Prediction of death after percutaneous coronary interventional procedures

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

Cardiovascular diseases (CVDs) carry significant morbidity and mortality and are associated with substantial economic burden on healthcare systems around the world. Coronary artery disease, as one disease entity under the CVDs umbrella, had a prevalence of 7.2% among adults in the United States and incurred a financial burden of 360 billion US dollars in the years 2016–2017. The introduction of artificial intelligence (AI) and machine learning over the last two decades has unlocked new dimensions in the field of cardiovascular medicine. From automatic interpretations of heart rhythm disorders via smartwatches, to assisting in complex decision-making, AI has quickly expanded its realms in medicine and has demonstrated itself as a promising tool in helping clinicians guide treatment decisions. Understanding complex genetic interactions and developing clinical risk prediction models, advanced cardiac imaging, and improving mortality outcomes are just a few areas where AI has been applied in the domain of coronary artery disease. Through this review, we sought to summarize the advances in AI relating to coronary artery disease, current limitations, and future perspectives.

Development and validation of a simple risk score to predict 30-day readmission after percutaneous coronary intervention in a cohort of medicare patients

OBJECTIVES

To develop a risk model that can be used to identify PCI patients at higher risk of readmission who may benefit from additional resources at the time of discharge.

BACKGROUND

A high proportion of patients undergoing PCI are readmitted within 30 days of discharge.

METHODS

The sample comprised patients aged ≥65 years who underwent PCI at a CathPCI Registry®-participating hospital and could be linked with 100% Medicare fee-for-service claims between 01/2007 and 12/2009. The sample (n = 388,078) was randomly divided into risk score development (n = 193,899) and validation (n = 194,179) cohorts. We did not count as readmissions those associated with staged revascularization procedures. Multivariable logistic regression models using stepwise selection models were estimated to identify variables independently associated with all-cause 30-day readmission.

RESULTS

The mean 30-day readmission rates for the development (11.36%) and validation (11.35%) cohorts were similar. In total, 19 variables were significantly associated with risk of 30-day readmission (P < 0.05), and model c-statistics were similar in the development (0.67) and validation (0.66) cohorts. The simple risk score based on 14 variables identified patients at high and low risk of readmission. Patients with a score of ≥13 (15.4% of sample) had more than an 18.5% risk of readmission, while patients with a score ≤6 (41.9% of sample) had less than an 8% risk of readmission.

CONCLUSION

Among PCI patients, risk of readmission can be estimated using clinical factors present at the time of the procedure. This risk score may guide clinical decision-making and resource allocation for PCI patients at the time of hospital discharge. © 2016 Wiley Periodicals, Inc.

Public reporting and coronary revascularization: risk and benefit

Since the 1980s, the evolution of public reporting of provider-specific and institution-specific clinical outcomes has historically been rooted in the field of cardiology. Although public reporting is not a novel concept, how we collect, analyze, report, and interpret outcome data remains a critical element in quality improvement and in the quest toward providing truly high-value care. In this review, we explore the emergence of public reporting within the scope of cardiovascular medicine, specifically as it relates to surgical and percutaneous coronary revascularization. We highlight both the advantages and the disadvantages of public reporting from the perspective of the patient, the practicing physician, the hospital, and the healthcare system. A discussion on the limitations of public reporting and specific strategies by which it can be improved is presented.

Angiographic Lesion Complexity Score and In-Hospital Outcomes after Percutaneous Coronary Intervention

OBJECTIVE

We devised a percutaneous coronary intervention (PCI) scoring system based on angiographic lesion complexity and assessed its association with in-hospital complications.

BACKGROUND

Although PCI is finding increasing application in patients with coronary artery disease, lesion complexity can lead to in-hospital complications.

METHODS

Data from 3692 PCI patients were scored based on lesion complexity, defined by bifurcation, chronic total occlusion, type C, and left main lesion, along with acute thrombus in the presence of ST-segment elevation myocardial infarction (1 point assigned for each variable).

RESULTS

The patients' mean age was 67.5 +/- 10.8 years; 79.8% were male. About half of the patients (50.3%) presented with an acute coronary syndrome, and 2218 (60.1%) underwent PCI for at least one complex lesion. The patients in the higher-risk score groups were older (p < 0.001) and had present or previous heart failure (p = 0.02 and p = 0.01, respectively). Higher-risk score groups had significantly higher in-hospital event rates for death, heart failure, and cardiogenic shock (from 0 to 4 risk score; 1.7%, 4.5%, 6.3%, 7.1%, 40%, p < 0.001); bleeding with a hemoglobin decrease of >3.0 g/dL (3.1%, 11.0%, 13.1%, 10.3%, 28.6%, p < 0.001); and postoperative myocardial infarction (1.5%, 3.1%, 3.8%, 3.8%, 10%, p = 0.004), respectively. The association with adverse outcomes persisted after adjustment for known clinical predictors (odds ratio 1.72, p < 0.001).

CONCLUSION

The complexity score was cumulatively associated with in-hospital mortality and complication rate and could be used for event prediction in PCI patients.

Simplifying clinical risk prediction for percutaneous coronary intervention of bifurcation lesions: the case for the ACEF (age, creatinine, ejection fraction) score

AIMS

We aimed to appraise the predictive accuracy of a novel and user-friendly risk score, the ACEF (age, creatinine, ejection fraction), in patients undergoing PCI for coronary bifurcations.

METHODS AND RESULTS

A multicentre, retrospective study was conducted enrolling consecutive patients undergoing bifurcation PCI between January 2002 and December 2006 in 22 Italian centres. Patients with complete data to enable computation of the ACEF score were divided into three groups according to tertiles of ACEF score. The primary endpoint was 30-day mortality. The discrimination of the ACEF score as a continuous variable was also appraised with area under the curve (AUC) of the receiver-operating characteristic. A total of 3,535 patients were included: 1,119 in the lowest tertile of ACEF score, 1,190 in the mid tertile, and 1,153 in the highest tertile. Increased ACEF score was associated with significantly different rates of 30-day mortality (0.1% in the lowest tertile vs. 0.5% in the mid tertile and 3.0% in the highest tertile, p<0.001), with similar differences in myocardial infarction (0.3% vs. 0.7% and 1.8%, p<0.001) and major adverse cardiac events (MACE, 0.5% vs. 1.2% and 4.3%, p<0.001). After an average follow-up of 24.4±15.1 months, increased ACEF score was still associated with a higher rate of all-cause death (1.3% vs. 2.4% and 11.0%, p<0.001), cardiac death (0.9% vs. 1.4% and 7.2%, p<0.001), myocardial infarction (3.4% vs. 2.7% and 5.7%, p<0.001), MACE (13.6% vs. 15.9% and 22.3%, p<0.001), and stent thrombosis (2.3% vs. 1.8% and 5.0%, p<0.001). Discrimination of ACEF score was satisfactory for 30-day mortality (AUC=0.82 [0.77-0.87], p<0.001), 30-day MACE (AUC=0.73 [0.67-0.78], p<0.001), long-term mortality (AUC=0.77 [0.74-0.81], p<0.001), and moderate for long-term MACE (AUC=0.60 [0.57-0.62], p<0.001).

CONCLUSIONS

The simple and extremely user-friendly ACEF score can accurately identify patients undergoing PCI for coronary bifurcation lesions at high risk of early fatal or non-fatal complications, as well as long-term fatality.

EuroHeart score for the evaluation of in-hospital mortality in patients undergoing percutaneous coronary intervention

AIMS

The applicability of currently available risk prediction models for patients undergoing percutaneous coronary interventions (PCIs) is limited. We aimed to develop a model for the prediction of in-hospital mortality after PCI that is based on contemporary and representative data from a European perspective.

METHODS AND RESULTS

Our analyses are based on the Euro Heart Survey of PCIs, which contains information on 46 064 consecutive patients who underwent PCI for different indications in 176 participating European centres during 2005-08. Patients were randomly divided into a training (n = 23 032) and a validation (n = 23 032) set with similar characteristics. In these sets, 339 (1.5%) and 305 (1.3%) patients died during hospitalization, respectively. On the basis of the training set, a logistic model was constructed that related 16 independent patient or lesion characteristics with mortality, including PCI indication, advanced age, haemodynamic instability, multivessel disease, and proximal LAD disease. In both the training and validation data sets, the model had a good performance in terms of discrimination (C-index 0.91 and 0.90, respectively) and calibration (Hosmer-Lemeshow P-value 0.39 and 0.18, respectively).

