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.

Stingray CART (K14 technique): A novel antegrade dissection reentry strategy.

A novel device based CART technique (K14 technique) has been described with 2 case examples to illustrate the same. This CART has been performed after ADR and Reverse-CART were unsuccessful.

Government Regulation and Percutaneous Coronary Intervention Volume, Access and Outcomes: Insights From the Washington State Cardiac Care Outcomes Assessment Program.

Background It is unclear how to geographically distribute percutaneous coronary intervention (PCI) programs to optimize patient outcomes. The Washington State Certificate of Need program seeks to balance hospital volume and patient access through regulation of elective PCI. Methods and Results We performed a retrospective cohort study of all non-Veterans Affairs hospitals with PCI programs in Washington State from 2009 to 2018. Hospitals were classified as having (1) full PCI services and surgical backup (legacy hospitals, n=17); (2) full services without surgical backup (new certificate of need [CON] hospitals, n=9); or (3) only nonelective PCI without surgical backup (myocardial infarction [MI] access hospitals, n=9). Annual median hospital-level volumes were highest at legacy hospitals (605, interquartile range, 466-780), followed by new CON, (243, interquartile range, 146-287) and MI access, (61, interquartile range, 23-145). Compared with MI access hospitals, risk-adjusted mortality for nonelective patients was lower for legacy (odds ratio [OR], 0.59 [95% CI, 0.48-0.72]) and new-CON hospitals (OR, 0.55 [95% CI, 0.45-0.65]). Legacy hospitals provided access within 60 minutes for 90% of the population; addition of new CON and MI access hospitals resulted in only an additional 1.5% of the population having access within 60 minutes. Conclusions Many PCI programs in Washington State do not meet minimum volume standards despite regulation designed to consolidate elective PCI procedures. This CON strategy has resulted in a tiered system that includes low-volume centers treating high-risk patients with poor outcomes, without significant increase in geographic access. CON policies should re-evaluate the number and distribution of PCI programs.

Potential Impact of the 2019 ACC/AHA Guidelines on the Primary Prevention of Cardiovascular Disease Recommendations on the Inappropriate Routine Use of Aspirin and Aspirin Use Without a Recommended Indication for Primary Prevention of Cardiovascular Disease in Cardiology Practices: Insights From the NCDR PINNACLE Registry.

BACKGROUND: Aspirin is recommended in patients with atherosclerotic cardiovascular disease for secondary prevention. In patients without atherosclerotic cardiovascular disease and not at high 10-year risk, there is no evidence aspirin reduces adverse cardiovascular events and it could increase bleeding. The 2019 American College of Cardiology/American Heart Association Guidelines on Primary Prevention of Cardiovascular Disease state that aspirin may be considered for primary prevention (class IIb) in patients 40 to 70 years that are at higher risk of atherosclerotic cardiovascular disease and that routine use of aspirin should be avoided (class III:Harm) for patients >70 years. We examined the frequency of patients on aspirin for primary prevention that would have been considered unindicated or potentially harmful per the recent guideline where aspirin discontinuation may be beneficial. METHODS: To assess the potential impact, within the National Cardiovascular Disease Registry Practice Innovation and Clinical Excellence Registry, we assessed 855 366 patients from 400 practices with encounters between January 1, 2018 and March 31, 2019, that were receiving aspirin for primary prevention. We defined inappropriate use as the use of aspirin in patients <40 or >70 years and use without a recommended indication as use of aspirin in patients 40 to 70 years with low, borderline, or intermediate 10-year atherosclerotic cardiovascular disease risk. Frequency of inappropriate use and use without a recommended indication were calculated and practice-level variation was evaluated using the median rate ratio. RESULTS: Inappropriate use occurred in 27.6% (193 674/701 975) and use without a recommended indication in 26.0% (31 810/122 507) with significant practice-level variation in inappropriate use (predicted median practice-level rate 33.5%, interquartile range, 24.1% to 40.8%; median rate ratio, 1.71 [95% CI, 1.67-1.76]). CONCLUSIONS: Immediately before the 2019 American College of Cardiology/American Heart Association Guidelines on Primary Prevention of Cardiovascular Disease, over one-fourth of patients in this national registry were receiving aspirin for primary prevention inappropriately or without a recommended indication with significant practice-level variation. These findings help to determine the potential impact of guideline recommendations on contemporary use of aspirin for primary prevention.

Coronary revascularisation outcomes in patients with cancer.

