The primary goal of the NLP working group is to promote the use of textual information from Electronic Health Records (EHRs) for observational studies under the OHDSI umbrella. To facilitate this objective, the group will develop methods and software that can be implemented to utilize clinical text for studies by the OHDSI community.

Hua Xu

Vipina K Keloth

When: Second Wednesday of every month at 1 PM - 2 PM CT

Where: Click here to join the meeting

Monthly Meeting: Upcoming - August 10, 2022

Agenda

1. Note_NLP proposal revision
2. Call for participation - Mayo clinic

Project Abstract: Delirium is a syndrome with symptoms that present as confusion and is characterized by an acute change in mental status, fluctuating course, lack of attention, and disorganized thinking or altered level of consciousness. Delirium is routinely underdiagnosed, particularly mild cases, and electronic billing codes incompletely capture this condition. In addition, incomplete identification of delirium can substantially hamper clinical research efforts that use large databases to identify risk factors for and outcomes of delirium. Although billing codes in administrative datasets may incompletely identify delirium cases, clinical notes frequently contain details that are relevant to a delirium diagnosis. Therefore, we have developed a natural language processing (NLP) algorithm to identify delirium episodes from electronic health record (EHR) clinical notes based on the confusion assessment method (CAM) framework for identifying episodes. To characterize changes in delirium over time, we aim to apply this algorithm to different institutions, and compare the cases identified via the algorithm to cases identified using international classification of diseases (ICD) billing codes. We will also examine differences in rates of delirium over time and by age, sex, race, and ethnicity using these methods.

Original NLP study: https://academic.oup.com/biomedgerontology/article/77/3/524/5943765

Presented by: Dr. Sunyang Fu, Dr. Jennifer St. Sauver

Bio: Sunyang Fu is an incoming Research Associate at Mayo Clinic Department of AI and Informatics Research. The overarching goal of his research is to accelerate, improve and govern the secondary use of Electronic Health Records (EHRs) for clinical and translational research towards high throughput, reproducible, fair, and trustworthy discoveries. He has extensive informatics research experience in (1) assessing EHR data quality and heterogeneity, (2) developing natural language processing (NLP) techniques for clinical information extraction, and (3) designing and developing informatics frameworks for clinical research workflow optimization. He also has extensive collaborative research experience in clinical and translational science, epidemiology, outcome research, standards, and precision medicine.

Dr. Jennifer St. Sauver is the associate scientific director of the Population Health Science Program at Mayo Clinic's Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery. She is also co-principal investigator of the Rochester Epidemiology Project, a National Institutes of Health-funded research infrastructure that collates and indexes health care information from medical care available to residents of a 27-county region of southeast Minnesota and southwest Wisconsin. These data have been used by investigators throughout the United States, resulting in nearly 3,000 publications on a wide range of health care topics.

• Clinical Abbreviations
• Post-acute sequelae of SARS-CoV-2 infection (PASC) study
• Extraction, Transformation, and Load Process (ETL)
• Note type normalization
• Open source Python NLP package

• Note_NLP table
• COVID-19 testing normalization (TestNorm)
• Note type
• NLP tools: NLP Wrappers; THEIA; Ananke

A noncomprehensive list of participants: Click here

• August 10
• September 14
• October 12
• November 9
• December 14

• NLP Tools in OHDSI GitHub https://github.com/OHDSI/NLPTools
• OHDSIananke https://github.com/thepanacealab/OHDSIananke

2022

1. WG_meeting_sep_14_2022
2. WG_meeting_aug_10_2022
3. WG_meeting_jun_08_2022
4. WG_meeting_may_11_2022
5. WG_meeting_apr_13_2022
6. WG_meeting_mar_09_2022
7. WG_meeting_feb_09_2022
8. WG_meeting_jan_12_2022

2021

1. WG_meeting_dec_08_2021
2. WG_meeting_nov_10_2021
3. WG_meeting_oct_13_2021
4. WG_meeting_sep_08_2021
5. WG_meeting_aug_11_2021

2019

1. WG_meeting_10092019
2. WG_meeting_09112019
3. WG_meeting_08142019
4. WG_meeting_07102019
5. WG_meeting_05082019
6. WG_meeting_04102019
7. WG_meeting_03132019
8. WG_meeting_02132019
9. WG_meeting_01092019

2018

1. WG_meeting_11142018
2. WG_meeting_09122018
3. WG_meeting_06132018
4. WG_meeting_05092018
5. WG_meeting_04142018
6. WG_meeting_03142018
7. WG_meeting_02142018
8. WG_meeting_01102018

2017

1. WG_meeting_12122017
2. WG_meeting_10112017
3. WG_meeting_09132017
4. WG_meeting_07122017
5. WG_meeting_06142017

2016

1. WG_meeting_04202016
2. WG_meeting_04132016
3. WG_meeting_03092016
4. WG_meeting_02032016
5. WG_meeting_01062016

2015

1. WG_meeting_11042015
2. WG_meeting_10072015

Join on your computer or mobile app

Click here to join the meeting

Learn More