Accessing the AI Revolution

Kalypso (Milwaukee, WI) is a company helping businesses to strengthen their digital transformation strategies and leverage digital technologies and capabilities to “fundamentally change the way they discover, create, make and sell new products.” Its pharmaceutical, biotech and contract development and manufacturing organizations (CDMO) focus areas include digital knowledge management, digital thread strategy, digital regulatory information management (RIM), smart connected operations, digital technology transfer & scale up, and extended reality.

Recently, Pharma Commerce sat down with Rodney Holmes, Kalypso’s senior manager & IoMT (Internet of Medical Things) lead of life sciences, to discuss the ongoing advance of artificial intelligence (AI) throughout the pharmaceutical industry and explore how companies not yet invested in it can get started with AI.

Pharma Commerce: How is AI being used to improve drug discovery, clinical support, wearable technologies, and predictive analytics on equipment?

Rodney Holmes: Drug discovery: Drug discovery is an area where pharma companies can incorporate AI into the expensive and lengthy process of drug discovery. The benefits of AI focus on timesaving and pattern recognition upon testing and identification of new drugs. For example, in early-stage drug discovery, algorithms dig through portions of data for patterns too complex for humans to identify.

Rodney Holmes

Clinical decision support: AI in healthcare can prove useful within clinical decision support to help doctors make better decisions faster with pattern recognition of health complications. The time saved and the conditions diagnosed are vital in an industry where the time spent, and decisions made can be life-altering for patients.

Wearables: AI is revolutionizing patient delivery care. Wearable technologies are augmented with AI to improve medical outcomes. Artificial intelligence is leveraged to collect, analyze and interpret massive amounts of data which can improve the quality of life of patients everywhere.

Predictive analytics on equipment: AI can predict failures of equipment and allows medical providers to maintain their high value medical equipment proactively with high performance. Real-time collection of the right parameters and utilization of machine learning tools to predict and classify healthy and faulty equipment status will help improve medical equipment availability in hospitals, reduce downtime and wait times for servicing patients and improve patient outcomes. AI can also help optimize for better efficiencies by looking at utilization and operational data to predict and optimize operation room or hospital bed utilization and improve overall operational efficiency and availability of critical healthcare resources.

How has the pandemic impacted the use of AI in the pharmaceutical sector?

In a traditionally conservative and highly regulated industry with famously long product development cycles, COVID-19 forced the healthcare industry to accelerate the use of digital capabilities, including artificial intelligence, to ensure patient safety and reduce the risk of infections. This successful pivot has brought more awareness and acceptance of digital tools to end users in medicine. Leading to manufactures fast-tracking the development of new applications and processes, which will inevitably lead to better consumer and provider adoption of IoMT solutions.

Also, as manufacturers digitize their products and solutions, they are trying to understand how to do something with the data they are collecting off devices in the field to generate valuable insights and outcomes from the mass amounts of data they collect.

How will pharma companies implement AI in the future?

In 2022, pharmaceutical manufacturers will begin to implement model predictive control (MPC). This digital twin methodology simulates how a complex system will respond to operational inputs and changes in its environment and is able to autonomously adjust controls to optimize quality, safety and efficacy.

This is key to reducing process variability and inefficiency, improving product quality and consistency and reducing energy costs. The pharmaceutical manufacturing process today heavily relies on operator-driven input– meaning that physical operators tweak the controls of the manufacturing process to achieve the critical quality attributes that are defined and approved by the regulatory agencies. This process has not yet been digitalized due to the risk averse regulatory agencies that control the manufacturing process and therefore, has slowed adoption of emerging data-scientific methods.

Regulatory agencies will become more confident in adopting data-scientific methods and pharmaceutical companies that employ MPC will be able to continually optimize their plant and asset performance and remain competitive as business practices and policies evolve.

What are some ways pharma companies can get started with AI?

Driving real value requires different ways of thinking, new and highly sought-after skills within the organization, distinct IT architectures and novel corporate strategies. With the potential to lower cost, create new and effective treatments, and improve patient outcomes, AI is the future of pharma. While new technologies open up new possibilities, enablement of the technology has to keep the end-user and experience in mind. Here are three steps for getting started with AI in pharma:

• Identify and empower champions for AI and machine learning to explore potential applications and create pull across the organization.
• Cultivate partnerships with the emerging artificial intelligence and machine learning ecosystem of like-minded research labs, academic institutions, technology providers, application developers and start-ups.
• Prioritize AI and machine learning use cases for small-scale proof of value (PoV) investments according to their potential for attaining business insights and value. When prioritizing, consider your organization’s therapeutic focus areas, business strategy, associated customer value propositions and future growth plans. Monitor PoV performance and quickly scale those that prove most effective.