Big data modeling to predict platelet usage and minimize wastage in a tertiary care system

Demand forecasting for platelet usage: From univariate time series to multivariable models

Platelet products are both expensive and have very short shelf lives. As usage rates for platelets are highly variable, the effective management of platelet demand and supply is very important yet challenging. The primary goal of this paper is to present an efficient forecasting model for platelet demand at Canadian Blood Services (CBS). To accomplish this goal, five different demand forecasting methods, ARIMA (Auto Regressive Integrated Moving Average), Prophet, lasso regression (least absolute shrinkage and selection operator), random forest, and LSTM (Long Short-Term Memory) networks are utilized and evaluated via a rolling window method. We use a large clinical dataset for a centralized blood distribution centre for four hospitals in Hamilton, Ontario, spanning from 2010 to 2018 and consisting of daily platelet transfusions along with information such as the product specifications, the recipients' characteristics, and the recipients' laboratory test results. This study is the first to utilize different methods from statistical time series models to data-driven regression and machine learning techniques for platelet transfusion using clinical predictors and with different amounts of data. We find that the multivariable approaches have the highest accuracy in general, however, if sufficient data are available, a simpler time series approach appears to be sufficient. We also comment on the approach to choose predictors for the multivariable models.

Characterizing the limitations of using diagnosis codes in the context of machine learning for healthcare

BACKGROUND

Diagnostic codes are commonly used as inputs for clinical prediction models, to create labels for prediction tasks, and to identify cohorts for multicenter network studies. However, the coverage rates of diagnostic codes and their variability across institutions are underexplored. The primary objective was to describe lab- and diagnosis-based labels for 7 selected outcomes at three institutions. Secondary objectives were to describe agreement, sensitivity, and specificity of diagnosis-based labels against lab-based labels.

METHODS

This study included three cohorts: SickKids from The Hospital for Sick Children, and StanfordPeds and StanfordAdults from Stanford Medicine. We included seven clinical outcomes with lab-based definitions: acute kidney injury, hyperkalemia, hypoglycemia, hyponatremia, anemia, neutropenia and thrombocytopenia. For each outcome, we created four lab-based labels (abnormal, mild, moderate and severe) based on test result and one diagnosis-based label. Proportion of admissions with a positive label were presented for each outcome stratified by cohort. Using lab-based labels as the gold standard, agreement using Cohen's Kappa, sensitivity and specificity were calculated for each lab-based severity level.

RESULTS

The number of admissions included were: SickKids (n = 59,298), StanfordPeds (n = 24,639) and StanfordAdults (n = 159,985). The proportion of admissions with a positive diagnosis-based label was significantly higher for StanfordPeds compared to SickKids across all outcomes, with odds ratio (99.9% confidence interval) for abnormal diagnosis-based label ranging from 2.2 (1.7-2.7) for neutropenia to 18.4 (10.1-33.4) for hyperkalemia. Lab-based labels were more similar by institution. When using lab-based labels as the gold standard, Cohen's Kappa and sensitivity were lower at SickKids for all severity levels compared to StanfordPeds.

CONCLUSIONS

Across multiple outcomes, diagnosis codes were consistently different between the two pediatric institutions. This difference was not explained by differences in test results. These results may have implications for machine learning model development and deployment.

Harnessing the potential of data-driven strategies to optimise transfusion practice

No one doubts the significant variation in the practice of transfusion medicine. Common examples are the variability in transfusion thresholds and the use of tranexamic acid for surgery with likely high blood loss despite evidence-based standards. There is a long history of applying different strategies to address this variation, including education, clinical guidelines, audit and feedback, but the effectiveness and cost-effectiveness of these initiatives remains unclear. Advances in computerised decision support systems and the application of novel electronic capabilities offer alternative approaches to improving transfusion practice. In England, the National Institute for Health and Care Research funded a Blood and Transplant Research Unit (BTRU) programme focussing on 'A data-enabled programme of research to improve transfusion practices'. The overarching aim of the BTRU is to accelerate the development of data-driven methods to optimise the use of blood and transfusion alternatives, and to integrate them within routine practice to improve patient outcomes. One particular area of focus is implementation science to address variation in practice.

Application of Time-Series Analysis and Expert Judgment in Modeling and Forecasting Blood Donation Trends in Zimbabwe

Background. Blood cannot be artificially manufactured, and there is currently no substitute for human blood. The supply of blood in transfusion facilities requires constant and timely collection of blood from donors. Modeling and forecasting trends in blood collections are critical for determining both the current and future capacity requirements and appropriate models of adequate blood provision. Objectives. The objective of this study is to determine blood collection or donation patterns and develop time-series models that can be updated and refined in predicting future blood donations in Zimbabwe when given the historical data. Materials and Methods. Monthly blood donation data for the period 2009 to 2019 were collected retrospectively from the National Blood Service Zimbabwe database. Time-series models (i.e., the Seasonal Autoregressive Integrated Moving Average [SARIMA] and Error, Trend and Seasonal [ETS]) models were applied and compared. The models were chosen because of their ability to handle the seasonality and other time-series components evident in the blood donation data. Expert opinions and experience were used in selecting the models and in making inferences in the analysis. Results. Time-series plots of blood donations showed seasonal patterns, with significant drops in blood donations in months associated with Zimbabwe's school holidays (April, August, and December) and public holidays. During these holidays, there is a reduced number of school donors, while at about the same time, there is increasing blood demand as a result of road accidents. Model identification procedures established the SARIMA ( 1 , 1 , 2 ) ( 0 , 1 , 1 ) 12 model as the appropriate model for forecasting total blood donation in Zimbabwe. The results and forecasts show an upward trend in blood donations. According to the accuracy measures used, the SARIMA model outperforms the ETS model. Conclusions. Expert knowledge in the blood donation process, coupled with statistical models, can help explain trends exhibited in blood donation data in Zimbabwe. These findings help the blood authorities plan for blood donor campaign drives. The findings are key indicators of where to allocate more resources toward blood donation and when to collect more blood units. The increasing blood donation projections ensure a stable blood bank inventory in the near future.

