Differentiating Laparoscopic Skills of Trainees with Computer Vision Based Metrics

Deng, Shiyu; Kulkarni, Chaitanya; Wang, Tianzi; Hartman-Kenzler, Jacob; Barnes, Laura E.; Parker, Sarah; Safford, Shawn D.; Rajamohan, Srijith; Lau, Nathan

doi:10.1177/1071181321651263

Cited by 5 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adopting the same metric as a gauge of deviation and thus potentially passing a FLS skill test would also seem reasonable extension of the gaze metric. However, our recent research examining skill progression of medical students on a FLS practice task indicates that trainees seem to have faster completion time but exhibit worse gaze metrics after some training before attaining the best completion time and gaze metrics (Deng et al, 2021). We postulated this non-linear relationship is probably because trainees might commit "errors" in order to shift their gaze behaviors from feedback to feedforward control as they gain some familiarity and skills with the task.…”

Section: Examples Of Participant Sampling On Consequential Validitymentioning

confidence: 97%

Toward a Consequential Validity Perspective for Selecting Participant Groups in Testing and Evaluation Studies for Complex Systems

Lau¹,

Boring²

2022

Human Factors and Simulation

View full text Add to dashboard Cite

Testing and evaluation of technology design for complex systems cannot readily attain conclusive results. This is because skilled professionals are often not available for testing while non-professionals may not be capable of operating the actual systems or high-fidelity simulators. Thus, practitioners and applied scientists can be challenged with decisions on selecting participant groups, which can severely constrain choices in the experimental tasks. This article presents the perspective of consequential validity, highlighting that general validity or rules to participant selection probably do not exist. Most importantly, the validity of a testing method or an empirical finding critically rests on the decisions of interest that must take into account nuances or idiosyncrasies of specific situations and desired outcomes. This perspective stands in contrast to how the literature predominantly portrays validity of testing methods or empirical findings as universal rather than focusing on outcomes within the confines of the study methods. The perspective of consequential validity calls for studies on how classical metrics of reliability and validity could manifest in consequence of specific decisions informed by empirical testing.

show abstract

Section: Examples Of Participant Sampling On Consequential Validitymentioning

confidence: 97%

Toward a Consequential Validity Perspective for Selecting Participant Groups in Testing and Evaluation Studies for Complex Systems

Lau¹,

Boring²

2022

Human Factors and Simulation

View full text Add to dashboard Cite

show abstract

“…Eye metrics can be generally classified into scene independent and scene dependent eye metrics (Deng et al, 2021). Scene independent eye metrics are independent of where eye gazes target, and thus are computed without specifying any areas of interest (AOIs).…”

Section: Introductionmentioning

confidence: 99%

Assessing Laparoscopic Surgical Skills of Trainees with Scene Independent and Dependent Eye Gaze Metrics

Deng,

Oh,

Wang

et al. 2023

Proceedings of the Human Factors and Ergonomics Society Annual

Self Cite

View full text Add to dashboard Cite

Eye metrics have been used to objectively evaluate proficiency levels in psychomotor tasks, including aviation, driving, sports, and surgery. Despite extensive research devoted to developing and utilizing eye metrics, the literature does not contain any explicit comparison between scene independent and dependent eye metrics for understanding skill acquisition or characterizing expertise. This study collected eye tracking data from medical students practicing the peg transfer task and computed both scene independent and dependent eye metrics to indicate proficiency. K-means clustering analysis on the eye metrics yielded three clusters corresponding to three proficiency levels which showed significantly different trial completion time. The box plots of the eye-gaze metrics illustrated different patterns of scene independent and dependent eye metrics with respect to proficiency levels, highlighting the need for further examination of these metrics for accurate and useful applications.

show abstract

Scene-dependent, feedforward eye gaze metrics can differentiate technical skill levels of trainees in laparoscopic surgery

Kulkarni

Deng²,

Wang³

et al. 2022

Surg Endosc

View full text Add to dashboard Cite

Differentiating Laparoscopic Skills of Trainees with Computer Vision Based Metrics

Cited by 5 publications

References 23 publications

Toward a Consequential Validity Perspective for Selecting Participant Groups in Testing and Evaluation Studies for Complex Systems

Toward a Consequential Validity Perspective for Selecting Participant Groups in Testing and Evaluation Studies for Complex Systems

Assessing Laparoscopic Surgical Skills of Trainees with Scene Independent and Dependent Eye Gaze Metrics

Scene-dependent, feedforward eye gaze metrics can differentiate technical skill levels of trainees in laparoscopic surgery

Contact Info

Product

Resources

About