Validation of EPIC's Readmission Risk Model, the LACE+ Index and SQLape as Predictors of Unplanned Hospital Readmissions

Completed

• Conditions: Hospital Readmission
• Interventions: Other: An US Readmission Risk Prediction Model; Other: LACE+ score; Other: SQLAPE model

• Registration Number: NCT04306172
• Lead Sponsor: Luzerner Kantonsspital

Brief Summary

The primary objective of this study is to externally validate the EPIC's Readmission Risk model and to compare it with the LACE+ index and the SQLape Readmission model.

As secondary objective, the EPIC's Readmission Risk model will be adjusted based on the validation sample, and finally, it´s performance will be compared with machine learning algorithms.

Detailed Description

Introduction: Readmissions after an acute care hospitalization are relatively common, costly to the health care system and are associated with significant burden for patients. As one way to reduce costs and simultaneously improve quality of care, hospital readmissions receive increasing interest from policy makers. It is only relatively recently that strategies were developed with the specific aim of reducing unplanned readmissions by applying prediction models. EPIC's Readmission Risk model, developed in 2015 for the U.S. acute care hospital setting, promises superior calibration and discriminatory abilities. However, its routine application in the Swiss hospital setting requires external validation first. Therefore, the primary objective of this study is to externally validate the EPIC's Readmission Risk model and to compare it with the LACE+ index (Length of stay, Acuity, Comorbidities, Emergency Room visits index) and the SQLape (Striving for Quality Level and analysing of patient expenditures) Readmission model.

Methods: For this reason, a monocentric, retrospective, diagnostic cohort study will be conducted. The study will include all inpatients, who were hospitalized between the 1st January 2018 and the 31st of January 2019 in the Lucerne Cantonal hospital in Switzerland. Cases will be inpatients that experienced an unplanned (all-cause) readmission within 18 or 30 days after the index discharge. The control group will consist of individuals who had no unscheduled readmission.

For external validation, discrimination of the scores under investigation will be assessed by calculating the area under the receiver operating characteristics curves (AUC). For calibration, the Hosmer-Lemeshow goodness-of-fit test will be graphically illustrated by plotting the predicted outcomes by decile against the observations. Other performance measures to be estimated will include the Brier Score, Net Reclassification Improvement (NRI) and the Net Benefit (NB).

All patient data will be retrieved from clinical data warehouses.

Study Timeline

• Study First Submitted: 2020-03-06
• Study Start: 2020-03-10
• Study First Submitted QC: 2020-03-10
• Study First Posted: 2020-03-12
• Primary Completion: 2020-04-10
• Status Verified: 2020-10
• Study Completion: 2020-10-01
• Last Update Submitted: 2020-10-18
• Last Update Posted: 2020-10-20

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 23116

Inclusion Criteria

• All inpatients, aged one year or older (max. 100 years), who were hospitalized either between the 1st of January 2018 and the 31st of December 2018, or between the 23rd of September and the 31st of December 2019 will be included.

Exclusion criteria:

• admission/transfer from another psychiatric, rehabilitative or acute care ward from the same institution,
• discharge destination other than the patient's home or
• transfer to another acute care hospital, both being considered as treatment continuation;
• foreign residence,
• deceased before discharge,
• discharged on admission day,
• refusal of general consent, and
• unknown patient residence or discharge destination.