Highlights

A SARIMA model can be used to predict the flow of blood donations in Zimbabwe.The seasonal blood donation pattern peaks in the months of March, June/July, and September.The donations troughs are in the months of April, August, December, and January. These are the months coinciding with school holidays in Zimbabwe.Both the SARIMA and ETS models provided similar forecasts, but measures of fit and expert knowledge gave a slight preference to the SARIMA ( 1 , 1 , 2 ) ( 0 , 1 , 1 ) 12 model in predicting the flow of blood donations in Zimbabwe.These model results are useful for guiding allocation of blood donation resources and blood donation drive timing.

Liposomal Resveratrol Alleviates Platelet Storage Lesion via Antioxidation and the Physical Buffering Effect

Platelet transfusion is essential in the treatment of platelet-related diseases and the prevention of bleeding in patients with surgical procedures. Platelet transfusion efficacy and shelf life are limited mainly by the development of platelet storage lesion (PSL). Mitigating PSL is the key to prolonging the platelet shelf life and reducing wastage. Excess intracellular reactive oxygen species (ROS) are one of the main factors causing PSL. In this study, we explored a nanomedicine strategy to improve the quality and functions of platelets in storage. Resveratrol (Res), a natural plant product, is known for its antioxidative effect. However, medical applications of Res are limited due to its low water solubility and stability. Therefore, we used a resveratrol-loaded liposomal system (Res-Lipo) to better utilize the antioxidant effect of the drug. This study aimed to evaluate the effect of Res-Lipo on platelet oxidative stress and alleviation of PSL during the storage time. Res-Lipo scavenged intracellular ROS and inhibited platelet apoptosis and activation during storage. Res-Lipo not only maintained mitochondrial function but also improved platelet aggregation in response to adenosine 5'-diphosphate. These results revealed that Res-Lipo ameliorated PSL and prolonged the platelet survival time in vivo. The strategy provides a potential method for extending the platelet storage time and might be considered a potential and safe additive to alleviate PSL.

Blood Demand Forecasting and Supply Management: An Analytical Assessment of Key Studies Utilizing Novel Computational Techniques

Use of data-driven methodologies in enhancing blood transfusion practices is rising, leveraging big data, machine learning, and optimization techniques to improve demand forecasting and supply chain management. This review used a narrative approach to identify, evaluate, and synthesize key studies that considered novel computational techniques for blood demand forecasting and inventory management through a search of PubMed and Web of Sciences databases for studies published from January 01, 2016, to March 30, 2023. The studies were analyzed for their utilization of various techniques, and their strengths, limitations, and areas for improvement. Seven key studies were identified. The studies focused on different blood components using various computational methods, such as regression, machine learning, hybrid models, and time series models, across different locations and time periods. Key variables used for demand forecasting were largely derived from electronic health record data, including clinical related predictors such as laboratory test results and hospital census by location. Each study offered unique strengths and valuable insights into the use of data-driven methods in blood bank management. Common limitations were unknown generalizability to other healthcare settings or blood components, need for field-specific performance measures, lack of ABO compatibility consideration, and ethical challenges in resource allocation. While data-driven research in blood demand forecasting and management has progressed, limitations persist and further exploration is needed. Understanding these innovative, interdisciplinary methods and their complexities can help refine inventory strategies and address healthcare challenges more effectively, leading to more robust, accurate models to enhance blood management across diverse healthcare scenarios.

Platelet transfusion in adults: An update

Many patients worldwide receive platelet components (PCs) through the transfusion of diverse types of blood components. PC transfusions are essential for the treatment of central thrombocytopenia of diverse causes, and such treatment is beneficial in patients at risk of severe bleeding. PC transfusions account for almost 10% of all the blood components supplied by blood services, but they are associated with about 3.25 times as many severe reactions (attributable to transfusion) than red blood cell transfusions after stringent in-process leukoreduction to less than 10⁶ residual cells per blood component. PCs are not homogeneous, due to the considerable differences between donors. Furthermore, the modes of PC collection and preparation, the safety precautions taken to limit either the most common (allergic-type reactions and febrile non-hemolytic reactions) or the most severe (bacterial contamination, pulmonary lesions) adverse reactions, and storage and conservation methods can all result in so-called PC "storage lesions". Some storage lesions affect PC quality, with implications for patient outcome. Good transfusion practices should result in higher levels of platelet recovery and efficacy, and lower complication rates. These practices include a matching of tissue ABH antigens whenever possible, and of platelet HLA (and, to a lesser extent, HPA) antigens in immunization situations. This review provides an overview of all the available information relating to platelet transfusion, from donor and donation to bedside transfusion, and considers the impact of the measures applied to increase transfusion efficacy while improving safety and preventing transfusion inefficacy and refractoriness. It also considers alternatives to platelet component (PC) transfusion.

