Identifying patients with neurofibromatosis type 1 related optic pathway glioma using the OMOP CDM

Abstract

Neurofibromatosis type 1 (NF1) is a rare tumour predisposition syndrome. Optic pathway gliomas (NF1-related OPG) are a well-characterised tumour type. There is great need for tools that can efficiently identify patients with NF1-related OPG at hospitals. Computable phenotypes algorithms can be used to find patients with certain clinical features in an electronic database. We developed computable phenotype algorithms using the Observational Medical Outcome Partnership (OMOP) Common Data Model. We subsequently assessed if these algorithms could identify patients with NF1-related OPG in an electronic health records (EHR) derived database. We created phenotype algorithms based on diagnosis codes, visits, and radiologic procedures. These phenotypes were applied to the EHR-derived database of an academic hospital. To assess the performance of the phenotypes, we calculated the precision, recall, and F2 score against a list of known cases (n = 61), provided by a clinician. To evaluate the ability of the phenotypes to identify additional cases, we manually reviewed the predicted positives of each phenotype algorithm. The phenotype algorithm based on the diagnosis codes ‘Neurofibromatosis syndrome’ and ‘Neoplasm of optic nerve’ performed best (precision = 1.000, recall = 0.614, F2-score = 0.665). The phenotype ‘Neurofibromatosis syndrome and three or more Ophthalmology visits and one or more MRI of brain’ performed best of the phenotypes based on visits and radiologic procedures (precision = 0.489, recall = 0.511, F2-score = 0.507). Generally, increased precision came at the cost of a decrease in recall. Following review of the predicted positives of each phenotype, 27 additional cases were identified. OMOP computable phenotype algorithms successfully identified NF1-related OPG patients in an EHR-derived database. They provided swift insight into the number of NF1-related OPG cases and were able to identify additional cases, which were not included in the original list of known cases. Phenotype algorithms created with OMOP could be an invaluable tool to facilitate patient screening, especially in multi-centric trials for rare diseases.