Development of a machine learning-based model to predict major adverse events after surgery for type A aortic dissection complicated by malnutrition.

Objective: This study aims to develop a predictive model for the risk of major adverse events (MAEs) in type A aortic dissection (AAAD) patients with malnutrition after surgery, utilizing machine learning (ML) algorithms. Methods: We retrospectively collected clinical data from AAAD patients with malnutrition who underwent surgical treatment at our center. Through least absolute shrinkage and selection operator (LASSO) regression analysis, we screened for preoperative and intraoperative characteristic variables. Based on the random forest (RF) algorithm, we constructed a ML predictive model, and further evaluated and interpreted this model. Results: Through LASSO regression analysis and univariate analysis, we ultimately selected seven feature variables for modeling. After comparing six different ML models, we confirmed that the RF model demonstrated the best predictive performance in this dataset. Subsequently, we constructed a model using the RF algorithm to predict the risk of postoperative MAEs in AAAD patients with malnutrition. The test set results indicated that this model has excellent predictive efficacy and clinical applicability. Finally, we employed the Shapley additive explanations (SHAP) method to further interpret the predictions of this model. Conclusion: We have successfully constructed a risk prediction model for postoperative MAEs in AAAD patients with malnutrition using the RF algorithm, and we have interpreted the model through the SHAP method. This model aids clinicians in early identification of high-risk patients for MAEs, thereby potentially mitigating adverse clinical outcomes associated with malnutrition.

Risk prediction and prognostic analysis of post-implantation syndrome after thoracic endovascular aortic repair.

This study aimed to establish a predictive model for the risk of post-thoracic endovascular aortic repair (TEVAR) post-implantation syndrome (PIS) in type B aortic dissection (TBAD) patients, assisting clinical physicians in early risk stratification and decision management for high-risk PIS patients. This study retrospectively analyzed the clinical data of 547 consecutive TBAD patients who underwent TEVAR treatment at our hospital. Feature variables were selected through LASSO regression and logistic regression analysis to construct a nomogram predictive model, and the model's performance was evaluated. The optimal cutoff value for the PIS risk nomogram score was calculated through receiver operating characteristic (ROC) curve analysis, further dividing patients into high-risk group (HRG) and low-risk group (LRG), and comparing the short to midterm postoperative outcomes between the two groups. In the end, a total of 158 cases (28.9%) experienced PIS. Through LASSO regression analysis and multivariable logistic regression analysis, variables including age, emergency surgery, operative time, contrast medium volume, and number of main prosthesis stents were selected to construct the nomogram predictive model. The model achieved an area under the curve (AUC) of 0.86 in the training set and 0.82 in the test set. Results from calibration curve, decision curve analysis (DCA) and clinical impact curve (CIC) demonstrated that the predictive model exhibited good performance and clinical utility. Furthermore, after comparing the postoperative outcomes of HRG and LRG patients, we found that the incidence of postoperative PIS significantly increased in HRG patients. The duration of ICU stay and mechanical assistance time was prolonged, and the incidence of postoperative type II entry flow and acute kidney injury (AKI) was higher. The risk of aortic-related adverse events (ARAEs) and major adverse events (MAEs) at the first and twelfth months of follow-up also significantly increased. However, there was no significant difference in the mortality rate during hospitalization. This study established a nomogram model for predicting the risk of PIS in patients with TBAD undergoing TEVAR. It serves as a practical tool to assist clinicians in early risk stratification and decision-making management for patients.

The prognostic value of preoperative systemic inflammatory response index in predicting outcomes of acute type A aortic dissection patients underwent surgical treatment.

Background: The systemic inflammatory response index (SIRI) is a novel inflammatory-immune biological marker that has prognostic value in various cardiovascular diseases. This study aims to investigate the relationship between SIRI and short-term and long-term prognosis in patients with acute type A aortic dissection (AAAD) underwent surgical treatment. Methods: We conducted a retrospective analysis of patients with AAAD who underwent emergency surgical treatment at our center. Through multifactorial logistics regression analysis and cox proportional hazards regression analysis, we identified SIRI as an independent risk factor for major adverse events (MAEs) and long-term aorta-related adverse events (ARAEs) post-surgery. The optimal cutoff value of preoperative SIRI was determined using receiver operating characteristic (ROC) curve analysis, and patients were divided into low SIRI group and high SIRI group. The prognostic outcomes at different time points post-surgery for the two groups of patients were analyzed using Kaplan-Meier survival analysis, and the significance was determined by log-rank test. Results: A total of 691 AAAD patients were included in this study. Among them, 50 patients (7.2%) died within 30 days post-surgery, and 175 patients (25.3%) experienced MAEs. A total of 641 patients were followed up, with an average follow-up time of 33.5 ± 17.5 months, during which 113 patients (17.6%) experienced ARAEs. The results of multifactorial logistics regression analysis and cox proportional hazards regression analysis showed that SIRI was an independent risk factor for postoperative MAEs (OR=3.148, 95%CI[1.650-6.006], p<0.001) and ARAEs (HR=2.248, 95%CI[1.050-4.809], p<0.037). Kaplan-Meier analysis demonstrated that the MAEs-free survival in the high SIRI group was significantly lower than that in the low SIRI group, and a similar trend was observed in the ARAEs-free survival during follow-up (log-rank test, p<0.001). Conclusion: Preoperative SIRI is significantly associated with the short-term and long-term prognosis of AAAD patients underwent emergency open surgery, demonstrating its valuable prognostic value. Therefore, preoperative SIRI is a reliable biological marker that can serve as a valuable tool for preoperative risk stratification and decision management.