Cancer and coronary artery disease (CAD) overlap in traditional risk factors as well as molecular mechanisms underpinning the development of these two disease states. Patients with cancer are at increased risk of developing CAD, representing a high-risk population that are increasingly undergoing coronary revascularisation. Over 1 in 10 patients with CAD that require revascularisation with either percutaneous coronary intervention or coronary artery bypass grafting have either a history of cancer or active cancer. These patients are typically older, have more comorbidities and have more extensive CAD compared with patients without cancer. Haematological abnormalities with competing risks of thrombosis and bleeding pose further unique challenges during and after revascularisation. Management of patients with concurrent cancer and CAD requiring revascularisation is challenging as these patients carry a higher risk of morbidity and mortality compared with those without cancer, often driven by the underlying cancer and associated comorbidities. However, due to variability by different types and stages of cancer, revascularisation outcomes are specific to cancer characteristics such as the timing of onset, cancer subtype and site, stage, presence of metastases, and cancer-related therapies received. Recent studies have provided insights into defining revascularisation outcomes, procedural considerations and best practices in managing patients with cancer. Nevertheless, many gaps remain that require further studies to inform clinical best practices in this population.

Intravascular coronary brachytherapy combined with a drug-coated balloon.

BACKGROUND: Coronary artery disease leads to stenosis of the major cardiac vessels, resulting in ischemia and infarction. Percutaneous intervention (PCI) with balloon angioplasty can re-open stenosed vessels. Drug eluting stents (DES) and intravascular brachytherapy (IVBT) and drug-coated balloons (DCBs) are proven to decrease the likelihood of another restenosis after PCI, but neither is completely effective. Due to the limited long-term effectiveness of IVBT or DCB used separately for salvage PCI, we combined the two in some poor prognosis patients. METHODS: Combined IVBT+DCB was intended for a total of 36 patients from 2015-2020. PCI with some combination of ballooning, laser and directional/rotational atherectomy was used to maximally open the stenotic region prior to IVBT+DCB. Beta-radiation brachytherapy for all patients was done with a Novoste Beta-Cath. Lutonix 4.0 x 40 mm paclitaxel-coated balloons (Bard, Murray Hill, NJ) were employed. RESULTS: Overall survival at two years was 88%. Nine patients had follow-up angiograms, all for cardiac symptoms. Time from IVBT+DCB to follow-up angiography ranged from 4 to 33 months. The average months PCI-free interval before brachy therapy was 11.1 mos (95% CI 1.03-23.25) versus 23.3 mos after VBT (23.3 95% CI 12.3-32.3). The mean difference was 11.2 mos (95% CI 1.06-21.4, p < 0.031). None of the follow-up angiographic procedures displayed evidence of what could be interpreted as radiation damage. CONCLUSIONS: In this uncontrolled series, IVBT plus DCB appeared to lengthen the ISR-free interval relative to what had been achieved prior to the combined intervention. We view these results as mildly encouraging, worthy of further study.

Outcomes of Acute Myocardial Infarction in Patients with Familial Hypercholesteremia.

BACKGROUND: There is a paucity of contemporary data regarding the outcomes of acute myocardial infarction among patients with familial hypercholesteremia. METHODS: We queried the Nationwide Readmissions Database (2016-2018) for hospitalizations with acute myocardial infarction. Multivariable regression analysis was used to compare in-hospital outcomes and 30-day readmissions among patients with and without familial hypercholesteremia. RESULTS: The analysis included 1,363,488 hospitalizations with acute myocardial infarction. The prevalence of familial hypercholesteremia was 0.07% among acute myocardial infarction admissions. Compared with those without familial hypercholesteremia, admissions with familial hypercholesteremia were younger and had less comorbidities but were more likely to have had prior infarct and revascularization. Admissions with familial hypercholesteremia were more likely to present with ST-elevation myocardial infarction and undergo revascularization. After multivariable adjustment, there was no difference in in-hospital case fatality among patients with hypercholesteremia compared with those without it (adjusted odds ratio [aOR] = 0.76; 95% confidence interval [CI] 0.41-1.39). Admissions with acute myocardial infarction and familial hypercholesteremia had higher adjusted rates of cardiac arrest and utilization of mechanical support. There were no group differences in overall 30-day readmission (aOR 0.75; 95% CI 0.51-1.10) or 30-day readmission for acute myocardial infarction. However, a nonsignificant trend toward higher readmission for percutaneous coronary intervention was observed among patients with familial hypercholesteremia (aOR 1.89; 95% CI 0.98-3.64). CONCLUSION: In this contemporary nationwide observational analysis, patients with familial hypercholesteremia represent a small proportion of the overall population with acute myocardial infarction and have a distinctive clinical profile but do not appear to have worse in-hospital case fatality compared with those without familial hypercholesteremia.

Interventional cardiologists' perceptions of percutaneous coronary intervention quality measurement and feedback.

