SingaporeFinance and insurance2024 – ongoingPrudential
MedLM medical-claims document analysis and assessment
Prudential said MedLM doubled claims-review automation in proof-of-concept tests
Problem
Medical claims required staff to extract and code information from supporting documents. Manual entry created opportunities for errors as claims volumes grew.
Approach
Prudential tested Google's healthcare language models on medical-claims documents. MedLM extracted relevant information to support human assessment. Following proof-of-concept results, Prudential announced a comparison against existing approval decisions on selected claims in Singapore and Malaysia.
Results
Takeaway
The reported automation gain came from early tests. Prudential had yet to establish the result across routine claims processing.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
Prudential reported doubled claims-review automation and improved decision accuracy in proof-of-concept tests. It announced further assessment on selected claims with human oversight at critical stages.
Full details are in the original sources.
