Association of decreasing hemoglobin levels with the incidence of acute kidney injury after percutaneous coronary intervention: a prospective multi-center study

Risk Factors for Acute Kidney Injury in Adult Patients Under Veno-Arterial Extracorporeal Membrane Oxygenation Support

OBJECTIVE

To investigate the incidence and risk factors of acute kidney injury (AKI) stage 3 in adult patients under veno-arterial extracorporeal membrane oxygenation (VA-ECMO) support.

DESIGN

A retrospective case-control study.

SETTING

Single center, Fuwai Hospital.

PARTICIPANTS

Adult VA-ECMO patients age ≥18 years and older treated between January 2020 and December 2022 were included.

INTERVENTIONS

The patients were grouped by whether they developed AKI Kidney Disease: Improving Global Outcomes (KDIGO) stage 3 or <3. Multivariate logistic regression was performed t"o evaluate risk factors of AKI stage 3.

MEASUREMENTS AND MAIN RESULTS

Among enrolled patients, 40 (53.3%) developed AKI stage 3. The in-hospital mortality of AKI stage 3 patients was significantly higher than that of AKI stage <3 patients (67.5% vs 34.3%; p = 0.004). Multivariate logistic regression analysis revealed that concomitant hypertension (odds ratio [OR], 0.250; 95% confidence interval [CI], 0.063, 0.987), p = 0.048), pre-ECMO hemoglobin (OR, 0.969; 95% CI, 0.947-0.992; p = 0.009), pre-ECMO lactate (OR, 1.173; 95% CI, 1.028-1.339; p = 0.018), and pre-ECMO creatinine (OR, 1.014; 95% CI, 1.003-1.025; p = 0.011) were independent risk factors for AKI stage 3.

CONCLUSIONS

This study found a high incidence (53.3%) of AKI stage 3 in adult patients with VA-ECMO support and an association with increased in-hospital mortality. Concomitant hypertension, low pre-ECMO hemoglobin, and elevated pre-ECMO lactate and pre-ECMO creatinine were independent risk factors for AKI stage 3 in patients receiving VA-ECMO. It is imperative to identify and adjust these risk factors to enhance outcomes for those supported by VA-ECMO.

Accuracy of machine learning in predicting outcomes post-percutaneous coronary intervention: a systematic review

Background

Recent studies have shown potential in introducing machine learning (ML) algorithms to predict outcomes post-percutaneous coronary intervention (PCI).

Aims

We aimed to critically appraise current ML models' effectiveness as clinical tools to predict outcomes post-PCI.

Methods

Searches of four databases were conducted for articles published from the database inception date to 29 May 2021. Studies using ML to predict outcomes post-PCI were included. For individual post-PCI outcomes, measures of diagnostic accuracy were extracted. An adapted checklist comprising existing frameworks for new risk markers, diagnostic accuracy, prognostic tools and ML was used to critically appraise the included studies along the stages of the translational pathway: development, validation, and impact. Quality of training data and methods of dealing with missing data were evaluated.

Results

Twelve cohorts from 11 studies were included with a total of 4,943,425 patients. ML models performed with high diagnostic accuracy. However, there are concerns over the development of the ML models. Methods of dealing with missing data were problematic. Four studies did not discuss how missing data were handled. One study removed patients if any of the predictor variable data points were missing. Moreover, at the validation stage, only three studies externally validated the models presented. There could be concerns over the applicability of these models. None of the studies discussed the cost-effectiveness of implementing the models.

Conclusions

ML models show promise as a useful clinical adjunct to traditional risk stratification scores in predicting outcomes post-PCI. However, significant challenges need to be addressed before ML can be integrated into clinical practice.

Impact of anemia on outcomes and resource utilization in patients with myocardial infarction: A national database analysis

BACKGROUND

Although anemia is common in patients with myocardial infarction (MI), management remains controversial. We quantified the association of anemia with in-hospital outcomes and resource utilization in patients admitted with MI using a large national database.

