Malnutrition provides important long-term prognostic information in patients undergoing endovascular abdominal aortic aneurysm repair

Predicting Long-Term Survival after Endovascular Aneurysm Repair Using Machine Learning-Based Decision Tree Analysis

ObjectiveEndovascular aneurysm repair (EVAR) has become a preferred method for treating abdominal aortic aneurysms (AAA) due to its minimally invasive approach. However, identifying factors that influence long-term patient outcomes is crucial for improving prognosis. This study investigates whether machine learning (ML)-based decision tree analysis (DTA) can predict long-term survival (over 5 years postoperatively) by uncovering complex patterns in patient data.MethodsWe retrospectively analyzed data from 142 patients who underwent elective EVAR for AAA at Tokyo Medical University Hospital between October 2013 and July 2018. The dataset comprised 24 variables, including age, gender, nutritional status, comorbidities, and surgical details. The decision tree classifier was developed and validated using Python 3.7 and the scikit-learn toolkit.ResultsDTA identified poor nutritional status as the most significant predictor, followed by compromised immunity, active cancer, octogenarians, chronic kidney disease, and chronic obstructive pulmonary disease. The decision tree identified 9 terminal nodes with probabilities of long-term survival. Four of these terminal nodes represented groups of patients with a high probability of long-term survival: 100%, 84%, 77%, and 60%, whereas the other 5 terminal nodes represented groups of patients with a low probability of long-term survival: 17%, 25%, 30%, 45%, and 47%. The model achieved a moderately high accuracy of 76.1%, specificity of 72.4%, sensitivity of 81.8%, precision of 65.2%, and area under the receiver operating characteristic curve of 0.84.ConclusionML-based DTA effectively predicts long-term survival after EVAR, highlighting the importance of comprehensive preoperative assessments and personalized management strategies to improve patient outcomes.

Prognostic Value of Nutritional Markers for Long-Term Mortality in Patients Undergoing Endovascular Aortic Repair

Objective: The relationship between nutritional status and morbidity and death in a number of diseases and disorders has garnered considerable attension. In patients having endovascular aneurysm repair (EVAR) for abdominal aortic aneurysms (AAA), we assessed the prognostic value of nutritional markers of albumin (ALB), body mass index (BMI), and geriatric nutritional risk index (GNRI) for long-term mortality. Materials and Methods: Retrospective data analysis was done on patients who had undergone elective EVAR for AAA more than 5 years earlier. Results: A total of 176 patients underwent EVAR for AAA between March 2012 and April 2016. The optimal cutoff value of ALB, BMI, and GNRI for predicting long-term mortality was calculated as 3.75 g/dL (area under the curve [AUC] 0.64), 21.4 kg/m2 (AUC 0.65), and 101.4 (AUC 0.70), respectively. Low ALB, low BMI, and low GNRI as well as age ≥75 years, chronic obstructive pulmonary disease, chronic kidney disease, and active cancer were independent risk factors for long-term mortality. Conclusion: Malnutrition, which is measured by ALB, BMI, and GNRI, is an independent risk factor for long-term mortality in patients receiving EVAR for AAA. Of the nutritional markers, the GNRI can be the most reliable nutritional indicator to identify a potentially high-risk group of mortality after EVAR.

C-reactive protein to albumin ratio provides important long-term prognostic information in patients undergoing endovascular abdominal aortic repair

BACKGROUND

The prognostic value of C-reactive protein/albumin ratio (CAR) is of import in cardiovascular diseases. Our aim was to evaluate the impact of the CAR in patients with asymptomatic abdominal aortic aneurysm (AAA) undergoing endovascular aneurysm repair (EVAR).

MATERIAL AND METHOD

We retrospectively evaluated 127 consecutive patients who underwent technically successful elective EVAR procedure between December 2014 and September 2020. The optimal CAR cut-off value was determined by using receiver operating characteristic (ROC) curve analysis. Based on the cut-off value, we investigated the association of CAR with long-term all-cause mortality.

RESULTS

32 (25.1%) of the patients experienced all-cause mortality during a mean 32.7 ± 21.7 months' follow-up. In the group with mortality, CAR was significantly higher than in the survivor group (4.63 (2.60-11.88) versus 1.63 (0.72-3.24), p < 0.001). Kaplan-Meier curves showed a higher incidence of all-cause mortality in patients with high CAR compared to patients with low CAR (log-rank test, p < 0.001). Multivariable Cox regression analysis revealed that glucose ≥ 110 mg/dL (HR: 2.740; 95% CI: 1.354-5.542; p = 0.005), creatinine ≥ 0.99 mg/dL (HR: 2.957, 95% CI: 1.282-6.819, p = 0.011) and CAR > 2.05 (HR: 8.190, 95% CI: 1.899-35.320, p = 0.005) were the independent predictors of mortality.

CONCLUSION

CAR was associated with a significant increase in postoperative long-term mortality in patients who underwent EVAR. Preoperatively calculated CAR can be used as an important prognostic factor.

Association of neutrophils, lymphocytes, and neutrophil-lymphocyte ratio to overall mortality after endovascular abdominal aortic aneurysm repair

BACKGROUND

The purpose of this study was to determine the predictive ability of neutrophilia, lymphocytopenia, and neutrophil-lymphocyte ratio (NLR) for overall mortality after EVAR for AAA.

METHODS

Data on patients with AAA treated by EVAR between March 2012 and December 2016 were obtained from a prospectively maintained EVAR database at Tokyo Medical University Hospital. The NLR was calculated by dividing the absolute neutrophil count by the absolute lymphocyte count. A cut-off value of total WBC count, neutrophil count, lymphocyte count, and NLR was determined according to a receiver operating characteristic (ROC) curve. Univariate and multivariate analyses were performed using the Cox proportional hazard analyses to account for the time at risk.

RESULTS

178 patients were included in this study after selection based on the exclusion criteria. The subjects consisted of 150 men and 28 women with a mean age of 77.5 years (range, 51-89 years). A ROC curve analysis determined the optimal cut-off values of preoperative total WBC, neutrophils, lymphocytes, and NLR for predicting overall mortality with 7,050 /μL, 4,012 /μL, 1,312 /μL, and 3.19, respectively. On univariate analysis and multivariate analyses, octogenarian, obesity, COPD, active cancer, and lymphocytopenia or NLR were detected as independent predictors for overall mortality.

CONCLUSIONS

Specific leukocyte populations, such as lymphocyte count and NLR, are useful biomarkers to predict overall mortality in patients undergoing EVAR for AAA, suggesting that WBC count and its subsets, which are easy to perform a test, may be used to stratify patients at risk for poor prognosis following EVAR.