Objective Veno-Arterial Extra Corporeal Life Support (VA ECLS) is widely used as an effective device for patients in cardiogenic shock. The need for predictive markers that daily guide physicians in the evaluation of these patients could be of great value. Our aim was to investigate the role of cholesterol value during VA ECLS in predicting the Intensive Care Unit (ICU) survival. Methods Between January 2013 and November 2019, 67 patients with VA ECLS due to cardiogenic shock were included in this study. Demographic data, laboratory values, ICU data and outcomes were collected. Cholesterol was measured during morning routine blood samples. The minimal cholesterol value during the ICU stay was registered. Groups were stratified by minimal cholesterol cut-off point of 2.0 mmol/L. Logistic regression analysis were performed to identify variables associated with ICU survival. Results The ECLS duration was not significantly different (p=0.36) between the non-survivors (median 5.0 (2.0-7.5) days) and survivors (median 6.0 (1.8-12.0) days). The minimal cholesterol level was significantly lower (p=0.04) in non-survivors group (1.54 (1.00-1.87) mmol/L) compared to survivors (1.85 (1.38-2.24) mmol/L). By using logistic regression analysis, minimal cholesterol level of ≥2.0 mmol/L was associated with a higher ICU survival (p=0.02; OR 3.77; 95% CI 1.20-11.81). Conclusion Cholesterol level could be an additional marker for ICU survival of patients with cardiogenic shock on VA ECLS. A larger cohort of patients is necessary to determine total cholesterol as a specific risk factor for survival in these patients.

Objective: To develop a prediction model to predict surgical re-intervention within two years after endometrial ablation (EA) by using a random forest technique (RF). The performance of the developed prediction model was then compared with a previously published multivariate logistic regression model (LR) (1). Design: Retrospective cohort study. Setting: Data from two non-university teaching hospitals in the Netherlands were used. Population: 446 pre-menopausal women who have had an EA for heavy menstrual bleeding between January 2004 and April 2013. Methods: The RF model was trained in MATLAB (2018b) using the TreeBagger function in the Statistics and Machine Learning Toolbox. Main outcome measures: The performance of the two models was compared using the area under the Receiving Operating Characteristic (ROC) curve (AUROC). Measurements and Main Results: The LR model had an AUC of 0.71 (95% CI 0.64-0.78). The RF model had an AUC of 0.63 (95% CI 0.54-0.71). and an AUC of 0.65 (95% CI 0.56-0.74) after hyperparameter optimization. Conclusion: The RF model is not superior compared to the LR model in predicting the outcome of surgical re-intervention within two years after EA. Machine learning techniques are gaining popularity in development of clinical prediction tools, but they are not necessarily superior to traditional statistical logistic regression techniques. The performance of a model is influenced by the sample size and the number of features, hyperparameter tuning and the linearity of associations. Both techniques should be considered when developing a prediction model.