Background: Perioperative anemia has been associated with increased risk of red blood cell transfusion and increased morbidity and mortality after surgery. The optimal approach to the diagnosis and management of perioperative anemia is not fully established. Objective: To develop consensus recommendations for anemia management in surgical patients. Methods: An international expert panel reviewed the current evidence and developed recommendations using modified RAND Delphi methodology. Results: The panel recommends that all patients except those undergoing minor procedures be screened for anemia before surgery. Appropriate therapy for anemia should be guided by an accurate diagnosis of the etiology. The need to proceed with surgery in some patients with anemia is expected to persist. However, early identification and effective treatment of anemia has the potential to reduce the risks associated with surgery and improve clinical outcomes. As with preoperative anemia, postoperative anemia should be treated in the perioperative period. Conclusions: Early identification and effective treatment of anemia has the potential to improve clinical outcomes in surgical patients.

Background: The ability to predict transfusions arising during hospital admission might enable economized blood supply management and might furthermore increase patient safety by ensuring a sufficient stock of red blood cells (RBCs) for a specific patient. We therefore investigated the precision of four different machine learning–based prediction algorithms to predict transfusion, massive transfusion, and the number of transfusions in patients admitted to a hospital.Study Design and Methods: This was a retrospective, observational study in three adult tertiary care hospitals in Western Australia between January 2008 and June 2017. Primary outcome measures for the classification tasks were the area under the curve for the receiver operating characteristics curve, the F₁ score, and the average precision of the four machine learning algorithms used: neural networks (NNs), logistic regression (LR), random forests (RFs), and gradient boosting (GB) trees.Results: Using our four predictive models, transfusion of at least 1 unit of RBCs could be predicted rather accurately (sensitivity for NN, LR, RF, and GB: 0.898, 0.894, 0.584, and 0.872, respectively; specificity: 0.958, 0.966, 0.964, 0.965). Using the four methods for prediction of massive transfusion was less successful (sensitivity for NN, LR, RF, and GB: 0.780, 0.721, 0.002, and 0.797, respectively; specificity: 0.994, 0.995, 0.993, 0.995). As a consequence, prediction of the total number of packed RBCs transfused was also rather inaccurate.Conclusion: This study demonstrates that the necessity for intrahospital transfusion can be forecasted reliably, however the amount of RBC units transfused during a hospital stay is more difficult to predict.

For many years, in daily clinical practice, the traditional 10/30 rule (hemoglobin 10 g/dL – hematocrit 30%) has been the most commonly used trigger for blood transfusions. Over the years, this approach is believed to have contributed to a countless number of unnecessary transfusions and an unknown number of overtransfusion-related deaths. Recent studies have shown that lower hemoglobin levels can safely be accepted, even in critically ill patients. However, even these new transfusion thresholds are far beyond the theoretical limits of individual anemia tolerance. For this reason, almost all publications addressing the limits of acute anemia recommend physiological transfusion triggers to indicate the transfusion of erythrocyte concentrates as an alternative. Although this concept appears intuitive at first glance, no solid scientific evidence supports the safety and benefit of physiological transfusion triggers to indicate the optimal time point for transfusion of allogeneic blood. It is therefore imperative to continue searching for the most sensitive and specific parameters that can guide the clinician when to transfuse in order to avoid anemia-induced organ dysfunction while avoiding overtransfusion-related adverse effects. This narrative review discusses the concept of anemia tolerance and critically compares hemoglobin-based triggers with physiological transfusion for various clinical indications.

Many previous studies claim to have developed machine learning models that diagnose COVID-19 from blood tests. However, we hypothesize that changes in the underlying distribution of the data, so called domain shifts, affect the predictive performance and reliability and are a reason for the failure of such machine learning models in clinical application. Domain shifts can be caused, e.g., by changes in the disease prevalence (spreading or tested population), by refined RT-PCR testing procedures (way of taking samples, laboratory procedures), or by virus mutations. Therefore, machine learning models for diagnosing COVID-19 or other diseases may not be reliable and degrade in performance over time. We investigate whether domain shifts are present in COVID-19 datasets and how they affect machine learning methods. We further set out to estimate the mortality risk based on routinely acquired blood tests in a hospital setting throughout pandemics and under domain shifts. We reveal domain shifts by evaluating the models on a large-scale dataset with different assessment strategies, such as temporal validation. We present the novel finding that domain shifts strongly affect machine learning models for COVID-19 diagnosis and deteriorate their predictive performance and credibility. Therefore, frequent re-training and re-assessment are indispensable for robust models enabling clinical utility.

Machine learning (ML) and artificial intelligence (AI) are widely used in many different fields of modern medicine. This narrative review gives, in the first part, a brief overview of the methods of ML and AI used in patient blood management (PBM) and, in the second part, aims at describing which fields have been analyzed using these methods so far. A total of 442 articles were identified by a literature search, and 47 of them were judged as qualified articles that applied ML and AI techniques in PBM. We assembled the eligible articles to provide insights into the areas of application, quality measures of these studies, and treatment outcomes that can pave the way for further adoption of this promising technology and its possible use in routine clinical decision making. The topics that have been investigated most often were the prediction of transfusion (30%), bleeding (28%), and laboratory studies (15%). Although in the last 3 years a constantly increasing number of questions of ML in PBM have been investigated, there is a vast scientific potential for further application of ML and AI in other fields of PBM.

Aims: Patient admission is a decision relying on sparsely available data. This study aims to provide prediction models for discharge versus admission for ward observation or intensive care, and 30 day-mortality for patients triaged with the Manchester Triage System. Methods: This is a single-centre, observational, retrospective cohort study from data within ten minutes of patient presentation at the interdisciplinary emergency department of the Kepler University Hospital, Linz, Austria. We trained machine learning models including Random Forests and Neural Networks individually to predict discharge versus ward observation or intensive care admission, and 30 day-mortality. For analysis of the features’ relevance, we used permutation feature importance. Results: A total of 58323 adult patients between 1 December 2015 and 31 August 2020 were included. Neural Networks and Random Forests predicted admission to ward observation with an AUC-ROC of 0.842 ± 0.00 with the most important features being age and chief complaint. For admission to intensive care, the models had an AUC-ROC of 0.819 ± 0.002 with the most important features being the Manchester Triage category and heart rate, and for the outcome 30 day-mortality an AUC-ROC of 0.925 ± 0.001. The most important features for the prediction of 30 day-mortality were age and general ward admission. Conclusion: Machine learning can provide prediction on discharge versus admission to general wards and intensive care and inform about risk on 30 day-mortality for patients in the emergency department.