Clinical predictive value of the age, creatinine, and ejection fraction score in patients in acute type A aortic dissection after total arch replacement.

The age, creatinine, and ejection fraction (ACEF) score has been accepted as a predictor of poor outcome in elective operations. This study aimed to investigate the predictive value of ACEF score in acute type A aortic dissection (AAAD) patients after total arch replacement. A total of 227 AAAD patients from July 2021 and June 2022 were enrolled and divided into Tertiles 1 (ACEF ≤ 0.73), Tertiles 2 (0.73 < ACEF ≤ 0.95), and Tertiles 3 (ACEF > 0.95). Using inverse probability processing weighting (IPTW) to balance the baseline characteristics and compare the outcomes. Cox logistic regression was used to further evaluate the survival prediction ability of ACEF score. The in-hospital mortality was 9.8%. After IPTW, in the baseline characteristics reached an equilibrium, a higher ACEF score before operation still associated with higher in-hospital mortality. After 1 year follow-up, 184 patients (90.6%) survival. Multivariable analysis revealed that ACEF score (adjusted hazard ratio 1.68; 95% confidence interval 1.34-4.91; p = 0.036) and binary ACEF score (adjusted HR 2.26; 95% CI 1.82-6.20; p < 0.001) was independently associated with 1-year survival. In addition, net reclassification improvement (NRI) and integrated differentiation improvement (IDI) verified that the ACEF score and binary ACEF score is an accurate predictive tool in clinical settings. In conclusions, ACEF score could be considered as a useful tool to risk stratification in patients with AAAD before operation in daily clinical work.

Surgical management of the aortic root in acute type A aortic dissection: A comparative analysis.

BACKGROUND: This study aimed to assess the early- and mid-term outcomes of aortic root repair and replacement, and to provide evidence to improve root management in acute type A aortic dissection (AAAD). METHODS: This study enrolled 455 patients who underwent AAAD root repair (n = 307) or replacement (n = 148) between January 2016 and December 2017. Inverse probability of treatment weighting (IPTW) method was used to control for treatment selection bias. The primary outcomes were in-hospital mortality, mid-term survival, and proximal aortic reintervention. RESULTS: The success rate of root repair was 99.7%. The in-hospital mortality in the conservative root repair (CRR) and aggressive root replacement (ARR) were 8.1% and 10.8%. The median follow-up time was 67.76 months (IQR, 67-72 months). After adjusting for baseline factors, there was no significant differences in mid-term survival (p = .750) or the proximal aortic reintervention rate (p = .550) between the two groups. According to Cox analysis, age, hypertension, severe aortic regurgitation, CPB time, and concomitant CABG were all factors associated with mid-term mortality. Regarding reintervention, multivariate analysis identified renal insufficiency, bicuspid aortic valve, root diameter ≥ 45 mm, and severe aortic regurgitation as risk factors, while CRR did not increase the risk of reintervention. The subgroup analysis revealed heterogeneity in the effects of surgical treatment across diverse populations based on a variety of risk factors. CONCLUSIONS: For patients with AAAD, both CRR and ARR are appropriate operations with promising early and mid-term outcomes. The effects of treatment show heterogeneity across diverse populations based on various risk factors.

A predictive model for postoperative adverse outcomes following surgical treatment of acute type A aortic dissection based on machine learning.

Acute type A aortic dissection (AAAD) has a high probability of postoperative adverse outcomes (PAO) after emergency surgery, so exploring the risk factors for PAO during hospitalization is key to reducing postoperative mortality and improving prognosis. An artificial intelligence approach was used to build a predictive model of PAO by clinical data-driven machine learning to predict the incidence of PAO after total arch repair for AAAD. This study included 380 patients with AAAD. The clinical features that are associated with PAO were selected using the LASSO regression analysis. Six different machine learning algorithms were tried for modeling, and the performance of each model was analyzed comprehensively using receiver operating characteristic curves, calibration curve, precision recall curve, and decision analysis curves. Explain the optimal model through Shapley Additive Explanation (SHAP) and perform an individualized risk assessment. After comprehensive analysis, the authors believe that the extreme gradient boosting (XGBoost) model is the optimal model, with better performance than other models. The authors successfully built a prediction model for PAO in AAAD patients based on the XGBoost algorithm and interpreted the model with the SHAP method, which helps to identify high-risk AAAD patients at an early stage and to adjust individual patient-related clinical treatment plans in a timely manner.

