Health Care Analytics and Big Data Management in Influenza Vaccination Programs: Use of Information- Entropy Approach

Sharon Hovav, Hanan Tell, Eugene Levner,

Alexander Ptuskin, and Avi Herbon


Annual influenza epidemics impose great losses in both human and financial terms. A key question arising in large-scale vaccination programs is the need to balance program costs and public benefits. Risks occur in the vaccination supply chain due to the stochastic nature of the vaccination process, which fluctuates from year to year, depending on many factors that are difficult to predict and control. Large data sets representing the information involved are Big Data sets of sizes far beyond the ability of commonly used software packages to capture, process, and manage data within a reasonable computing time. We suggest an entropic approach to handle this challenging problem.


For a vaccination supply chain consisting of manufacturers, distribution centers, warehouses, pharmacies, clinics, and customers, we seek to reduce the problem size and then decrease the total expenses of all stakeholders while taking into account public benefits on a nationwide level. We propose an analytics-driven research approach for enhancing the efficiency of influenza vaccination programs, using supply chain concepts. We seek to minimize the total cost of the vaccination supply chain while upholding the individual interests of its stakeholders.


Information entropy is widely used in information control and management as a measure of uncertainty in a random environment. Extending Shannon’s classical information entropy concept used in information theory, we use the term to quantify and evaluate the expected value of the information contained in a supply chain with uncertain but predictable data about the costs and benefits. An integer-programing model is developed in which the problem of minimizing the total loss is effectively solved in a reduced vaccination supply chain.


Knowing the history of adverse events, we estimate the entropy and knowledge about the risks occurring in the vaccination supply chain, reduce the problem size, define the most vulnerable components in the supply chain, and evaluate the economic loss. This new analytics approach permits us to estimate and balance the manufacturing, inventory, and distribution costs with possible public benefits and reduce the incurred losses.

Research Limitations/Implications

In this chapter, we assume that the data on the vaccination demands are deterministic and known in advance to a decision maker. In our future research, we intend to lift this limitation and accomplish a more scrupulous analysis of links between the entropy as a data uncertainty measure and the costs in medical supply chains. Moreover, we intend to perform a more sophisticated cost—benefit—risk analysis of the vaccination supply chains, taking into account the stochastic behavior of demands for different population groups.

Practical Implications

A case study has been implemented to test the suggested methodology; we successfully used our approach to analyze and improve the nationwide vaccination program carried out by the CLALIT Health Services (Israel). We believe that the suggested analytics methodology can be used for wider applications in other types of health care supply chains.


This chapter develops a novel integrated approach for optimizing costs and public benefits within the influenza vaccine supply chain. The methodology is applicable for wider health care management applications.

< Prev   CONTENTS   Source   Next >