Feature Engineering and Selection for Rheumatoid Arthritis Disease Activity Classification Using Electronic Medical Records
نویسندگان
چکیده
We study feature engineering and feature selection related to a clinical research application -automatically discovering the patient’s disease activity from the electronic medical records. Different feature representations of clinical documents such as user specified terms, Unified Medical Language System Concept Unique Identifiers, bag of words, and bigram features are compared with filter-based feature selection methods. Performance evaluations are conducted given all feature sets and under varied feature selection conditions on a gold standard set.
منابع مشابه
Automatic Prediction of Rheumatoid Arthritis Disease Activity from the Electronic Medical Records
OBJECTIVE We aimed to mine the data in the Electronic Medical Record to automatically discover patients' Rheumatoid Arthritis disease activity at discrete rheumatology clinic visits. We cast the problem as a document classification task where the feature space includes concepts from the clinical narrative and lab values as stored in the Electronic Medical Record. MATERIALS AND METHODS The Tra...
متن کاملModeling and design of a diagnostic and screening algorithm based on hybrid feature selection-enabled linear support vector machine classification
Background: In the current study, a hybrid feature selection approach involving filter and wrapper methods is applied to some bioscience databases with various records, attributes and classes; hence, this strategy enjoys the advantages of both methods such as fast execution, generality, and accuracy. The purpose is diagnosing of the disease status and estimating of the patient survival. Method...
متن کامل25(OH) vitamin D serum values and rheumatoid arthritis disease activity (DAS28ESR)
Background: The role of vitamin D in the pathogenesis of rheumatoid arthritis is under investigation. This study was designed to evaluate the correlation between serum values of 25(OH) vitamin D [25(OH)D] and disease activity in rheumatoid arthritis (RA) patients according to Disease Activity Score 28 joints and ESR (DAS28ESR). Methods: Ninety-nine patients according to ACR classification crit...
متن کاملToward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources
OBJECTIVE Analysis of narrative (text) data from electronic health records (EHRs) can improve population-scale phenotyping for clinical and genetic research. Currently, selection of text features for phenotyping algorithms is slow and laborious, requiring extensive and iterative involvement by domain experts. This paper introduces a method to develop phenotyping algorithms in an unbiased manner...
متن کاملSerum YKL-40 levels and disease characteristics in patients with rheumatoid arthritis
Background: The present study aimed to evaluate serum YKL-40 levels in patients with rheumatoid arthritis (RA) compared to healthy subjects and to search whether there is an association between YKL-40 levels and disease characteristics in RA. Methods: In this cross-sectional study, 60 RA patients based on the ACR/EULAR 2010 criteria and 30 age- and sex-matched healthy controls were included. I...
متن کامل