CONCLUSION

In-hospital mortality in PCI patients was well predicted by a risk score that contains 16 factors. The score has strong applicability for European practices.

Contemporary mortality risk prediction for percutaneous coronary intervention: results from 588,398 procedures in the National Cardiovascular Data Registry

OBJECTIVES

We sought to create contemporary models for predicting mortality risk following percutaneous coronary intervention (PCI).

BACKGROUND

There is a need to identify PCI risk factors and accurately quantify procedural risks to facilitate comparative effectiveness research, provider comparisons, and informed patient decision making.

METHODS

Data from 181,775 procedures performed from January 2004 to March 2006 were used to develop risk models based on pre-procedural and/or angiographic factors using logistic regression. These models were independently evaluated in 2 validation cohorts: contemporary (n = 121,183, January 2004 to March 2006) and prospective (n = 285,440, March 2006 to March 2007).

RESULTS

Overall, PCI in-hospital mortality was 1.27%, ranging from 0.65% in elective PCI to 4.81% in ST-segment elevation myocardial infarction patients. Multiple pre-procedural clinical factors were significantly associated with in-hospital mortality. Angiographic variables provided only modest incremental information to pre-procedural risk assessments. The overall National Cardiovascular Data Registry (NCDR) model, as well as a simplified NCDR risk score (based on 8 key pre-procedure factors), had excellent discrimination (c-index: 0.93 and 0.91, respectively). Discrimination and calibration of both risk tools were retained among specific patient subgroups, in the validation samples, and when used to estimate 30-day mortality rates among Medicare patients.

CONCLUSIONS

Risks for early mortality following PCI can be accurately predicted in contemporary practice. Incorporation of such risk tools should facilitate research, clinical decisions, and policy applications.

Validation of the Mayo Clinic Risk Score for In-Hospital Mortality After Percutaneous Coronary Interventions Using the National Cardiovascular Data Registry

Background— We sought to validate the recently developed Mayo Clinic Risk Score model for in-hospital mortality after percutaneous coronary intervention using an independent data set. The Mayo Clinic Risk Score has 7 simple clinical and noninvasive variables, available before coronary angiography, for prediction of in-hospital mortality. External validation using an independent data set would support broader applicability of the model.

Methods and Results— In-hospital mortality after percutaneous coronary intervention on 309 351 patients from the National Cardiovascular Data Registry admitted from January 1, 2004, to March, 30, 2006, was studied. Using the Mayo Clinic Risk Score equation, we assigned predicted probabilities of death to each patient. The area under the receiver-operating characteristics curve was 0.884, indicating excellent discrimination overall as well as among subgroups, including gender, diabetes mellitus, renal failure, low ejection fraction, different age groups, and multivessel disease. Ninety-seven percent of patients undergoing percutaneous coronary intervention had a Mayo Clinic Risk Score <10, indicating low to intermediate risk. The Mayo Clinic Risk Score model initially slightly underpredicted event rates when applied in National Cardiovascular Data Registry data (observed 1.23% versus predicted 1.10%), but this underprediction was corrected after recalibration. The recalibrated risk score discriminated (c index=0.885) and calibrated well in an National Cardiovascular Data Registry validation data set consisting of procedures performed between April 1, 2006, and March 30, 2007.

Conclusions— Seven variables can be combined into a convenient risk scoring system before coronary angiography is performed to predict in-hospital mortality after percutaneous coronary intervention. This model may be useful for providing patients with individualized, evidence-based estimates of procedural risk as part of the informed consent process before percutaneous coronary intervention.

Comorbid conditions and outcomes after percutaneous coronary intervention

OBJECTIVE

To evaluate whether adding comorbid conditions to a risk model can help predict in-hospital outcome and long-term mortality after percutaneous coronary intervention (PCI).

