projects:workgroups:nlp-wg
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision | Next revision Both sides next revision | ||
|
projects:workgroups:nlp-wg [2023/05/10 01:34] vipina [OHDSI NLP WG Monthly Meeting] |
projects:workgroups:nlp-wg [2023/05/10 01:34] vipina [OHDSI NLP WG Monthly Meeting] |
||
|---|---|---|---|
| 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.\\ | ||
projects/workgroups/nlp-wg.txt · Last modified: 2023/05/10 01:37 by vipina
Page Tools
