Clinical concept normalization with a hybrid natural language processing system combining multilevel matching and machine learning ranking.

OBJECTIVE: Normalizing clinical mentions to concepts in standardized medical terminologies, in general, is challenging due to the complexity and variety of the terms in narrative medical records. In this article, we introduce our work on a clinical natural language processing (NLP) system to automatically normalize clinical mentions to concept unique identifier in the Unified Medical Language System. This work was part of the 2019 n2c2 (National NLP Clinical Challenges) Shared-Task and Workshop on Clinical Concept Normalization. MATERIALS AND METHODS: We developed a hybrid clinical NLP system that combines a generic multilevel matching framework, customizable matching components, and machine learning ranking systems. We explored 2 machine leaning ranking systems based on either ensemble of various similarity features extracted from pretrained encoders or a Siamese attention network, targeting at efficient and fast semantic searching/ranking. Besides, we also evaluated the performance of a general-purpose clinical NLP system based on Unstructured Information Management Architecture. RESULTS: The systems were evaluated as part of the 2019 n2c2 challenge, and our original best system in the challenge obtained an accuracy of 0.8101, ranked fifth in the challenge. The improved system with newly designed machine learning ranking based on Siamese attention network improved the accuracy to 0.8209. CONCLUSIONS: We demonstrate the successful practice of combining multilevel matching and machine learning ranking for clinical concept normalization. Our results indicate the capability and interpretability of our proposed approach, as well as the limitation, suggesting the opportunities of achieving better performance by combining general clinical NLP systems.

Aryl Hydrocarbon Receptor Activates NDRG1 Transcription under Hypoxia in Breast Cancer Cells.

Hypoxia has been intensively investigated over the past several decades based on the observations that hypoxic tumors are more resistant to therapy and have a worse prognosis. Previously, we reported that N-myc downstream-regulated gene 1 (NDRG1) is strongly up-regulated under hypoxia and may play an important role in tumor adaptation to fluctuating oxygen concentrations. However, the regulatory mechanism of NDRG1 under hypoxia remains elusive. Therefore, the purpose of this study was to identify the transcription factors that regulate NDRG1 and to investigate the functional roles of NDRG1 in hypoxia. We showed that binding sites of aryl hydrocarbon receptor (AHR) were predicted in the NDRG1 promoter. Nuclear AHR was up-regulated in the presence of cobalt and hypoxia. AHR translocated to nuclei and bound between base pairs -412 and -388 of the NDRG1 promoter in hypoxia. Moreover, hypoxia-mimetic induction of NDRG1 was attenuated by knockdown of AHR expression. Also, overexpression of AHR facilitated cell proliferation and migration via up-regulation of NDRG1. These results showed for the first time that AHR positively regulates NDRG1 transcription through an AHR binding site by way of hypoxia-mimetic signaling, which may lead to development of a specific therapeutic regimen to prevent tumor malignancy under hypoxia.