The normalization performed by the StandardAnalyzer is quite simple. An additional coder dissected at least one randomly selected item from each instrument. Efficiently moving and aggregating patient data creates an important foundation for many tools and processes with the capability of improving healthcare delivery. An advantage of our data-driven approach is that it did not require any domain-specific tailoring. Abstract Objective To determine whether the knowledge contained in a rich corpus of local terms mapped to LOINC Logical Observation Identifiers Names and Codes could be leveraged to help map local terms from other institutions. If human review of the ranked list reveals that a matching LOINC code is not present, the reviewer can default back to the typical term-specific search using interactive functions of RELMA.
|Date Added:||18 December 2012|
|File Size:||57.45 Mb|
|Operating Systems:||Windows NT/2000/XP/2003/2003/7/8/10 MacOS 10/X|
|Price:||Free* [*Free Regsitration Required]|
This evaluation was an initial step toward the representation of standardized assessment items in a manner that facilitates data sharing and re-use. Published online May Such a cut-off score is valuable in separating local terms that can be mapped with little or no human review from those that need more extensive review. A case report of an outpatient EHR”. Results of Maxent, Lucene and Lab Auto Mapper using laboratory terms from three test institutions The first test institution contained local laboratory terms mapped to unique LOINC codes and has total words and unique words.
A dot that is not followed by whitespace is considered part of a token. If LOINC codes are used in clinical messages, each system participating in data exchange needs to match its local vocabulary to the standard vocabulary only once.
A corpus-based approach for automated LOINC mapping
Rationale for using Maxent and Lucene models Given a rich corpus of existing mappings loknc by domain experts, we wanted to explore the validity and performance of a purely data-driven approach to automated LOINC mapping.
Percentage of local laboratory terms from each test institution that when applied against Maxent, Lucene and Lab Auto Mapper had the correct LOINC code ranked highest top 1 and among the highest five top 5.
For all analyses, these existing LOINC mappings from the operational health information exchange served as our gold standard. Methods We developed re,ma models to test our hypothesis. Splitting the corpus at the term level rather than at the level of a whole set of terms from an institution demonstrates the prediction of the models for a heterogeneous set of terms with varying naming conventions. From Wikipedia, the free encyclopedia.
Maxent and Lucene scores for each LOINC from the corpus in table 1 when local term descriptions are queried against both models. To create a Maxent model each local term in the training set was considered as a separate event with its normalized description used as predicates and the mapped LOINC code used as outcome.
Open in a separate window.
LOINC Essentials – Daniel Vreeman
Missing clinical information during primary care visits. Each document then contained the normalized description from all local terms mapped to that LOINC code as its indexed field. Each training set contained terms in increments. As illustrated lionc figure 3this plot shows that when the score was above 0.
Our choice of creating 12 training sets loinv with additional terms was arbitrary, but illustrates how the models perform as the corpus grows when new terms are added. Considerations for practical application Expert review is a high cost resource in mapping.
The goal of the study was to create universal names and codes for clinical observations that could be used by all clinical information systems. Information filtering and information retrieval: McGraw-Hill, [ Google Scholar ].
A unique code format: Each institution code set re,ma the set of tests performed by typical community hospital laboratory, and reflects the idiosyncratic naming conventions established by that institution. Health information technology has the potential to improve the quality and efficiency of care. Manning Publications, [ Google Scholar ].
Methods Establishing the gold standard and normalizing the corpus We compiled a corpus of all local terms from different institutional code sets that were mapped to LOINC through the INPC common dictionary between and Although the core software tools we used in this study Maxent and Lucene are available at no cost under open-source licenses, the corpus of local term descriptions mapped to LOINC from the INPC is not available publicly.