A huge challenge in a busy hospital is accurately predicting usage – which beds and wards will be filled, how many surgical sponges will be required, what volumes of medical waste will be created and much more. Pharmaceutical and medical device companies often deal with very similar difficulties: How can the organization anticipate demand for a particular drug and therefore ensure sufficient supply? In both cases, there is also the question of supply chain resilience. Can everyone be absolutely sure that supplies and equipment will travel safely and arrive on time at the right destination?

These challenges are being met head on by advanced data analytics, a logical extension of patient-centered healthcare. The global healthcare analytics market is set to expand by nearly 24%, from $8.48 billion in 2015 to $23.8 billion in 2020. Accurately crunching high-volume, high-value, high-velocity data can help save lives. Many of life sciences and healthcare companies are investing wisely.

In-depth perspectives in real time

A real-time view of operations and analytics tools can improve demand accuracy, leading to less resource waste and avoiding a shortage of supply.

The public hospital system of Paris, France – L’Assistance Publique-Hôpitaux de Paris – is trialing platforms that predict hospital admission rates based on past admission records. The objective is to improve bed management and logistics. Meanwhile the physician-led healthcare system, Geisinger Health System, in northeastern and central Pennsylvania, USA, is using a big data platform to track and correlate supply chain data on supplies to clinical information from its electronic medical records by surgery type and provider.

Both of these examples illustrate the value of linking a real-time view of demand to supply. It enables optimization across the whole value chain, all the ways from “making it to taking it”, or manufacturing to consumption.

Knowing when to meet demand

Crowdsourced data can contribute valuable near-real-time insight into any demand spikes. Bayer AG is using big data from climate change and global weather trends to model the occurrence of hay fever in the USA. With this data, the organization knows to ramp up production of its anti-allergy drug Claritin as far as nine months ahead of a spike in allergies. Soon it may even prove possible to predict influenza outbreaks. Harvard researchers have used Google search data see the number of times people search for flu-related symptoms or treatments, giving a good indication of increased demand.

These examples show the power of data. Manufacturers can use it to scale up production ahead of peaks in demand, as well as work with logistics partners to increase speed to market for new drugs and devices when required.

Using data to manage risk

In addition, crowdsourced data can be used to identify events that may disrupt the movement or quality of shipments – natural disasters, socio-political unrest, supplier failure and other uncontrollable and unexpected incidents.

Many life sciences and healthcare products’ manufacturers use our cloud-based Resilience360 solution to turn potential disruption into competitive advantage with global supply chain visualization, near-real-time monitoring of incidents and much more. Further solutions offering lane risk assessment, such as DHL Thermonet for temperature-controlled logistics, help manufacturers to identify risk scores and optimize their choice of lanes, packaging and other shipment parameters. Each risk score is derived from deep analysis of past shipment data.

How will advanced data analytics keep on shaping our future? What other applications will further develop in 2018? While we witness these changes, I recommend reading ‘The Future of Life Sciences and Healthcare Logistics’. As always, if you want to add your comments and thoughts below, I would be very happy to hear from you.

Published: December 2017

Images: DHL/Shutterstock