Have FDA Initiatives like KASA Helped with the Covid Vaccine?

In 2002 the U.S. Food and Drug Administration (FDA) launched its Pharmaceutical Quality for the 21st Century Initiative to “modernize FDA’s regulation of […] drugs and select human biological products such as vaccines.” It has been in full-swing since then with several successes in terms of pharmaceutical manufacturing quality already under its belt. As part of this program, FDA also proposed sweeping changes in the way it reviews drug applications, partly to help reduce the burden in years like 2020.

The FDA recognizes that the world is accelerating. Pharma companies are submitting a huge number of applications with short deadlines, and the FDA is struggling with the workload. Instead of extending response times, the FDA did an efficiency review and found several issues with its current quality assessment.

1. FDA reviewers have trouble finding relevant historical data to compare an application against, which causes bottlenecks.
2. Current submissions are mostly narrative and unstructured which opens the door for regulatory inconsistency and redundancy.

In September 2018, the FDA admitted that the current system is a solution for a 20th century process when reports were still mostly submitted on paper. The time for modernization is here — and that means moving from unstructured text-based knowledge and life-cycle management to structured reporting.

The key for pharmaceutical industry is that the FDA is creating a new interface to receive submissions — this means that pharma companies will have to comply with the new format. Since many details are still up in the air, moving to a structured knowledge management system is the best way to prepare for KASA, whatever the new format will be.

FDA’s push towards structured data also creates an entire new industry. Technology experts often chide healthcare firms, including its regulator, as being behind the curve on most things. With initiatives like KASA, FDA is trying to leap-frog and shed its conservative image. In doing so it’s also pushing technology players to innovate and adopt new standards of information management. It is easier than it appears on surface.

Knowledge-aided Assessment and Structured Applications (KASA) is the natural evolution of the current eCTD format optimized for the 21st century. It tracks the drug development cycle better than eCTD and gets rid of unstructured data, making information consistent across submissions. This gives the FDA more clarity and better risk mitigation and speeds up the review process.

At a high level, the FDA will set rules and algorithms which it can use to standardize review and capture risk early-on. Better risk management upfront will reduce the iterations needed to reach approval, and because each submission will arrive in a standardized format, reviewers will be able to automate redundant work and pull better historical data.

The details of the exact KASA infrastructure are still emerging, but stated goals as of 2018 are:

• To review applications more efficiently.
• To spot information gaps and deficiencies earlier.
• To manage knowledge across all aspects of the review process (including pulling in the right historical data for comparison).
• To track product quality and risk throughout the entire life-cycle.
• Deliver consistent and predictable analysis.
• To automate analysis of portions of the application.

KASA or not, the time has come for big pharma and the enterprise world in general to embrace structured knowledge management. It’s a powerful tool for efficient operations, and now it’s a competitive advantage as well -giving an edge over companies still slogging through unstructured text-based documents.

Drug approval submissions that are complete, transparent, and easy for the FDA to process will get approved faster and go to market faster. It’s as simple as that. We can say the same about workflows in all industries — workflows based on structured data automate and scale much better.

With AI enabled natural language search, moving from unstructured to structured knowledge management can be easy.

1. Create/reuse a guideline or a template including key data elements and terminologies you will need to include.
2. Auto-populate using Narrow Search, which focuses on getting the best answer with high confidence. In data science terms it can be thought of as a high precision operation.
3. Check the results from Narrow Search and update using Normal Search. The focus here is on helping the user by finding helpful content. Human interaction is required to learn and becomes more helpful over time.
4. Publish as XML/PDF/DOCX. This must be done automatically based on your template, so that there is no need to assemble the report on your own.

It is unlikely that KASA came in time to help with the Covid vaccine. Right now FDA is focused on only generics when it comes to KASA. Even there, currently KASA is just a recommendation. The timelines are unclear. If it was here, FDA and scientists could have meaningfully accelerated the search for new vaccine.

However, what is certain is that KASA is coming is some shape or form. It will not stop with generics, or even branded drug approvals. Once the advantages are all to evident, such workflows based on structured knowledge will take over the pharma industry and beyond.