Merging machine learning and patient preference: a novel tool for risk prediction of percutaneous coronary interventions.

BACKGROUND AND AIMS: Predicting personalized risk for adverse events following percutaneous coronary intervention (PCI) remains critical in weighing treatment options, employing risk mitigation strategies, and enhancing shared decision-making. This study aimed to employ machine learning models using pre-procedural variables to accurately predict common post-PCI complications. METHODS: A group of 66 adults underwent a semiquantitative survey assessing a preferred list of outcomes and model display. The machine learning cohort included 107 793 patients undergoing PCI procedures performed at 48 hospitals in Michigan between 1 April 2018 and 31 December 2021 in the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) registry separated into training and validation cohorts. External validation was conducted in the Cardiac Care Outcomes Assessment Program database of 56 583 procedures in 33 hospitals in Washington. RESULTS: Overall rate of in-hospital mortality was 1.85% (n = 1999), acute kidney injury 2.51% (n = 2519), new-onset dialysis 0.44% (n = 462), stroke 0.41% (n = 447), major bleeding 0.89% (n = 942), and transfusion 2.41% (n = 2592). The model demonstrated robust discrimination and calibration for mortality {area under the receiver-operating characteristic curve [AUC]: 0.930 [95% confidence interval (CI) 0.920-0.940]}, acute kidney injury [AUC: 0.893 (95% CI 0.883-0.903)], dialysis [AUC: 0.951 (95% CI 0.939-0.964)], stroke [AUC: 0.751 (95%CI 0.714-0.787)], transfusion [AUC: 0.917 (95% CI 0.907-0.925)], and major bleeding [AUC: 0.887 (95% CI 0.870-0.905)]. Similar discrimination was noted in the external validation population. Survey subjects preferred a comprehensive list of individually reported post-procedure outcomes. CONCLUSIONS: Using common pre-procedural risk factors, the BMC2 machine learning models accurately predict post-PCI outcomes. Utilizing patient feedback, the BMC2 models employ a patient-centred tool to clearly display risks to patients and providers (https://shiny.bmc2.org/pci-prediction/). Enhanced risk prediction prior to PCI could help inform treatment selection and shared decision-making discussions.

Failure to Rescue After Percutaneous Coronary Intervention: Insights From the National Cardiovascular Data Registry.

BACKGROUND: Failure to rescue (FTR) describes in-hospital mortality following a procedural complication and has been adopted as a quality metric in multiple specialties. However, FTR has not been studied for percutaneous coronary intervention (PCI) complications. METHODS: This is a retrospective study of patients undergoing PCI from the American College of Cardiology National Cardiovascular Data Registry's CathPCI Registry between April 1, 2018, and June 30, 2021. PCI complications evaluated were significant coronary dissection, coronary artery perforation, vascular complication, significant bleeding within 48 hours, new cardiogenic shock, and tamponade. Secular trends for FTR were evaluated with descriptive analysis, and hospital-level variation and clinical predictors were analyzed with logistic regression. RESULTS: Among 2 196 661 patients undergoing PCI at 1483 hospitals, 3.5% had at least 1 PCI complication. In-hospital mortality occurred more frequently following a complication compared with cases without a complication (19.7% versus 1.3%). FTR increased during the study period from 17.1% to 20.1% (P<0.001). The median odds ratio for FTR was 1.48 (95% CI, 1.44-1.53) indicating significant hospital-level variation. Spearman rank correlation demonstrated the modest correlation between FTR and in-hospital mortality, 0.525 (P<0.001). CONCLUSIONS: Major procedural complications during PCI are infrequent, but FTR occurs in roughly 1 in 5 patients following a PCI procedural complication with significant hospital-level variation. Improved understanding of practices associated with low FTR could meaningfully improve patient outcomes following a PCI complication.