BACKGROUND: Interventional cardiologists receive feedback on their clinical care from a variety of sources including registry-based quality measures, case conferences, and informal peer interactions. However, the impact of this feedback on clinical care is unclear. METHODS: We interviewed interventional cardiologists regarding the use of feedback to improve their care of percutaneous coronary intervention (PCI) patients. Interviews were assessed with template analysis using deductive and inductive techniques. RESULTS: Among 20 interventional cardiologists from private, academic, and Department of Veterans Affairs practice, 85% were male, 75% performed at least 100 PCIs annually, and 55% were in practice for 5 years or more. All reported receiving feedback on their practice, including formal quality measures and peer learning activities. Many respondents were critical of quality measure reporting, citing lack of trust in outcomes measures and poor applicability to clinical care. Some respondents reported the use of process measures such as contrast volume and fluoroscopy time for benchmarking their performance. Case conferences and informal peer feedback were perceived as timelier and more impactful on clinical care. Respondents identified facilitators of successful feedback interventions including transparent processes, respectful and reciprocal peer relationships, and integration of feedback into collective goals. Hierarchy and competitive environments inhibited useful feedback. CONCLUSIONS: Despite substantial resources dedicated to performance measurement and feedback for PCI, interventional cardiologists perceive existing quality measures to be of only modest value for improving clinical care. Catherization laboratories should seek to integrate quality measures into a holistic quality program that emphasizes peer learning, collective goals and mutual respect.

Toolbox for Coronary Chronic Total Occlusion Percutaneous Coronary Intervention.

Since the publication of the hybrid algorithm there has been rapid development of new specialty wires, microcatheters, guide extensions, and low-profile balloons to facilitate successful coronary chronic total occlusion percutaneous coronary intervention. With development of new devices, it is best to categorize them by design and intended task. This enables a safe and systematic approach to coronary chronic total occlusion percutaneous coronary intervention and avoid overlap and waste. This article serves as a guide for tool selection for the interventional cardiologist performing coronary chronic total occlusion percutaneous coronary intervention.

Eligibility for Low-Dose Rivaroxaban Based on the COMPASS Trial: Insights from the Veterans Affairs Healthcare System.

INTRODUCTION: Low-dose rivaroxaban reduced major adverse cardiac and limb events among patients with stable atherosclerotic vascular disease (ASCVD) in the COMPASS trial. The objective of our study was to evaluate the eligibility and budgetary impact of the COMPASS trial in a real-world population. METHODS: The VA administrative and clinical databases were utilized to conduct a cross-sectional study to identify patients eligible for low-dose rivaroxaban receiving care at all 141 facilities between October 1, 2014 and September 30, 2015. Proportion of patients with stable ASCVD eligible for low-dose rivaroxaban and prevalence of multiple risk enrichment criteria among eligible patients. Pharmaceutical budgetary impact using VA pharmacy pricing. Chi-squared and Student's t tests were used to compare patients eligible versus ineligible patients. RESULTS: From an initial cohort of 1,248,214 patients with ASCVD, 488,495 patients (39.1%) met trial eligibility criteria. Eligible patients were older (74.2 vs 64.5 years) with higher proportion of hypertension (84.1% vs 82.1%) and diabetes (46.2% vs 32.9) compared with ineligible patients (p < 0.001 for all comparisons). A median of 38.7% (IQR 4.6%) of total ASCVD patients per facility were rivaroxaban eligible. Estimated annual VA pharmacy budgetary impact would range from $0.47 billion to $1.88 billion for 25% to 100% treatment penetration. Annual facility level pharmaceutical budgetary impact would be a median of $12.3 million (IQR $8.0-$16.3 million) for treatment of all eligible patients. Among eligible patients, age greater than 65 years was the most common risk enrichment factor (86.9%). Prevalence of eligible patients with multiple enrichment factors varied from 34.2% (one factor) to 6.2% (four or more). CONCLUSION: Over one third of patients with stable ASCVD may qualify for low-dose rivaroxaban within the VA. Additional studies are needed to understand eligibility in other populations and a formal cost-effectiveness analysis is warranted.

Association Between 90-Minute Door-to-Balloon Time, Selective Exclusion of Myocardial Infarction Cases, and Access Site Choice: Insights From the Cardiac Care Outcomes Assessment Program (COAP) in Washington State.

