Subject-wise standardization of eye-tracking features marginally improved the fit of performance and learning rate models¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person · recheck by 2027: tool and model accuracy changes quickly

Subclaims¶

q2 i? Subject-wise standardization increased R2 by 0.17 for Tubes performance, 0.04 for Dots and Needles performance, and 0.09 for Dots and Needles learning rate relative to unstandardized models. → Shafiei 2024

Evidence¶

Shafiei 2024¶

Shafiei, S. B., Shadpour, S., Sasangohar, F., Mohler, J. L., Attwood, K. & Jing, Z. (2024). Development of performance and learning rate evaluation models in robot-assisted surgery using electroencephalography and eye-tracking. npj Science of Learning 9:3. https://doi.org/10.1038/s41539-024-00216-y

q2 · i? · associational · r1

Comparison of the standardized models (Tables 1–6) against unstandardized models reported in the Supplementary Information. The authors state standardization reduces the impact of individual variances among subjects so features reflect skill differences rather than individual characteristics. R2 changes are printed but no standardized effect size.

"The results indicate that subject-wise standardization of eye-tracking features marginally enhanced the R2 values for both performance (0.17 increase for the Tubes task, 0.04 increase for the Dots and Needles task) and learning rate evaluations (0.09 increase for the Dots and Needles task)."

Discussion¶

Related Claims¶

• In the Tubes task, larger average pupil diameter of the nondominant eye and higher rate of saccade are associated with lower RAS simulator performance — related
• In the Dots and Needles task, higher entropy of the nondominant eye's pupil diameter is associated with lower performance — related
• Certain multimodal data combinations improve predictive model performance, with audio plus eye-tracking data most effective in one K–8 study — related
• First-attempt EEG features and initial performance score predict learning rate, with higher initial scores associated with lower learning rates — related