DESIGN

Retrospective chart review

SETTING

Academic medical centre.

PATIENTS

7659 patients who had 9032 PCIs.

INTERVENTIONS

PCI performed at Mayo Clinic between 1 January 1999 and 30 June 2004.

MAIN OUTCOME MEASURES

The Mayo Clinic Risk Score (MCRS) and the coronary artery disease (CAD)-specific index for determination of comorbid conditions in all patients.

RESULTS

The mean (SD) MCRS score was 6.5 (2.9). The CAD-specific index was 0 or 1 in 46%, 2 or 3 in 30% and 4 or higher in 24%. The rate of in-hospital major adverse cardiovascular events (MACE) increased with higher MCRS and CAD-specific index (Cochran-Armitage test, p<0.001 for both models). The c-statistic for the MCRS for in-hospital MACE was 0.78; adding the CAD-specific index did not improve its discriminatory ability for in-hospital MACE (c-statistic = 0.78; likelihood ratio test, p = 0.29). A total of 707 deaths after dismissal occurred after 7253 successful procedures. The c-statistic for all-cause mortality was 0.69 for the MCRS model alone and 0.75 for the MCRS and CAD-specific indices together (likelihood ratio test, p<0.001), indicating significant improvement in the discriminatory ability.

CONCLUSIONS

Addition of comorbid conditions to the MCRS adds significant prognostic information for post-dismissal mortality but adds little prognostic information about in-hospital complications after PCI. Such health-status measures should be included in future risk stratification models that predict long-term mortality after PCI.

Discrimination and calibration of mortality risk prediction models in interventional cardiology

OBJECTIVES

Using a local percutaneous coronary intervention (PCI) data repository, we sought to compare the performance of a number of local and well-known mortality models with respect to discrimination and calibration.

BACKGROUND

Accurate risk prediction is important for a number of reasons including physician decision support, quality of care assessment, and patient education. Current evidence on the value of applying PCI risk models to individual cases drawn from a different population is controversial.

METHODS

Data were collected from January 01, 2002 to September 30, 2004 on 5216 consecutive percutaneous coronary interventions at Brigham and Women's Hospital (Boston, MA). Logistic regression was used to create a local risk model for in-hospital mortality in these procedures, and a number of statistical methods were used to compare the discrimination and calibration of this new and old local risk models, as well as the Northern New England Cooperative Group, New York State (1992 and 1997), University of Michigan consortium, American College of Cardiology-National Cardiovascular Data Registry, and The Cleveland Clinic Foundation risk prediction models. Areas under the ROC (AUC) curves were used to evaluate discrimination, and the Hosmer-Lemeshow (HL) goodness-of-fit test and calibration curves assessed applicability of the models to individual cases.

RESULTS

Multivariate risk factors included in the newly constructed local model were: age, prior intervention, diabetes, unstable angina, salvage versus elective procedure, cardiogenic shock, acute myocardial infarction (AMI), and left anterior descending artery intervention. The area under the ROC curve (AUC) was 0.929 (SE=0.017), and the p value for the Hosmer-Lemeshow (HL) goodness-of-fit was 0.473. This indicates good discrimination and calibration. Bootstrap re-sampling indicated AUC stability. Evaluation of the external models showed an AUC range from 0.82 to 0.90 indicating good discrimination across all models, but poor calibration (HL p value < or = 0.0001).

CONCLUSIONS

Validation of AUC values across all models suggests that certain risk factors have remained important over the last decade. However, the lack of calibration suggests that small changes in patient populations and data collection methods quickly reduce the accuracy of patient level estimations over time. Possible solutions to this problem involve either recalibration of models using local data or development of new local models.

Public Reporting and Case Selection for Percutaneous Coronary Interventions

OBJECTIVES

The purpose of this research was to determine the potential effect of public reporting on case selection for percutaneous coronary intervention (PCI).

BACKGROUND

Previous studies have suggested that public reporting of coronary artery bypass graft surgery (CABG) mortality might result in case selection bias and in denial of care to or out migration of high-risk patients. The potential effect of public reporting on case selection for PCI is unknown.

