High density optical neuroimaging predicts surgeons's subjective experience and skill levels

Area of Science:

• Neurosurgery
• Cognitive Neuroscience
• Medical Education

Background:

• Objective measurement of surgeon cognitive load is crucial for patient safety and surgical training.
• Traditional methods like behavioral metrics and surveys have limitations, including subjectivity and sporadic data.
• Existing methods cannot reliably differentiate between varying skill levels.

Purpose of the Study:

• To investigate the potential of functional near-infrared spectroscopy (fNIRS) and machine learning to objectively assess cognitive load and skill levels in surgeons.
• To correlate prefrontal cortex (PFC) activation patterns with subjective task load and surgical expertise.
• To develop an automated and accurate evaluation method for surgical performance.

Main Methods:

• Collected high-density wireless fNIRS data from 16 surgeons and 17 students performing laparoscopic tasks.
• Assessed subjective mental workload using the NASA-TLX survey.
• Applied machine learning algorithms to predict subjective experience and skill levels based on PFC activation.

Main Results:

• PFC activation patterns differed between students and attending surgeons in relation to task load.
• Machine learning models accurately predicted skill level and subjective task load (nearly 90% accuracy) using PFC activation data.
• fNIRS optical signals contain sufficient information for precise prediction of surgeons' experiences and skill.

Conclusions:

• fNIRS combined with machine learning provides a promising, objective method for evaluating surgical cognitive load and skill.
• This approach can overcome the limitations of traditional subjective and behavioral assessment tools.
• The developed strategy supports the creation of automated, more accurate, and objective surgical evaluation systems.