projects:workgroups:nlp-wg
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
projects:workgroups:nlp-wg [2023/05/10 01:34] vipina [OHDSI NLP WG Monthly Meeting] |
projects:workgroups:nlp-wg [2023/05/10 01:37] (current) vipina [Ongoing Projects] |
||
|---|---|---|---|
| Line 5: | Line 5: | ||
| 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. | 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. | ||
| - | ==== Project Lead ==== | + | ==== Workgroup Lead ==== |
| [[https://www.ohdsi.org/who-we-are/collaborators/hua-xu/|Hua Xu]]\\ | [[https://www.ohdsi.org/who-we-are/collaborators/hua-xu/|Hua Xu]]\\ | ||
| Line 24: | Line 24: | ||
| **Agenda** | **Agenda** | ||
| - | 1) Presentation - Nic Dobbins (Principal Solutions Architect at UW Medicine Research IT; PhD Candidate in biomedical informatics at the University of Washington)\\ | + | 1) Presentation - **Nic Dobbins** (Principal Solutions Architect at UW Medicine Research IT; PhD Candidate in biomedical informatics at the University of Washington)\\ |
| - | **Title:** LeafAI: query generator for clinical cohort discovery rivaling a human programmer | + | **Title:** LeafAI: query generator for clinical cohort discovery rivaling a human programmer\\ |
| **Abstract:** Identifying study-eligible patients within clinical databases is a critical step in clinical research. However, accurate query design typically requires extensive technical and biomedical expertise. We sought to create a system capable of generating data model-agnostic queries while also providing novel logical reasoning capabilities for complex clinical trial eligibility criteria. We incorporated hybrid deep learning and rule-based modules for these, as well as a knowledge base of the Unified Medical Language System (UMLS) and linked ontologies. To enable data-model agnostic query creation, we introduce a novel method for tagging database schema elements using UMLS concepts. To evaluate our system, called LeafAI, we compared the capability of LeafAI to a human database programmer to identify patients who had been enrolled in 8 clinical trials conducted at our institution. We measured performance by the number of actual enrolled patients matched by generated queries. LeafAI matched a mean 43% of enrolled patients with 27,225 eligible across 8 clinical trials, compared to 27% matched and 14,587 eligible in queries by a human database programmer. The human programmer spent 26 total hours crafting queries compared to several minutes by LeafAI. Finally, we introduce a novel multimodal user interface for interaction with LeafAI.\\ | **Abstract:** Identifying study-eligible patients within clinical databases is a critical step in clinical research. However, accurate query design typically requires extensive technical and biomedical expertise. We sought to create a system capable of generating data model-agnostic queries while also providing novel logical reasoning capabilities for complex clinical trial eligibility criteria. We incorporated hybrid deep learning and rule-based modules for these, as well as a knowledge base of the Unified Medical Language System (UMLS) and linked ontologies. To enable data-model agnostic query creation, we introduce a novel method for tagging database schema elements using UMLS concepts. To evaluate our system, called LeafAI, we compared the capability of LeafAI to a human database programmer to identify patients who had been enrolled in 8 clinical trials conducted at our institution. We measured performance by the number of actual enrolled patients matched by generated queries. LeafAI matched a mean 43% of enrolled patients with 27,225 eligible across 8 clinical trials, compared to 27% matched and 14,587 eligible in queries by a human database programmer. The human programmer spent 26 total hours crafting queries compared to several minutes by LeafAI. Finally, we introduce a novel multimodal user interface for interaction with LeafAI.\\ | ||
| Line 41: | Line 41: | ||
| * Psychiatry - NLP for capturing administration of neuropsychiatric scales and their scores | * 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 | * Oncology - NLP for getting oncology data using Tumor Reg data as a gold standard for assessing the information obtained through the NLP algorithm | ||
| + | * Book of OHDSI NLP Chapter | ||
| ==== Past Projects ==== | ==== Past Projects ==== | ||
| Line 54: | Line 55: | ||
| ==== Upcoming Meeting Dates (2023) ==== | ==== Upcoming Meeting Dates (2023) ==== | ||
| - | * March 8 | ||
| - | * April 12 | ||
| - | * May 10 | ||
| * June 14 | * June 14 | ||
| * July 12 | * July 12 | ||
projects/workgroups/nlp-wg.1683682443.txt.gz · Last modified: 2023/05/10 01:34 by vipina
Page Tools