METHODS

We compared demographics, indications, and outcomes of 11,374 patients included in a multicenter (eight hospitals) PCI database in Michigan where no public reporting is present, with 69,048 patients in a statewide (34 hospitals) PCI database in New York, where public reporting is present. The primary end point was in-hospital mortality.

RESULTS

Patients in Michigan more frequently underwent PCI for acute myocardial infarction (14.4% vs. 8.7%, p < 0.0001) and cardiogenic shock (2.56% vs. 0.38%, p < 0.0001) than those in New York. The Michigan cohort also had a higher prevalence of congestive heart failure and extracardiac vascular disease. The unadjusted in-hospital mortality rate was significantly lower in New York than in Michigan (0.83% vs. 1.54%, p < 0.0001; odds ratio [OR] 0.54, 95% confidence interval [CI] 0.45 to 0.63). However, after adjustment for comorbidities, there was no significant difference in mortality between the two groups (adjusted OR 1.05, 95% CI 0.84 to 1.31, p = 0.70, c-statistic 0.88).

CONCLUSIONS

There are significant differences in case mix between patients undergoing PCI in Michigan and New York that result in marked differences in unadjusted mortality rates. A propensity in New York toward not intervening on higher-risk patients because of fear of public reporting of high mortality rates is a possible explanation for these differences.

Risk stratification and interventional cardiology: Robert L. Frye Lecture

Risk stratification and risk-benefit ratios are extremely important in guiding patient-physician interactions as well as patient and family counseling. Risks associated with percutaneous transluminal coronary angioplasty are (1) compromise of the vessel lumen or vessel integrity, (2) unsuccessful procedure, and (3) restenosis. Predicting mortality risk depends on the specific patient population to be treated and on the specific mortality model used. The most common models are those from New York State, the American College of Cardiology, the Northern New England Cooperative Group, the University of Michigan, and The Cleveland Clinic Foundation. As more data and sophisticated analyses become available, risk stratification will become more accurate as long as the approach used is straightforward, makes intuitive sense, and is easy and efficient to apply.

Validation of Mayo clinic risk adjustment model for in-hospital complications after percutaneous coronary interventions, using the National Heart, Lung, and Blood Institute dynamic registry

OBJECTIVES

We sought to validate the recently proposed Mayo Clinic risk score model for complications after percutaneous coronary interventions (PCI), using an independent data set.

BACKGROUND

The Mayo Clinic risk score has eight simple clinical and angiographic variables for the prediction of complications defined as either death, Q-wave myocardial infarction, emergent or urgent coronary artery bypass graft surgery, or cerebrovascular accident after PCI. External validation using an independent data set is lacking.

METHODS

A total of 3,264 patients undergoing PCI at each of the 17 sites in the National Heart, Lung, and Blood Institute's Dynamic Registry during two enrollment periods (July 1997 to February 1998 and February to June 1999) were studied. Logistic regression was used to model the calculated risk score and major procedural complications. The expected number of complications, with 95% confidence bounds (CBs), was also calculated.

RESULTS

There were 96 (2.94%) observed procedural complications, and the Mayo Clinic risk score predicted 93.5 events (2.86%; 95% CB 2.32% to 3.41%; p = NS). The Hosmer-Lemeshow goodness-of-fit p value was 0.28, and the area under the receiver operating curve was 0.76, indicating excellent overall discrimination. There were no statistical differences between observed and predicted procedural complications using the Mayo Clinic risk score among the most selected high- and low-risk subgroups.

CONCLUSIONS

Eight variables were combined into a convenient risk scoring system that accurately predicts cardiovascular complications after PCI. The Mayo clinic predictive model for procedural complications yielded excellent results when applied to a multi-center external data set.

Modeling and risk prediction in the current era of interventional cardiology: a report from the National Heart, Lung, and Blood Institute Dynamic Registry

BACKGROUND

Validation of in-hospital mortality models after percutaneous coronary interventions using multicenter data remains limited.

