Video Commentary & Machine Learning: Tell Me What You See, I Tell You Who You Are

BACKGROUND & OBJECTIVE

Teaching and assessment of complex problem solving are a challenge for medical education. Integrating Machine Learning (ML) into medical education has the potential to revolutionize teaching and assessment of these problem-solving processes. In order to demonstrate possible applications of ML to education, we sought to apply ML in the context of a structured Video Commentary (VC) assessment, using ML to predict residents' training level.

SETTING

A secondary analysis of multi-institutional, IRB approved study. Participants had completed the VC assessment consisting of 13 short (20-40 seconds) operative video clips. They were scored in real-time using an extensive checklist by an experienced proctor in the assessment. A ML model was developed using TensorFlow and Keras. The individual scores of the 13 video clips from the VC assessment were used as the inputs for the ML model as well as for regression analysis.

PARTICIPANTS

A total of 81 surgical residents of all postgraduate years (PGY) 1-5 from 7 institutions constituted the study sample.

RESULTS

Scores from individual VC clips were strongly positively correlated with PGY level (p = 0.001). Some video clips were identified to be strongly correlated with a higher total score on the assessment; others had significant influence when used to predict trainees' PGY levels. Using a supervised machine learning model to predict trainees' PGY resulted in a 40% improvement over traditional statistical analysis.

CONCLUSIONS

Performing better in a few select video clips was key to obtaining a higher total score but not necessarily foretelling of a higher PGY level. The use of the total score as a sole measure may fail to detect deeper relationships. Our ML model is a promising tool in gauging learners' levels on an assessment as extensive as VC. The model managed to approximate residents' PGY levels with a lower MAE than using traditional statistics. Further investigations with larger datasets are needed.

Video Commentary: Rapid-Fire Assessment of Surgical Cognitive Skills

OBJECTIVE

We describe the use of "Video Commentary", an assessment using a set of operative videos, to assess trainees' surgical cognitive skills (operative knowledge, spatial awareness, and surgical insight).

DESIGN & SETTING

The Video Commentary assessment has been routinely administered to Postgraduate Year (PGY) 1-5 general surgery residents since 2014 as part of a biannual multistation, OSCE-type exam at Mayo Clinic, Rochester, MN. Video Commentary is a rapid-fire, 6-minute assessment, where trainees watch a series of 20 to 30 second operative video clips and comment on them as they play. Each clip varies in procedure, approach, difficulty, and complexity. The combination of video clips differs according to trainees' PGY level except for a few videos that overlap among PGY groups. The name of the procedure is provided at the beginning of each clip with a countdown timer showing in the corner of the screen. A comprehensive checklist is used to score trainees' performance in real-time.

DISCUSSION

Assessment of trainees of different levels and staff surgeons show a positive correlation with the experience level (p = 0.0001). The assessment provides a safe alternative to assess trainees in the operating room and encourages them to become more effective communicators. With the use of technology, large video databases can be created to provide just-in-time tailored feedback to the trainees.

CONCLUSIONS

Video Commentary can serve as a time and resource-efficient assessment of trainees' surgical cognitive skills and insight. The use and demand of real-time commentary on operative videos may provide a viable approach to help surgeon educators determine trainees' baseline, progression, and readiness to advance.