Author + information
- Received September 10, 2018
- Revision received February 11, 2019
- Accepted February 20, 2019
- Published online June 26, 2019.
- Chad J. Zack, MD, MSa,∗,
- Conor Senecal, MDb,∗,
- Yaron Kinar, PhDc,
- Yaakov Metzger, MD, PhDc,
- Yoav Bar-Sinai, MSc,
- R. Jay Widmer, MD, PhDb,
- Ryan Lennon, MSd,
- Mandeep Singh, MD, MPHb,
- Malcolm R. Bell, MDb,
- Amir Lerman, MDb and
- Rajiv Gulati, MD, PhDb,∗ ()
- aHeart and Vascular Institute, Penn State Hershey Medical Center, Hershey, Pennsylvania
- bDepartment of Cardiovascular Diseases, Mayo Clinic College of Medicine, Rochester, Minnesota
- cMedial Research, Kfar Malal, Israel
- dDivision of Biostatistics, Mayo Clinic College of Medicine, Rochester, Minnesota
- ↵∗Address for correspondence:
Dr. Rajiv Gulati, Department of Cardiovascular Medicine, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
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.
↵∗ Drs. Zack and Senecal contributed equally to this work and are joint first authors.
This publication was made possible by funding from the National Institutes of Health Clinical and Translational Science Award (UL1 TR002377) from the National Center for Advancing Translational Sciences. The contents of this article are solely the responsibility of the authors and do not necessarily represent the official view of National Institutes of Health. Drs. Kinar, Metzger, and Bar Sinai are employees of Medial Research. Dr. Lerman is a consultant to Medial Research. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.
- Received September 10, 2018.
- Revision received February 11, 2019.
- Accepted February 20, 2019.
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.