantify surgeon performance using sensor-based kinematics and machine learning.

Main Methods:

• Thirty surgeons performed a micromanipulation task using neuroArmPLUS^HD and two other controllers.
• Surgical performance was evaluated using subjective surveys and objective sensor data.
• Statistical and regression analyses were used to develop a machine learning model for skill assessment.

Main Results:

• The neuroArmPLUS^HD device showed significant improvements in time, errors, distance, clutch incidents, and forces compared to other controllers.
• Surgeons reported the neuroArmPLUS^HD as smoother, more comfortable, less tiring, and offering more realistic force feedback.
• An ensemble machine learning model achieved 0.78 (0.15) accuracy in classifying surgeon skills.

Conclusions:

• The study validates the use of advanced haptic devices for objective surgical skill evaluation.
• Incorporating superior haptic technology is essential for standardizing surgical education and enhancing patient care.