Dataset Information

Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance.

ABSTRACT: To evaluate the phenotyping performance of three major electronic health record (EHR) components: International Classification of Disease (ICD) diagnosis codes, primary notes, and specific medications.We conducted the evaluation using de-identified Vanderbilt EHR data. We preselected ten diseases: atrial fibrillation, Alzheimer's disease, breast cancer, gout, human immunodeficiency virus infection, multiple sclerosis, Parkinson's disease, rheumatoid arthritis, and types 1 and 2 diabetes mellitus. For each disease, patients were classified into seven categories based on the presence of evidence in diagnosis codes, primary notes, and specific medications. Twenty-five patients per disease category (a total number of 175 patients for each disease, 1750 patients for all ten diseases) were randomly selected for manual chart review. Review results were used to estimate the positive predictive value (PPV), sensitivity, andF-score for each EHR component alone and in combination.The PPVs of single components were inconsistent and inadequate for accurately phenotyping (0.06-0.71). Using two or more ICD codes improved the average PPV to 0.84. We observed a more stable and higher accuracy when using at least two components (mean?±?standard deviation: 0.91?±?0.08). Primary notes offered the best sensitivity (0.77). The sensitivity of ICD codes was 0.67. Again, two or more components provided a reasonably high and stable sensitivity (0.59?±?0.16). Overall, the best performance (Fscore: 0.70?±?0.12) was achieved by using two or more components. Although the overall performance of using ICD codes (0.67?±?0.14) was only slightly lower than using two or more components, its PPV (0.71?±?0.13) is substantially worse (0.91?±?0.08).Multiple EHR components provide a more consistent and higher performance than a single one for the selected phenotypes. We suggest considering multiple EHR components for future phenotyping design in order to obtain an ideal result.

SUBMITTER: Wei WQ

PROVIDER: S-EPMC4954637 | biostudies-literature | 2016 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance.

Wei Wei-Qi WQ Teixeira Pedro L PL Mo Huan H Cronin Robert M RM Warner Jeremy L JL Denny Joshua C JC

Journal of the American Medical Informatics Association : JAMIA 20150902 e1

<h4>Objective</h4>To evaluate the phenotyping performance of three major electronic health record (EHR) components: International Classification of Disease (ICD) diagnosis codes, primary notes, and specific medications.<h4>Materials and methods</h4>We conducted the evaluation using de-identified Vanderbilt EHR data. We preselected ten diseases: atrial fibrillation, Alzheimer's disease, breast cancer, gout, human immunodeficiency virus infection, multiple sclerosis, Parkinson's disease, rheumatoi ...[more]

PMID: 26338219

Similar Datasets

Project description:ImportancePatients can develop multiple skin cancers, and their medical data can be spread over multiple health care systems. This fragmented care, combined with the lack of skin cancer registries, has limited our ability both to provide accurate estimates of incidence and to study the pathogenesis of multiple skin cancers.ObjectiveTo assess whether standard diagnostic and procedural codes present in the electronic health records at a single health care system are a valid proxy for estimating the number of overall skin cancers.Design, setting, and participantsRetrospective cohort study of patients seen at a single-center tertiary care hospital (ie, Vanderbilt University Medical Center) between July 1, 2008, and June 30, 2018. All patients with at least 1 electronic health record-based diagnostic or procedural code for any skin cancer and at least 1 pathology report of a skin cancer.ExposureThe number of International Classification of Disease (ICD) or Current Procedural Terminology (CPT) codes relating to skin cancer.Main outcomes and measuresPearson correlation coefficient and R2 were calculated for the total number of ICD or CPT codes for skin cancer and histologically verified skin cancers.ResultsIn this cohort study of 35 901 patients, the mean (SD) age was 70.4 (14.4) years, 20 404 (56.8%) were men, and 31 623 (88.1%) were White individuals. Of these patients, 6307 had at least 1 ICD or CPT code or pathology report for a skin cancer, of whom 5688 patients had both a CPT code related to skin malignancy and a histologically verified skin cancer. There was a strong linear correlation between the number of CPT codes and pathology records (r = 0.87). There was a poor correlation between the number of ICD codes and pathology records (r = 0.22).Conclusions and relevanceThis cohort study found that the use of ICD codes was a poor proxy measure for the number of skin cancers per patient. In contrast, CPT codes accounted for more than 75% of the variability in the number of skin cancers (R2 = 0.76) and were a better proxy measure for the total number of skin cancers per patient.

