Sorry, you need to enable JavaScript to visit this website.

Can AI solve the generation of patient friendly label from scientific content?

Completed on Apr 16, 2021


Design a ‘Smart Patient Label’ solution that can detect and link Summary of Product Characteristics (SmPC) to the appropriate sections of a corresponding version of a Patient Information Leaflet (PIL). When there is a change in SmPC, the solution should be capable of auto-detecting the corresponding PIL changes. Ultimately, having the capability to detect and link would be coupled with AI/ML techniques to auto-generate a PIL from a SmPC


In Europe, the SmPC (the Summary of Product Characteristics) is the scientific label developed for all medicines describing the safety, efficacy, etc. of the product in scientific terms and consumed by Healthcare professionals who consult it before safely prescribing the product. In the UK, the SmPC is available electronically. The Patient Information Leaflet (PIL) is the patient facing version of the SmPC, written in patient friendly terms, and inserted in the commercial pack given to all patients. The license holder is responsible for keeping the SmPC and PIL up to date to reflect the latest benefit-risk information for the medicine and ensures that the two documents are kept synchronized and consistent in terms of meaning.

In the initial phase of the challenge, collaborators are expected to develop an AI/ML based solution to auto-detect and link the sections of the SmPC with appropriate sections of the PIL. The focus of the challenge initially is on SmPC and PIL pairs registered in the European markets. Training data will be sourced from Pfizer in the form of SmPC and PIL pairs in addition, collaborators should also reference public domain information (see Public Domain References section). Pfizer labelling SMEs will be made available to the selected collaborators during the execution stage of the challenge. 

In the next phase of this challenge, when a change to the SmPC is made, the Collaborator will demonstrate that the solution is capable of detecting the context of the change along with all the relevant sections of the PIL that needs to change in order to link and recommend suggestions for the patient friendly language. SMEs will review machine recommendations and provide ‘human-in-the-loop’ feedback that will be applied to the appropriate sentences in the PIL. Collaborators will have to demonstrate the solution’s capability to continuously learn from the reviewers feedback and progressively improve the solutions accuracy to correctly identify, link and recommend PIL language. The recommended test should be consistent with defined business rules and regulatory requirements. Ultimately the solution should scale to auto-generate de novo content for example, creation of a PIL in its entirety given a SmPC with appropriate contextual relevancy of recommended section in the PIL 

Business Problem

  • Label authoring process is manual and time-intensive, and learning or best practice from labeler’s experience is not repeatable
  • Complexity of Regulatory requirements are increasing with varied label update requirements across global health authorities
  • Pfizer is seeking a novel approach to content generation which requires less SME effort, continuous Machine Learning capability and deliver better quality of content that is patient friendly.

Reference example guidelines (non-exhaustive)

  • Annotated QRD (Quality Review of Documents) template from EMA website
  • Patient friendly dictionaries for adverse drug reaction 
  • Excipient guideline for human Use 
  • Guideline on the readability of the labelling and package leaflet of medicinal products for human use 
  • A guideline on Summary of Product Characteristics (SmPC)
  • Shortcomings assessment report on Labeling – a good reference guide
  • Declaration of Storage Conditions
  • MEDRA classification for side effects.
  • Guidance on electronic product information from EMA website
What you can expect
2 weeks

Phase 1

Show your Interest

Complete and submit a registration form.


By registering, you acknowledge that Pfizer will be reviewing the information submitted by you. You also acknowledge that registration on this website is not a guarantee of participating in any challenge. Pfizer will notify selected participants, who will then be required to execute confidentiality and other agreements

2 weeks

Phase 2

Prepare to participate

During this phase, Pfizer will notify the participants, who will then be required to execute confidentiality and other agreements. 
We will share our onboarding process and developer user guide to help you to set up your environment.

6-8 weeks

Phase 3

Compete to win

Most of the hackathons run for 6-8 weeks. During this period, you would work on the challenge, with periodic check ins with our team. The team will be available to support you work towards a solution.

Deadline for submission of work is Feb 19, 2021

1 week

Phase 4

Show your work

During this phase, you'll present your solution and approach. The team will review submissions and will evaluate the solution.

On completion of evaluation, the team will provide their feedback for all teams. This would normally take couple of weeks.

2 weeks

Phase 5

Get onboarded

The team with the winning solution(s) will be asked to submit a simplified RFP. This should be approved within few weeks and once accepted, you will be ready to work with Pfizer for a complete solution implementation.

About the Breakthrough Change Accelerator 

Pfizer’s Breakthrough Change Accelerator is a competitive incubation sandbox created to power rapid and robust machine learning in a secure environment. We invite innovators to collaborate on challenges using large volumes of relevant datasets to create novel technology solutions that speed up development of medicines to patients.