From Unit to Dose: A Machine Learning Approach for Precise Prediction of Hemoglobin and Iron Content in Individual Packed Red Blood Cell Units

New mechanistic insights on transferrin synthesis inhibition and release of bound iron mediated by lead loaded ultrafine carbon black

The obstruction of transferrin-mediated Fe3+ transport has been identified as a potential initiator for hepatic ferroptosis. However, the understanding of how environmental pollutants influence the Fe3+ transport of transferrin remains missing. In this study, we firstly developed a combination strategy to evaluate the impairment of conformation and function of transferrin induced by ultrafine carbon black under Pb2+ loading (Pb-UFCB) at cellular and protein molecular levels. Specifically, the exposure of Pb-UFCB led to a notable 46.3 ± 4.2 % reduction in transferrin expression, which can be ascribed to the oxidative DNA damage (203.3 ± 28.0 %) induced by reactive oxygen species and apoptosis mediated via mitochondrial pathway. Flow cytometry analysis revealed a dose-time-dependent increase in intracellular Pb2+ content. This escalation intensified the adverse effects of UFCB. Furthermore, at protein molecular levels, Pb-UFCB triggered a significant release of Fe3+ from transferrin (373.7 ± 25.0 % of control) by inducing the compact skeleton, reorganization of secondary structure and fluorescence sensitization of transferrin. Our results unveil the pathways of Fe3+ transport impairment of transferrin induced by Pb-UFCB, which can provide theoretical support for the prevention and diagnosis of ferroptosis-related diseases.

Implications of packed red bloods cells production and transfer on post transfusion hemoglobin increase

BACKGROUND

Blood loss resulting in severe anemia is the most common indication for postoperative allogenic red blood cell (RBC) transfusions. In high-income countries, the majority of transfusions is received by elderly patients. Preservatives extend the storage of RBCs, though concerns exist about potential harm from transfusing older RBCs. This study tested the hypothesis that RBC storage duration effects hemoglobin increase in patients older than 70 years who underwent non-cardiac surgery.

METHOD

Observations on surgical cohorts from two study sites of the LIBERAL-Trial were collected. Transfusion events and hemoglobin between 2018 and 2022 assessments in addition to manufacturing and product specific quality review information were evaluated.

RESULTS

A total of 1626 transfusion events in 505 patients were analyzed. A linear mixed effects model was used to estimate the effect size of different predictors on hemoglobin increment upon red blood cell transfusion. No statistically significant effect of the RBC unit storage duration was found. Confounding variables resulting in higher hemoglobin increase included lower hemoglobin values prior to transfusion, the length of Hb measurement intervals before and after transfusion, as well as the method of RBC cell separation in line with different manufacturer hemoglobin values.

CONCLUSIONS

The aspired increase in hemoglobin can be achieved with red blood cell concentrates of any storage duration. In general, elderly patients exhibit a sufficient hemoglobin rise following transfusion. However, if this is associated with improved outcomes cannot be answered.

Advancing Laboratory Medicine Practice With Machine Learning: Swift yet Exact

Machine learning (ML) is currently being widely studied and applied in data analysis and prediction in various fields, including laboratory medicine. To comprehensively evaluate the application of ML in laboratory medicine, we reviewed the literature on ML applications in laboratory medicine published between February 2014 and March 2024. A PubMed search using a search string yielded 779 articles on the topic, among which 144 articles were selected for this review. These articles were analyzed to extract and categorize related fields within laboratory medicine, research objectives, specimen types, data types, ML models, evaluation metrics, and sample sizes. Sankey diagrams and pie charts were used to illustrate the relationships between categories and the proportions within each category. We found that most studies involving the application of ML in laboratory medicine were designed to improve efficiency through automation or expand the roles of clinical laboratories. The most common ML models used are convolutional neural networks, multilayer perceptrons, and tree-based models, which are primarily selected based on the type of input data. Our findings suggest that, as the technology evolves, ML will rise in prominence in laboratory medicine as a tool for expanding research activities. Nonetheless, expertise in ML applications should be improved to effectively utilize this technology.