BUPNN: Manifold Learning Regularizer-Based Blood Usage Prediction Neural Network for Blood Centers

Blood centers are an essential component of the healthcare system, as timely blood collection, processing, and efficient blood dispatch are critical to the treatment of patients and the performance of the entire healthcare system. At the same time, an efficient blood dispatching system through the high-precision predictive capability of artificial intelligence is crucial for the efficiency improvement of the blood centers. However, the current artificial intelligence (AI) models for predicting blood usage do not meet the needs of blood centers. The challenges of AI models mainly include lower generalization ability in different hospitals, limited stability under missing values, and low interpretability. An artificial neural network-based model named the blood usage prediction neural network (BUPNN) has been developed to address these challenges. BUPNN includes a novel similarity-based manifold regularizer that aims to enhance network mapping consistency and, thus, overcome the domain bise of different hospitals. Moreover, BUPNN diminishes the performance degradation caused by missing values through data enhancement. Experimental results on a large amount of accurate data demonstrate that BUPNN outperforms the baseline method in classification and regression tasks and excels in generalization and consistency. Moreover, BUPNN has solid potential to be interpreted. Therefore, the decision-making process of BUPNN is explored to the extent that it acts as an aid to the experts in the blood center.

A data-driven approach to determine daily platelet order quantities at hospitals

BACKGROUND

Determining the required daily number of platelet units in hospitals is a challenging task due to the high uncertainty in daily usage and short shelf life of platelets.

STUDY DESIGN AND METHODS

We developed a linear prediction model to guide the daily ordering quantity of platelet units at a hospital that orders the required units from a central supplier. The predictive model relies on historical demand data and other information from the hospital's information system. The ordering strategy is to place an order at the end of each day to bring the platelet inventory to the predicted demand for the next day. Unlike typical prediction models, the quality of the predictions is measured with respect to the resulting inventory costs of wastage and shortage. We used data from two hospitals in Hamilton, Ontario from 2015 to 2016 to train our model and evaluated its performance based on the resulting wastage and shortage rates in 2017.

RESULTS

In 2017, respectively 1915 and 4305 platelet units were transfused at the two hospitals, with daily average (SD) usage of 5.2 (3.7) and 11.8 (4.4). The expiry (estimated shortage) rates were 8.67% (13.86%), and 2.28% (8.48%) at the two hospitals, respectively. Our baseline model would have reduced the expiry (shortage) rates to 2.54% (4.01%) and 0.05% (0.44%) for the two hospitals, respectively.

DISCUSSION

Guiding daily ordering decisions for platelets using our proposed model could lead to a significant reduction of wastage and shortage rates at hospitals.

Cold-stored platelet function is not significantly altered by agitation or manual mixing

BACKGROUND

Cold storage of platelets (CS-PLT), results in better maintained hemostatic function compared to room-temperature stored platelets (RT-PLT), leading to increased interest and use of CS-PLT for actively bleeding patients. However, questions remain on best storage practices for CS-PLT, as agitation of CS-PLT is optional per the United States Food and Drug Administration. CS-PLT storage and handling protocols needed to be determined prior to upcoming clinical trials, and blood banking standard operating procedures need to be updated accordingly for the release of units due to potentially modified aggregate morphology without agitation.

STUDY DESIGN AND METHODS

We visually assessed aggregate formation, then measured surface receptor expression (GPVI, CD42b (GPIbα), CD49 (GPIa/ITGA2), CD41/61 (ITGA2B/ITGB3; GPIIB/GPIIIA; PACI), CD62P, CD63, HLAI), thrombin generation, aggregation (collagen, adenosine diphosphate [ADP], and epinephrine activation), and viscoelastic function (ExTEM, FibTEM) in CS-PLT (Trima collection, 100% plasma) stored for 21 days either with or without agitation (Phase 1, n = 10 donor-paired units) and then without agitation with or without daily manual mixing to minimize aggregate formation and reduce potential effects of sedimentation (Phase 2, n = 10 donor-paired units).

RESULTS

Agitation resulted in macroaggregate formation, whereas no agitation caused film-like sediment. We found no substantial differences in CS-PLT function between storage conditions, as surface receptor expression, thrombin generation, aggregation, and clot formation were relatively similar between intra-Phase storage conditions.

DISCUSSION

Storage duration and not condition impacted phenotype and function. CS-PLT can be stored with or without agitation, and with or without daily mixing and standard metrics of hemostatic function will not be significantly altered.

Statistical Learning and Uncommon Soil Microbiota Explain Biogeochemical Responses after Wildfire

Wildfires are a perennial event globally, and the biogeochemical underpinnings of soil responses at relevant spatial and temporal scales are unclear. Soil biogeochemical processes regulate plant growth and nutrient losses that affect water quality, yet the response of soil after variable intensity fire is difficult to explain and predict. To address this issue, we examined two wildfires in Colorado, United States, across the first and second postfire years and leveraged statistical learning (SL) to predict and explain biogeochemical responses. We found that SL predicts biogeochemical responses in soil after wildfire with surprising accuracy. Of the 13 biogeochemical analytes analyzed in this study, 9 are best explained with a hybrid microbiome + biogeochemical SL model. Biogeochemical-only models best explain 3 features, and 1 feature is explained equally well with the hybrid and biogeochemical-only models. In some cases, microbiome-only SL models are also effective (such as predicting NH₄⁺). Whenever a microbiome component is employed, selected features always involve uncommon soil microbiota (i.e., the "rare biosphere" [existing at <1% mean relative abundance]). Here, we demonstrate that SL paired with DNA sequence and biogeochemical data predicts environmental features in postfire soils, although this approach could likely be applied to any biogeochemical system. IMPORTANCE Soil biogeochemical processes are critical to plant growth and water quality and are substantially disturbed by wildfire. However, soil responses to fire are difficult to predict. To address this issue, we developed a large environmental data set that tracks postfire changes in soil and used statistical learning (SL) to build models that exploit complex data to make predictions about biogeochemical responses. Here, we show that SL depends upon uncommon microbiota in soil (the "rare biosphere") to make surprisingly accurate predictions about soil biogeochemical responses to wildfire. Using SL to explain variation in a natively chaotic environmental system is mechanism independent. Likely, the approach that we describe for combining SL with microbiome and biogeochemical parameters has practical applications across a range of issues in the environmental sciences where predicting responses would be useful.

