COHORT IDENTIFICATION FROM FREE-TEXT CLINICAL NOTES USING SNOMED CT’S SEMANTIC RELATIONS
Public Deposited- Creator
-
Chang, Eunsuk
- Affiliation: University of North Carolina at Chapel Hill. Graduate School, Health Informatics PhD Program
- Abstract
- In this paper, a new cohort identification framework that exploits the semantic hierarchy of SNOMED CT is proposed to overcome the limitations of supervised machine learning-based approaches. Eligibility criteria descriptions and free-text clinical notes from the 2018 National NLP Clinical Challenge (n2c2) were processed to map to relevant SNOMED CT concepts and to measure semantic similarity between the eligibility criteria and patients. The eligibility of a patient was determined if the patient had a similarity score higher than a threshold cut-off value, which was established where the best F1 score could be achieved. The performance of the proposed system was evaluated for three eligibility criteria. The current framework’s macro-average F1 score across three eligibility criteria was higher than the previously reported results of the 2018 n2c2 (0.933 vs. 0.889). This study demonstrated that SNOMED CT alone can be leveraged for cohort identification tasks without referring to external textual sources for training.
- Date of publication
- 2022
- Keyword
- DOI
- Resource type
- Rights statement
- In Copyright - Educational Use Permitted
- Advisor
- Mostafa, Javed
- Yu, Fei
- Pfaff, Emily R.
- Potenziani, David D.
- Robasky, Kimberly
- Degree
- Doctor of Philosophy
- Degree granting institution
- University of North Carolina at Chapel Hill Graduate School
- Graduation year
- 2022
- Language
Relations
- Parents:
This work has no parents.
Items
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
Chang_unc_0153D_20838.pdf | 2022-05-26 | Public | Download |