Machine Learning Prediction Model for Acute Renal Failure After Acute Aortic Syndrome Surgery

BackgroundAcute renal failure (ARF) is the most common major complication following cardiac surgery for acute aortic syndrome (AAS) and worsens the postoperative prognosis. Our aim was to establish a machine learning prediction model for ARF occurrence in AAS patients.MethodsWe included AAS patient data from nine medical centers (n = 1,637) and analyzed the incidence of ARF and the risk factors for postoperative ARF. We used data from six medical centers to compare the performance of four machine learning models and performed internal validation to identify AAS patients who developed postoperative ARF. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to compare the performance of the predictive models. We compared the performance of the optimal machine learning prediction model with that of traditional prediction models. Data from three medical centers were used for external validation.ResultsThe eXtreme Gradient Boosting (XGBoost) algorithm performed best in the internal validation process (AUC = 0.82), which was better than both the logistic regression (LR) prediction model (AUC = 0.77, p < 0.001) and the traditional scoring systems. Upon external validation, the XGBoost prediction model (AUC =0.81) also performed better than both the LR prediction model (AUC = 0.75, p = 0.03) and the traditional scoring systems. We created an online application based on the XGBoost prediction model.ConclusionsWe have developed a machine learning model that has better predictive performance than traditional LR prediction models as well as other existing risk scoring systems for postoperative ARF. This model can be utilized to provide early warnings when high-risk patients are found, enabling clinicians to take prompt measures.

Predictors of hypoxemia in type-B acute aortic syndrome: a retrospective study

Acute aortic syndrome (AAS) can be life-threatening owing to a variety of complications, and it is managed in the intensive care unit (ICU). Although Stanford type-B AAS may involve hypoxemia, its predictors are not yet clearly understood. We studied clinical factors and imaging parameters for predicting hypoxemia after the onset of type-B AAS. We retrospectively analyzed patients diagnosed with type-B AAS in our hospital between January 2012 and April 2020. We defined hypoxemia as PaO2/FiO2 ≤ 200 within 7 days after AAS onset and used logistic regression analysis to evaluate prognostic factors for hypoxemia. We analyzed 224 consecutive patients (140 males, mean age 70 ± 14 years) from a total cohort of 267 patients. Among these, 53 (23.7%) had hypoxemia. The hypoxemia group had longer ICU and hospital stays compared with the non-hypoxemia group (median 20 vs. 16 days, respectively; p = 0.039 and median 7 vs. 5 days, respectively; p < 0.001). Male sex (odds ratio [OR] 2.87; 95% confidence interval [CI] 1.24–6.63; p = 0.014), obesity (OR 2.36; 95% CI 1.13–4.97; p = 0.023), patent false lumen (OR 2.33; 95% CI 1.09–4.99; p = 0.029), and high D-dimer level (OR 1.01; 95% CI 1.00–1.02; p = 0.047) were independently associated with hypoxemia by multivariate logistic analysis. This study showed a significant difference in duration of ICU and hospital stays between patients with and without hypoxemia. Furthermore, male sex, obesity, patent false lumen, and high D-dimer level may be significantly associated with hypoxemia in patients with type-B AAS.

Influence of nocturnal hypoxemia on follow-up course after type B acute aortic syndrome

Introduction Association between sleep nocturnal breathing disorders and acute aortic syndrome (AAS) has been described but mid-term data are scarce. Objectives We assessed the prognostic value of sleep apnea parameters and their relationship with aortic morphology after the onset of a type B AAS. Methods Between January 2010 and January 2018, sleep apnea screening in post type B AAS was prospectively performed. The association of sleep apnea parameters with aortic morphology and aortic expansion during follow-up was studied. Results Over the 8-year-study period, 103 patients were included, with a mean age of 57.8 ± 12.1 years old. Median follow-up was 25.0 months (11.0–51.0). Thirty-two patients (31%) required aortic stenting during the acute phase. In patients treated by aortic stenting, the descending thoracic aortic diameter was positively associated with a higher percentage of nocturnal time of saturation ≤ 90% after adjustment (p = 0.016). During follow-up, the nocturnal time of saturation ≤ 90% in patients treated by medical therapy was the only parameter associated with significant aortic expansion rate (r = 0.26, p = 0.04). Thirty-eight patients started and sustained nocturnal ventilation during follow-up. The association between aortic expansion rate and nocturnal time of saturation ≤ 90% did not persist during follow-up after adjustment on nocturnal ventilation initiation (r = 0.25, p = 0.056). Conclusions Nocturnal hypoxemia parameters are positively associated with the max onset aortic diameter and significant aortic growth after type B AAS. Nocturnal ventilation seems to mitigate aortic expansion during follow-up.