Cohort Identification from Free-Text Clinical Notes Using SNOMED CT's Hierarchical Semantic Relations

In this paper, a new cohort identification system 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. The performance of the proposed system was evaluated for three eligibility criteria. The performance of the current system exceeded the previously reported results of the 2018 n2c2, achieving the average F1 score of 0.933. This study demonstrated that SNOMED CT alone can be leveraged for cohort identification tasks without referring to external textual sources for training.