A robust autonomous method for blood demand forecasting

Background

Blood supply chain management requires estimates about the demand of blood products. The more accurate these estimates are, the less wastage and fewer shortages occur. While the current literature demonstrates tangible benefits from statistical forecasting approaches, it highlights issues that discourage their use in blood supply chain optimization: there is no single approach that works everywhere, and there are no guarantees that any favorable method performance continues into the future.

Study Design and Methods

We design a novel autonomous forecasting system to solve the aforementioned issues. We show how possible changes in blood demand could affect prediction performance using partly synthetic demand data. We use these data then to investigate the performances of different method selection heuristics. Finally, the performances of the heuristics and single method approaches were compared using historical demand data from Finland and the Netherlands. The development code is publicly accessible.

Results

We find that a shift in the demand signal behavior from stochastic to seasonal would affect the relative performances of the methods. Our autonomous system outperforms all examined individual methods when forecasting the synthetic demand series, exhibiting meaningful robustness. When forecasting with real data, the most accurate methods in Finland and in the Netherlands are the autonomous system and the method average, respectively.

Discussion

Optimal use of method selection heuristics, as with our autonomous system, may overcome the need to constantly supervise forecasts in anticipation of changes in demand while being sufficiently accurate in the absence of such changes.

Autophagy Ameliorates Reactive Oxygen Species-Induced Platelet Storage Lesions

Platelet transfusion is a life-saving therapy to prevent bleeding; however, the availability of platelets for transfusion is limited by the markedly short shelf life owing to the development of platelet storage lesions (PSLs). The mechanism of PSLs remains obscure. Dissection of the intracellular biological changes in stored platelets may help to reduce PSLs and improve platelet transfusion efficiency. In the present study, we explore the changes of stored platelets at room temperature under constant agitation. We found that platelets during storage showed an increased reactive oxygen species (ROS) generation accompanied with receptor shedding, apoptosis, and diminished platelet aggregation. ROS scavenger reduced platelet shedding but also impaired platelet aggregation. Autophagy is a conserved catabolic process that sequesters protein aggregates and damaged organelles into lysosomes for degradation and platelets’ own intact autophagic system. We revealed that there exist a stable autophagic flux in platelets at the early stage of storage, and the autophagic flux in platelets perished after long-term storage. Treatment stored platelets with rapamycin, which stimulates autophagy in eukaryotic cells, markedly ameliorated PSLs, and improved platelet aggregation in response to extracellular stimuli.

Reduction of Platelet Outdating and Shortage by Forecasting Demand With Statistical Learning and Deep Neural Networks: Modeling Study

Background

Platelets are a valuable and perishable blood product. Managing platelet inventory is a demanding task because of short shelf lives and high variation in daily platelet use patterns. Predicting platelet demand is a promising step toward avoiding obsolescence and shortages and ensuring optimal care.

Objective

The aim of this study is to forecast platelet demand for a given hospital using both a statistical model and a deep neural network. In addition, we aim to calculate the possible reduction in waste and shortage of platelets using said predictions in a retrospective simulation of the platelet inventory.

Methods

Predictions of daily platelet demand were made by a least absolute shrinkage and selection operator (LASSO) model and a recurrent neural network (RNN) with long short-term memory (LSTM). Both models used the same set of 81 clinical features. Predictions were passed to a simulation of the blood inventory to calculate the possible reduction in waste and shortage as compared with historical data.

Results

From January 1, 2008, to December 31, 2018, the waste and shortage rates for platelets were 10.1% and 6.5%, respectively. In simulations of platelet inventory, waste could be lowered to 4.9% with the LASSO and 5% with the RNN, whereas shortages were 2.1% and 1.7% with the LASSO and RNN, respectively. Daily predictions of platelet demand for the next 2 days had mean absolute percent errors of 25.5% (95% CI 24.6%-26.6%) with the LASSO and 26.3% (95% CI 25.3%-27.4%) with the LSTM (P=.01). Predictions for the next 4 days had mean absolute percent errors of 18.1% (95% CI 17.6%-18.6%) with the LASSO and 19.2% (95% CI 18.6%-19.8%) with the LSTM (P<.001).

Conclusions

Both models allow for predictions of platelet demand with similar and sufficient accuracy to significantly reduce waste and shortage in a retrospective simulation study. The possible improvements in platelet inventory management are roughly equivalent to US $250,000 per year.

The path from big data analytics capabilities to value in hospitals: a scoping review

BACKGROUND

As the uptake of health information technologies increased, most healthcare organizations have become producers of big data. A growing number of hospitals are investing in the development of big data analytics (BDA) capabilities. If the promises associated with these capabilities are high, how hospitals create value from it remains unclear. The present study undertakes a scoping review of existing research on BDA use in hospitals to describe the path from BDA capabilities (BDAC) to value and its associated challenges.

METHODS

This scoping review was conducted following Arksey and O'Malley's 5 stages framework. A systematic search strategy was adopted to identify relevant articles in Scopus and Web of Science. Data charting and extraction were performed following an analytical framework that builds on the resource-based view of the firm to describe the path from BDA capabilities to value in hospitals.

RESULTS

Of 1,478 articles identified, 94 were included. Most of them are experimental research (n=69) published in medical (n=66) or computer science journals (n=28). The main value targets associated with the use of BDA are improving the quality of decision-making (n=56) and driving innovation (n=52) which apply mainly to care (n=67) and administrative (n=48) activities. To reach these targets, hospitals need to adequately combine BDA capabilities and value creation mechanisms (VCM) to enable knowledge generation and drive its assimilation. Benefits are endpoints of the value creation process. They are expected in all articles but realized in a few instances only (n=19).

