Leveraging Machine Learning Techniques to Forecast Patient Prognosis After Percutaneous Coronary Intervention.

OBJECTIVES This study sought to determine whether machine learning can be used to better identify patients at risk for death or congestive heart failure (CHF) rehospitalization after percutaneous coronary intervention (PCI). BACKGROUND Contemporary risk models for event prediction after PCI have limited predictive ability. Machine learning has the potential to identify complex nonlinear patterns within datasets, improving the predictive power of models. METHODS We evaluated 11,709 distinct patients who underwent 14,349 PCIs between January 2004 and December 2013 in the Mayo Clinic PCI registry. Fifty-two demographic and clinical parameters known at the time of admission were used to predict in-hospital mortality and 358 additional variables available at discharge were examined to identify patients at risk for CHF readmission. For each event, we trained a random forest regression model (i.e., machine learning) to estimate the time-to-event. Eight-fold cross-validation was used to estimate model performance. We used the predicted time-to-event as a score, generated a receiver operating characteristic curve, and calculated the area under the curve (AUC). Model performance was then compared with a logistic regression model using pairwise comparisons of AUCs and calculation of net reclassification indices. RESULTS The predictive algorithm identified a high-risk cohort representing 2% of all patients who had an in-hospital mortality of 45.5% (95% confidence interval: 43.5% to 47.5%) compared with a risk of 2.1% for the general population (AUC: 0.925; 95% confidence interval: 0.92 to 0.93). Advancing age, CHF, and shock on presentation were the leading predictors for the outcome. A high-risk group representing 1% of all patients was identified with 30-day CHF rehospitalization of 8.1% (95% confidence interval: 6.3% to 10.2%). Random forest regression outperformed logistic regression for predicting 30-day CHF readmission (AUC: 0.90 vs. 0.85; p = 0.003; net reclassification improvement: 5.14%) and 180-day cardiovascular death (AUC: 0.88 vs. 0.81; p = 0.02; net reclassification improvement: 0.02%). CONCLUSIONS Random forest regression models (machine learning) were more predictive and discriminative than standard regression methods at identifying patients at risk for 180-day cardiovascular mortality and 30-day CHF rehospitalization, but not in-hospital mortality. Machine learning was effective at identifying subgroups at high risk for post-procedure mortality and readmission.

[1]  Prashant Warier,et al.  Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients , 2018, Journal of the American Heart Association.

[2]  T. Maddox,et al.  Temporal Trends in Coronary Angiography and Percutaneous Coronary Intervention: Insights From the VA Clinical Assessment, Reporting, and Tracking Program. , 2018, JACC. Cardiovascular interventions.

[3]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[4]  W. Laskey,et al.  Incidence and predictors of 30-day hospital readmission rate following percutaneous coronary intervention (from the National Heart, Lung, and Blood Institute Dynamic Registry). , 2012, The American journal of cardiology.

[5]  J. Spertus,et al.  Risk Factors for Rehospitalization for Acute Coronary Syndromes and Unplanned Revascularization Following Acute Myocardial Infarction , 2015, Journal of the American Heart Association.

[6]  T. Ryan,et al.  Multivariate prediction of in-hospital mortality after percutaneous coronary interventions in 1994-1996. Northern New England Cardiovascular Disease Study Group. , 1999, Journal of the American College of Cardiology.

[7]  B. Gersh,et al.  Factors associated with 30-day readmission rates after percutaneous coronary intervention. , 2012, Archives of internal medicine.

[8]  R. Cody,et al.  Discharge Education Improves Clinical Outcomes in Patients With Chronic Heart Failure , 2005, Circulation.

[9]  Thomas D. Scott,et al.  Readmission in the 30 days after percutaneous coronary intervention. , 2013, JACC. Cardiovascular interventions.

[10]  S. Kimmel,et al.  Development and validation of a simplified predictive index for major complications in contemporary percutaneous transluminal coronary angioplasty practice , 1995 .

[11]  Sunil V. Rao,et al.  Burden of 30-Day Readmissions After Percutaneous Coronary Intervention in 833,344 Patients in the United States: Predictors, Causes, and Cost: Insights From the Nationwide Readmission Database. , 2018, JACC. Cardiovascular interventions.

[12]  Z. Obermeyer,et al.  Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. , 2016, The New England journal of medicine.

[13]  W. O’Neill,et al.  Simplified scoring system for predicting mortality after percutaneous coronary intervention. , 2003, Journal of the American College of Cardiology.

[14]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[15]  D. Holmes,et al.  Risk scores for 30-day mortality after percutaneous coronary intervention: new insights into causes and risk of death. , 2014, Mayo Clinic proceedings.

[16]  Rehospitalization following percutaneous coronary intervention for commercially insured patients with acute coronary syndrome: a retrospective analysis , 2012, BMC Research Notes.

[17]  M. Naylor,et al.  Comprehensive Discharge Planning for the Hospitalized Elderly , 1994, Annals of Internal Medicine.

[18]  B. Gersh,et al.  Prediction of Cardiac and Noncardiac Mortality After Percutaneous Coronary Intervention , 2015, Circulation. Cardiovascular interventions.

[19]  L Ohno-Machado,et al.  Simplified risk score models accurately predict the risk of major in-hospital complications following percutaneous coronary intervention. , 2001, The American journal of cardiology.

[20]  Partho P Sengupta,et al.  Intelligent platforms for disease assessment: novel approaches in functional echocardiography. , 2013, JACC. Cardiovascular imaging.

[21]  B. Levin,et al.  Performance analysis of a machine learning flagging system used to identify a group of individuals at a high risk for colorectal cancer , 2017, PloS one.

[22]  B. Gersh,et al.  Sex Differences in Long-Term Cause-Specific Mortality After Percutaneous Coronary Intervention: Temporal Trends and Mechanisms , 2018, Circulation. Cardiovascular interventions.

[23]  P. Sengupta,et al.  Prediction of Abnormal Myocardial Relaxation From Signal Processed Surface ECG. , 2018, Journal of the American College of Cardiology.

[24]  John D. Kelleher,et al.  Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies , 2015 .

[25]  J. Spertus,et al.  Bedside estimation of risk from percutaneous coronary intervention: the new Mayo Clinic risk scores. , 2007, Mayo Clinic proceedings.

[26]  Kirit Patel,et al.  Simple Bedside Additive Tool for Prediction of In-Hospital Mortality After Percutaneous Coronary Interventions , 2001, Circulation.

[27]  Samin K. Sharma,et al.  A risk score to predict in-hospital mortality for percutaneous coronary interventions. , 2006, Journal of the American College of Cardiology.

[28]  J. Seward,et al.  Disparate patterns of left ventricular mechanics differentiate constrictive pericarditis from restrictive cardiomyopathy. , 2008, JACC. Cardiovascular imaging.

[29]  Sijian Wang,et al.  Algorithms outperform metabolite tests in predicting response of patients with inflammatory bowel disease to thiopurines. , 2010, Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association.

[30]  M. Hornbrook,et al.  Early Colorectal Cancer Detected by Machine Learning Model Using Gender, Age, and Complete Blood Count Data , 2017, Digestive Diseases and Sciences.

[31]  J Carpenter,et al.  Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians. , 2000, Statistics in medicine.