BGLM: big data-guided LOINC mapping with multi-language support. Issue 4 (25th November 2022)

• Record Type: Journal Article
• Authors: Liu, Ke; Witteveen-Lane, Martin; Glicksberg, Benjamin S; Kulkarni, Omkar; Shankar, Rama; Chekalin, Evgeny; Paithankar, Shreya; Yang, Jeanne; Chesla, Dave; Chen, Bin
• Is Part Of: JAMIA open. Volume 5:Issue 4(2022)
• Publication Date: 2022-11-25
• Subjects: big data -- LOINC code mapping -- electronic health records -- multi-language support; Medical informatics -- Periodicals; 610.285
• DOI: 10.1093/jamiaopen/ooac099
• Languages: English
• ISSNs: 2574-2531

Abstract

Abstract: Motivation: Mapping internal, locally used lab test codes to standardized logical observation identifiers names and codes (LOINC) terminology has become an essential step in harmonizing electronic health record (EHR) data across different institutions. However, most existing LOINC code mappers are based on text-mining technology and do not provide robust multi-language support. Materials and methods: We introduce a simple, yet effective tool called big data-guided LOINC code mapper (BGLM), which leverages the large amount of patient data stored in EHR systems to perform LOINC coding mapping. Distinguishing from existing methods, BGLM conducts mapping based on distributional similarity. Results: We validated the performance of BGLM with real-world datasets and showed that high mapping precision could be achieved under proper false discovery rate control. In addition, we showed that the mapping results of BGLM could be used to boost the performance of Regenstrief LOINC Mapping Assistant (RELMA), one of the most widely used LOINC code mappers. Conclusions: BGLM paves a new way for LOINC code mapping and therefore could be applied to EHR systems without the restriction of languages. BGLM is freely available at https://github.com/Bin-Chen-Lab/BGLM . Lay Summary: Mapping internal, locally used lab test codes to standardized logical observation identifiers names and codes (LOINC) terminology has become an essential step in harmonizing Electronic Health Record (EHR) data across different institutions. In this study, we propose a novel tool called big-data guided LOINC code mapper (BGLM) for automatic LOINC code mapping. We validated the performance of BGLM with real-world EHR datasets and showed that high mapping precision could be achieved under proper false discovery rate control. In addition, we showed that the mapping results of BGLM could be used to boost the performance of Regenstrief LOINC Mapping Assistant (RELMA), one of the most widely used LOINC code mappers. Compared with existing methods, there are two significant advantages of BGLM. First, BGLM provides robust multi-language support; second, the performance of BGLM could be further improved with more EHR data integrated. BGLM has the potential to become a useful tool in large-scale EHR data harmonization procedures and would be of immense interest to both the scientific and clinical community.