The good news is the today’s life sciences companies have an opportunity to accelerate this process, and ultimately improve patient care, by using machine learning to enable key portions of the R&D processes. In fact, according to a recent study, many already are. Nearly half of life science professionals (44 percent) are already experimenting with AI-based solutions.¹ In this article, we’ll take a closer look at some of the ways in which that’s happening.  

How machine learning ichanging the way life sciences companies address clinical trials 

Machine learning has a number of different applications within life sciences. One of the most important is to correlate structured and unstructured data to provide answers to complex questions. Another is to enable predictive modeling to support the detection of conditions like sepsis. 

In the life sciences, and the corresponding clinical trials specifically, we’re seeing companies de-identify patient records using cloud-based machine learning technologies so that they can run clinical trials against geographies and demographics of the data they have. That way they can correlate where the commonalities are against a patient and clinical trial population. That, in turn, allows data scientists to focus solely on asking the right questions and building algorithms behind the scenes to support those questions, while letting the machine learning technology from public cloud vendors do all of the front-end work.  

Johnson & Johnson is a great real-life example. The company uses de-identified patient data to understand how its products are performing. In doing so, the company tries to assess if people are benefiting from their products as much as they were in clinical trials and if new sides effects are emerging that physicians need to be made aware of. This has also enabled Johnson & Johnson to analyze more data then ever before, while also empowering them to respond in a more agile way to changes in development. 

To that end, another important application of machine learning in the life sciences is the ability to enable much more complex and sophisticated segmentation so you can track individual behaviors across millions of users inside a patient population. This has helped drive better commercial experiences, so when drugs are ready to be tested through clinical trials, they get quicker response and higher levels of engagement. In turn, this results in real-time feedback loops that can be used to expedite the approval process. 

Practically speaking, advances like this can lead to faster time to market and ultimately cost savings. Considering that developing the average enterprise drug costs well over $1 billion, anywhere you can help reduce costs is critical to profitability. 

Of course, it’s not just during clinical trials that machine learning has a role to play. It’s also critical in manufacturing and providing quality assurance for new products, as well as for analyzing the growing datasets associated with real world evidence. According to the 2018 Deloitte Real World Evidence benchmark survey, 60 percent of life sciences companies are currently using machine learning to analyze real world data  but almost 95 percent expect to use it in coming years Other areas that could be impacted include supply chain management, lot release, compliance operations, and drug discovery, to name just a few. By leveraging machine learning services, combined with public cloud technology, all while following GxP for quality assurance, life science organizations are able to prove supply chain compliance.  

PHI considerations 

If your company is ingesting personal health information (PHI) into any kind of enterprise data warehouse or public cloud, you need to take care to follow any rules set forth in regulations like HIPAA, GDPR, and GxP. That includes requirements like encryption in transit and encryption at rest, to name a few. In addition, all of the tooling that data scientists use to view, monitor, and log PHI activities need to have a business association agreement (BAA) around it. That agreement is the promise that third-parties make to treat, process, and store PHI in a secure manner.  

De-identification is another important consideration around PHI. There are lots of tricks of the trade and interpretation around de-identification, making it critical to align with your legal teams before running clinical trials against any patient data. 

Importantly, if your goal is to go to market faster by harnessing the benefits of PHI in the cloud, the key is to use the existing healthcare reference architectures or blueprints from public cloud providers like Microsoft Azure, Google Cloud Platform, or Amazon Web Services. Those blueprints will give you a good idea of how other life sciences companies are already using PHI in the cloud. In addition, make sure to take advantage of the scale and agility that public cloud providers offer you, so you can focus more of your attention on your core competencies. 

better way forward 

By allowing life sciences companies to aggregate vast amounts of data, machine learning is helping to accelerate both the process by which drugs get tested and manufactured, and how they ultimately reach patients. Although we’re still in the early days of embracing machine learning, the promise of agility that it brings is very real. If you want to accelerate your drug and clinical trial research, using the public cloud will help by allowing you to spin up the infrastructure you need in a matter of minutes without having to go through IT. 
 

One thing to remember: As you apply machine learning to PHI throughout the drug and device life cyclesecurity and compliance breaches can happen if you don’t take the right precautions and understand the constant change throughout the cloud industry. That could mean hiring dedicated resources to manage these critical elements, or seeking thirdparty support. 

In the case of a partnership, the right partner will understand the unique needs of a life sciences organization looking to innovate in the cloudhelping you mitigate risk as you as you work through clinical trials and beyond