Hospital readmission risk prediction based on claims data available at admission: a pilot study in Switzerland

Predicting Hospital Readmissions in a Commercially Insured Population over Varying Time Horizons

BACKGROUND

Reducing hospital readmissions is a federal policy priority, and predictive models of hospital readmissions have proliferated in recent years; however, most such models tend to focus on the 30-day readmission time horizon and do not consider readmission over shorter (or longer) windows.

OBJECTIVES

To evaluate the performance of a predictive model of hospital readmissions over three different readmission timeframes in a commercially insured population.

DESIGN

Retrospective multivariate logistic regression with an 80/20 train/test split.

PARTICIPANTS

A total of 2,213,832 commercially insured inpatient admissions from 2016 to 2017 comprising 782,768 unique patients from the Health Care Cost Institute.

MAIN MEASURES

Outcomes are readmission within 14 days, 15-30 days, and 31-60 days from discharge. Predictor variables span six different domains: index admission, condition history, demographic, utilization history, pharmacy, and environmental controls.

KEY RESULTS

Our model generates C-statistics for holdout samples ranging from 0.618 to 0.915. The model's discriminative power declines with readmission time horizon: discrimination for readmission predictions within 14 days following discharge is higher than for readmissions 15-30 days following discharge, which in turn is higher than predictions 31-60 days following discharge. Additionally, the model's predictive power increases nonlinearly with the inclusion of successive risk factor domains: patient-level measures of utilization and condition history add substantially to the discriminative power of the model, while demographic information, pharmacy utilization, and environmental risk factors add relatively little.

CONCLUSION

It is more difficult to predict distant readmissions than proximal readmissions, and the more information the model uses, the better the predictions. Inclusion of utilization-based risk factors add substantially to the discriminative ability of the model, much more than any other included risk factor domain. Our best-performing models perform well relative to other published readmission prediction models. It is possible that these predictions could have operational utility in targeting readmission prevention interventions among high-risk individuals.

Established and Novel Risk Factors for 30-Day Readmission Following Total Knee Arthroplasty: A Modified Delphi and Focus Group Study to Identify Clinically Important Predictors

Thirty-day readmission following total knee arthroplasty (TKA) is an important outcome influencing the quality of patient care and health system efficiency. The aims of this study were (1) to ascertain the clinical importance of established risk factors for 30-day readmission risk and give clinicians the opportunity to suggest and discuss novel risk factors and (2) to evaluate consensus on the importance of these risk factors. This study was conducted in two stages: a modified Delphi survey followed by a focus group. Orthopaedic surgeons and anaesthetists involved in the care of TKA patients completed an anonymous survey to judge the clinical importance of risk factors selected from a systematic review and meta-analysis and to suggest other clinically meaningful risk factors, which were then discussed in a focus group designed using elements of nominal group technique. Eleven risk factors received a majority (≥50%) vote of high importance in the Delphi survey overall, and six risk factors received a majority vote of high importance in the focus group overall. Lack of consensus highlighted the fact that this is a highly complex problem which is challenging to predict and which depends heavily on risk factors which may be open to interpretation, difficult to capture, and dependent upon personal clinical experience, which must be tailored to the individual patient.

Man vs. Machine: Comparing Physician vs. Electronic Health Record-Based Model Predictions for 30-Day Hospital Readmissions

BACKGROUND

Electronic health record (EHR)-based readmission risk prediction models can be automated in real-time but have modest discrimination and may be missing important readmission risk factors. Clinician predictions of readmissions may incorporate information unavailable in the EHR, but the comparative usefulness is unknown. We sought to compare clinicians versus a validated EHR-based prediction model in predicting 30-day hospital readmissions.

METHODS

We conducted a prospective survey of internal medicine clinicians in an urban safety-net hospital. Clinicians prospectively predicted patients' 30-day readmission risk on 5-point Likert scales, subsequently dichotomized into low- vs. high-risk. We compared human with machine predictions using discrimination, net reclassification, and diagnostic test characteristics. Observed readmissions were ascertained from a regional hospitalization database. We also developed and assessed a "human-plus-machine" logistic regression model incorporating both human and machine predictions.

