What is the clinical evidence from this study?

Study design: Observational. Population: Pneumonia (n=1463). Intervention: Full-stay pneumonia-specific EHR readmission risk-prediction model vs. First-day pneumonia-specific EHR model. Primary outcome: Discrimination (C statistic) for 30-day all-cause readmission (NRI 0.08, p=0.02).

April 1, 2017Open Access

Predicting 30‐Day Pneumonia Readmissions Using Electronic Health Record Data

Key Result

A full-stay pneumonia-specific electronic health record model outperformed a first-day model in predicting 30-day readmissions (C statistic 0.731 vs 0.695).

Study Design

Type

Observational (n=1,463)

Multicenter

Yes

Structured PICO

Does a full-stay pneumonia-specific EHR risk-prediction model improve the prediction of 30-day readmissions compared to first-day or standard models in patients hospitalized for pneumonia?

Population

1,463 adults (≥18 years) hospitalized with a principal discharge diagnosis of pneumonia, sepsis, or respiratory failure (with secondary pneumonia) at 6 diverse hospitals in north Texas between November 2009 and October 2010.

Intervention

Full-stay pneumonia-specific EHR readmission risk-prediction model (incorporating data from the entire hospitalization including disposition status, vital sign instabilities on discharge, and an updated pneumonia severity index).

Comparator

First-day pneumonia-specific EHR model, multi-condition EHR models, CMS pneumonia model, and standard pneumonia severity of illness scores (PSI and CURB-65).

Outcome

All-cause nonelective 30-day readmission to any of 75 acute care hospitals within a 100-mile radius.

An EHR-based risk-prediction model utilizing data from the entire hospitalization significantly improves the accuracy of predicting 30-day readmissions for pneumonia compared to models using only admission data.

Main Result

Effect estimate: NRI 0.08

Absolute Event Rate: 0.731% vs 0.695%

p-value: p=0.02

Limitations

Generalizability to other regions beyond north Texas is unknown
The pneumonia-specific models were not externally validated in a separate cohort
PSI and CURB-65 scores were modified to use diagnostic codes for altered mental status and pleural effusion, and omitted nursing home residence
Unable to include data on medications (antibiotics and steroid use) and outpatient visits
Included only the first pneumonia hospitalization per patient

Abstract

BACKGROUND: Readmissions after hospitalization for pneumonia are common, but the few risk-prediction models have poor to modest predictive ability. Data routinely collected in the electronic health record (EHR) may improve prediction. OBJECTIVE: To develop pneumonia-specific readmission risk-prediction models using EHR data from the first day and from the entire hospital stay ("full stay"). DESIGN: Observational cohort study using stepwise-backward selection and cross-validation. SUBJECTS: Consecutive pneumonia hospitalizations from 6 diverse hospitals in north Texas from 2009-2010. MEASURES: All-cause nonelective 30-day readmissions, ascertained from 75 regional hospitals. RESULTS: Of 1463 patients, 13.6% were readmitted. The first-day pneumonia-specific model included sociodemographic factors, prior hospitalizations, thrombocytosis, and a modified pneumonia severity index; the full-stay model included disposition status, vital sign instabilities on discharge, and an updated pneumonia severity index calculated using values from the day of discharge as additional predictors. The full-stay pneumonia-specific model outperformed the first-day model (C statistic 0.731 vs 0.695; P = 0.02; net reclassification index = 0.08). Compared to a validated multi-condition readmission model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores, the full-stay pneumonia-specific model had better discrimination (C statistic range 0.604-0.681; P < 0.01 for all comparisons), predicted a broader range of risk, and better reclassified individuals by their true risk (net reclassification index range, 0.09-0.18). CONCLUSIONS: EHR data collected from the entire hospitalization can accurately predict readmission risk among patients hospitalized for pneumonia. This approach outperforms a first-day pneumonia-specific model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores. Journal of Hospital Medicine 2017;12:209-216.

Bookmark

View Full Paper