-
https://d1y502jg6fpugt.cloudfront.net/13418/archive/files/9554c92419ee4ecb07551bab14b3274a.pdf?Expires=1712793600&Signature=nkPSiXigg4%7EiOqANOaTV%7Ec7AaZb812o-%7EX3YXOpRG3tXzFM7UDt7MQGg83ntzgoJd7ifE%7Ey5gukKKcu7au%7ELYaqYtljVr%7EM1uef9BpbVxGLYfr1fdK7iOB6U0cU3DAEEuqp9G2FTyoLmpupGM3EOcBa%7ExXdaWW6L6aZy3yaRDtMpuiHnGnzdqUSamW2wPudIwofbs9uDwqHtmc-JcpGQOpRUrA3lsNcyFqSBaohutbWWN7v-6kSkrHq0iEkNCgIdOWOx8cP8HXrPPxyY3f%7Ec09yvJfaYp-UcDWODZ%7EPCLfLJrPMmejjqIethGaDxU9HRdz6xDsV708AF4f9zR3E6Fw__&Key-Pair-Id=K6UGZS9ZTDSZM
3cd488c83918a73f7b575598a403d89e
PDF Text
Text
Using Machine Learning to Identify Consent Forms
The Problem
The Interventions
Perioperative staff often manually look for various documents including consent forms
prior to surgery. In 2017 there were 15,866 surgical cases where documentation
(including consent forms) was faxed to BIDMC resulting in a total of 106,134 faxed
pages that staff needed to manually review in order to find the consent forms. Delays
in finding or absence of consent forms impacted surgery schedules.
Aim/Goal
Using Machine Learning (ML), proactively identify if a patient has a consent form and
prompt the perioperative staff with this information in advance. Components include:
An icon will display at the top of the screen if a consent form has been identified
and staff can click on it to view the document
Users can also continue to search for document via the PAT Fax View
The Results/Progress to Date
Live on 2/28/2018
The Team
The BIDMC Center for IT Exploration (ITEx) was established in 2017. The Center’s
mission is to evaluate innovative technologies to enhance our EHR in modular and
interoperable ways. The Center is comprised of BIDMC staff along with partners
including Google, Amazon, and MIT.
The goal is to experiment with new technologies and identify use cases where those
technologies could benefit BIDMC. In some cases, there are no viable use cases so
efforts are refocused to other work (try fast, fail fast, and move on). This is the first
ITEx Machine Learning effort to be placed into production at BIDMC.
Special thanks to:
• Kevin Afonso
• Phyllis Agresti
• Bela Cardoso
• Jane Cody
• Chuck Fuller
• Alvin Gayles
• Anand Kumar
• Edna Moody
• Huili Shao
• Si Wong
Lessons Learned
Discussion of challenges and technologies in a heterogeneous group comprised of
clinical, business, and technology people leads to opportunities to match technology
with real world clinical challenges.
Next Steps/What Should Happen Next
The ITEx will continue to support and maintain the IS Strategic Plan and IT Steering
Committee through:
Experimenting with ML to identify History and Physical (H&P) form
Actively seeking additional ways to apply this technology
For more information, contact:
ISStrategicPlanningTeam@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.
IS Strategic Planning Team (<a href="mailto:isstrategicplanningteam@bidmc.harvard.edu">isstrategicplanningteam@bidmc.harvard.edu</a>)
Department
Any departments listed on the poster or identified in the spreadsheet.
Information Systems
Perioperative Staff
Project Team
Kevin Afonso
Chuck Fuller
Edna Moody
Phyllis Agresti
Alvin Gayles
Huili Shao
Bela Cardoso
Anand Kumar
Si Wong
Jane Cody
BIDMC Location
The BIDMC location where the poster team resides if identified in spreadsheet. If not identified, choose BIDMC.
BIDMC
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
Using Machine Learning to Identify Consent Forms
Date
A point or period of time associated with an event in the lifecycle of the resource
2018
Format
The file format, physical medium, or dimensions of the resource
pdf
Efficiency