METHODS

All hospitalizations with a primary diagnosis code for acute MI in the National Inpatient Sample (NIS) between 2014 and 2018 were identified. Among these hospitalizations, patients with anemia were identified using a secondary diagnosis code. Data on demographic and clinical variables were collected. Outcomes of interest included in-hospital adverse events, length of stay (LOS), and total cost. Multivariable logistic regression and generalized linear models were used to evaluate the relationship between anemia and outcomes.

RESULTS

Among 1,113,181 MI hospitalizations, 254,816 (22.8%) included concomitant anemia. Anemic patients were older and more likely to be women. After adjustment for demographics and comorbidities, anemia was associated with higher mortality (7.1 vs. 4.3%; odds ratio 1.09; 95% confidence interval [CI] 1.07-1.12, p < 0.001). Anemia was also associated with a mean of 2.71 days longer LOS (average marginal effects [AME] 2.71; 95% CI 2.68-2.73, p < 0.05), and $ 9703 mean higher total costs (AME $9703, 95% CI $9577-$9829, p < 0.05). Anemic patients who received blood transfusions had higher mortality as compared with those who did not (8.2% vs. 7.0, p < 0.001).

CONCLUSION

In MI patients, anemia was associated with higher in-hospital mortality, adverse events, total cost, and length of stay. Transfusion was associated with increased mortality, and its role in MI requires further research.

Prediction of Acute Kidney Injury in Intracerebral Hemorrhage Patients Using Machine Learning

Background

Acute kidney injury (AKI) is prevalent in patients with intracerebral hemorrhage (ICH) and is associated with mortality. This study aimed to verify the predictive accuracy of different machine learning algorithms for AKI in patients with ICH using a large dataset.

Methods

A total of 1366 ICH patients received treatments between 2001 and 2012 from the Medical Information Mart for Intensive Care-III (MIMIC-III) database were identified based on the ICD-9 code: 431. The main outcome of AKI during hospitalizations was confirmed based on the KDIGO criteria. Overall, ICH patients were randomly divided into the training cohort and validation cohort with the ratio of 7:3. Six machine learning algorithms including extreme gradient boosting, logistic, light gradient boosting machine, random forest, adaptive boosting, support vector machine were trained in the training cohort with the 5-fold cross-validation method to predict the AKI. The predictive accuracy of those algorithms was compared by area under the receiver operating characteristics curve (AUC).

Results

A total of 1213 ICH patients were included with the incidence of AKI being 29.3%. The incidence of AKI was 29.3% among the 1213 patients with ICH. The AKI group had higher 30-day mortality (p<0.001), longer ICU stay (p<0.001), and longer hospital stay (p<0.001). Among the six machine learning algorithms, the random forest performed the best in predicting AKI in both the training cohort (AUC=1.000) and the validation cohort (AUC=0.698). The top five features in the random forest algorithm-based model were platelets, serum creatinine, vancomycin, hemoglobin, and hematocrit.

Conclusion

The random forest algorithm-based predictive model we developed incorporating important features, including platelet count, serum creatinine level, vancomycin level, hemoglobin level, and hematocrit level, performed the best in predicting AKI among patients with ICH.

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.

Continuous and early prediction of future moderate and severe Acute Kidney Injury in critically ill patients: Development and multi-centric, multi-national external validation of a machine-learning model

BACKGROUND

Acute Kidney Injury (AKI) is a major complication in patients admitted to Intensive Care Units (ICU), causing both clinical and economic burden on the healthcare system. This study develops a novel machine-learning (ML) model to predict, with several hours in advance, the AKI episodes of stage 2 and 3 (according to KDIGO definition) acquired in ICU.

METHODS

A total of 16'760 ICU adult patients from 145 different ICU centers and 3 different countries (US, Netherland, Italy) are retrospectively enrolled for the study. Every hour the model continuously analyzes the routinely-collected clinical data to generate a new probability of developing AKI stage 2 and 3, according to KDIGO definition, during the ICU stay.

