Representation of EHR data for predictive modeling: a comparison between UMLS and other terminologies.

Autor:	Rasmy, Laila1 (AUTHOR), Tiryaki, Firat1 (AUTHOR), Zhou, Yujia1 (AUTHOR), Xiang, Yang1 (AUTHOR), Tao, Cui1 (AUTHOR), Xu, Hua1 (AUTHOR), Zhi, Degui1 (AUTHOR) degui.zhi@uth.tmc.edu
Předmět:	*Data modeling *Electronic health records *Databases *Research *Subject headings *Medical information storage & retrieval systems *Research methodology *Medical subject headings Prediction models Dengue hemorrhagic fever Receiver operating characteristic curves Recurrent neural networks Arbovirus diseases Medical cooperation Evaluation research Comparative studies Research funding
Zdroj:	Journal of the American Medical Informatics Association. Oct2020, Vol. 27 Issue 10, p1593-1599. 7p. 1 Diagram, 4 Charts.
Abstrakt:	Objective: Predictive disease modeling using electronic health record data is a growing field. Although clinical data in their raw form can be used directly for predictive modeling, it is a common practice to map data to standard terminologies to facilitate data aggregation and reuse. There is, however, a lack of systematic investigation of how different representations could affect the performance of predictive models, especially in the context of machine learning and deep learning.Materials and Methods: We projected the input diagnoses data in the Cerner HealthFacts database to Unified Medical Language System (UMLS) and 5 other terminologies, including CCS, CCSR, ICD-9, ICD-10, and PheWAS, and evaluated the prediction performances of these terminologies on 2 different tasks: the risk prediction of heart failure in diabetes patients and the risk prediction of pancreatic cancer. Two popular models were evaluated: logistic regression and a recurrent neural network.Results: For logistic regression, using UMLS delivered the optimal area under the receiver operating characteristics (AUROC) results in both dengue hemorrhagic fever (81.15%) and pancreatic cancer (80.53%) tasks. For recurrent neural network, UMLS worked best for pancreatic cancer prediction (AUROC 82.24%), second only (AUROC 85.55%) to PheWAS (AUROC 85.87%) for dengue hemorrhagic fever prediction.Discussion/conclusion: In our experiments, terminologies with larger vocabularies and finer-grained representations were associated with better prediction performances. In particular, UMLS is consistently 1 of the best-performing ones. We believe that our work may help to inform better designs of predictive models, although further investigation is warranted. [ABSTRACT FROM AUTHOR]
Databáze:	Library, Information Science & Technology Abstracts
Externí odkaz:	Zobrazit plný text záznamu