RESULTS

We included 1183 hospitalizations from 106 clinicians, with a readmission rate of 20.8%. Both clinicians and the EHR model had similar discrimination (C-statistic 0.66 vs. 0.66, p = 0.91). Clinicians had higher specificity (79.0% vs. 48.9%, p < 0.001) but lower sensitivity (43.9 vs. 75.2%, p < 0.001) than EHR model predictions. Compared with machine, human was better at reclassifying non-readmissions (non-event NRI + 30.1%) but worse at reclassifying readmissions (event NRI - 31.3%). A human-plus-machine approach best optimized discrimination (C-statistic 0.70, 95% CI 0.67-0.74), sensitivity (65.5%), and specificity (66.7%).

CONCLUSION

Clinicians had similar discrimination but higher specificity and lower sensitivity than EHR model predictions. Human-plus-machine was better than either alone. Readmission risk prediction strategies should incorporate clinician assessments to optimize the accuracy of readmission predictions.

A comparison of general and disease-specific machine learning models for the prediction of unplanned hospital readmissions

Unplanned hospital readmissions are a burden to patients and increase healthcare costs. A wide variety of machine learning (ML) models have been suggested to predict unplanned hospital readmissions. These ML models were often specifically trained on patient populations with certain diseases. However, it is unclear whether these specialized ML models-trained on patient subpopulations with certain diseases or defined by other clinical characteristics-are more accurate than a general ML model trained on an unrestricted hospital cohort. In this study based on an electronic health record cohort of consecutive inpatient cases of a single tertiary care center, we demonstrate that accurate prediction of hospital readmissions may be obtained by general, disease-independent, ML models. This general approach may substantially decrease the cost of development and deployment of respective ML models in daily clinical routine, as all predictions are obtained by the use of a single model.

Current Trends in Readmission Prediction: An Overview of Approaches

Hospital readmission shortly after discharge threatens the quality of patient care and leads to increased medical care costs. In the United States, hospitals with high readmission rates are subject to federal financial penalties. This concern calls for incentives for healthcare facilities to reduce their readmission rates by predicting patients who are at high risk of readmission. Conventional practices involve the use of rule-based assessment scores and traditional statistical methods, such as logistic regression, in developing risk prediction models. The recent advancements in machine learning driven by improved computing power and sophisticated algorithms have the potential to produce highly accurate predictions. However, the value of such models could be overrated. Meanwhile, the use of other flexible models that leverage simple algorithms offer great transparency in terms of feature interpretation, which is beneficial in clinical settings. This work presents an overview of the current trends in risk prediction models developed in the field of readmission. The various techniques adopted by researchers in recent years are described, and the topic of whether complex models outperform simple ones in readmission risk stratification is investigated.

Validating a methodology to measure frailty syndromes at hospital level utilising administrative data

BACKGROUND

Identifying older people with clinical frailty, reliably and at scale, is a research priority. We measured frailty in older people using a novel methodology coding frailty syndromes on routinely collected administrative data, developed on a national English secondary care population, and explored its performance of predicting inpatient mortality and long length of stay at a single acute hospital.

METHODOLOGY

We included patient spells from Secondary User Service (SUS) data for those ≥65 years with attendance to the emergency department or admission to West Middlesex University Hospital between 01 July 2016 to 01 July 2017. We created eight groups of frailty syndromes using diagnostic coding groups. We used descriptive statistics and logistic regression to explore performance of diagnostic coding groups for the above outcomes.

RESULTS

We included 17,199 patient episodes in the analysis. There was at least one frailty syndrome present in 7,004 (40.7%) patient episodes. The resultant model had moderate discrimination for inpatient mortality (area under the receiver operating characteristic curve (AUC) 0.74; 95% confidence interval (CI) 0.72-0.76) and upper quartile length of stay (AUC 0.731; 95% CI 0.722-0.741). There was good negative predictive value for inpatient mortality (98.1%).

CONCLUSIONS

Coded frailty syndromes significantly predict outcomes. Model diagnostics suggest the model could be used for screening of elderly patients to optimise their care.