Dataset Information

Mining high-dimensional administrative claims data to predict early hospital readmissions.

ABSTRACT:

Background

Current readmission models use administrative data supplemented with clinical information. However, the majority of these result in poor predictive performance (area under the curve (AUC)<0.70).

Objective

To develop an administrative claim-based algorithm to predict 30-day readmission using standardized billing codes and basic admission characteristics available before discharge.

Materials and methods

The algorithm works by exploiting high-dimensional information in administrative claims data and automatically selecting empirical risk factors. We applied the algorithm to index admissions in two types of hospitalized patient: (1) medical patients and (2) patients with chronic pancreatitis (CP). We trained the models on 26,091 medical admissions and 3218 CP admissions from The Johns Hopkins Hospital (a tertiary research medical center) and tested them on 16,194 medical admissions and 706 CP admissions from Johns Hopkins Bayview Medical Center (a hospital that serves a more general patient population), and vice versa. Performance metrics included AUC, sensitivity, specificity, positive predictive values, negative predictive values, and F-measure.

Results

From a pool of up to 5665 International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) diagnoses, 599 ICD-9-CM procedures, and 1815 Current Procedural Terminology codes observed, the algorithm learned a model consisting of 18 attributes from the medical patient cohort and five attributes from the CP cohort. Within-site and across-site validations had an AUC?0.75 for the medical patient cohort and an AUC?0.65 for the CP cohort.

Conclusions

We have created an algorithm that is widely applicable to various patient cohorts and portable across institutions. The algorithm performed similarly to state-of-the-art readmission models that require clinical data.

SUBMITTER: He D

PROVIDER: S-EPMC3932470 | biostudies-literature | 2014 Mar-Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Mining high-dimensional administrative claims data to predict early hospital readmissions.

He Danning D Mathews Simon C SC Kalloo Anthony N AN Hutfless Susan S

Journal of the American Medical Informatics Association : JAMIA 20130927 2

<h4>Background</h4>Current readmission models use administrative data supplemented with clinical information. However, the majority of these result in poor predictive performance (area under the curve (AUC)<0.70).<h4>Objective</h4>To develop an administrative claim-based algorithm to predict 30-day readmission using standardized billing codes and basic admission characteristics available before discharge.<h4>Materials and methods</h4>The algorithm works by exploiting high-dimensional information ...[more]

PMID: 24076748

Similar Datasets

Project description:IntroductionData are lacking on severe asthma burden in elderly people in Japan. We assessed the prevalence and clinical/economic burden of severe asthma and asthma-related hospitalizations in elderly and younger Japanese patients.MethodsThis retrospective study analyzed outpatient claims data and inpatient hospital discharge records among patients aged ≥ 15 years with asthma (defined as ≥ 2 prescriptions of inhaled corticosteroids [ICS] or ICS/long-acting beta-agonists [LABA]) between 1 July 2014 and 30 June 2017. We analyzed the outpatient visit assessment population with severe asthma (≥ 240-day prescription of high-dose ICS and ≥ 90-day prescription of ≥ 1 additional controllers) and the asthma-related hospitalization population (≥ 1 hospital admission[S] with a primary diagnosis of asthma/status asthmaticus and use of systemic corticosteroids) over a 1-year observation period before the date of each patient's latest asthma prescription or asthma-related hospitalization within the study period. The primary outcome was the proportion of elderly (≥ 65 years) and younger (15-39 and 40-64 years) patients among the outpatient visit assessment population. Secondary outcomes included outpatient and inpatient characteristics, asthma-related healthcare resource utilization, and asthma-associated costs, by age group.ResultsOf the outpatient visit assessment population (n = 35,742), 4211 had severe asthma, with the prevalence of 8.2%, 12.8%, and 12.4% for the 15-39, 40-64, and ≥ 65 years age groups, respectively. Elderly versus younger outpatients with severe asthma had higher cumulative oral corticosteroid doses. Among both outpatient visit assessment population and hospitalization assessment population, elderly versus younger outpatients with severe asthma or asthma-related hospitalizations had more comorbidities, required more biological, hematological, immunological, and microbiological tests, and incurred higher asthma-associated costs.ConclusionsIn addition to reaffirming the higher prevalence of severe asthma in Japanese patients ≥ 40 years versus those < 40 years of age, our results demonstrated higher clinical and economic burden in elderly versus younger patients.

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.

Dataset Information

Mining high-dimensional administrative claims data to predict early hospital readmissions.

Background

Objective

Materials and methods

Results

Conclusions

Publications

Mining high-dimensional administrative claims data to predict early hospital readmissions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets