Application of unsupervised machine learning to identify areas of blood product wastage in transfusion medicine

Process Mining Uncovers Actionable Patterns of Red Blood Cell Unit Wastage in a Health Care Network

Packed red blood cell transfusions are integral to the care of the critically and chronically ill patient, but require careful storage and a large, coordinated network to ensure their integrity during distribution and administration. Auditing a Transfusion Medicine service can be challenging due to the complexity of this network. Process mining is an analytical technique that allows for the identification of high-efficiency pathways through a network, as well as areas of challenge for targeted innovation. Here, we detail a case study of an efficiency audit of the Transfusion Medicine service of the Nova Scotia Health Administration Central Zone using process mining, across a period encompassing years prior to, during, and after the acute COVID-19 pandemic. Service efficiency from a product wastage perspective was consistently demonstrated at benchmarks near globally published optima. Furthermore, we detail key areas of continued challenge in product wastage, and suggest potential strategies for further targeted optimization.

Impact of Implementing a Standard Operating Procedure to Reduce Blood Wastage in Blood Centers of Iran

BACKGROUND

Blood wastage leads to additional costs and reduced blood availability to patients. Above all is the moral issue of wasting donor gifts. This study aimed to determine the rate of blood wastage before and after implementing a new standard operating procedure (SOP) in Iran.

METHODS

In this interventional study, a SOP for wastage management was prepared and implemented in all blood centers throughout the country. Data were extracted from the integrated software of the Iranian Blood Transfusion Organization (IBTO). The wastage rate of blood components in the post-intervention years (2016-2017) was then compared with that in the pre-intervention years (2013-2015) using the Z test.

RESULTS

The overall wastage rate decreased by 36.86% (P<0.001, 95% CI [36.84-36.88]) after the intervention. Red blood cell (RBC) wastage decreased from 2.6% to 2.5%, platelet wastage from 19.5% to 10.6% and plasma wastage from 15.5% to 7.3% (P<0.001). The highest percentage of waste reduction pertained to plasma components, which decreased by 52.90% (P<0.001, 95% CI [52.86-52.94]). Expiration was the most common cause of RBC and platelet wastage. The most common causes of plasma wastage were RBC contamination and rupture or leakage of the bags. The intervention resulted in a drop of over 250000 discarded components each year, equal to approximately thirty-six million dollars in savings.

CONCLUSION

This intervention effectively reduced waste and increased efficiency. Ongoing blood wastage reviews, auditing, and receiving feedback from the central headquarters were powerful tools in following the compliance of blood centers. Further studies are recommended, especially concerning blood wastage in hospital blood banks and various wards.

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.

Artificial Intelligence and Machine Learning in Patient Blood Management: A Scoping Review

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.