Development and evaluation of an early death risk prediction model after acute type A aortic dissection

Abstract Objectives: The partial upper sternotomy (PUS) approach is acceptable for aortic valve replacement, and even aortic root operation. However, the efficiency of PUS for extensive arch repair of acute type A aortic dissection (AAAD) in older adult patients has not been well investigated.Methods: Between January 2012 and December 2019, 222 older adult patients (≥65 years) diagnosed with AAAD went through extensive arch repair, among which 127 received PUS, and 95 underwent full sternotomy (FS). Logistic regression analysis was used to identify risk factors for early death, and negative binomial regression analysis was applied to explore risk factors related to post-operative ventilator-supporting time and intensive care unit stay time. Results: Total early mortality was 8.1% (18/222 patients). The PUS group had shorter Cardiopulmonary bypass time (133.0 vs.155.0 minutes, P<0.001), cross-clamp time (44.0 vs. 61.0 minutes, P<0.001) and shorter selective cerebral perfusion time (11.0 vs. 21.0 minutes, P<0.001) than the FS group. Left ventricle ejection fraction (LVEF)<50% (odds ratio [OR], 17.05; 95% confidence interval [CI] 1.87-155.63; P=0.012) and malperfusion syndromes (OR, 65.83; 95% CI 11.53-375.86; P<0.001) were related to early death. In the multivariate model, the PUS approach contributed to shorter ventilator-supporting time (incidence rate ratio [IRR], 0.76; 95% CI 0.64-0.91; P=0.003) , when compared with the FS group. Conclusions: The early results of emergency extensive arch repair of AAAD via PUS in older adult patients were satisfactory. However, the long-term results remain to be investigated.

Download Full-text

The Construction of a Risk Prediction Model Based on Neural Network for Pre-operative Acute Ischemic Stroke in Acute Type A Aortic Dissection Patients

Frontiers in Neurology ◽

10.3389/fneur.2021.792678 ◽

2021 ◽

Vol 12 ◽

Author(s):

Hongliang Zhao ◽

Ziliang Xu ◽

Yuanqiang Zhu ◽

Ruijia Xue ◽

Jing Wang ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Ischemic Stroke ◽

Aortic Dissection ◽

Prediction Model ◽

Risk Prediction ◽

Deep Neural Network ◽

Validation Cohort ◽

Acute Type ◽

Type A Aortic Dissection

Objective: To establish a pre-operative acute ischemic stroke risk (AIS) prediction model using the deep neural network in patients with acute type A aortic dissection (ATAAD).Methods: Between January 2015 and February 2019, 300 ATAAD patients diagnosed by aorta CTA were analyzed retrospectively. Patients were divided into two groups according to the presence or absence of pre-operative AIS. Pre-operative AIS risk prediction models based on different machine learning algorithm was established with clinical, transthoracic echocardiography (TTE) and CTA imaging characteristics as input. The performance of the difference models was evaluated using the receiver operating characteristic (ROC), precision-recall curve (PRC) and decision curve analysis (DCA).Results: Pre-operative AIS was detected in 86 of 300 patients with ATAAD (28.7%). The cohort was split into a training (211, 70% patients) and validation cohort (89, 30% patients) according to stratified sampling strategy. The constructed deep neural network model had the best performance on the discrimination of AIS group compare with other machine learning model, with an accuracy of 0.934 (95% CI: 0.891–0.963), 0.921 (95% CI: 0.845–0.968), sensitivity of 0.934, 0.960, specificity of 0.933, 0.906, and AUC of 0.982 (95% CI: 0.967–0.997), 0.964 (95% CI: 0.932–0.997) in the training and validation cohort, respectively.Conclusion: The established risk prediction model based on the deep neural network method may have the big potential to evaluate the risk of pre-operative AIS in patients with ATAAD.

Download Full-text

Development and Validation of a Risk Prediction Model for Postoperative Pneumonia in Adult Patients Undergoing Stanford Type a Acute Aortic Dissection Surgery: A Case Control Study

10.21203/rs.3.rs-296062/v1 ◽

2021 ◽

Author(s):

Dashuai Wang ◽

Xiaofan Huang ◽

Hongfei Wang ◽

Xing Chen ◽

Sheng Le ◽

...

Keyword(s):

Aortic Dissection ◽

Prediction Model ◽

Risk Prediction ◽

Clinical Utility ◽

Acute Aortic Dissection ◽

Univariate Analysis ◽

Type A ◽

Risk Prediction Model ◽

Smoking History ◽

Training Set

Abstract BackgroundPneumonia is a common complication after Stanford type A acute aortic dissection surgery (AADS) and contributes significantly to morbidity, mortality, and length of stay. The purpose of this study was to identify independent risk factors associated with pneumonia after AADS and to develop and validate a risk prediction model.MethodsAdults undergoing AADS between 2016 and 2019 were identified in a single-institution database. Patients were randomly divided into training and validation sets at a ratio of 2:1. Preoperative and intraoperative variables were included for analysis. A multivariate logistic regression model was constructed using significant variables from univariate analysis in the training set. A nomogram was constructed for clinical utility and the model was validated in an independent dataset.ResultsPostoperative pneumonia developed in 170 of 492 patients (34.6%). In the training set, multivariate analysis identified seven independent predictors for pneumonia after AADS including age, smoking history, chronic obstructive pulmonary disease, renal insufficiency, leucocytosis, low platelet count, and intraoperative transfusion of red blood cells. The model demonstrated good calibration (Hosmer-Lemeshow χ2 = 3.31, P = 0.91) and discrimination (C-index = 0.77) in the training set. The model was also well calibrated (Hosmer-Lemeshow χ2 = 5.73, P = 0.68) and showed reliable discriminatory ability (C-index = 0.78) in the validation set. By visual inspection, the calibrations were good in both the training and validation sets.ConclusionWe developed and validated a risk prediction model for pneumonia after AADS. The model may have clinical utility in individualized risk evaluation and perioperative management.Clinical Trial Registry NumberChiCTR1900028127.

Download Full-text