Enhancing Prediction of 30-Day Readmission After PCI by Querying Electronic Health Record

Study Questions:

Can the prediction of readmission after percutaneous coronary interventions (PCIs) be improved by querying the electronic medical record?


The authors performed a case-control study in which they matched readmitted to non-readmitted patients in a 1:2 ratio by risk of readmission, and extracted both unstructured and structured data from the electronic medical record. The extracted data included need for medical interpretation, albumin level, medical nonadherence, previous number of emergency department visits, atrial fibrillation/flutter, syncope/presyncope, end-stage liver disease, malignancy, and anxiety. Logistic regression was used to assess the independent association of these variables with the risk of readmission at 30 days.


The study population consisted of 9,288 PCIs, of whom 888 readmitted patients were matched with 1,776 non-readmitted patients. In univariate analysis, cases and controls were significantly different with respect to interpreter (7.9% for cases and 5.3% for controls; p = 0.009), emergency department visits (1.12 vs. 0.77, p < 0.001), homelessness (3.2% vs. 1.6%, p = 0.007), anticoagulation (33.9% vs. 22.1%, p < 0.001), atrial fibrillation/flutter (32.7% vs. 28.9%, p = 0.045), presyncope or syncope (27.8% vs. 21.3%, p < 0.001), and anxiety (69.4% vs. 62.4%, p < 0.001). The independent predictors of readmission were anticoagulation, emergency department visits, and anxiety.


The authors concluded that prediction for hospital readmission after PCI can be enhanced using structured and unstructured review of the electronic health record.


While there is considerable focus on reducing readmissions after PCI, identifying those at high risk remains a challenge. The previously described risk models have poor discrimination and the authors identified important clinical factors that are not routinely collected in registries and yet are important predictors of readmission after PCI. The enhanced risk model, however, still had modest discrimination (albeit better than what has been previously described), and better tools are needed to identify patients at risk of readmission after PCI.

Clinical Topics: Anticoagulation Management, Arrhythmias and Clinical EP, Invasive Cardiovascular Angiography and Intervention, Anticoagulation Management and Atrial Fibrillation, Atrial Fibrillation/Supraventricular Arrhythmias

Keywords: Albumins, Anticoagulants, Anxiety, Atrial Fibrillation, Electronic Health Records, Emergency Service, Hospital, Patient Readmission, Percutaneous Coronary Intervention, Risk, Syncope

< Back to Listings