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.

Neuroprotective strategies with circulatory arrest in open aortic surgery – A meta-analysis

Objective Deep hypothermic circulatory arrest (DHCA) in aortic surgery is associated with morbidity and mortality despite evolving strategies. With the advent of antegrade cerebral perfusion (ACP), moderate hypothermic circulatory arrest (MHCA) was reported to have better outcomes than DHCA. There is no standardised guideline or consensus regarding the hypothermic strategies to be employed in open aortic surgery. Meta-analysis was performed comparing DHCA with MHCA + ACP in patients having aortic surgery. Methods A systematic review of the literature was undertaken. Any studies with DHCA versus MHCA + ACP in aortic surgeries were selected according to specific inclusion criteria and analysed to generate summative data. Statistical analysis was performed using STATS Direct. The primary outcomes were hospital mortality and post-operative stroke. Secondary outcomes were cardiopulmonary bypass time (CPB), post-operative blood transfusion, length of ICU stay, respiratory complications, renal failure and length of hospital stay. Subgroup analysis of primary outcomes for Arch surgery alone was also performed. Results Fifteen studies were included with a total of 5869 patients. There was significantly reduced mortality (Pooled OR = +0.64, 95% CI = +0.49 to +0.83; p = 0.0006) and stroke rate (Pooled OR = +0.62, 95% CI = +0.49 to +0.79; p < 0.001) in the MHCA group. MHCA was associated significantly with shorter CPB times, shorter duration in ICU, less pulmonary complications, and reduced rates of sepsis. There was no statistical difference between the two groups in terms of circulatory arrest times, X-Clamp times, total operation duration, transfusion requirements, renal failure and post-op hospital stay. Conclusion MHCA + ACP are associated with significantly better post-operative outcomes compared with DHCA for both mortality and stroke and majority of the secondary outcomes.

The frequency of periodontitis in end-stage renal disease on hemodialysis in a sample of Egyptian population: multi-center clinical cross-sectional study

Background There is a general assumption that periodontal disease is highly prevalent among patients with chronic renal failure undergoing hemodialysis. The aim of the study to estimate the frequency of periodontitis in patients on hemodialysis among a sample of the Egyptian population, as well as the correlation between different clinical parameters of periodontal status with serum creatinine and blood urea. This may rule out the bidirectional relationship between periodontitis and renal failure in patients on hemodialysis. Methods The study was conducted on 263 hemodialysis patients (165 males and 98 females) at three dialysis centers in Benha Governorate, Egypt (Benha Hospital, Tukh hospital, Qalyub hospital). Periodontal parameters including plaque index (PI), gingival index (GI), clinical attachment level (CAL), and probing pocket depth (PPD) had been recorded in these patients. Serum urea and creatinine levels had been measured, the data had been collected and undergone statistical analysis. Results Frequency of periodontitis was 85.6% with stage III is the most prevalent stage. There was a significant positive strong correlation between age and periodontitis stage (rs = 0.707, p < 0.001). There was a positive correlation between clinical parameters and serum creatinine level. Conclusion In the present study, a high frequency of periodontitis had been found among ESRD patients on hemodialysis in the severe form (stage III) periodontitis. There was a significant direct correlation between the severity of periodontitis and CAL with a duration of hemodialysis. There was a weak insignificant association between periodontal indices (PD, BOP, and plaque score) and duration of hemodialysis.