United StatesHealthcare and life sciences2021–2022MDLIVE for Cigna
Machine learning forecasts for provider staffing
MDLIVE saved about $1 million each busy season on provider incentives with machine learning forecasts
Problem
Annual demand forecasts left MDLIVE exposed to seasonal shortages of doctors. Credentialing took 90 to 120 days, limiting its ability to add providers quickly.
Approach
MDLIVE worked with AIDAN Health to build state-level demand forecasts using Azure Machine Learning. Models incorporated seasonal and economic variables. The project finished in spring 2022, replacing annual forecasts with weekly and monthly forecasts for staffing decisions.
Results
Takeaway
Earlier staffing decisions reduced MDLIVE's need to pay doctors extra during demand surges.
Categories
- Size
- Large enterprise
- Industry
- Healthcare and life sciences
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Partner co-development
- Evidence
- Vendor case study
Sources
Source summaries
Microsoft described demand forecasting developed with AIDAN Health. MDLIVE's chief operations officer reported about $1 million saved each busy season on provider incentives.
Full details are in the original sources.