Connectivity in transfusion medicine: Challenges, benefits, and goals

Transfusion medicine requires meticulous record keeping from the time a blood donation is made to the time a patient receives a transfusion. As such, blood collection establishments and processing laboratories generate large amounts of data. This data must be managed, analyzed, and visualized appropriately to ensure safety of the blood supply. Today, the use of information technology (IT) solutions for data management in transfusion medicine varies widely between institutions. In this report, blood center professionals describe how they currently use IT solutions to improve their blood processing methods, the challenges they have, and how they envision IT solutions improving transfusion medicine in the future.

Circulating Biomarkers Instead of Genotyping to Establish Metabolizer Phenotypes

Pharmacogenomics (PGx) enables personalized treatment for the prediction of drug response and to avoid adverse drug reactions. Currently, PGx mainly relies on the genetic information of absorption, distribution, metabolism, and excretion (ADME) targets such as drug-metabolizing enzymes or transporters to predict differences in the patient's phenotype. However, there is evidence that the phenotype-genotype concordance is limited. Thus, we discuss different phenotyping strategies using exogenous xenobiotics (e.g., drug cocktails) or endogenous compounds for phenotype prediction. In particular, minimally invasive approaches focusing on liquid biopsies offer great potential to preemptively determine metabolic and transport capacities. Early studies indicate that ADME phenotyping using exosomes released from the liver is reliable. In addition, pharmacometric modeling and artificial intelligence improve phenotype prediction. However, further prospective studies are needed to demonstrate the clinical utility of individualized treatment based on phenotyping strategies, not only relying on genetics. The present review summarizes current knowledge and limitations.

High-sensitivity hemoglobin detection based on polarization-differential spectrophotometry

Hemoglobin content is recognized as a momentous and fundamental physiological indicator, especially the precise detection of trace hemoglobin is of great significance for early diagnosis and prevention of tumors, cancer, organic injury, etc. Therefore, high-sensitivity hemoglobin detection is imperative. However, effective detection methods and reliable detection systems are still lacking and remain enormous challenges. Herein, we present a synthetical strategy to break through the existing bottleneck based on polarization-differential spectrophotometry and high-performance single-frequency green fiber laser. Importantly, this framework not only has precisely extracted the two-dimensional information of intensity and polarization during the interaction between laser and hemoglobin, but also has taken advantage of the high monochromaticity and fine directivity in the optimized laser source to reduce the undesirable scattered disturbance. Thus, the hemoglobin detection sensitivity of 7.2 × 10-5 g/L has advanced a hundredfold compared with conventional spectrophotometry, and the responsive dynamic range is close to six orders of magnitude. Results indicate that our technology can realize high-sensitivity detection of trace hemoglobin content, holding promising applications for precision medicine and early diagnosis as an optical direct and fast detection method.

Predicting Thalassemia Using Feature Selection Techniques: A Comparative Analysis

Thalassemia represents one of the most common genetic disorders worldwide, characterized by defects in hemoglobin synthesis. The affected individuals suffer from malfunctioning of one or more of the four globin genes, leading to chronic hemolytic anemia, an imbalance in the hemoglobin chain ratio, iron overload, and ineffective erythropoiesis. Despite the challenges posed by this condition, recent years have witnessed significant advancements in diagnosis, therapy, and transfusion support, significantly improving the prognosis for thalassemia patients. This research empirically evaluates the efficacy of models constructed using classification methods and explores the effectiveness of relevant features that are derived using various machine-learning techniques. Five feature selection approaches, namely Chi-Square (χ2), Exploratory Factor Score (EFS), tree-based Recursive Feature Elimination (RFE), gradient-based RFE, and Linear Regression Coefficient, were employed to determine the optimal feature set. Nine classifiers, namely K-Nearest Neighbors (KNN), Decision Trees (DT), Gradient Boosting Classifier (GBC), Linear Regression (LR), AdaBoost, Extreme Gradient Boosting (XGB), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Support Vector Machine (SVM), were utilized to evaluate the performance. The χ2 method achieved accuracy, registering 91.56% precision, 91.04% recall, and 92.65% f-score when aligned with the LR classifier. Moreover, the results underscore that amalgamating over-sampling with Synthetic Minority Over-sampling Technique (SMOTE), RFE, and 10-fold cross-validation markedly elevates the detection accuracy for αT patients. Notably, the Gradient Boosting Classifier (GBC) achieves 93.46% accuracy, 93.89% recall, and 92.72% F1 score.