BACKGROUND: For patients presenting with ST-segment-elevation myocardial infarction, national quality initiatives monitor hospitals' proportion of cases with door-to-balloon (D2B) time under 90 minutes. Hospitals are allowed to exclude patients from reporting and may modify behavior to improve performance. We sought to identify whether there is a discontinuity in the number of cases included in the D2B time metric at 90 minutes and whether operators were increasingly likely to pursue femoral access in patients with less time to meet the 90-minute quality metric. METHODS: Adult patients with ST-segment-elevation myocardial infarction undergoing primary percutaneous coronary intervention from 2011 to 2018 were identified from the Cardiac Care Outcomes Assessment Program, a quality improvement registry in Washington state. We used the regression discontinuity framework to test for discontinuity at 90 minutes among the included cases. We defined a novel variable, remaining D2B as 90 minutes minus the time between hospital arrival and catheterization laboratory arrival. We estimated multivariable logistic regression models to assess the relationship between remaining D2B time and access site. RESULTS: A total of 19 348 patients underwent primary percutaneous coronary intervention and were included in the analysis. Overall, 7436 (38.4%) were excluded from the metric. There appeared to be a visual discontinuity in included cases around 90 minutes; however, local quadratic regression around the 90-minute cutoff did not reveal evidence of a significant discontinuity (P=0.66). Multivariable analysis showed no significant relationship between remaining D2B time and the odds of undergoing femoral access (P=0.73). CONCLUSIONS: Among patients undergoing percutaneous coronary intervention for ST-segment-elevation myocardial infarction, we did not find evidence of a statistically significant discontinuity in the frequency of included cases around 90 minutes or an increased preference for femoral access correlated with decreasing time to meet the 90-minute D2B time quality metric. Together, these findings indicate no evidence of widespread inappropriate methods to improve performance on D2B time metrics.

Management of Percutaneous Coronary Intervention Complications: Algorithms From the 2018 and 2019 Seattle Percutaneous Coronary Intervention Complications Conference.

Complications of percutaneous coronary intervention (PCI) may have significant impact on patient survival and healthcare costs. PCI procedural complexity and patient risk are increasing, and operators must be prepared to recognize and treat complications, such as perforations, dissections, hemodynamic collapse, no-reflow, and entrapped equipment. Unfortunately, few resources exist to train operators in PCI complication management. Uncertainty regarding complication management could contribute to the undertreatment of patients with high-complexity coronary disease. We, therefore, coordinated the Learning From Complications: How to Be a Better Interventionalist courses to disseminate the collective experience of high-volume PCI operators with extensive experience in chronic total occlusion and high-risk PCI. From these conferences in 2018 and 2019, we developed algorithms that emphasize early recognition, effective treatment, and team-based care of PCI complications. We think that an algorithmic approach will result in a logical and systematic response to life-threatening complications. This construct may be useful for operators who plan to perform complex PCI procedures.

Diagnostic accuracy of early computed tomographic coronary angiography to detect coronary artery disease after out-of-hospital circulatory arrest.

AIM: To test the diagnostic accuracy of ECG-gated coronary computed tomography angiography (CCTA) to detect coronary artery disease (CAD) among survivors of out-of-hospital circulatory arrest (OHCA). METHODS: We prospectively studied head-to-pelvis computed tomography (CT) scanning (<6 h from hospital arrival) in OHCA survivors. This sub-study tested the primary outcome of CCTA diagnostic accuracy to identify obstructive CAD (≥50% stenosis) compared to clinically-ordered invasive coronary angiography. Patients were not optimized with beta receptor blockade or nitroglycerin. Secondary analyses included CCTA accuracy for CAD in major coronary arteries, obstructive disease at ≥70% stenosis threshold, and where non-evaluable CCTA segments were considered either obstructive or non-obstructive. RESULTS: Of the 104 enrolled OHCA survivors, 28 (27%) received both CT and invasive angiography in this sub study. All CCTA studies were evaluable although 49/346 (14%) individual coronary segments were unevaluable, primarily due to being too small to evaluate (65%). Patient-level diagnostic accuracy for the ≥50% stenosis threshold was high at 0.93 (95% CI 0.77-0.98) with a specificity of 1.0 (95% CI 0.8-1.0), sensitivity of 0.85 (95%CI 0.58-0.96), negative predictive value of 0.88 (95% CI 0.66-0.97) and positive predictive value of 1.0 (0.74-1.0). When non-evaluable segments were considered obstructive, the sensitivity rose to 0.92 (95% CI 0.67-0.99) with lower specificity of 0.27 (95% CI 0.11-0.52). CONCLUSION: Early CCTA of OHCA survivors has high diagnostic accuracy to detect obstructive coronary artery disease. However, the number of non-diagnostic coronary segments is high suggesting further CCTA refinement is needed, such as the pre-CCTA use of nitroglycerin. CLINICAL TRIAL REGISTRATION: NCT03111043 https://clinicaltrials.gov/ct2/show/record/NCT03111043.