RESULTS

The predictive model obtains an auROC of 0.884 for AKI (stage 2/3 KDIGO) prediction, when evaluated on the internal test set composed by 1'749 ICU stays from US and EU centers. When externally tested on a multi-centric US dataset of 6'985 ICU stays and multi-centric Italian dataset of 1'025 ICU stays, the model achieves an auROC of 0.877 and of 0.911, respectively. In all datasets, the time between model prediction and AKI (stage 2/3 KDIGO) onset is at least of 14 hours after the first day of ICU hospitalization.

CONCLUSIONS

In this study, a novel ML model for continuous and early AKI (stage 2/3 KDIGO) prediction is successfully developed, leveraging only routinely-available data. It continuously predicts AKI episodes during ICU stay, at least 14 hours in advance when the AKI episode happens after the first 24 hours of ICU admission. Its performances are validated in an extensive, multi-national and multi-centric cohort of ICU adult patients. This ML model overcomes the main limitations of currently available predictive models. The benefits of its real-world implementation enable an early proactive clinical management and the prevention of AKI episodes in ICU patients. Furthermore, the software could be directly integrated with IT system of the ICU.

In-Hospital Bleeding in Elderly Patients With Acute Coronary Syndrome: Are Potent Antiplatelet Agents Safe?

Despite implementation of new interventional techniques and therapeutic advances, elderly patients with acute coronary syndrome (ACS) continue to be susceptible to in-hospital bleeding compared with younger ones. Thus, we investigated the incidence of in-hospital bleeding events and associated risk factors in elderly (≥ 75°years) ACS patients. We also wanted to define the bleeding sites, characteristics, and associated mortality. Bleeding Academic Research Consortium (BARC) classification type 2, 3, or 5 was used to define bleeding events. Overall, 539 patients were included in the study (mean age: 82.5 ± 4.8°years; 282 (52.3%) females). Of these patients, 69 (12.8%) developed in-hospital bleeding. Factors that were independently related with in-hospital bleeding were age (odds ratio (OR): 1.08; 95% confidence interval (CI): 1.011.14, P = .01), acute kidney injury (OR: 3.66; 95% CI: 2.016.69; P < .01), tirofiban (OR: 4.43; 95% CI: 1.7810.99; P < .01), and ticagrelor (OR: 1.93; 95% CI: 1.013.73; P = .04) administration. The urinary tract was the most frequent bleeding site, followed by femoral arteries. In conclusion, ticagrelor and tirofiban should be used with caution in elderly ACS patients.

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

Acute kidney injury (AKI) after percutaneous coronary intervention (PCI) is associated with a significant risk of morbidity and mortality. The traditional risk model provided by the National Cardiovascular Data Registry (NCDR) is useful for predicting the preprocedural risk of AKI, although the scoring system requires a number of clinical contents. We sought to examine whether machine learning (ML) techniques could predict AKI with fewer NCDR-AKI risk model variables within a comparable PCI database in Japan. We evaluated 19,222 consecutive patients undergoing PCI between 2008 and 2019 in a Japanese multicenter registry. AKI was defined as an absolute or a relative increase in serum creatinine of 0.3 mg/dL or 50%. The data were split into training (N = 16,644; 2008-2017) and testing datasets (N = 2578; 2017-2019). The area under the curve (AUC) was calculated using the light gradient boosting model (GBM) with selected variables by Lasso and SHapley Additive exPlanations (SHAP) methods among 12 traditional variables, excluding the use of an intra-aortic balloon pump, since its use was considered operator-dependent. The incidence of AKI was 9.4% in the cohort. Lasso and SHAP methods demonstrated that seven variables (age, eGFR, preprocedural hemoglobin, ST-elevation myocardial infarction, non-ST-elevation myocardial infarction/unstable angina, heart failure symptoms, and cardiogenic shock) were pertinent. AUC calculated by the light GBM with seven variables had a performance similar to that of the conventional logistic regression prediction model that included 12 variables (light GBM, AUC [training/testing datasets]: 0.779/0.772; logistic regression, AUC [training/testing datasets]: 0.797/0.755). The AKI risk model after PCI using ML enabled adequate risk quantification with fewer variables. ML techniques may aid in enhancing the international use of validated risk models.

The association of hemoglobin drop with in-hospital outcomes in COVID-19 patients

BACKGROUND

Bleeding events can be critical in hospitalized patients with COVID-19, especially those with aggressive anticoagulation therapy.

AIM

We aimed to investigate whether hemoglobin drop was associated with increased risk of acute kidney injury (AKI) and in-hospital mortality among patients with COVID-19.

DESIGN

Retrospective cohort study.

METHODS

This retrospective study was conducted by review of the medical records of 6683 patients with laboratory-confirmed COVID-19 hospitalized in the Mount Sinai Health system between 1st March 2020 and 30th March 2021. We compared patients with and without hemoglobin drop >3 g/dl during hospitalization within a week after admissions, using inverse probability treatment weighted analysis (IPTW). Outcomes of interest were in-hospital mortality and AKI which was defined as serum creatine change of 0.3 mg/dl increase or 1.5 times baseline.

RESULTS

Of the 6683 patients admitted due to COVID-19, 750 (11.2%) patients presented with a marked hemoglobin drop. Patients with hemoglobin drop were more likely to receive therapeutic anticoagulation within 2 days after admissions. Patients with hemoglobin drop had higher crude in-hospital mortality (40.8% vs. 20.0%, P < 0.001) as well as AKI (51.4% vs. 23.9%, P < 0.001) compared to those without. IPTW analysis showed that hemoglobin drop was associated with higher in-hospital mortality compared to those without (odds ratio (OR) [95% confidential interval (CI)]: 2.21 [1.54-2.88], P < 0.001) as well as AKI (OR [95% CI]: 2.79 [2.08-3.73], P < 0.001).

CONCLUSIONS

Hemoglobin drop during COVID-19 related hospitalizations was associated with a higher risk of AKI and in-hospital mortality.

Association of the Hemoglobin to Serum Creatinine Ratio with In-Hospital Adverse Outcomes after Percutaneous Coronary Intervention among Non-Dialysis Patients: Insights from a Japanese Nationwide Registry (J-PCI Registry)

Although baseline hemoglobin and renal function are both important predictors of adverse outcomes after percutaneous coronary intervention (PCI), scarce data exist regarding the combined impact of these factors on outcomes. We sought to investigate the impact and threshold value of the hemoglobin to creatinine (Hgb/Cr) ratio, on in-hospital adverse outcomes among non-dialysis patients in a Japanese nationwide registry. We analyzed 157,978 non-dialysis patients who underwent PCI in 884 Japanese medical institutions in 2017. We studied differences in baseline characteristics and in-hospital clinical outcomes among four groups according to their quartiles of the Hgb/Cr ratios. Compared with patients with higher Hgb/Cr ratios, patients with lower ratios were older and had more comorbidities and complex coronary artery disease. Patients with lower hemoglobin and higher creatinine levels had a higher rate of in-hospital adverse outcomes including in-hospital mortality and procedural complications (defined as occurrence of cardiac tamponade, cardiogenic shock after PCI, emergency operation, or bleeding complications that required blood transfusion). On multivariate analyses, Hgb/Cr ratio was inversely associated with in-hospital mortality (odds ratio: 0.91, 95% confidence interval: 0.89–0.92; p < 0.001) and bleeding complications (odds ratio: 0.92, 95% confidence interval: 0.90–0.94; p < 0.001). Spline curve analysis demonstrated that these risks started to increase when the Hgb/Cr ratio was <15, and elevated exponentially when the ratio was <10. Hgb/Cr ratio is a simple index among non-dialysis patients and is inversely associated with in-hospital mortality and bleeding complications after PCI.