Fact Based List:
Kristine Daynes: Five caveats for choosing predictive analytics
Submitted by Charlene Ice on Tue, 10/24/2017 - 15:48
- Predictive models are meant to be a supplement to human expertise, not replace it.
- Choose models developed by teams with deep understanding of medical practice and the business of healthcare—domain knowledge
- Look for algorithms that have been developed using large, clean data sets.
- Choose tools that are appropriate for the intended use.
- Assess your information infrastructure to make sure data can be easily extracted.
Source: Inside Angle blog/3M, October 23, 2017
Source URL: https://www.3mhisinsideangle.com/blog-post/five-caveats-choo...
List Ratings: |
Lists You Might Also Be Interested In
- FAIR Health: Median Cost of Giving Birth in the U.S.: 8 Things to Know
- CHIME: Technology Tool Types Used to Target Patients for Population Health Outreach
- Top U.S. Life Science R&D Expenditures for Q1-Q3 2012
- Number of Beneficiaries Assigned to MSSP ACOs, 2012-2013 to 2022
- Heather Punke: 10 Hospitals with the Lowest Readmission Rates
Login or register to post comments