CONCLUSIONS

This review confirms the value creation potential of BDA solutions in hospitals. It also shows the organizational challenges that prevent hospitals from generating actual benefits from BDAC-building efforts. The configuring of strategies, technologies and organizational capabilities underlying the development of value-creating BDA solutions should become a priority area for research, with focus on the mechanisms that can drive the alignment of BDA and organizational strategies, and the development of organizational capabilities to support knowledge generation and assimilation.

From demand forecasting to inventory ordering decisions for red blood cells through integrating machine learning, statistical modeling, and inventory optimization

BACKGROUND

The demand and supply of blood are highly variable over time. Blood inventory management that relies heavily on experience-based decisions may not be adaptive to real demand, leading to high operational costs, wastage, and shortages.

METHODS

We combined statistical modeling, machine learning, and optimization methods to develop a data-driven demand forecasting and inventory management strategy for red blood cells (RBCs). We then used the strategy to inform daily blood orders. A secondary semi-weekly (twice per week) ordering strategy was developed to handle the last-mile split delivery problem for blood suppliers, characterized by multi-deliveries to the same location multiple times during a short period of time. Both strategies were evaluated using the TRUST database including all patient data across four hospitals in Hamilton, Ontario.

RESULTS

We identified 227,944 RBC transfusions for 40,787 patients in Hamilton, Ontario from 2012 to 2018. The predicted daily demand from the hybrid demand forecasting model was not significantly different from the actual daily demand (paired t-test p-value = 0.163); however, the proposed daily ordering quantity from the model was significantly lower than the actual ordering quantity (p-value <0.001). The proposed daily ordering strategy reduced inventory levels by 38.4% without risk of shortages, leading to an overall cost reduction of 43.0% (95% confidence interval [CI]: 42.3%, 43.7%) compared with the actual cost. The semi-weekly ordering strategy reduced ordering frequency by 62.6% (95% CI: 61.5%, 63.7%).

CONCLUSION

The proposed data-driven ordering strategy combining demand forecasting and inventory optimization can achieve significant cost savings for healthcare systems and blood suppliers.

Transfusion Medicine Informatics: A Review of Current Practice and a Glimpse into the Future

Clinical informatics has been described as the "relentless pursuit of assisting people" by using data and information technology to improve health care. A core principle is that a person supported by information technology is superior to either a person or machine alone. Striving toward this harmonization, the transfusion medicine field has had a significant number of accomplishments. Clinical informatics interventions have helped achieve better quality, efficiency, and safety in nearly all aspects of transfusion medicine. This review summarizes these accomplishments and provides a preview of novel ideas that could transform transfusion medicine into a proactive, data-driven, and patient-centered discipline.

A survey of US hospitals on platelet inventory management, transfusion practice, and platelet availability

BACKGROUND

A survey of US hospitals was conducted to increase our understanding of the current state of platelet (PLT) practice and supply. The survey captures information on transfusion practice and inventory management, including stock levels, outdate rates, ability to return or transfer PLTs, and low dose PLTs. Notably, the survey also elucidates PLT availability challenges and impact to patient care.

STUDY DESIGN AND METHODS

A 27 question online survey was distributed directly to over 995 US hospitals and indirectly through blood centers to many more between September 27 and October 25, 2019. Descriptive statistics were used for respondent characteristics. Bivariate analysis was performed and correlation coefficients, chi square tests, and p values determined statistical significance of relationships between variables.

RESULTS

Four hundred and eighty-one hospitals completed the survey of which 21.6%, 53.2%, and 25.2% were characterized as small, medium, and large hospitals, respectively. Some key observations from this survey include: (1) there is an opportunity for greater adherence to evidence-based guidelines; (2) higher outdate rates occur in hospitals stocking less than five PLTs and the ability to return or transfer PLTs lowers outdates; (3) use of low dose apheresis PLTs varies; and (4) decreased PLT availability is commonly reported, especially in hospitals with high usage, and can lead to delays in transfusions or surgeries.

CONCLUSION

This survey represents a comprehensive national assessment of inventory management practices and PLT availability challenges in US hospitals. Findings from this survey can be used to guide further research, help shape future guidance for industry, and assist with policy decisions.

Blood usage at a large academic center in Maryland in relation to the COVID-19 pandemic in 2020

BACKGROUND

Blood usage and collections were impacted throughout 2020 both by the severity of the COVID-19 pandemic as well as public health decisions affecting hospital operations. We sought to understand the longer-term effects of the pandemic on blood usage via changes in case volume and clinical intensity as well as whether the blood needs of COVID-19-positive patients differed from other transfused patients.

STUDY DESIGN AND METHODS

A single-center retrospective study of blood use in 2020 as compared to 2014-2019 was conducted at a tertiary care center. Statistical analysis was performed in an R-based workflow. p values are reported using two-sided t-tests for total hospital blood usage and using Mann-Whitney U tests for comparisons of patient blood usage.

RESULTS

Mean monthly red cell usage in 2020 decreased by 11.2% (p = .003), plasma usage decreased by 23.8%, (p < .001) platelet usage decreased by 11.4% (p < .001), and monthly cryoprecipitate use increased by 18% (p = .03). A linear regression model predicted significant associations between total blood usage and the year, number of Medicare eligible discharges, and Case Mix Index. COVID-19-positive patients requiring at least one blood product did not use significantly different amounts of red cells, plasma, or platelets from all other transfused patients.

