Key result
Gradient boosting machine model predicts 30-day unplanned hospital readmissions with an AUC of ~84.
Why the study?
Unplanned hospital readmissions reflect quality of care and discharge appropriateness, motivating the development of prediction models based on a common data model applicable across multiple institutions.
Does a machine learning prediction model based on a common data model (CDM) accurately predict all-cause unplanned hospital readmissions within 30 days of discharge in patients visiting tertiary hospitals?
Cohort (n=199,857)
Yes
Does a machine learning prediction model based on a common data model (CDM) accurately predict all-cause unplanned hospital readmissions within 30 days of discharge in patients visiting tertiary hospitals?
Machine learning models utilizing a Common Data Model (CDM) can effectively predict 30-day unplanned hospital readmissions and demonstrate transportability across different institutions.
Answers are grounded in this paper and cite their sources.
May support CDM-based readmission risk stratification; leaves open prospective validation before practice change.
BACKGROUND: Unplanned hospital readmission after discharge reflects low satisfaction and reliability in care and the possibility of potential medical accidents, and is thus indicative of the quality of patient care and the appropriateness of discharge plans. OBJECTIVES: The purpose of this study was to develop and validate prediction models for all-cause unplanned hospital readmissions within 30 days of discharge, based on a common data model (CDM), which can be applied to multiple institutions for efficient readmission management. METHODS: Retrospective patient-level prediction models were developed based on clinical data of two tertiary general university hospitals converted into a CDM developed by Observational Medical Outcomes Partnership. Machine learning classification models based on the LASSO logistic regression model, decision tree, AdaBoost, random forest, and gradient boosting machine (GBM) were developed and tested by manipulating a set of CDM variables. An internal 10-fold cross-validation was performed on the target data of the model. To examine its transportability, the model was externally validated. Verification indicators helped evaluate the model performance based on the values of area under the curve (AUC). RESULTS: Based on the time interval for outcome prediction, it was confirmed that the prediction model targeting the variables obtained within 30 days of discharge was the most efficient (AUC of 82.75). The external validation showed that the model is transferable, with the combination of various clinical covariates. Above all, the prediction model based on the GBM showed the highest AUC performance of 84.14 ± 0.015 for the Seoul National University Hospital cohort, yielding in 78.33 in external validation. CONCLUSIONS: This study showed that readmission prediction models developed using machine-learning techniques and CDM can be a useful tool to compare two hospitals in terms of patient-data features.
No takes yet. Share an insight, caveat, or question.
Yoo et al. (2021) conducted a cohort in Unplanned hospital readmission (n=199,857). Gradient boosting machine (GBM) prediction model based on OMOP CDM vs. Other machine learning models (LASSO, Decision Tree, Random Forest, AdaBoost) was evaluated on Area under the curve (AUC) for predicting 30-day unplanned hospital readmission. A gradient boosting machine prediction model utilizing clinical variables obtained within 30 days of discharge achieved the highest performance in predicting 30-day unplanned hospital readmissions with an AUC of 84.14.
Synapse has enriched 10 related papers. Consider them for comparative context: