Designing an optimal inventory management model for the blood supply chain: Synthesis of reusable simulation and neural network

Platelet demand forecasting based on the SARIMA model: optimizing blood bank resource allocation and clinical supply

BACKGROUND

With advances in medical technology and an aging population, the demand for single-donor platelet transfusions is increasing because of their significant therapeutic effects. However, the short shelf-life of platelets and the lack of large-scale reserves make accurate demand forecasting crucial for blood bank inventory management, resource allocation and clinical supply.

OBJECTIVE

This study aims to forecast platelet demand trends via time series analysis, specifically the SARIMA model, to provide scientific evidence for blood banks, optimize resource allocation and improve clinical supply efficiency.

METHODS

Monthly aggregate data from type A BPC units supplied by Huzhou Central Blood Station from January 2015 to December 2023 were collected. By analyzing these data, a SARIMA model was constructed to predict platelet demand in the first half of 2024.

RESULTS

The SARIMA(0,1,1)(0,1,1)12 model performed best in terms of goodness of fit and Bayesian information criterion (BIC) tests and accurately predicted platelet demand. The predicted results revealed that the actual monthly supply in the first half of 2024 was within the 95% confidence interval of the forecast, with a mean relative error of 3.61%.

CONCLUSION

The SARIMA model effectively predicts platelet demand, providing a practical tool for blood banks to optimize inventory management and clinical supply. Future research should explore further optimizations and improvements to better serve clinical needs and resource management.

Designing an optimal model of blood logistics management with the possibility of return in the three-level blood transfusion network

BACKGROUND

Inventory managers in the blood supply chain always endeavor to provide their clients with prompt and appropriate responses. On the other hand, timely and regular blood deliveries to consumers are essential since ineffective delivery and transportation practices promote shortages, returns, blood loss. The paper attempted to develop an extensive and integrated optimal model of blood transfusion network logistics management by blood type to reduce the cost of losses, returns, and blood shortages given the relevance of this for the blood transfusion network.

METHODS

The regional blood transfusion network in Khorasan Razavi, which contains one main base, six central bases, and 54 hospitals, should be constructed using the optimal model for blood inventory management and distribution. A reusable simulation process was used to identify the optimal behavior for the inventory of all participants in the region (central bases as suppliers and hospitals as consumers), and the demand of hospitals as consumers has been calculated using artificial neural networks. This will lead to a significant reduction of returned blood units by consumers, optimal management of suppliers' and consumers' inventory to prevent waste and shortages. The routing method was used to proceed with the designed model and look into the optimal strategy to distribute blood requested by the consumers. with the aim of reducing the cost and increasing the speed of transportation.

RESULTS

The model's solution allowed for the estimation of the amount of consumers' demand, the optimal amount of target stock, the central bases and hospitals' reorder points, as well as the method of distributing blood from the supplier to its consumers. Implementing the model leads to outcomes such as reducing the time of blood transfer from the central bases to their consumers, increasing the speed of blood delivery to the consumers, increasing the average stock of blood in the central bases, reducing the accumulation of distribution machines at the location of the central bases, the amount of stock, the method for requesting, consuming, and storing blood, and the performance of the central bases' consumers all affect how much control they have over them.

Platelet inventory management with demand and supply uncertainty and variable pricing considerations

Managing the inventory of blood is a crucial operation in hospitals owing to its significance in medical treatment. At the same time, blood is characterized by unique attributes, such as perishability and the unpredictable nature of its supply and demand. While models have been developed to optimize the said process, gaps in literature exist in terms of considering the possibility of variable pricing and extensively accounting for uncertainties in the supply chain. In this light, the present study proposes a stochastic multi-period mixed integer linear programming cost minimization model that determines the optimal inventory plan for a hospital purchasing platelets, assuming that prices fluctuate along with the blood center's supply. To implement uncertain supply and demand, the model considers a discrete set of scenarios for each parameter. A study was performed, and the results indicate a promising direction as inventory costs decreased relative to models without the new considerations.

Applications of deep learning into supply chain management: a systematic literature review and a framework for future research

In today’s complex and ever-changing world, Supply Chain Management (SCM) is increasingly becoming a cornerstone to any company to reckon with in this global era for all industries. The rapidly growing interest in the application of Deep Learning (a class of machine learning algorithms) in SCM, has urged the need for an up-to-date systematic review on the research development. The main purpose of this study is to provide a comprehensive vision by reviewing a set of 43 papers about applications of Deep Learning (DL) methods to the SCM, as well as the trends, perspectives, and potential research gaps. This review uses content analysis to answer three research questions namely: 1- What SCM problems have been solved by the use of DL techniques? 2- What DL algorithms have been used to solve these problems? 3- What alternative algorithms have been used to tackle the same problems? And do DL outperform these methods and through which evaluation metrics? This review also responds to this call by developing a conceptual framework in a value-adding perspective that provides a full picture of areas on where and how DL can be applied within the SCM context. This makes it easier to identify potential applications to corporations, in addition to potential future research areas to science. It might also provide businesses a competitive advantage over their competitors by allowing them to add value to their data by analyzing it quickly and precisely.

Design an Effective Blood Distribution Network with Minimal Impacts on the Environment and Blood Supply Assurance

As the world's population grows, resulting in the aggravating trend of aging population, it brings with it an increase in the demand for blood. Nowadays, in most cities, the blood distribution network is based on a single distribution centre pattern, with the blood centre acting as distribution centre for one-to-one distribution. However, despite its convenience, this pattern has a high frequency of delivery, increased risk of blood shortage, and generates high carbon emissions. This paper aims to understand the real-life problems of the current blood distribution network and to design a more rational blood distribution network by taking the characteristics of the blood supply chain into account. Two blood distribution network patterns are considered, the current single distribution centre pattern and the proposed multiple distribution centre pattern. In order to minimise environmental impacts, we introduce open vehicle routing problem for blood delivery routes planning, using mixed integer programming for modelling, to compare the carbon emissions between the two blood distribution network patterns. Numerical experimental results demonstrate that applying the proposed BDN can reduce carbon emissions by an average of 25.84% and up to 29.59%, and the delivery time in emergency situations is significantly reduced by an average of 33.15%. Such studies are essential for both reducing carbon emissions and safeguarding patients' lives.

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.