Machine learning prediction model of acute kidney injury after percutaneous coronary intervention

Using the Super Learner algorithm to predict risk of major adverse cardiovascular events after percutaneous coronary intervention in patients with myocardial infarction

BACKGROUND

The primary treatment for patients with myocardial infarction (MI) is percutaneous coronary intervention (PCI). Despite this, the incidence of major adverse cardiovascular events (MACEs) remains a significant concern. Our study seeks to optimize PCI predictive modeling by employing an ensemble learning approach to identify the most effective combination of predictive variables.

METHODS AND RESULTS

We conducted a retrospective, non-interventional analysis of MI patient data from 2018 to 2021, focusing on those who underwent PCI. Our principal metric was the occurrence of 1-year postoperative MACEs. Variable selection was performed using lasso regression, and predictive models were developed using the Super Learner (SL) algorithm. Model performance was appraised by the area under the receiver operating characteristic curve (AUC) and the average precision (AP) score. Our cohort included 3,880 PCI patients, with 475 (12.2%) experiencing MACEs within one year. The SL model exhibited superior discriminative performance, achieving a validated AUC of 0.982 and an AP of 0.971, which markedly surpassed the traditional logistic regression models (AUC: 0.826, AP: 0.626) in the test cohort. Thirteen variables were significantly associated with the occurrence of 1-year MACEs.

CONCLUSION

Implementing the Super Learner algorithm has substantially enhanced the predictive accuracy for the risk of MACEs in MI patients. This advancement presents a promising tool for clinicians to craft individualized, data-driven interventions to better patient outcomes.

Predictive modeling for acute kidney injury after percutaneous coronary intervention in patients with acute coronary syndrome: a machine learning approach

BACKGROUND

Acute kidney injury (AKI) is one of the preventable complications of percutaneous coronary intervention (PCI). This study aimed to develop machine learning (ML) models to predict AKI after PCI in patients with acute coronary syndrome (ACS).

METHODS

This study was conducted at Tehran Heart Center from 2015 to 2020. Several variables were used to design five ML models: Naïve Bayes (NB), Logistic Regression (LR), CatBoost (CB), Multi-layer Perception (MLP), and Random Forest (RF). Feature importance was evaluated with the RF model, CB model, and LR coefficients while SHAP beeswarm plots based on the CB model were also used for deriving the importance of variables in the population using pre-procedural variables and all variables. Sensitivity, specificity, and the area under the receiver operating characteristics curve (ROC-AUC) were used as the evaluation measures.

RESULTS

A total of 4592 patients were included, and 646 (14.1%) experienced AKI. The train data consisted of 3672 and the test data included 920 cases. The patient population had a mean age of 65.6 ± 11.2 years and 73.1% male predominance. Notably, left ventricular ejection fraction (LVEF) and fasting plasma glucose (FPG) had the highest feature importance when training the RF model on only pre-procedural features. SHAP plots for all features demonstrated LVEF and age as the top features. With pre-procedural variables only, CB had the highest AUC for the prediction of AKI (AUC 0.755, 95% CI 0.713 to 0.797), while RF had the highest sensitivity (75.9%) and MLP had the highest specificity (64.35%). However, when considering pre-procedural, procedural, and post-procedural features, RF outperformed other models (AUC: 0.775). In this analysis, CB achieved the highest sensitivity (82.95%) and NB had the highest specificity (82.93%).

CONCLUSION

Our analyses showed that ML models can predict AKI with acceptable performance. This has potential clinical utility for assessing the individualized risk of AKI in ACS patients undergoing PCI. Additionally, the identified features in the models may aid in mitigating these risk factors.

Enhancing Coronary Intervention Outcomes Using Intravascular Ultrasound: Analysis of Long-Term Benefits in a Japanese Multicenter Registry

Background

Although the use of intravascular ultrasound (IVUS) during percutaneous coronary intervention (PCI) has been shown to improve clinical outcomes, its utilization remains inconsistent. We aimed to assess the association between IVUS-guided PCI and long-term outcomes in Japan, where a high proportion of patients undergo IVUS.

