Risk Prediction Models for Hospital Readmission: A Systematic Review

By D. Kansagara, Honora Englander, A. Salanitro, D. Kagen, C. Theobald, M. Freeman, S. Kripalani. Journal of the American Medical Association (JAMA), 2011

1,792 citations recorded by the source corpus.

Context Predicting hospital readmission risk is of great interest to identify which patients would benefit most from care transition interventions, as well as to risk-standardize readmission rates for purposes of hospital comparison. Objective To summarize validated readmission risk prediction models, describe their performance, and assess suitability for clinical or administrative use. Data Sources MEDLINE, CINAHL, and Cochrane Library through March 2011, EMBASE through August 2011, and hand search of reference lists. Study Selection Dual review to identify English language studies of prediction models tested with medical patients, with both derivation and validation cohorts. Data Extraction Data were extracted on the population, setting, sample size, follow-up interval, readmission rate, model discrimination and calibration, type of data used, and timing of data collection. Results Of 7,843 citations reviewed, 30 studies of 26 unique models met criteria. The most common outcome used was 30-day readmission; only one model specifically addressed preventable readmissions. Fourteen models relying on retrospective administrative data could be potentially used for standardization of readmission risk and hospital comparisons; of these, nine were tested in large US populations and had poor discriminative ability (c-statistics 0.55 – 0.65). Seven models could potentially be used to identify high-risk patients for intervention early during a hospitalization (c-statistics 0.56 – 0.72), and five could be used at hospital discharge (c-statistics 0.68 – 0.83). Six studies compared different models in the same population and two of these found that functional and social variables improved model discrimination. Though most models incorporated medical comorbidity and prior utilization variables, few examined variables associated with overall health and function, illness severity, or social determinants of health. Conclusions Most current readmission risk prediction models, whether designed for comparative or clinical purposes, perform poorly. Though in certain settings such models may prove useful, efforts to improve their performance are needed as use becomes more widespread.

Subfields: Cardiology and Cardiovascular Medicine, Emergency Medicine, Epidemiology

View Paper: https://www.semanticscholar.org/paper/cf6e1126bcc8e100d8adc7114967bcdfb8ae28ae

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Emergency Medicine

In Epidemiology

Citations in the corpus

Limestone: High-throughput candidate phenotype generation via tensor factorization (2014, background): “Unfortunately, EHR data do not always directly and reliably map to medical concepts that clinical researchers need or use.”
Scalable and accurate deep learning with electronic health records (2018, background): “The primary endpoints for those predictions were at discharge, when most readmission prediction scores are computed and when all information necessary to assign billing diagnoses is available [28].”
PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies (2019, background): “Prediction models, both diagnostic and prognostic, are widely used for a variety of medical domains and settings,(14-16) evidenced by the large number of models developed, especially in cancer,(17, 18) neurology,(19, 20) and cardiovascular disease domains.”
Enhancing Recovery From Sepsis (2018, neutral): “However, it is important to recognize and treat mental health impairments because they are associated with a more complicated clinical course.(52,53)”
Neighborhood Socioeconomic Disadvantage and 30 Day Rehospitalizations: An Analysis of Medicare Data (2014, background): “However, the targeting of these programs has proven challenging, potentially because important factors contributing to rehospitalizations, such as socioeconomic disadvantage, are not well-measured (4, 5).”
FAM-FACE-SG: a score for risk stratification of frequent hospital admitters (2017, methodology): “Currently, based on Kansagara’s review [1] and more recent Zhou’s review [17], around ten published predictive models utilized real-time administrative data.”
Understanding Black-box Predictions via Influence Functions (2017, background): “Domain mismatches are common in biomedical data, e.g., different hospitals serve different populations, and models trained on one population can do poorly on another (Kansagara et al., 2011).”