CONCLUSIONS

Year 2020 began with decreased blood usage that was normalized by late spring. Reassuringly, transfused COVID-19-positive patients in general and those requiring ICU level care do not use significantly increased amounts of blood as compared to similar transfused hospital patients.

RBC Inventory-Management System Based on XGBoost Model

It is difficult to predict RBC consumption accurately. This paper aims to use big data to establish a XGBoost Model to understand the trend of RBC accurately, and forecast the demand in time. XGBoost, which implements machine learning algorithms under the Gradient Boosting framework can provide a parallel tree boosting. The daily RBC usage and inventory (May 2014-September 2017) were investigated, and rules for RBC usage were analysed. All data were divided into training sets and testing sets. A XGBoost Model was established to predict the future RBC demand for durations ranging from a day to a week. In addition, the alert range was added to the predicted value to ensure RBC demand of emergency patients and surgical accidents. The gap between RBC usage and inventory was fluctuant, and had no obvious rule. The maximum residual inventory of a certain blood group was up to 700 units one day, while the minimum was nearly 0 units. Upon comparing MAE (mean absolute error):A:10.69, B:11.19, O:10.93, and AB:5.91, respectively, the XGBoost Model was found to have a predictive advantage over other state-of-the-art approaches. It showed the model could fit the trend of daily RBC usage. An alert range could manage the demand of emergency patients or surgical accidents. The model had been built to predict RBC demand, and the alert range of RBC inventory is designed to increase the safety of inventory management.

Adverse events associated with donor plateletpheresis: 10 years’ experience from Vojvodina, Serbia

Background/Aim. Plateletpheresis is a medical procedure used for the collection of donor platelets with multiple benefits for patients who will receive apheresis platelets. The procedure takes one hour and is well tolerated by donors. Nevertheless, adverse events may occur during and after the plateletpheresis procedure. The aim was to present one centre experiences in order to determine the incidence and type of adverse events associated with donor plateletpheresis. Methods. A retrospective analysis of adverse events associated with donor plateletpheresis was conducted in the Blood Transfusion Institute of Vojvodina over the period from January 1, 2010 through December 31, 2019. Results. Out of 2073 platelet donors 94.84% were multiple blood donors, predominantly male (98.55%). Adverse events were identified during 180 (8.68%) platelet donations with no statistical significance in occurrence in the first time (10.28%) and repeat donors (8.59%). Mild local reactions related to venous access (42.22%) were the most common adverse events. Generalized symptoms exhibited 16.67% of donors, 26.11% exhibited symptoms related to apheresis - citrate reactions and 15% exhibited those related to other complications. During plateletpheresis occurred 95.55% adverse events and 4.45% after. Conclusion. Donor plateletpheresis is a generally safe procedure, well tolerated by donors. Understanding risk factors for possible occurrence of adverse events provide support for adoption of measures to prevent them.

Antioxidant prevents clearance of hemostatically competent platelets after long-term cold storage

BACKGROUND

Cold storage of platelets (PLTs) has the potential advantage of prolonging storage time while reducing posttransfusion infection given the decreased likelihood of bacterial outgrowth during storage and possibly beneficial effects in treating bleeding patients. However, cold storage reduces PLT survival through the induction of complex storage lesions, which are more accentuated when storage is prolonged.

STUDY DESIGN AND METHODS

Whole blood-derived PLT-rich plasma concentrates from seven PLT pools (n = 5 donors per pool). PLT additive solution was added (67%/33% plasma) and the product was split into 50-mL bags. Split units were stored in the presence or absence of 1 mM of N-acetylcysteine (NAC) under agitation for up to 14 days at room temperature or in the cold and were analyzed for PLT activation, fibrinogen-dependent spreading, microparticle formation, mitochondrial respiratory activity, reactive oxygen species (ROS) generation, as well as in vivo survival and bleeding time correction in immunodeficient mice.

RESULTS

Cold storage of PLTs for 7 days or longer induces significant PLT activation, cytoskeletal damage, impaired fibrinogen spreading, enhances mitochondrial metabolic decoupling and ROS generation, and increases macrophage-dependent phagocytosis and macrophage-independent clearance. Addition of NAC prevents PLT clearance and allows a correction of the prolonged bleeding time in thrombocytopenic, aspirin-treated, immunodeficient mice.

CONCLUSIONS

Long-term cold storage induces mitochondrial uncoupling and increased proton leak and ROS generation. The resulting ROS is a crucial contributor to the increased macrophage-dependent and -independent clearance of functional PLTs and can be prevented by the antioxidant NAC in a magnesium-containing additive solution.

Platelets transfusion in Greece: Where, when, why? A national survey

BACKGROUND

Platelet transfusion is among the most useful therapeutic tools in modern clinical settings which mean that ensuring an adequate supply is of paramount importance.

AIM

The aim of our study was to record the use and wastage of platelet concentrates (PCs) in Greece, so as to come up with evidence-based interventions.

METHODS

The study was conducted during May and June 2015. We evaluated the use of random-donor platelets (RDPs) and single-donor apheresis platelets (SDPs). We analyzed such parameters as hospital department and diagnosis, indication for transfusion, PCs' age at the time of transfusion, and wastage rate.

RESULTS

We used data from 21 hospitals across the country. A total of 12,061 RDPs and 1189 SDPs were transfused, with an average of 4.84 (±2.72) and 1.12 (±2.73) units per episode, respectively. Most patients had been admitted to the internal medicine and hematology departments. The transfusions were mostly given prophylactically, usually in cases of acute leukemia, and mostly on the day before expiration. Wastage rate was 16.75% for RPDs and 2.70% for SDPs, primarily because of the expiration of the use-by date.