Project description:BackgroundA cancer diagnosis is a source of psychological and emotional stress, which are often maintained for sustained periods of time that may lead to depressive disorders. Depression is one of the most common psychological conditions in patients with cancer. According to the Global Cancer Observatory, breast and colorectal cancers are the most prevalent cancers in both sexes and across all age groups in Spain.ObjectiveThis study aimed to compare the prevalence of depression in patients before and after the diagnosis of breast or colorectal cancer, as well as to assess the usefulness of the analysis of free-text clinical notes in 2 languages (Spanish or Catalan) for detecting depression in combination with encoded diagnoses.MethodsWe carried out an analysis of the electronic health records from a general hospital by considering the different sources of clinical information related to depression in patients with breast and colorectal cancer. This analysis included ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification) diagnosis codes and unstructured information extracted by mining free-text clinical notes via natural language processing tools based on Systematized Nomenclature of Medicine Clinical Terms that mentions symptoms and drugs used for the treatment of depression.ResultsWe observed that the percentage of patients diagnosed with depressive disorders significantly increased after cancer diagnosis in the 2 types of cancer considered-breast and colorectal cancers. We managed to identify a higher number of patients with depression by mining free-text clinical notes than the group selected exclusively on ICD-9-CM codes, increasing the number of patients diagnosed with depression by 34.8% (441/1269). In addition, the number of patients with depression who received chemotherapy was higher than those who did not receive this treatment, with significant differences (P<.001).ConclusionsThis study provides new clinical evidence of the depression-cancer comorbidity and supports the use of natural language processing for extracting and analyzing free-text clinical notes from electronic health records, contributing to the identification of additional clinical data that complements those provided by coded data to improve the management of these patients.

Project description:BACKGROUND:Administrative health records (AHRs) and electronic medical records (EMRs) are two key sources of population-based data for disease surveillance, but misclassification errors in the data can bias disease estimates. Methods that combine information from error-prone data sources can build on the strengths of AHRs and EMRs. We compared bias and error for four data-combining methods and applied them to estimate hypertension prevalence. METHODS:Our study included rule-based OR and AND methods that identify disease cases from either or both data sources, respectively, rule-based sensitivity-specificity adjusted (RSSA) method that corrects for inaccuracies using a deterministic rule, and probabilistic-based sensitivity-specificity adjusted (PSSA) method that corrects for error using a statistical model. Computer simulation was used to estimate relative bias (RB) and mean square error (MSE) under varying conditions of population disease prevalence, correlation amongst data sources, and amount of misclassification error. AHRs and EMRs for Manitoba, Canada were used to estimate hypertension prevalence using validated case definitions and multiple disease markers. RESULTS:The OR method had the lowest RB and MSE when population disease prevalence was 10%, and the RSSA method had the lowest RB and MSE when population prevalence increased to 20%. As the correlation between data sources increased, the OR method resulted in the lowest RB and MSE. Estimates of hypertension prevalence for AHRs and EMRs alone were 30.9% (95% CI: 30.6-31.2) and 24.9% (95% CI: 24.6-25.2), respectively. The estimates were 21.4% (95% CI: 21.1-21.7), for the AND method, 34.4% (95% CI: 34.1-34.8) for the OR method, 32.2% (95% CI: 31.8-32.6) for the RSSA method, and ranged from 34.3% (95% CI: 34.1-34.5) to 35.9% (95% CI, 35.7-36.1) for the PSSA method, depending on the statistical model. CONCLUSIONS:The OR and AND methods are influenced by correlation amongst the data sources, while the RSSA method is dependent on the accuracy of prior sensitivity and specificity estimates. The PSSA method performed well when population prevalence was high and average correlations amongst disease markers was low. This study will guide researchers to select a data-combining method that best suits their data characteristics.

Dataset Information

Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance.

Publications

Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets