case study

Generative AI-powered Contract Management System for healthcare

Life Sciences Healthcare

Business Impacts

Improved reviewer productivity by reducing redlining efforts by 60%

Enabled reviewers to find answers to 143 intricate contract questions with over 80% accuracy

Customer Key Facts

  • Country : Canada
  • Industry : HCLS

AI Assisted Contract Comparison

The customer, a leading healthcare provider based in Toronto, Canada, partnered with Quantiphi to develop an advanced contract redlining solution using generative AI. This solution is deployed in a user-friendly interface, allowing employees to cross-verify results and provide feedback.

Challenges

  • Hundreds of hours spent weekly on manual contract analysis
  • Low accuracy of contract comparisons due to manual errors

Technologies Used

Cloud Storage Bucket

Cloud Storage Bucket

Firestore

Firestore

Elastic search

Elastic search

Vertex AI Workbench

Vertex AI Workbench

Virtual Private Cloud

Virtual Private Cloud

Cloud Run

Cloud Run

Cloud Build

Cloud Build

Cloud Functions

Cloud Functions

Cloud Task

Cloud Task

GKE

GKE

Gitlab

Gitlab

Cloud CDN

Cloud CDN

Model Garden

Model Garden

Solution

Quantiphi proposed baioniq, our in-house generative AI platform for legal documents, capable of reading, ingesting, summarizing, and redlining contracts.

The project handled four types of contracts: Letter of Indemnification, Academic, Contract Research Organization, and Non-Contract Research Organization.

We developed a three-layer ML solution for redlining:

  • Clause Extraction: Finetuned text-bison model to extract relevant clauses from contracts.
  • Retriever: Built a retriever layer to extract the right clauses based on rules provided by the UH team.
  • Redlining: Finetuned text-bison model to perform contract redlining.

Results

Quantiphi implemented a standard train, test, and evaluation strategy for our model, which is currently being tested by the customer on the UI. Preliminary results show 60-65% accuracy for the redlining layer, while the clause extraction and retriever layers achieve over 85% accuracy.

Start Your Next Gen AI Journey Today

Discover how Quantiphi’s AI-powered solutions can transform your business. Fill out the form, and we’ll help you explore tailored AI strategies to unlock new opportunities for growth.

Thank you for reaching out to us!

Our experts will be in touch with you shortly.

In the meantime, explore our insightful blogs and case studies.

Something went wrong!

Please try it again.

Share