Methods

We analyzed 8721 consecutive patients in a multicenter PCI registry. The primary outcome was a composite of death, acute coronary syndrome, and heart failure requiring admission and coronary artery bypass grafting at 2 years after discharge. The secondary outcome was each component of the primary outcome. We used inverse probability-weighted analysis for adjustment. Subgroup analysis was conducted on patients with complex coronary anatomy (eg, those with bifurcation, chronic total occlusion, type C lesion, left main and those who underwent rotational atherectomy).

Results

Overall, 83.8% of patients underwent IVUS-guided PCI (mean age, 68.3 ± 11.3 years). After adjustments, the IVUS group had significantly lower rates of death and coronary bypass compared to no IVUS group (hazard ratio [HR], 0.73; 95% CI, 0.55-0.96; and HR, 0.62; 95% CI, 0.39-0.98) at 2-year follow-up, although the primary outcome showed only marginal differences (HR, 0.85; 95% CI, 0.71-1.01). In the subgroup analysis of complex coronary anatomy, the use of IVUS was significantly associated with a reduced risk of the primary outcome (HR, 0.72; 95% CI, 0.55-0.93) as well as death, coronary bypass, and heart failure.

Conclusions

IVUS was frequently utilized in our registry and demonstrated potential benefit in reducing mortality and need for coronary bypass surgery, particularly in patients with complex coronary anatomy.

Long-term outcomes of periprocedural coronary dissection and perforation for patients undergoing percutaneous coronary intervention in a Japanese multicenter registry

Long-term outcomes of iatrogenic coronary dissection and perforation in patients undergoing percutaneous coronary intervention (PCI) remains under-investigated. We analyzed 8,721 consecutive patients discharged after PCI between 2008 and 2019 from Keio Cardiovascular (KiCS) PCI multicenter prospective registry in the Tokyo metropolitan area. Significant coronary dissection was defined as persistent contrast medium extravasation or spiral or persistent filling defects with complete distal and impaired flow. The primary outcome was a composite of all-cause death, acute coronary syndrome, heart failure, bleeding, stroke requiring admission, and coronary artery bypass grafting two years after discharge. We used a multivariable Cox hazard regression model to assess the effects of these complications. Among the patients, 68 (0.78%) had significant coronary dissections, and 61 (0.70%) had coronary perforations at the index PCI. Patients with significant coronary dissection had higher rates of the primary endpoint and heart failure than those without (25.0% versus 14.3%, P = 0.02; 10.3% versus 4.2%, P = 0.03); there were no significant differences in the primary outcomes between the patients with and without coronary perforation (i.e., primary outcome: 8.2% versus 14.5%, P = 0.23) at the two-year follow-up. After adjustments, patients with coronary dissection had a significantly higher rate of the primary endpoint than those without (HR 1.70, 95% CI 1.02-2.84; P = 0.04), but there was no significant difference in the primary endpoint between the patients with and without coronary perforation (HR 0.51, 95% CI 0.21-1.23; P = 0.13). For patients undergoing PCI, significant coronary dissection was associated with poor long-term outcomes, including heart failure readmission.

Gender Differences in Long-Term Outcomes of Young Patients Who Underwent Percutaneous Coronary Intervention: Long-Term Outcome Analysis from a Multicenter Registry in Japan

