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.

Development, Evaluation, and Multisite Deployment of a Machine Learning Decision Tree Algorithm To Optimize Urinalysis Parameters for Predicting Urine Culture Positivity.

PittUDT, a recursive partitioning decision tree algorithm for predicting urine culture (UC) positivity based on macroscopic and microscopic urinalysis (UA) parameters, was developed in support of a broader system-wide diagnostic stewardship initiative to increase appropriateness of UC testing. Reflex algorithm training utilized results from 19,511 paired UA and UC cases (26.8% UC positive); the average patient age was 57.4 years, and 70% of samples were from female patients. Receiver operating characteristic (ROC) analysis identified urine white blood cells (WBCs), leukocyte esterase, and bacteria as the best predictors of UC positivity, with areas under the ROC curve of 0.79, 0.78, and 0.77, respectively. Using the held-out test data set (9,773 cases; 26.3% UC positive), the PittUDT algorithm met the prespecified target of a negative predictive value above 90% and resulted in a 30 to 60% total negative proportion (true-negative plus false-negative predictions). These data show that a supervised rule-based machine learning algorithm trained on paired UA and UC data has adequate predictive ability for triaging urine specimens by identifying low-risk urine specimens, which are unlikely to grow pathogenic organisms, with a false-negative proportion under 5%. The decision tree approach also generates human-readable rules that can be easily implemented across multiple hospital sites and settings. Our work demonstrates how a data-driven approach can be used to optimize UA parameters for predicting UC positivity in a reflex protocol, with the intent of improving antimicrobial stewardship and UC utilization, a potential avenue for cost savings.

Proceedings of the 2022 NHLBI and OASH state of the science in transfusion medicine symposium.

BACKGROUND: State of the Science (SoS) meetings are used to define and highlight important unanswered scientific questions. The National Heart, Lung, and Blood Institute (NHLBI), National Institutes of Health, and the Office of the Assistant Secretary for Health (OASH), Department of Health and Human Services held a virtual SoS in transfusion medicine (TM) symposium. STUDY DESIGN AND METHODS: In advance of the symposium, six multidisciplinary working groups (WG) convened to define research priorities in the areas of: blood donors and the supply, optimizing transfusion outcomes for recipients, emerging infections, mechanistic aspects of components and transfusion, new computational methods in transfusion science, and impact of health disparities on donors and recipients. The overall objective was to identify key basic, translational, and clinical research questions that will help to increase and diversify the volunteer donor pool, ensure safe and effective transfusion strategies for recipients, and identify which blood products from which donors best meet the clinical needs of specific recipient populations. RESULTS: On August 29-30, 2022, over 400 researchers, clinicians, industry experts, government officials, community members, and patient advocates discussed the research priorities presented by each WG. Dialogue focused on the five highest priority research areas identified by each WG and included the rationale, proposed methodological approaches, feasibility, and barriers for success. DISCUSSION: This report summarizes the key ideas and research priorities identified during the NHLBI/OASH SoS in TM symposium. The report highlights major gaps in our current knowledge and provides a road map for TM research.

Application of a recursive partitioning decision tree algorithm for the prediction of massive transfusion in civilian trauma: the MTPitt prediction tool.

BACKGROUND: A supervised machine learning algorithm was used to generate decision trees for the prediction of massive transfusion at a Level 1 trauma center. METHODS: Trauma patients who received at least one unit of RBCs and/or low-titer group O whole blood between January 1, 2015, and December 31, 2017, were included. Massive transfusion was defined as the transfusion of 10 or more units of RBCs and/or low-titer group O whole blood in the first 24 hours of admission. A recursive partitioning algorithm was used to generate two decision trees for prediction of massive transfusion using a training data set (n = 550): the first, MTPitt, was based on demographic and clinical parameters, and the second, MTPitt+Labs, also included laboratory data. Decision tree performance was compared with the Assessment of Blood Consumption score and the Trauma Associated Severe Hemorrhage score. RESULTS: The incidence of massive transfusion in the validation data set (n = 199) was 7.5%. The MTPitt decision tree had a higher balanced accuracy (81.4%) and sensitivity (86.7%) compared to an Assessment of Blood Consumption Score of 2 or higher (77.9% and 66.7%, respectively) and a Trauma Associated Severe Hemorrhage score of 9 or higher (75.0% and 73.3%, respectively), although the 95% confidence intervals overlapped. Addition of laboratory data to the MTPitt decision tree (MTPitt+Labs) resulted in a higher specificity and balanced accuracy compared to MTPitt without an increase in sensitivity. CONCLUSIONS: The MTPitt decisions trees are highly sensitive tools for identifying patients who received a massive transfusion and do not require computational resources to be implemented in the trauma setting.

Objective Assessment of Adherence to Inhalers by Patients with Chronic Obstructive Pulmonary Disease.

RATIONALE: Objective adherence to inhaled therapy by patients with chronic obstructive pulmonary disease (COPD) has not been reported. OBJECTIVES: To objectively quantify adherence to preventer Diskus inhaler therapy by patients with COPD with an electronic audio recording device (INCA). METHODS: This was a prospective observational study. On discharge from hospital patients were given a salmeterol/fluticasone inhaler with an INCA device attached. Analysis of this audio quantified the frequency and proficiency of inhaler use. MEASUREMENTS AND MAIN RESULTS: Patients with COPD (n = 244) were recruited. The mean age was 71 years, mean FEV1 was 1.3 L, and 59% had evidence of mild/moderate cognitive impairment. By combining time of use, interval between doses, and critical technique errors, thus incorporating both intentional and unintentional nonadherence, a measure "actual adherence" was calculated. Mean actual adherence was 22.6% of that expected if the doses were taken correctly and on time. Six percent had an actual adherence greater than 80%. Hierarchical clustering found three equally sized well-separated clusters corresponding to distinct patterns. Cluster 1 (34%) had low inhaler use and high error rates. Cluster 2 (25%) had high inhaler use and high error rates. Cluster 3 (36%) had overall good adherence. Poor lung function and comorbidities were predictive of poor technique, whereas age and cognition with poor lung function distinguished those with poor adherence and frequent errors in technique. CONCLUSIONS: These data may inform clinicians in understanding why a prescribed inhaler is not effective and to devise strategies to promote adherence in COPD.