aceTRV-2026-0957Version 1 · Certified
Reason for this version
Certified into the record
Canonical text (the exact bytes fingerprinted)
TRUVACE RECORD VERSION record: TRV-2026-0957 version: 1 kind: certified reason: Certified into the record timestamp: 2026-09-01T06:06:48.407499Z status: published lens: trace sector: health headline: An informatics framework to harmonize electronic health record medication data for managed care analytics and artificial intelligence applications dek: Background Artificial intelligence (AI) applications in managed care pharmacy depend on semantically consistent medication data, yet heterogeneous medication identifiers across real-world electronic health records (EHRs) could undermine analytic fidelity and risk propagating classification errors. To enable transportable, reproducible AI tools, methods for harmonizing disparate medication identifiers (eg, National Drug Code [NDC] and Multum drug synonym ID) to standardized vocabularies are required. Objective To… gain_title: A two-layered RxCUI ingredient and ATC framework harmonized 214,080 discharge medication records from older adults into standardized representations, achieving 100% initial mapping via deterministic crosswalks to support transportable managed care AI tools. problem_title: Heterogeneous NDC, Multum, and RxCUI identifiers in real-world EHRs undermined semantic consistency, with over half of records needing string reconciliation and up to 57.4% requiring correction due to branded formulation omissions and indication- or route-based ATC ambiguities. trace_subject: harmonizing heterogeneous EHR medication identifiers into standardized RxCUI ingredient and ATC representations to enable managed care AI analytics gain_reading: A two-layered RxCUI ingredient and ATC framework harmonized 214,080 discharge medication records from older adults into standardized representations, achieving 100% initial mapping via deterministic crosswalks to support transportable managed care AI tools. gain_evidence: Mapping using deterministic crosswalks achieved a 100% initial mapping rate | transform raw EHR medication records into standardized representations at the ingredient and pharmacological levels problem_reading: Heterogeneous NDC, Multum, and RxCUI identifiers in real-world EHRs undermined semantic consistency, with over half of records needing string reconciliation and up to 57.4% requiring correction due to branded formulation omissions and indication- or route-based ATC ambiguities. problem_evidence: heterogeneous medication identifiers across real-world electronic health records (EHRs) could undermine analytic fidelity and risk propagating classification errors | 30% to 35% of unique records requiring ATC assignment corrections quick_read: Researchers developed and tested an informatics framework to convert heterogeneous discharge medication identifiers from EHRs of adults 65 and older at Buffalo General Medical Center between 2020 and 2024 into standardized RxCUI ingredient and ATC class codes. Of 214,080 records, 53% were nonstandardized Multum IDs requiring string-based reconciliation, and the team measured mapping success and correction needs after deterministic crosswalks and expert validation. Standardized medication semantics are presented as a prerequisite for transparent, transportable AI tools in managed care pharmacy, where inconsistent identifiers could propagate classification errors. The results show full initial mapping is achievable but depends on extensive correction for branded formulations and indication- or route-based ambiguities like moxifloxacin mapping to J01MA14 or S01AE07, leaving open how the framework performs beyond a single center and older adult population. limitation: Framework evaluated only in adults 65+ at a single tertiary center and required substantial manual correction due to crosswalk omissions, lexical misclassifications, and taxonomic ambiguities requiring clinical context. tag: Dual reading key_points: Retrospective analysis of 214,080 discharge records from adults 65+ hospitalized 2020-2024 at Buffalo General Medical Center. | 53.0% of records were Multum Drug Synonym IDs requiring string-based reconciliation to RxCUI and ATC. | Deterministic crosswalks from RxNorm Full Monthly Release plus TriNetX reference achieved 100% initial mapping, but 30% to 35% needed ATC corrections. | String-based alignment achieved 78.5% and 75.5% initial match rates for RxCUI [IN] and ATC, with 57.4% requiring correction after pharmacy expert validation. rundown: The study used a 2-layered architecture anchored to RxCUI ingredient concepts and abstracted to ATC classification, with deterministic crosswalks derived from RxNorm Full Monthly Release complemented by a validated TriNetX reference file. Unmapped records underwent structured string-based reconciliation aligning medication name strings between raw records and reference terminologies, followed by manual validation by a pharmacy expert of both reconciliation and RxCUI-to-ATC mapping. sources: - peer_reviewed | Journal of Managed Care & Specialty Pharmacy | https://doi.org/10.18553/jmcp.2026.32.9.1052 | 2026-09-01 prev: 0000000000000000000000000000000000000000000000000000000000000000
- sha256
- f6a38bcf0b7a66ed748b1ecdb5d1fbd9181ba4a4f6c31a543a3a69dbed09d89b
- previous
- 0000000000000000000000000000000000000000000000000000000000000000
Verify this record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-0957 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.