Background/Purpose: Readmissions can be defined as the return of a patient to a healthcare setting after a discharge. Attention has been mainly focused on readmissions following inpatient hospitalizations. In the outpatient setting, readmissions have been far less studied. As the first step in preventing outpatient readmission, the assessment of the individual patient’s risk could be useful to help identify those subjects at greatest risk, so, in a further step we could focus the delivery of an intervention in those patients to reduce their risk. Therefore, our objective was to develop and validate a machine learning predictive model based on Random Forest, to estimate the risk of readmission in an outpatient rheumatology clinic after discharge (outpatient readmission)

Methods: Patients stored in a departmental electronic health record from April 1st, 2007 to November 30th, 2016, and followed-up until November 30th, 2017, were included in this study. Only readmissions taking place between 2 and 12 months after discharge were analyzed. Discharge episodes were split into training, validation and test datasets. Clinical and demographic variables, including diagnoses, treatments, quality of life, and comorbidities, were used as predictors. Models were developed using Random Forest in the training dataset, though the combination of several tuning parameters. Models that maximized the area under the receiver operating characteristic curve (ROC-AUC) in the validation set were assessed in the test set. The model with the highest AUC-ROC in the test dataset was considered as the best final model

Results: 17,772 patients (18,648 discharges episodes) were analyzed and 2,513 (13.5%) discharges episodes were classified as outpatient readmissions. 39,120 possible model combinations were finally tested. The best final model showed an AUC-ROC of 0.677 a sensitivity of 0.479 and a specificity of 0.757. The most important variables were related to follow-up duration, number of previous discharges, corticosteroid and Disease-Modifying Antirheumatic Drugs use, polyarthritis diagnoses, and quality of life

Conclusion: We have developed a predictive model for outpatient readmission in a rheumatology setting. Identification of patients with higher risk could optimize the allocation of healthcare resources

« Back to 2019 ACR/ARP Annual Meeting

ACR Meeting Abstracts - https://acrabstracts.org/abstract/outpatient-readmission-in-rheumatology-a-machine-learning-predictive-model-of-patients-return-to-the-clinic/