Key result
Machine learning algorithms improved predictive performance for 30-day preventable hospital readmissions, identifying length of stay, disease severity, and non-English language as risk factors.
Why the study?
Do machine learning algorithms improve the prediction of 30-day preventable hospital readmissions in Medicare patients?
Do machine learning algorithms improve the prediction of 30-day preventable hospital readmissions in Medicare patients?
Machine learning algorithms can improve the prediction of 30-day preventable hospital readmissions, potentially enabling better targeted interventions for high-risk patients.
No takes yet. Share an insight, caveat, or question.
May support targeted readmission prevention; hypothesis-generating and requires prospective validation before practice change.
García-Arce et al. (2017) studied 30-day preventable hospital readmissions. Machine learning predictive models was evaluated on Model performance measured by the area under the receiver operating characteristic curve (AUC) for 30-day preventable hospital readmissions. Machine learning algorithms improved predictive performance for 30-day preventable hospital readmissions, identifying length of stay, disease severity, and non-English language as risk factors.