Differences

This shows you the differences between two versions of the page.

--- projects:workgroups:nlp-wg [2023/03/03 20:38]
vipina [Project Coordinator]
+++ projects:workgroups:nlp-wg [2023/05/10 01:30]
vipina [Past WG meetings (Agenda/Minutes/Recordings)]
@@ Line 13: / Line 13: @@
 ==== Project Coordinator ====
- [[vipina.kuttichikeloth@yale.edu | Vipina K Keloth ]]
+ [[vipina.kuttichikeloth@yale.edu | Vipina K. Keloth ]]
 ==== OHDSI NLP WG Monthly Meeting ====
@@ Line 20: / Line 20: @@
 **Where:** [[https://teams.microsoft.com/dl/launcher/launcher.html?url=%2F_%23%2Fl%2Fmeetup-join%2F19%3Acd9841fec6df4f3d8eb6a6bf49ea305f%40thread.tacv2%2F1610663053273%3Fcontext%3D%257b%2522Tid%2522%253a%2522a30f0094-9120-4aab-ba4c-e5509023b2d5%2522%252c%2522Oid%2522%253a%252200626e72-b11c-482a-9dc4-d8eff51c5e5f%2522%257d%26anon%3Dtrue&type=meetup-join&deeplinkId=42431bac-788d-4a7b-8531-5eb2612224a6&directDl=true&msLaunch=true&enableMobilePage=true&suppressPrompt=true|Click here to join the meeting]]
-**Monthly Meeting:** Upcoming - December 14, 2022
+**Monthly Meeting:** Upcoming - March 8, 2023
 **Agenda**
- - Invited talk: Dr. Yanjun Gao, University of Wisconsin
+) Presentation - Dr. Daniel G. Smith, Emory University\\
+**Abstract:** Implementing an NLP process into production is an often challenging task, with considerable requirements for accuracy prior to being relied upon in a clinical workflow. However, including other local members of the clinical and research  community in the process at each stage of model selection and development could provide considerable advantages. At Winship Cancer Institute, we’re starting to bring NLP to our research abstractors, as well as our tumor registrars, so that they can provide critical feedback on dictionary curation, NER label verification, and final accuracy of the models in development. We seek feedback from the NLP working group regarding our model of the current process, as well as discuss your experiences in bringing clinical and research staff into the NLP process.\\
+) Updates on the progress of ongoing studies
+  - SDoH
+  - Psychiatry
+  - Oncology
+) NLP book chapter and other OKRs
-**Title: Hierarchical Annotation for Building a Suite of Clinical Natural Language Processing Tasks**
-**Abstract:** Applying methods in natural language processing on electronic health records (EHR) data has attracted rising interests. Existing corpus and annotation focus on modeling textual features and relation prediction. However, there are a paucity of annotated corpus built to model clinical diagnostic thinking, a processing involving text understanding, domain knowledge abstraction and reasoning. In this talk, I will introduce a hierarchical annotation schema with three tasks to address clinical text understanding, clinical reasoning and summarization. We create an annotated corpus based on a large collection of publicly available daily progress notes, a type of EHR that is time-sensitive, problem-oriented, and well-documented by the format of Subjective, Objective, Assessment and Plan (SOAP). I will present the experiment results of applying state-of-the-art language models to this new suite. I will also talk about how this new suite of tasks could perform the paradigm shift of clinical NLP from information extraction and outcome prediction to diagnostic reasoning, and ultimately to effective clinical decision support systems for physicians at the bedside care.
-**Presenter:**\\
-Dr. Yanjun Gao is a postdoc research associate in the Critical Care Medicine (ICU) Data Science Lab in the Division of Allergy, Pulmonary and Critical Care Medicine within the Department of Medicine. She serves on the organizing committee of 2022 National NLP Clinical Challenges (N2C2), and Graph-based Natural Language Processing Workshop (TextGraphs). She has publications across major NLP and AI conferences including ACL, COLING, CoNLL, and reviews for several NLP and clinical informatics conferences and journals. Her current focus is developing NLP models for diagnostic reasoning using clinical text and medical knowledge.
 ==== Ongoing Projects ====
-  * 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
+  * Social Determinants of Health
+  * Psychiatry - NLP for capturing administration of neuropsychiatric scales and their scores
+  * Oncology - NLP for getting oncology data using Tumor Reg data as a gold standard for assessing the information obtained through the NLP algorithm
 ==== Past Projects ====
@@ Line 49: / Line 51: @@
 A noncomprehensive list of participants: [[ Click here ]]
-==== Upcoming Meeting Dates (2022) ====
+==== Upcoming Meeting Dates (2023) ====
-  * December 14
+  * March 8
+  * April 12
+  * May 10
+  * June 14
+  * July 12
+  * August 9
+  * September 13
+  * October 11
+  * November 8
+  * December 13
 ==== Repository ====
@@ Line 63: / Line 74: @@
 ==== Past WG meetings (Agenda/Minutes/Recordings) ====
+**2023**\\
+  -[[WG_meeting_may_10_2023]]
+  -[[WG_meeting_apr_12_2023]]
+  -[[WG_meeting_mar_08_2023]]
+  -[[WG_meeting_feb_08_2023]]
+  -[[WG_meeting_jan_11_2023]]
 **2022**\\
   -[[WG_meeting_dec_14_2022]]

Observational Health Data Sciences and Informatics

User Tools

Site Tools

Differences

Page Tools