Young patients who underwent percutaneous coronary intervention (PCI) have shown worse long-term outcomes but remain inadequately investigated. We analyzed 1,186 consecutive young patients (aged ≤55 years) from the Keio Cardiovascular PCI registry who were successfully discharged after PCI (2008 to 2019) and compared them to 5,048 older patients (aged 55 to 75 years). The primary outcome was a composite of all-cause death, acute coronary syndrome, heart failure, bleeding, stroke requiring admission, and coronary artery bypass grafting within 2 years after discharge. In the young patients, the mean age was 48.4 ± 5.4 years, acute coronary syndrome cases accounted for 69.6%, and 92 (7.8%) were female. Body mass index; hemoglobin levels; and proportions of smoking, hyperlipidemia, and ST-elevation myocardial infarction were lower and dialysis or active cancer proportions were higher in young female patients than male patients. A higher number of young female than male patients reached the primary end point and all-cause death (15.2% vs 7.1%, p = 0.01; 4.3% vs 1.0%, p = 0.023), mainly because of noncardiac death (4.3% versus 0.5%, p = 0.001). After covariate adjustment, the primary end point rates were higher among young women than men (hazard ratio 2.00, 95% confidence interval 1.03 to 3.89, p = 0.042). Gender did not predict the primary end point among older patients (vs men; hazard ratio 0.84, 95% confidence interval 0.67 to 1.06, p = 0.14). In conclusion, young women showed worse outcomes during the 2-year post-PCI follow-up, but this gender difference was absent in patients aged 55 to 75 years.

Data heterogeneity in federated learning with Electronic Health Records: Case studies of risk prediction for acute kidney injury and sepsis diseases in critical care

With the wider availability of healthcare data such as Electronic Health Records (EHR), more and more data-driven based approaches have been proposed to improve the quality-of-care delivery. Predictive modeling, which aims at building computational models for predicting clinical risk, is a popular research topic in healthcare analytics. However, concerns about privacy of healthcare data may hinder the development of effective predictive models that are generalizable because this often requires rich diverse data from multiple clinical institutions. Recently, federated learning (FL) has demonstrated promise in addressing this concern. However, data heterogeneity from different local participating sites may affect prediction performance of federated models. Due to acute kidney injury (AKI) and sepsis' high prevalence among patients admitted to intensive care units (ICU), the early prediction of these conditions based on AI is an important topic in critical care medicine. In this study, we take AKI and sepsis onset risk prediction in ICU as two examples to explore the impact of data heterogeneity in the FL framework as well as compare performances across frameworks. We built predictive models based on local, pooled, and FL frameworks using EHR data across multiple hospitals. The local framework only used data from each site itself. The pooled framework combined data from all sites. In the FL framework, each local site did not have access to other sites' data. A model was updated locally, and its parameters were shared to a central aggregator, which was used to update the federated model's parameters and then subsequently, shared with each site. We found models built within a FL framework outperformed local counterparts. Then, we analyzed variable importance discrepancies across sites and frameworks. Finally, we explored potential sources of the heterogeneity within the EHR data. The different distributions of demographic profiles, medication use, and site information contributed to data heterogeneity.

Performance of resistive index and semi-quantitative power doppler ultrasound score in predicting acute kidney injury: A meta-analysis of prospective studies

This study aimed to assess the predictive value of the renal resistive index (RRI) and power Doppler ultrasound (PDU) on subsequent acute kidney injury (AKI) risk using a meta-analytic approach. We searched eligible studies in PubMed, EmBase, and the Cochrane library from inception until August 2021. The parameters included the sensitivity, specificity, positive and negative likelihood ratios (PLR and NLR), diagnostic odds ratio (DOR), and area under the receiver operating characteristic curves (AUC). Twenty-three prospective studies involving 2,400 patients were selected. The pooled sensitivity and specificity of the RRI and PDU were 0.76 and 0.79, and 0.64 and 0.90, respectively. The pooled PLR and NLR were 3.64 and 0.31, and 6.58 and 0.40 for the RRI and PDU, respectively. The DORs of the RRI and PDU for predicting AKI were 11.76, and 16.32, respectively. The AUCs of the RRI and PDU for predicting AKI were 0.83, and 0.86, respectively. There were no significant differences between the RRI and PDU for predicting AKI in terms of sensitivity, PLR, NLR, DOR, and AUC. The specificity of the RRI was lower than that of the PDU for predicting AKI. This study found that the predictive performance of the RRI and PDU from the Doppler ultrasound for AKI was similar, which need to be further verified based on the direct comparison results.