-
https://d1y502jg6fpugt.cloudfront.net/13418/archive/files/fa25a1b499e04b708cc1845f8403343f.pdf?Expires=1712793600&Signature=e5k6VOgq92L9%7EyY5uYvvvo-iQN36SG0xlJjfLl1CB7t34I71ZjTQACMyOVOh-dDm6c9rAjPoM3CHwSD9WgVWE9nSPdZOvTbPH6UKoylfoH8hUcc8oDCBA0IoGpYEBMtUk2E60VMSHqvnXsVhWPMn29UUbzxj2psrEXx60OBHmPw17l4jzDP2a2LNDd%7E-EbMNYoovMVdcODVBtYijUnxjokBuqQdkxbGBq5afgWA7rhM2uX-22guMQ8IOpxQMsavd4WVHFX4qj4ubS2ieCHthqIudBkz6Qz0kriI9s1wjgkRdaepMjg8Mdp-dlHrkIKM15HlDsVVA0nI%7EceOtTzpeiw__&Key-Pair-Id=K6UGZS9ZTDSZM
41a1a2cd4c4c7d88a2f709035489dd3e
PDF Text
Text
Leveraging a Real-Time Spatiotemporal AI Model for Surgical Resident Training and Education With
Implications during Pandemic-Related Surgical Volume Changes
Yilun Zhang1, Emmett Goodman2, Chris Kennedy1, Jevin Clark1, Hao Wei Chen1, Maren Downing1, Jordan Bohnen1, Serena Yeung2, Gabriel Brat1
1. Beth Israel Deaconess Medical Center, Boston, MA; 2. Department of Biomedical Data Science, Stanford University, Stanford, CA
Introduction/Problem
The Intervention
The COVID-19 pandemic exposed the existing need for more opportunities to
provide real-time feedback for surgical skills for surgical residents.
Real-Time Spatiotemporal AI Model
Aim/Goal
To Provide Automated Classification of Surgical Skill and Incorporate
Real-Time Feedback
The Team
Gabriel Brat, MD, MPH
Serena Yeung, PhD
For more information, contact:
Ilonzo, Nicole, Issam Koleilat, Vivek Prakash, John Charitable, Karan Garg, Daniel Han, Peter Faries, and John Phair. 2021. “The Effect of
COVID-19 on Training and Case Volume of Vascular Surgery Trainees.” Vascular and Endovascular Surgery 55 (5): 429–33.
�More Results/Progress to Date
Towards Understanding Surgical Skill
From Understanding Surgical Technique...
For more information, contact:
�More Results/Progress to Date
Model for Implementation
PGY1
Lessons Learned
Baseline
Next Steps
N = 104
For more information, contact:
�More Results/Progress to Date
Model for Implementation
PGY1
Lessons Learned
Baseline
Work on economy of motion by:
Reduce distance traveled by needle
driver hand
PGY1.5
Work on economy of motion by:
Continue to reduce distance traveled by needle
driver hand but also that of suture hand
Conserve hand pose by reducing unnecessary
rotation
Next Steps
N = 104
For more information, contact:
�More Results/Progress to Date
Model for Implementation
PGY1
Lessons Learned
Baseline
Work on economy of motion by:
Reduce distance traveled by needle
driver hand
PGY1.5
Work on economy of motion by:
Continue to reduce distance traveled by needle
driver hand but also that of suture hand
Conserve hand pose by reducing unnecessary
rotation
PGY2
Next Steps
New Baseline! Pred: PGY 3
Focus on conserving suture hand pose by reducing
unnecessary pronation
N = 104
For more information, contact:
�More Results/Progress to Date
Model for Implementation
Lessons Learned
Surgical Residents Require More Feedback during Case Load Changes
PGY1
Baseline
Automated evaluation of surgical skill is possible
Work on economy of motion by:
Reduce distance traveled by needle
driver hand
Providing “Just in Time” feedback after engaging in a task increases retention
PGY1.5
More discrete levels of training could allow for better than a binary skill
classification
Work on economy of motion by:
Continue to reduce distance traveled by needle
driver hand but also that of suture hand
Conserve hand pose by reducing unnecessary
rotation
PGY2
Next Steps
Improve integration of automated and remote forms of real-time feedback
for surgical trainees
New Baseline! Pred: PGY 3
Potential for other situations whenever the training path could be disrupted
Encourage increased collaboration between institutions
Focus on conserving suture hand pose by reducing
unnecessary pronation
PGY3
N = 104
Thank you to the peri-operative staff, the Shapiro Clinical Center, and
the residents who helped make this possible!
For more information, contact:
Contact: gbrat@bidmc.harvard.edu
�
Dublin Core
The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/.
Title
A name given to the resource
Silverman Symposium
Description
An account of the resource
Each year the Silverman Symposium poster session offers BIDMC staff and affiliates the opportunity to share experiences and learn about efforts to improve Quality and Safety.
Date
A point or period of time associated with an event in the lifecycle of the resource
2021
Silverman Poster
Primary Contact
If you would like more information about this project, contact this person. Make email address clickable.
Gabriel Brat (<a href="mailto:gbrat@bidmc.harvard.edu" target="_blank" rel="noreferrer noopener">gbrat@bidmc.harvard.edu</a>)
Project Team
Yilun Zhang
Emmett Goodman
Chris Kennedy
Jevin Clark
Hao Wei Chen
Maren Downing
Jordan Bohnen
Serena Yeung
Gabriel Brat
BIDMC Location
The BIDMC location where the poster team resides if identified in spreadsheet. If not identified, choose BIDMC.
BIDMC
Department
Any departments listed on the poster or identified in the spreadsheet.
Surgery
Dublin Core
The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/.
Title
A name given to the resource
Leveraging a Real-Time Spatiotemporal AI Model for Surgical Resident Training and Education with Implications during Pandemic-Related Surgical Volume Changes
Date
A point or period of time associated with an event in the lifecycle of the resource
2021
Format
The file format, physical medium, or dimensions of the resource
pdf
Safety
Timeliness