CONCLUSIONS

This is the first national survey regarding platelet transfusion in Greece. Since most patients were admitted in internal medicine and hematology departments, we recommend that the staff of the abovementioned departments should undergo training on contemporary transfusion guidelines. Platelet discard rate could further be lowered through the centralization of inventory management along with the extension of the lifetime of PCs by means of emerging technologies.

Effects of amotosalen treatment on human platelet lysate bioactivity: A proof-of-concept study

BACKGROUND

Clinical application of mesenchymal stromal cells (MSCs) usually requires an in vitro expansion step to reach clinically relevant numbers. In vitro cell expansion necessitates supplementation of basal mammalian cell culture medium with growth factors. To avoid using supplements containing animal substances, human platelet lysates (hPL) produced from expired and pathogen inactivated platelet concentrates can be used in place of fetal bovine serum. However, globally, most transfusion units are currently not pathogen inactivated. As blood banks are the sole source of platelet concentrates for hPL production, it is important to ensure product safety and standardized production methods. In this proof-of-concept study we assessed the feasibility of producing hPL from expired platelet concentrates with pathogen inactivation applied after platelet lysis by evaluating the retention of growth factors, cytokines, and the ability to support MSC proliferation and tri-lineage differentiation.

METHODOLOGY/PRINCIPAL FINDINGS

Bone marrow-derived MSCs (BM-MSCs) were expanded and differentiated using hPL derived from pathogen inactivated platelet lysates (hPL-PIPL), with pathogen inactivation by amotosalen/ultraviolet A treatment applied after lysis of expired platelets. Results were compared to those using hPL produced from conventional expired pathogen inactivated platelet concentrates (hPL-PIPC), with pathogen inactivation applied after blood donation. hPL-PIPL treatment had lower concentrations of soluble growth factors and cytokines than hPL-PIPC treatment. When used as supplementation in cell culture, BM-MSCs proliferated at a reduced rate, but more consistently, in hPL-PIPL than in hPL-PIPC. The ability to support tri-lineage differentiation was comparable between lysates.

CONCLUSION/SIGNIFICANCE

These results suggest that functional hPL can be produced from expired and untreated platelet lysates by applying pathogen inactivation after platelet lysis. When carried out post-expiration, pathogen inactivation may provide a valuable solution for further standardizing global hPL production methods, increasing the pool of starting material, and meeting future demand for animal-free supplements in human cell culturing.

Blood product wastage reduction by utilising low-cost, low-impact multimodal physician-to-physician communication initiatives

OBJECTIVES

To assess a multimodal physician-to-physician communication initiative that is low in cost and impact to daily workflow to reduce blood product wastage.

BACKGROUND

Blood product stewardship is an important issue in all hospital systems. Previous studies have proposed low-cost interventions to reduce blood product wastage, but few have evaluated improvements in communication between the blood bank and providers. We undertook a prospective quality improvement project focusing on improving communication to reduce blood product wastage.

METHODS

We conducted a prospective quality improvement project over the first quarter of 2017, identifying patients with issued but unused blood products. Each service overseeing the care of patients identified on the unit status report was contacted through two possible methods: (i) phone or (ii) proprietary Health Insurance Portability and Accountability Act of 1996 compliant digital messaging application. Collected variables included reserved blood product type and participant time spent. Outcomes included the rate of blood product release and changes in wastage compared with historical data tracked by the blood bank.

RESULTS

Eight hundred and forty products were reserved during the study period, of which 436 (52%) were released. Average participant times ranged from 2 ± 1 min to 15 ± 4 min with no significant differences in time spent between participants (P = 0·194). Compared with the average product wastage 10 months prior to project initiation, there were significant reductions in the average wastage for platelets (5·3 ± 2·5 units vs 2·5 ± 1·5 units, P = 0·05), RBCs (6·1 ± 3·7 units vs 0 ± 0 units, P = 0·01) and overall wastage (58·3 ± 14·9 units vs 40 ± 15·7 units, P = 0·05).

CONCLUSION

Efforts focusing on improving provider-to-provider communication can reduce blood product wastage.

Is Platelet Expiring Out of Date? A Systematic Review

Current platelet concentrates are perishable blood products with short shelf lives. Combined with often unpredictable demand, this results in platelet inventory management problems, manifested by high rates of outdating frequently reported at 10% to 20%, and sometimes inadequate clinical supply. The objective of this study was to critically review the published methodologies on measures to reduce platelet outdating rates, in order to determine how platelet outdating and availability can be improved. We performed a systematic review of journal articles published in English to May 2019 identified from MEDLINE, with reported methods to improve platelet inventory outdating rates and availability. The complexity of each methodology was scored based on whether a typical blood bank manager could design, implement and run a platelet outdating program based on the methodology. Twenty-four relevant citations were found-these included 8 citations employing operational research (OR) methodologies, 7 evaluation/best practice, 6 simulation and 3 forecasting. Over half the included studies have been published within the last decade. The citations reporting the lowest predicted outdating were also the most complex methods. Overall predicted outdating and shortages were less than 4% based on the available data. In conclusion, we found that research interest in platelet inventory management problems has increased in line with platelet demand and methods to assist in reducing outdating rates without increased shortages have been available now for 4 decades; high rates of platelet outdating do however continue to be reported around the world. Developments in platelet preparation and storage, and other new approaches, may assist in addressing this problem.

