The efficacy of pre-operative preparation with intravenous iron and/or erythropoietin in anaemic patients undergoing orthopaedic surgery: An observational study.

BACKGROUND: Pre-operative anaemia and transfusion are common among patients undergoing elective orthopaedic surgery. Application of 'patient blood management' might be the most effective way to reduce both anaemia and transfusion. Pre-operative administration of iron and/or erythropoietin (EPO) is one of the cornerstones of the first pillar of patient blood management, but in a daily clinical setting, efficacy and long-term safety of this measure have not been analysed thoroughly to date. OBJECTIVE: To investigate the influence of pre-operative preparation (PREP) of patients with iron and/or EPO on peri-operative transfusion needs and long-term survival. DESIGN: Single-centre, retrospective study. SETTING: Anaesthesia department, University hospital. INTERVENTIONS: Pre-operative preparation with iron and/or EPO versus no preparation. METHODS: After approval of our local ethics committee, data of 5518 patients who received total hip or total knee replacement between 2008 and 2014 were included. Patients receiving iron and/or EPO were included in the PREP group, whereas patients without iron and/or EPO were included in the no preparation group. From the full data set, a bias-reduced subset of 662 patients was obtained by means of propensity score-matching to compare peri-operative red blood cell utilisation and long-term survival of patients between groups. RESULTS: Patients in the PREP group needed a lower number of units of red blood cells than patients in the no preparation group (0.2 ±â€Š0.8 vs. 0.5 ±â€Š1.3, P < 0.001), had a lower transfusion rate (12 vs. 24%, P < 0.05) and had a similar haemoglobin concentration (10.7 ±â€Š1.3 vs. 10.6 ±â€Š1.1 g dl, not significant) at discharge. No differences in long-term survival were observed between the two study groups. CONCLUSION: PREP of patients with iron and/or EPO in orthopaedic patients can be considered highly effective in terms of transfusion reduction, without influencing long-term survival.

Machine learning-based risk profile classification of patients undergoing elective heart valve surgery.

OBJECTIVES: Machine learning methods potentially provide a highly accurate and detailed assessment of expected individual patient risk before elective cardiac surgery. Correct anticipation of this risk allows for the improved counselling of patients and avoidance of possible complications. We therefore investigated the benefit of modern machine learning methods in personalized risk prediction for patients undergoing elective heart valve surgery. METHODS: We performed a monocentric retrospective study in patients who underwent elective heart valve surgery between 1 January 2008 and 31 December 2014 at our centre. We used random forests, artificial neural networks and support vector machines to predict the 30-day mortality from a subset of 129 available demographic and preoperative parameters. Exclusion criteria were reoperation of the same patient, patients who needed anterograde cerebral perfusion due to aortic arch surgery and patients with grown-up congenital heart disease. Finally, the cohort consisted of 2229 patients with a 30-day mortality of 3.86% (86 of 2229 cases). This trial has been registered at clinicaltrials.gov (NCT03724123). RESULTS: The final random forest model trained on the entire data set provided an out-of-bag area under the receiver operator characteristics curve (AUC) of 0.839, which significantly outperformed the European System for Cardiac Operative Risk Evaluation (EuroSCORE) (AUC = 0.704) and a model trained only on the subset of features EuroSCORE uses (AUC = 0.745). CONCLUSIONS: Advanced machine learning methods can predict outcomes of valve surgery procedures with higher accuracy than established risk scores based on logistic regression on pre-selected parameters. This approach is generalizable to other elective high-risk interventions and allows for training models to the cohorts of specific institutions.