1 January 2021 in Seminars in Thoracic and Cardiovascular Surgery
1 July 2020 in Heart, Lung and Circulation
25 November 2022 in Acta Anaesthesiologica Scandinavica
Background: Patients undergoing cardiac surgery are at significant risk of developing postoperative acute kidney injury (AKI). Neutrophil–lymphocyte ratio (NLR) is a widely available inflammatory biomarker which may be of prognostic value in this setting.Methods: We conducted a systematic review and meta‐analysis of studies reporting associations between perioperative NLR with postoperative AKI. We searched Medline, Embase and the Cochrane Library, without language restriction, from inception to May 2022 for relevant studies. We meta‐analysed the reported odds ratios (ORs) with 95% confidence intervals (CIs) for both elevated preoperative and postoperative NLR with risk of postoperative AKI and need for renal replacement therapy (RRT). We conducted a meta‐regression to explore inter‐study statistical heterogeneity.Results: Twelve studies involving 10,724 participants undergoing cardiac surgery were included, with eight studies being deemed at high risk of bias using PROBAST modelling. We found statistically significant associations between elevated preoperative NLR and postoperative AKI (OR 1.45, 95% CI 1.18–1.77), as well as postoperative need for RRT (OR 2.37, 95% CI 1.50–3.72). Postoperative NLR measurements were not of prognostic significance.Conclusions: Elevated preoperative NLR is a reliable inflammatory biomarker for predicting AKI following cardiac surgery.
24 August 2022 in Journal of Cardiac Surgery
Machine learning (ML) models are promising tools for predicting adverse postoperative outcomes in cardiac surgery, yet have not translated to routine clinical use. We conducted a systematic review and meta‐analysis to assess the predictive performance of ML approaches. We conducted an electronic search to find studies assessing ML and traditional statistical models to predict postoperative outcomes. Our primary outcome was the concordance (C‐) index of discriminative performance. Using a Bayesian meta‐analytic approach we pooled the C‐indices with the 95% credible interval (CrI) across multiple outcomes comparing ML methods to logistic regression (LR) and clinical scoring tools. Additionally, we performed critical difference and sensitivity analysis. We identified 2792 references from the search of which 51 met inclusion criteria. Two postoperative outcomes were amenable for meta‐analysis: 30‐day mortality and in‐hospital mortality. For 30‐day mortality, the pooled C‐index and 95% CrI were 0.82 (0.79−0.85), 0.80 (0.77−0.84), 0.78 (0.74−0.82) for ML models, LR, and scoring tools respectively. For in‐hospital mortality, the pooled C‐index was 0.81 (0.78−0.84) and 0.79 (0.73−0.84) for ML models and LR, respectively. There were no statistically significant results indicating ML superiority over LR. In cardiac surgery patients, for the prediction of mortality, current ML methods do not have greater discriminative power over LR as measured by the C‐index.
4 July 2021 in Acta Ophthalmologica
10 July 2023 in Frontiers in Cardiovascular Medicine
Objectives: Machine learning (ML) classification tools are known to accurately predict many cardiac surgical outcomes. A novel approach, ML-based survival analysis, remains unstudied for predicting mortality after cardiac surgery. We aimed to benchmark performance, as measured by the concordance index (C-index), of tree-based survival models against Cox proportional hazards (CPH) modeling and explore risk factors using the best-performing model.Methods: 144,536 patients with 147,301 surgery events from the Australian and New Zealand Society of Cardiac and Thoracic Surgeons (ANZSCTS) national database were used to train and validate models. Univariate analysis was performed using Student's T-test for continuous variables, Chi-squared test for categorical variables, and stratified Kaplan-Meier estimation of the survival function. Three ML models were tested, a decision tree (DT), random forest (RF), and gradient boosting machine (GBM). Hyperparameter tuning was performed using a Bayesian search strategy. Performance was assessed using 2-fold cross-validation repeated 5 times.Results: The highest performing model was the GBM with a C-index of 0.803 (0.002), followed by RF with 0.791 (0.003), DT with 0.729 (0.014), and finally CPH with 0.596 (0.042). The 5 most predictive features were age, type of procedure, length of hospital stay, drain output in the first 4 h (ml), and inotrope use greater than 4 h postoperatively.Conclusion: Tree-based learning for survival analysis is a non-parametric and performant alternative to CPH modeling. GBMs offer interpretable modeling of non-linear relationships, promising to expose the most relevant risk factors and uncover new questions to guide future research.