Production and Quality Requirements of Human Platelet Lysate: A Position Statement from the Working Party on Cellular Therapies of the International Society of Blood Transfusion

Human platelet lysate (HPL), rich in growth factors, is an efficient alternative supplement to fetal bovine serum (FBS) for ex vivo propagation of stromal cell-based medicinal products. Since 2014, HPL has been a focus of the Working Party for Cellular Therapies of the International Society of Blood Transfusion (ISBT). Currently, as several Good Manufacturing Practice (GMP)-compliant manufacturing protocols exist, an international consensus defining the optimal modes of industrial production, product specification, pathogen safety, and release criteria of this ancillary material (AM) is needed. This opinion article by the ISBT Working Party summarizes the current knowledge on HPL production and proposes recommendations on manufacturing and quality management in line with current technological innovations and regulations of biological products and advanced therapy medicinal products.

Development and Implementation of Real-Time Web-Based Dashboards in a Multisite Transfusion Service

Background:

In hospital transfusion services, visualization of blood product inventory in the form of web-based dashboards has the potential to improve the workflow and efficiency of blood product inventory management. While off-the-shelf “business intelligence” solutions by external vendors may offer the ability to display and analyze blood bank inventory data, laboratories may lack resources to readily access this technology. Using in-house talent, our transfusion service developed real-time, web-based dashboards to replace manual processes for managing both blood product inventory and cooler tracking at two large academic hospital blood banks.

Methods:

Dashboards were developed using Hypertext Markup Language, Cascading Style Sheets, and Hypertext Preprocessor scripting/programming languages. Data are extracted in real time from Sunquest (v7.3) Laboratory Information Systems Database (InterSystems Cache) and are refreshed every 2 min. Data are hosted internally by our institution's web servers and are accessed on a webpage via Microsoft Group Policy shortcuts.

Results:

Dashboards were designed and implemented to provide a fully customizable, dynamic, and secure method of displaying blood product inventory and blood product cooler status. Transfusion service staff utilized dashboard data to maintain adequate blood product supply, modify blood product replacement orders to prevent excess inventory, and transfer short-dated blood products between our facilities to minimize wastage.

Conclusions:

Dashboard technology can be readily implemented at hospital transfusion services with minimal capital expenditure. The implementation of real-time web-based dashboards for blood product inventory and cooler management at our centers facilitated on-demand blood product monitoring and replaced a tedious, manual process with a user-friendly and intuitive electronic tool.

A double-virally-inactivated (Intercept-solvent/detergent) human platelet lysate for in vitro expansion of human mesenchymal stromal cells

BACKGROUND

Pooled human platelet lysate (HPL) can replace fetal bovine serum (FBS) as xeno-free supplement for ex vivo expansion of mesenchymal stromal cells (MSCs). We evaluate here whether a double-virally-inactivated HPL (DVI-HPL) prepared from expired Intercept-treated platelet concentrates (PCs) and treated by solvent/detergent (S/D) can be used for MSC expansion.

STUDY DESIGN AND METHODS

Expired Intercept-treated PCs in 65% platelet (PLT) additive solution were pooled and subjected to a 1% tri-n-butyl phosphate/1% Triton X-45 treatment followed by soybean oil, hydrophobic interaction chromatography purification, and sterile filtration. Bone marrow-derived MSCs (BM-MSCs) were expanded for four passages in growth medium containing 10% DVI-HPL, I-HPL (from Intercept-PC only), untreated HPL, and FBS. MSC morphology, doubling time, immunophenotype, immunosuppressive activity, and differentiation capacity were compared.

RESULTS

Expanded cells had typical spindle morphology and showed higher viability in all HPL conditions than in FBS. The DVI-HPL and FBS-expanded cells were morphologically larger than in I-HPL and HPL supplements. The cumulative population doubling was lower using DVI-HPL than with HPL and I-HPL, but significantly higher than using FBS. Immunophenotype was not affected by the supplements used. Immunosuppressive activity was maintained with all supplements. Differentiation capacity into chondrocytes and osteocytes was more effective in DVI-HPL but less toward adipocytes compared to other supplements.

CONCLUSIONS

Human PLT lysate made from Intercept-PCs subjected to S/D treatment may be an alternative to untreated HPL and to I-HPL for BM-MSC expansion. This finding reinforces the potential of HPL as a virally safe alternative to FBS for clinical grade MSC expansion protocols.

Streamlining a blood center and hospital transfusion service supply chain with an informatics vendor-managed inventory solution: development, implementation, and 3-month follow-up

BACKGROUND

The ordering process at Stanford Health Care involved twice-daily shipments predicated upon current stock levels from the blood center to the hospital transfusion service. Manual census determination is time consuming and error prone. We aimed to enhance inventory management by developing an informatics platform to streamline the ordering process and reallocate staff productivity.

STUDY DESIGN AND METHODS

The general inventory accounts for more than 50 product categories based on characteristics including component, blood type, irradiation status, and cytomegalovirus serology status. Over a 5-month calibration period, inventory levels were determined algorithmically and electronically. An in-house software program was created to determine inventory levels, optimize the electronic ordering process, and reduce labor time. A 3-month pilot period was implemented using this program.

RESULTS

This system showed noninferiority while saving labor time. The average weekly transfused:stocked ratios for cryoprecipitate, plasma, and red blood cells, respectively, were 1.03, 1.21, and 1.48 before the pilot period, compared with 0.88, 1.17, and 1.40 during (p = 0.28). There were 27 (before) and 31 (during) average STAT units ordered per week (p = 0.86). The number of monthly wasted products due to expiration was 226 (before) and 196 (during) units, respectively (p = 0.28). An estimated 7 hours per week of technologist time was reallocated to other tasks.

CONCLUSION

An in-house electronic ordering system can enhance information fidelity, reallocate and optimize valuable staff productivity, and further standardize ordering. This system showed noninferiority to the labor-intensive manual system while freeing up over 360 hours of staff time per year.