Read More

Exclusion Criteria

Not provided

Read More

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Readmitted inpatients/Cases	LACE+ score	Outcome 1: Patients who were readmitted within 18 days of index hospitalization discharge date to the same hospital, with a diagnosis leading to the same Major Diagnostic Group as the index stay (definition according to Swiss Diagnosis Related Groups system, case merger) Outcome 2: Patients with an unplanned readmission within 30 days of index hospitalization discharge date to the same hospital. An unplanned readmission was defined as a readmission through the emergency department.
Readmitted inpatients/Cases	SQLAPE model	Outcome 1: Patients who were readmitted within 18 days of index hospitalization discharge date to the same hospital, with a diagnosis leading to the same Major Diagnostic Group as the index stay (definition according to Swiss Diagnosis Related Groups system, case merger) Outcome 2: Patients with an unplanned readmission within 30 days of index hospitalization discharge date to the same hospital. An unplanned readmission was defined as a readmission through the emergency department.
Non-Readmitted inpatients/Controls	An US Readmission Risk Prediction Model	Outcome 1 \& 2: Patients who were not readmitted within 30 days of index hospitalization discharge date.
Non-Readmitted inpatients/Controls	SQLAPE model	Outcome 1 \& 2: Patients who were not readmitted within 30 days of index hospitalization discharge date.
Readmitted inpatients/Cases	An US Readmission Risk Prediction Model	Outcome 1: Patients who were readmitted within 18 days of index hospitalization discharge date to the same hospital, with a diagnosis leading to the same Major Diagnostic Group as the index stay (definition according to Swiss Diagnosis Related Groups system, case merger) Outcome 2: Patients with an unplanned readmission within 30 days of index hospitalization discharge date to the same hospital. An unplanned readmission was defined as a readmission through the emergency department.
Non-Readmitted inpatients/Controls	LACE+ score	Outcome 1 \& 2: Patients who were not readmitted within 30 days of index hospitalization discharge date.

Primary Outcome Measures

Name	Time	Method
Clinical usefulness (NB) at 18 days	18 days after index discharge date	Net Benefit (NB): NB = (TP - w FP) / N, where TP is the number of true positive decisions, FP the number of false positive decisions, N is the total number of patients and w is a weight equal to the odds of the cut-off (pt/(1-pt), or the ratio of harm to benefit
Discrimination at 30 days	30 days after index discharge date	For discrimination of the scores under investigation, the area under the receiver operating characteristics curves (AUC) will be calculated.
Clinical usefulness (NRI) at 30 days	30 days after index discharge date	Net Reclassification Improvement (NRI): In the calculation of the NRI, the improvement in sensitivity and the improvement in specificity are summed. The NRI ranges from 0 for no improvement and 1 for perfect improvement.
Discrimination at 18 days	18 days after index discharge date	For discrimination of the scores under investigation, the area under the receiver operating characteristics curves (AUC) will be calculated.
Calibration at 18 days	18 days after index discharge date	For calibration, the Hosmer-Lemeshow goodness-of-fit test will be graphically illustrated by plotting the predicted outcomes by decile against the observations.
Calibration at 30 days	30 days after index discharge date	For calibration, the Hosmer-Lemeshow goodness-of-fit test will be graphically illustrated by plotting the predicted outcomes by decile against the observations.
Overall Performance at 30 days	30 days after index discharge date	Brier Score (The Brier score is a quadratic scoring rule, where the squared difference between actual binary outcomes Y and predictions p are calculated. The Brier score can range from 0 for a perfect model to 0.25 for a non-informative model with a 50% incidence of the outcome.)
Clinical usefulness (NRI) at 18 days	18 days after index discharge date	Net Reclassification Improvement (NRI): In the calculation of the NRI, the improvement in sensitivity and the improvement in specificity are summed. The NRI ranges from 0 for no improvement and 1 for perfect improvement.
Clinical usefulness (NB) at 30 days	30 days after index discharge date	Net Benefit (NB): NB = (TP - w FP) / N, where TP is the number of true positive decisions, FP the number of false positive decisions, N is the total number of patients and w is a weight equal to the odds of the cut-off (pt/(1-pt), or the ratio of harm to benefit
Overall Performance at 18 days	18 days after index discharge date	Brier Score (The Brier score is a quadratic scoring rule, where the squared difference between actual binary outcomes Y and predictions p are calculated. The Brier score can range from 0 for a perfect model to 0.25 for a non-informative model with a 50% incidence of the outcome.)

Trial Locations

Locations (1)

Cantonal Hospital of Lucerne; 🇨🇭 Lucerne, Canton Lucerne, Switzerland