Quality of life in young patients with acute type a aortic dissection in China: comparison with Marfan syndrome and non-Marfan syndrome.

BACKGROUND: There is a paucity of Chinese studies evaluating the quality of life (QoL) in young acute type A aortic dissection (AAAD) patients with Marfan syndrome. METHODS: Young adult AAAD patients (younger than 45 years old) underwent surgical treatment at our institution from January 2017 to December 2020 were consecutive enrolled. The hospital survivors completed 1 year of follow up. Patients were divided into two groups according to the presence or absence of Marfan syndrome (MFS). A 1:1 propensity score matching (PSM) with a caliper 0.2 was conducted to balance potential bias in baseline. The follow-up data were analyzed primarily for change in quality of life and anxiety status. RESULTS: After PSM, 32 comparable pairs were matched. The baseline data were comparable and postoperative complications were similar between groups. In terms of SF-36 scale, the role physical, bodily pain, role emotional and mental health subscales were no significantly improved in MFS patients over time. At 1 year after discharged, the subscale of mental health and bodily pain were significantly lower in the MFS group than in the non-MFS group. In terms of HADS assessments, the level of anxiety in MFS patients was significantly higher than in non-MFS patients at 1 year after discharged. CONCLUSIONS: The QoL in young AAAD patients with MFS is lower than those without MFS after surgery. This may be associated with the uncontrollable persistent chronic pain and the uncertainty and concerns for the disease's progression.

A nomogram-based model to predict postoperative transient neurological dysfunctions in patients receiving acute type A aortic dissection surgery.

The purposes of this study were to develop and validate a nomogram for predicting postoperative transient neurological dysfunctions (TND) in patients with acute type A aortic dissection (AAAD) who underwent modified triple-branched stent graft implantation. This retrospective study developed a nomogram-based model in a consecutive cohort of 146 patients. Patient characteristics, preoperative clinical indices, and operative data were analyzed. Univariate and multivariable analyses were applied to identify the most useful predictive variables for constructing the nomogram. Discrimination and the calibration of the model was evaluated through the receiver operating characteristic curve (ROC), the Hosmer-Lemeshow goodness-of-fit test and the decision curve analysis (DCA). At the same time, to identify and compare long-term cumulative survival rate, Kaplan-Meier survival curve was plotted. The incidence rate of postoperative TND observed in our cohort were 40.9%. Supra-aortic dissection with or without thrombosis, creatinine >115 µmol and albumin <39.7 g/L, selective antegrade cerebral perfusion (SACP) time >7 min and total operation time >303 min, were confirmed as independent predictors that enhanced the likelihood of TND. Internal validation showed good discrimination of the model with under the ROC curve (AUC) of 0.818 and good calibration (Hosmer-Lemeshow test, p > .05). DCA revealed that the nomogram was clinically useful. In the long-term survival there was no significant difference between patients with or without TND history. The results showed the predict model based on readily available predictors has sufficient validity to identify TND risk in this population, that maybe useful for clinical decision-making.

Early Clinical Outcomes of Thoracoscopic Mitral Valvuloplasty: The First 90 Cases.

BACKGROUND: We reported 90 cases of thoracoscopic mitral valvuloplasty in its early stages and sought to analyze early clinical outcomes. METHODS: Ninety consecutive patients, who underwent thoracoscopic mitral valvuloplasty at our institute between April 2020 and December 2021, were assessed for outcomes. Clinical data, including baseline characteristics, operative data, postoperative data, and early follow-up results, were collected. The early clinical outcomes were used to assess the reliability and efficiency of this technique. RESULTS: No in-hospital death occurred. One patient underwent a median sternotomy for bleeding. Intraoperative transesophageal echocardiography revealed no mitral regurgitation in 82 patients and mitral regurgitation of 0-2 cm2 in six. The remaining two patients with mitral regurgitation >2 cm2 experienced serious systolic anterior motion but underwent successful re-valvuloplasty during a second pump-up. the mean cardiopulmonary bypass time was 177.1±54.8 min and aortic clamping time, 114.0±44.9 min. Each patient received a prosthetic ring (CG Future™), and 64 patients received artificial chordae with an average of 2.7±1.5 (ranging from 1 to 6) pairs. The mean follow up was 8.8±7.0 (range, 1-22 months), while two patients were lost to follow up. Recurrent severe mitral regurgitation was observed in one patient three months after the operation, and mitral valve replacement was performed via median sternotomy. During follow up, one patient died of upper respiratory tract infection, and one suffered from low cardiac output. CONCLUSIONS: Thoracoscopic mitral valvuloplasty is safe and effective and, once surgeons overcome the learning curve, can achieve excellent early clinical outcomes.