Automated Mapping of Real-world Oncology Laboratory Data to LOINC.

In this study we seek to determine the efficacy of using automated mapping methods to reduce the manual mapping burden of laboratory data to LOINC(r) on a nationwide electronic health record derived oncology specific dataset. We developed novel encoding methodologies to vectorize free text lab data, and evaluated logistic regression, random forest, and knn machine learning classifiers. All machine learning models did significantly better than deterministic baseline algorithms. The best classifiers were random forest and were able to predict the correct LOINC code 94.5% of the time. Ensemble classifiers further increased accuracy, with the best ensemble classifier predicting the same code 80.5% of the time with an accuracy of 99%. We conclude that by using an automated laboratory mapping model we can both reduce manual mapping time, and increase quality of mappings, suggesting automated mapping is a viable tool in a real-world oncology dataset.

Exchange of computable patient data between the Department of Veterans Affairs (VA) and the Department of Defense (DoD): terminology mediation strategy.

Complete patient health information that is available where and when it is needed is essential to providers and patients and improves healthcare quality and patient safety. VA and DoD have built on their previous experience in patient data exchange to establish data standards and terminology services to enable real-time bi-directional computable (i.e., encoded) data exchange and achieve semantic interoperability in compliance with recommended national standards and the eGov initiative. The project uses RxNorm, UMLS, and SNOMED CT terminology standards to mediate codified pharmacy and allergy data with greater than 92 and 60 percent success rates respectively. Implementation of the project has been well received by users and is being expanded to multiple joint care sites. Stable and mature standards, mediation strategies, and a close relationship between healthcare institutions and Standards Development Organizations are recommended to achieve and maintain semantic interoperability in a clinical setting.

Use of RxNorm to exchange codified drug allergy information between Department of Veterans Affairs (VA) and Department of Defense (DoD).

Under a congressional mandate, VA and DoD have built a framework to exchange standardized, codified patient drug allergy information through a mediation terminology. Initially, the Unified Medical Language System (UMLS) was deemed to be the most appropriate translator. After both agency files were mapped to UMLS, DoD could understand 45 percent of VA's mapped terms and VA could understand 26 percent of DoD's mapped terms. A significant portion of the non-mediated information was brand names in DoD with generic counterparts in VA. Recently, a Consolidated Health Informatics (CHI) group designated RxNorm as the standard for trade name allergies. An analysis was conducted to estimate mediation improvement using RxNorm. Both agency files were re-mapped to RxNorm. By utilizing the RxNorm defined relationships between brand names and generics and between variants of therapeutic moieties , DoD will understand 74 percent of VA terms and VA will understand 58 percent of DoD terms.

Implementation of RxNorm as a terminology mediation standard for exchanging pharmacy medication between federal agencies.

The federal government is working toward its goal of achieving interoperability between health information systems through several multi-agency efforts. While some interoperability partnerships exist between federal agencies, only a few systems are involved and these projects have proven difficult to implement. This paper describes the process of implementing an interoperable standard for exchanging computable pharmacy data between the Department of Defense (DoD) and the Department of Veterans Affairs (VA).

A simple strategy for implementing standard reference terminologies in a distributed healthcare delivery system with minimal impact to existing applications.

The Veterans Administration (VA) has adopted an ambitious program to standardize its clinical terminology to comply with industry-wide standards. The VA is using commercially available tools and in-house software to create a high-quality reference terminology system. The terminology will be used by current and future applications with no planned disruption to operational systems. The first large customer of the group is the national VA Health Data Repository (HDR). Unique enterprise identifiers are assigned to each standard term, and a rich network of semantic relationships makes the resulting data not only recognizable, but highly computable and reusable in a variety of applications, including decision support and data sharing with partners such as the Department of Defense (DoD). This paper describes the specific methods and approaches that the VA has employed to develop and implement this innovative program in existing information system. The goal is to share with others our experience with key issues that face our industry as we move toward an electronic health record for every individual.

HIV terms coverage by a commercial nomenclature.

A formal comparison of physician notes on HIV patients with MEDCIN was carried out. Terms from patient charts were divided into five groups: History, Physical Examination, Symptoms, Diagnosis and Doctor's Orders. Four types of matches were determined: Exact, Lexical, Semantic and No-Match. Across the five groups, exact matches ranged from 12 to 44 percent, lexical matches from 2 to 11 percent, semantic matches from 9 to 21 percent, and no-matches from 29 to 74 percent.