METHODS AND RESULTS

This study evaluated whether multivariable mortality models developed during the pre-stent era by New York State, American College of Cardiology (ACC)-National Cardiovascular Data Registry, Northern New England Cooperative Group, Cleveland Clinic Foundation, and the University of Michigan are relevant in patients undergoing percutaneous coronary intervention in the 1997 to 1999 National Heart, Lung, and Blood Institute Dynamic Registry. Of 4448 Dynamic Registry patients, 73% received > or =1 stent and 28% received a IIB/IIIA receptor inhibitor. In-hospital mortality occurred in 64 patients (1.4%). The New York state model predicted mortality in 69 patients (1.5%; 95% confidence bounds [CI], 0.89% to 1.70%); Northern New England predicted mortality in 60 patients (1.3%; 95% CI, 1.0% to 1.7%); and Cleveland Clinic predicted mortality in 76 patients (1.7%; 95% CI, 1.3% to 2.1%). Among high-risk subgroups, with these 3 models, observed and predicted in-hospital mortality rates in general were not different. The other 2 models yielded different results. The University of Michigan predicted fewer deaths (n=47; 1.1%; 95% CI, 0.7% to 1.3%), and the ACC Registry model predicted 603 deaths (13.5%; 95% CI, 12.6% to 14.4%). Using the ACC Registry model, predicted mortality was higher than observed in each subgroup.

CONCLUSIONS

Application of 5 mortality risk models developed from different data sets to patients undergoing percutaneous coronary intervention in the Dynamic Registry predicted, in 3 models, mortality rates that were not significantly different than those observed. In both high and low risk subgroups, the University of Michigan slightly underpredicted mortality, and the ACC Registry predicted significantly higher mortality than that observed.

Correlates of procedural complications and a simple integer risk score for percutaneous coronary intervention

OBJECTIVES

Our goals were to identify clinical and angiographic risk factors associated with major cardiovascular complications of percutaneous coronary intervention (PCI) (in-hospital death, Q-wave myocardial infarction, urgent or emergent coronary artery bypass surgery and stroke) and to construct a simple score for risk stratification.

BACKGROUND

Both clinical and angiographic features influence risk of PCIs.

METHODS

Percutaneous coronary interventions performed between January 1, 1996, and December 31, 1999, were analyzed. Logistic regression and bootstrap methods were used to create an integer risk score for estimating the risk of procedural complications using baseline, angiographic and procedural characteristics. The risk score was tested in a validation-set consisting of all procedures performed in the year 2000.

RESULTS

Among 5,463 procedures, 5 clinical and 3 angiographic variables were significantly correlated with procedural complications: cardiogenic shock, left main coronary artery disease, severe renal disease, urgent or emergent procedure, congestive heart failure class III or higher, thrombus, multivessel disease and older age. In the validation-set, the model fitted the data adequately; the average receiver operating characteristic curve area was 0.782 (standard deviation, 0.018).

CONCLUSIONS

Eight variables were combined into a convenient bedside risk scoring system that estimates the risk of complications after PCIs.

Intra-aortic balloon pump placement following aorto-iliac angioplasty and stent placement

Approximately 20% of patients are unable to receive an intra-aortic balloon pump (IABP) due to aorto-iliac atherosclerotic disease. Aorto-iliac stenoses can be managed with angioplasty or stent placement; however, there are limited data about this strategy to facilitate IABP placement. Thirty-seven IABPs were placed in 35 patients. A total of 45 revascularization procedures were performed. With revascularization, the minimal lumen diameter increased from 2.78 +/- 1.46 to 6.75 +/- 2.36 mm (P < 0.0001). Limb ischemia occurred following 2/37 (5%) IABP insertions. Limb ischemia was managed with IABP removal and angioplasty. The mortality rate was 32%. Mortality was more common with chronic renal insufficiency (8/11, 73%; P = 0.0014), dialysis-dependent renal failure (3/3, 100%; P = 0.028), and presentation with acute myocardial infarction (8/15 patients, 53%; P = 0.036). Although no patients required vascular surgery for limb ischemia, one patient required surgery for bleeding. Angioplasty or stenting to facilitate IABP placement in patients with peripheral vascular disease is safe and effective.