Dataset Information

Determination of colonoscopy indication from administrative claims data.

ABSTRACT: Colonoscopy outcomes, such as polyp detection or complication rates, may differ by procedure indication.To develop methods to classify colonoscopy indications from administrative data, facilitating study of colonoscopy quality and outcomes.We linked 14,844 colonoscopy reports from the Clinical Outcomes Research Initiative, a national repository of endoscopic reports, to the corresponding Medicare Carrier and Outpatient File claims. Colonoscopy indication was determined from the procedure reports. We developed algorithms using classification and regression trees and linear discriminant analysis (LDA) to classify colonoscopy indication. Predictor variables included ICD-9CM and CPT/HCPCS codes present on the colonoscopy claim or in the 12 months prior, patient demographics, and site of colonoscopy service. Algorithms were developed on a training set of 7515 procedures, then validated using a test set of 7329 procedures.Sensitivity was lowest for identifying average-risk screening colonoscopies, varying between 55% and 86% for the different algorithms, but specificity for this indication was consistently over 95%. Sensitivity for diagnostic colonoscopy varied between 77% and 89%, with specificity between 55% and 87%. Algorithms with classification and regression trees with 7 variables or LDA with 10 variables had similar overall accuracy, and generally lower accuracy than the algorithm using LDA with 30 variables.Algorithms using Medicare claims data have moderate sensitivity and specificity for colonoscopy indication, and will be useful for studying colonoscopy quality in this population. Further validation may be needed before use in alternative populations.

SUBMITTER: Ko CW

PROVIDER: S-EPMC3387505 | biostudies-literature | 2014 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Determination of colonoscopy indication from administrative claims data.

Ko Cynthia W CW Dominitz Jason A JA Neradilek Moni M Polissar Nayak N Green Pam P Kreuter William W Baldwin Laura-Mae LM

Medical care 20140401 4

<h4>Background</h4>Colonoscopy outcomes, such as polyp detection or complication rates, may differ by procedure indication.<h4>Objectives</h4>To develop methods to classify colonoscopy indications from administrative data, facilitating study of colonoscopy quality and outcomes.<h4>Research design</h4>We linked 14,844 colonoscopy reports from the Clinical Outcomes Research Initiative, a national repository of endoscopic reports, to the corresponding Medicare Carrier and Outpatient File claims. Co ...[more]

PMID: 22437619

Similar Datasets

Project description:IntroductionNontraumatic intracranial hemorrhage (ICH) is a neurological emergency of research interest; however, unlike ischemic stroke, has not been well studied in large datasets due to the lack of an established administrative claims-based definition. We aimed to evaluate both explicit diagnosis codes and machine learning methods to create a claims-based definition for this clinical phenotype.MethodsWe examined all patients admitted to our tertiary medical center with a primary or secondary International Classification of Disease version 9 (ICD-9) or 10 (ICD-10) code for ICH in claims from any portion of the hospitalization in 2014-2015. As a gold standard, we defined the nontraumatic ICH phenotype based on manual chart review. We tested explicit definitions based on ICD-9 and ICD-10 that had been previously published in the literature as well as four machine learning classifiers including support vector machine (SVM), logistic regression with LASSO, random forest and xgboost. We report five standard measures of model performance for each approach.ResultsA total of 1830 patients with 2145 unique ICD-10 codes were included in the initial dataset, of which 437 (24%) were true positive based on manual review. The explicit ICD-10 definition performed best (Sensitivity = 0.89 (95% CI 0.85-0.92), Specificity = 0.83 (0.81-0.85), F-score = 0.73 (0.69-0.77)) and improves on an explicit ICD-9 definition (Sensitivity = 0.87 (0.83-0.90), Specificity = 0.77 (0.74-0.79), F-score = 0.67 (0.63-0.71). Among machine learning classifiers, SVM performed best (Sensitivity = 0.78 (0.75-0.82), Specificity = 0.84 (0.81-0.87), AUC = 0.89 (0.87-0.92), F-score = 0.66 (0.62-0.69)).ConclusionsAn explicit ICD-10 definition can be used to accurately identify patients with a nontraumatic ICH phenotype with substantially better performance than ICD-9. An explicit ICD-10 based definition is easier to implement and quantitatively not appreciably improved with the additional application of machine learning classifiers. Future research utilizing large datasets should utilize this definition to address important research gaps.

Project description:BackgroundChildhood cancer relies heavily on inpatient hospital services to deliver tumor-directed therapy and manage toxicities. Hospitalizations have increased over the past decade, though not uniformly across childhood cancer diagnoses. Analysis of the reasons for admission of children with cancer could enhance comparison of resource use between cancers, and allow clinical practice data to be interpreted more readily. Such comparisons using nationwide data sources are difficult because of numerous subdivisions in the International Classification of Diseases Clinical Modification (ICD-9) system and inherent complexities of treatments. This study aimed to develop a systematic approach to classifying cancer-related admissions in administrative data into categories that reflected clinical practice and predicted resource use.MethodsWe developed a multistep algorithm to stratify indications for childhood cancer admissions in the Kids Inpatient Databases from 2003, 2006 and 2009 into clinically meaningful categories. This algorithm assumed that primary discharge diagnoses of cancer or cytopenia were insufficient, and relied on procedure codes and secondary diagnoses in these scenarios. Clinical Classification Software developed by the Healthcare Cost and Utilization Project was first used to sort thousands of ICD-9 codes into 5 mutually exclusive diagnosis categories and 3 mutually exclusive procedure categories, and validation was performed by comparison with the ICD-9 codes in the final admission indication. Mean cost, length of stay, and costs per day were compared between categories of indication for admission.ResultsA cohort of 202,995 cancer-related admissions was grouped into four categories of indication for admission: chemotherapy (N=77,791, 38%), to undergo a procedure (N=30,858, 15%), treatment for infection (N=30,380, 15%), or treatment for other toxicities (N=43,408, 21.4%). The positive predictive value for the algorithm was >95% for each category. Admissions for procedures had higher mean hospital costs, longer hospital stays, and higher costs per day compared with other admission reasons (p<0.001).ConclusionsThis is the first description of a method for grouping indications for childhood cancer admission within an administrative dataset into clinically relevant categories. This algorithm provides a framework for more detailed analyses of pediatric hospitalization data by cancer type.

Dataset Information

Determination of colonoscopy indication from administrative claims data.

Publications

Determination of colonoscopy indication from administrative claims data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets