Risk factors and long-term outcomes of acute kidney injury complication after type A acute aortic dissection surgery in young patients

Machine learning-based model to predict severe acute kidney injury after total aortic arch replacement for acute type A aortic dissection

Background

Severe acute kidney injury (AKI) after total aortic arch replacement (TAAR) is related to adverse outcomes in patients with acute type A aortic dissection (ATAAD). However, the early prediction of severe AKI remains a challenge. This study aimed to develop a novel model to predict severe AKI after TAAR in ATAAD patients using machine learning algorithms.

Methods

A total of 572 ATAAD patients undergoing TAAR were enrolled in this retrospective study, and randomly divided into a training set (70 %) and a validation set (30 %). Lasso regression, support vector machine-recursive feature elimination and random forest algorithms were used to screen indicators for severe AKI (defined as AKI stage III) in the training set, respectively. Then the intersection indicators were selected to construct models through artificial neural network (ANN) and logistic regression. The AUC-ROC curve was employed to ascertain the prediction efficacy of the ANN and logistic regression models.

Results

The incidence of severe AKI after TAAR was 22.9 % among ATAAD patients. The intersection predictors identified by different machine learning algorithms were baseline serum creatinine and ICU admission variables, including serum cystatin C, procalcitonin, aspartate transaminase, platelet, lactic dehydrogenase, urine N-acetyl-β-d-glucosidase and Acute Physiology and Chronic Health Evaluation II score. The ANN model showed a higher AUC-ROC than logistic regression (0.938 vs 0.908, p < 0.05). Furthermore, the ANN model could predict 89.1 % of severe AKI cases beforehand. In the validation set, the superior performance of the ANN model was further confirmed in terms of discrimination ability (AUC = 0.916), calibration curve analysis and decision curve analysis.

Conclusion

This study developed a novel and reliable clinical prediction model for severe AKI after TAAR in ATAAD patients using machine learning algorithms. Importantly, the ANN model showed a higher predictive ability for severe AKI than logistic regression.

Acute Kidney Injury in Patients Undergoing Surgery for Type A Acute Aortic Dissection

BACKGROUND

Acute kidney injury (AKI) after repair of type A acute aortic dissection (TAAAD) has been shown to affect both short- and long-term outcomes. This study aimed to validate the impact of postoperative AKI on in-hospital and long-term outcomes in a large population of dissection patients presenting to multinational aortic centers. Additionally, we assessed risk factors for AKI including surgical details.

METHODS

Patients undergoing surgical repair for TAAAD enrolled in the International Registry of Acute Aortic Dissection database were evaluated to determine the incidence and risk factors for the development of AKI.

RESULTS

A total of 3307 patients were identified. There were 761 (23%) patients with postoperative AKI (AKI group) vs 2546 patients without (77%, non-AKI group). The AKI group had a higher rate of in-hospital mortality (n = 193, 25.4% vs n = 122, 4.8% in the non-AKI group, P < .001). Additional postoperative complications were also more common in the AKI group including postoperative cerebrovascular accident, reexploration for bleeding, and prolonged ventilation. Independent baseline characteristics associated with AKI included a history of hypertension, diabetes, chronic kidney disease, evidence of malperfusion on presentation, distal extent of dissection to abdominal aorta, and longer cardiopulmonary bypass time. Kaplan-Meier survival curves revealed decreased 5-year survival among the AKI group (P < .001).

CONCLUSIONS

AKI occurs commonly after TAAAD repair and is associated with a significantly increased risk of operative and long-term mortality. In this large study using the International Registry of Acute Aortic Dissection database, several factors were elucidated that may affect risk of AKI.

Hotspots and development frontiers of postoperative complications of AD: Bibliometric analysis - a review

The research on the postoperative complications of aortic dissection (AD) has received great attention from scholars all over the world, and the number of research articles in this field has consistently increased year after year. However, no bibliometric reports have been published yet to analyze the scientific output and the current situation in this field. The Bibliometrix R-package, VOSviewer, and CiteSpace software were used to conduct a bibliometric analysis of the hotspots and development frontiers of AD. A total of 1242 articles were retrieved. The USA, China, and Japan had the highest number of publications. The five keywords with the highest frequency were "analysis," "incidence," "acute type," "graft," and "risk factor." The results also indicated that the research in related fields had shifted from surgical treatment and utilizing experience to the evidence-based exploration of risk factors and the construction of prediction models to help better manage postoperative complications of AD. This is the first bibliometric analysis of global publications on the postoperative complications of AD. The current research hotspots focus on three areas: common postoperative complications of AD, exploration of the related risk factors, and management of complications. Future research could focus on identifying risk factors through meta-analysis and using a multicenter database for AD as well as building relevant models to predict the development of complications to better facilitate the clinical management of AD patients.

Risk factors for severe acute kidney injury post complication after total arch replacement combined with frozen elephant trunk, in acute type A aortic dissection

Background

Total arch replacement with the frozen elephant trunk (TAR + FET) technique is a challenging approach for acute type A aortic dissection (ATAAD). Severe acute kidney injury (AKI) adversely affects the prognosis of hospitalized patients. The study aims to evaluate the incidence and risk factors of severe AKI.

Methods

We conducted a retrospective cross-sectional study of the records of ATAAD patients following TAR + FET, admitted between January 2013 and December 2018. A multivariate logistic regression model was used to identify predictors of severe postoperative AKI. Severe postoperative AKI was defined using the Kidney Disease Improving Global Outcomes criteria.

Results

The whole in-hospital mortality rate was 4.3%. Among 670 patients, major adverse outcomes were present in 169 patients (25.2%), 67 patients (10.0%) required renal replacement therapy (RRT), and 80 (11.9%) developed severe postoperative AKI. In-hospital mortality in the severe AKI group (13.8%) was 4.5 times higher than in the non-severe AKI group (3.1%). Compared with the non-severe AKI patients, the severe AKI patients had a higher incidence of major adverse outcomes (100% vs. 15.1%, P<0.001) and more frequent use of RRT (83.8% vs. 0.0%, P<0.001). Multivariate analysis revealed that severe postoperative AKI was predicted by advanced age [odds ratio (OR) =1.029; 95% confidence interval (CI): 1.002-1.056; P=0.032], lower limb symptoms (OR =4.384; 95% CI: 2.240-8.582; P<0.001), coronary artery involvement (OR =2.478; 95% CI: 1.432-4.288; P=0.001), preoperative postoperative serum creatinine (SCr) (OR =1.008; 95% CI: 1.003-1.013; P=0.001), and prolonged cardiopulmonary bypass (CPB) time (OR =1.011; 95% CI: 1.006-1.015; P<0.001).

Conclusions

There was a high incidence of severe AKI and high in-hospital mortality after TAR + FET in ATAAD patients. The risk factors for severe AKI in ATAAD patients undergoing TAR + FET were determined to help identify the high-risk patients and make rational treatment decisions.

Acute renal failure after acute type A aortic dissection repair. Insidious postoperative complication with poor short- and long-term prognosis

Acute type A aortic dissection (ATAAD) is a life-threatening aortic disease. Many systems and organs are affected by malperfusion which presents preoperatively and postoperatively. Postoperative acute renal failure after ATAAD constitutes a severe and insidious complication. Acute renal damage is observed in many patients with ATAAD preoperatively and it burdens the renal function postoperatively. Renal replacement therapy represents an additional risk factor for short-, mid-, and long-term outcomes after ATAAD repair. Brown et al.'s present study highlight the clinical significance of this complication. Also, they remind us of the importance of optimizing perioperative renal protective strategies in patients undergoing ATAAD repair.