Predictive Analytics in the Post-Pandemic World

There’s no arguing that the global COVID-19 crisis has transformed many aspects of our industry. There is also little doubt that many of the changes the pandemic has brought to our lives and businesses are here to stay.

Not only this, but the landscape continues to evolve as we emerge from [hopefully] the worst days of the pandemic. Practices which were generating traction in 2019 may no longer be relevant or their position in our working lives may have turned down a different path.

Predictive analytics is just one of the fields which has been forced to evolve due to the COVID-19 crisis with many companies forced to start over as we enter the so-called "new normal” and figure out or place within it.

Historical Data

One of the biggest consequences of the pandemic has been that it has made a great deal of the historical data held by pharma companies irrelevant. Patients and healthcare provider wants, needs, and behaviors have changed significantly as a direct result of the pandemic and the data we have from the beforetimes may no longer paint a completely accurate picture.

"Leaders have identified a major weakness in their analytics strategy: the reliance on historical data for algorithmic models,” writes McKinsey. "From customer behavior to supply and demand patterns, historical patterns and the assumption of continuity are what give predictive models their power. COVID-19’s impact on how we live, and work has challenged those patterns—and the models companies use for making business decisions.”

This means pharma brands need to expand their horizons when it comes to gathering data and effectively segregate information into pre- and post- pandemic categories. I know it’s incredibly unusual for one of these articles to promote the idea of data siloing but in this case, you may want to make an exception – providing the process is conducted intelligently.

It’s also important to consider carefully which data sets are still relevant post-pandemic as well. For example, while information regarding patient’s interactions with healthcare providers may have changed, data related to non-transmissible illnesses such as cancer are unlikely to have seen much alteration during the pandemic and are likely to remain largely relevant.

What’s most important is to fully understand how and to what extent each data point used to predict future healthcare activity is likely to have changed as a result of the pandemic and how we as an industry can use what information remains relevant and bring in new research to augment it and rebuild our predictive models for a transformed landscape.

"Companies need to make sure they understand the assumptions and data that are driving their models and choosing intrinsically transparent models or explainability techniques is key to this. They also need to be thoughtful about where to combine models with complementary human judgment. Last, they’ll also need to root out bias and have an end-to-end modelling process supported by tools to ensure harmful biases aren’t embedded in the models.”

Cloud Adoption

To make the most of data in the post pandemic world and ensure that the right information is being applied in the correct places, cloud adoption is likely to become even more important for pharma companies.

Increased cloud adoption is closely correlated with greater data sophistication and makes it significantly easier for data to be shared among collaborators – both within the same pharma company and with others in the space – to create a network of information sharing which has the potential to benefit all stakeholder.

We all know the extent to which COVID-19 shone a light on many of the weaknesses in our supply chains. Cloud capabilities enabling sharing of information up and down the value chain will make it far easier to build predictive models which will make it far easier to react to such challenges in the future.

"As companies tap into the promise of data analytics and AI/ML, they are turning to cloud for help,” writes Google Cloud in a blog post. "When considering which cloud providers to work with, 78% of respondents said big data analysis is a "must have” or a "major consideration,” which placed this capability at the top of the list of consideration factors. This is not surprising, as cloud solutions address the most common pain points and barriers to innovation.”

Final Thoughts

Pharma brands looking to succeed in the post-COVID environment will need to work hard to re-establish their predictive data capabilities. Firstly, by reassessing historical data and effectively combining it with fresh insights and secondly through increased transparency throughout the value chain to better react to future crises.

The role of predictive analytics in the post-pandemic world is sure to be a hot topic at DigiPharma Connect 2024, being held in March at the Westin Hilton Head Island Resort & Spa, SC. 

Download the 2023 agenda today for more information and insights on the DigiPharma Connect experience!