Dataset Information

Long-term mortality prediction after operations for type A ascending aortic dissection.

ABSTRACT:

Background

There are few long-term mortality prediction studies after acute aortic dissection (AAD) Type A and none were performed using new models such as neural networks (NN) or support vector machines (SVM) which may show a higher discriminatory potency than standard multivariable models.

Methods

We used 32 risk factors identified by Literature search and previously assessed in short-term outcome investigations. Models were trained (50%) and validated (50%) on 2 random samples from a consecutive 235-patient cohort. NN were run only on patients with complete data for all included variables (N = 211); SVM on the overall group. Discrimination was assessed by receiver operating characteristic area under the curve (AUC) and Gini's coefficients along with classification performance.

Results

There were 84 deaths (36%) occurring at 564 +/- 48 days (95%CI from 470 to 658 days). Patients with complete variables had a slightly lower death rate (60 of 211, 28%). NN classified 44 of 60 (73%) dead patients and 147 of 151 (97%) long-term survivors using 5 covariates: immediate post-operative chronic renal failure, circulatory arrest time, the type of surgery on ascending aorta plus hemi-arch, extracorporeal circulation time and the presence of Marfan habitus. Global accuracies of training and validation NN were excellent with AUC respectively 0.871 and 0.870 but classification errors were high among patients who died. Training SVM, using a larger number of covariates, showed no false negative or false positive cases among 118 randomly selected patients (error = 0%, AUC 1.0) whereas validation SVM, among 117 patients, provided 5 false negative and 11 false positive cases (error = 22%, AUC 0.821, p < 0.01 versus NN results). An html file was produced to adopt and manipulate the selected parameters for practical predictive purposes.

Conclusions

Both NN and SVM accurately selected a few operative and immediate post-operative factors and the Marfan habitus as long-term mortality predictors in AAD Type A. Although these factors were not new per se, their combination may be used in practice to index death risk post-operatively with good accuracy.

SUBMITTER: Macrina F

PROVIDER: S-EPMC2902218 | biostudies-literature | 2010 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Long-term mortality prediction after operations for type A ascending aortic dissection.

Macrina Francesco F Puddu Paolo E PE Sciangula Alfonso A Totaro Marco M Trigilia Fausto F Cassese Mauro M Toscano Michele M

Journal of cardiothoracic surgery 20100525

<h4>Background</h4>There are few long-term mortality prediction studies after acute aortic dissection (AAD) Type A and none were performed using new models such as neural networks (NN) or support vector machines (SVM) which may show a higher discriminatory potency than standard multivariable models.<h4>Methods</h4>We used 32 risk factors identified by Literature search and previously assessed in short-term outcome investigations. Models were trained (50%) and validated (50%) on 2 random samples ...[more]

PMID: 20497588

Similar Datasets

Project description:ImportanceAortic dilatation is frequently encountered in clinical practice among aging endurance athletes, but the distribution of aortic sizes in this population is unknown. It is additionally uncertain whether this may represent aortic adaptation to long-term exercise, similar to the well-established process of ventricular remodeling.ObjectiveTo assess the prevalence of aortic dilatation among long-term masters-level male and female athletes with about 2 decades of exercise exposure.Design, setting, and participantsThis cross-sectional study evaluated aortic size in veteran endurance athletes. Masters-level rowers and runners aged 50 to 75 years were enrolled from competitive athletic events across the United States from February to October 2018. Analysis began January 2019.ExposuresLong-term endurance exercise.Main outcomes and measuresThe primary outcome was aortic size at the sinuses of Valsalva and the ascending aorta, measured using transthoracic echocardiography in accordance with contemporary guidelines. Aortic dimensions were compared with age, sex, and body size-adjusted predictions from published nomograms, and z scores were calculated where applicable.ResultsAmong 442 athletes (mean [SD] age,?61?[6] years; 267 men [60%]; 228 rowers [52%]; 214 runners [48%]), clinically relevant aortic dilatation, defined by a diameter at sinuses of Valsalva or ascending aorta of 40 mm or larger, was found in 21% (n?=?94) of all participants (83 men [31%] and 11 women [6%]). When compared with published nomograms, the distribution of measured aortic size displayed a rightward shift with a rightward tail (all P?<?.001). Overall, 105 individuals (24%) had at least 1 z score of 2 or more, indicating an aortic measurement greater than 2 SDs above the population mean. In multivariate models adjusting for age, sex, body size, hypertension, and statin use, both elite competitor status (rowing participation in world championships or Olympics or marathon time under 2 hours and 45 minutes) and sport type (rowing) were independently associated with aortic size.Conclusions and relevanceClinically relevant aortic dilatation is common among aging endurance athletes, raising the possibility of vascular remodeling in response to long-term exercise. Longitudinal follow-up is warranted to establish corollary clinical outcomes in this population.

Dataset Information

Long-term mortality prediction after operations for type A ascending aortic dissection.

Background

Methods

Results

Conclusions

Publications

Long-term mortality prediction after operations for type A ascending aortic dissection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets