United StatesHealthcare and life sciences2021 – ongoingMemorial Hermann Health System
Chart Assist for clinical diagnosis documentation
Memorial Hermann reported a 6:1 acceptance ratio for AI-assisted diagnosis recommendations
Problem
Physicians sometimes omitted diagnoses or documented them without enough specificity. Documentation specialists often queried physicians days after treatment, outside their normal charting workflow.
Approach
Memorial Hermann piloted Cerner Chart Assist with hospitalists inside their existing electronic health record. Its natural language processing engine examined documentation alongside structured clinical data. It presented missing or insufficiently supported diagnoses during chart review so physicians could update their notes.
Results
Takeaway
The reported result measured physician acceptance of recommendations. It did not establish diagnostic accuracy or financial savings.
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
- Vendor solution
- Evidence
- Company's own claim
Sources
Source summaries
Memorial Hermann's informatics executive described an EHR-based hospitalist pilot. He reported a 6:1 acceptance-to-rejection ratio for recommendations covering 6 diagnoses.
Full details are in the original sources.