Kristine Daynes: Five caveats for choosing predictive analytics

1. Predictive models are meant to be a supplement to human expertise, not replace it.
2. Choose models developed by teams with deep understanding of medical practice and the business of healthcare—domain knowledge
3. Look for algorithms that have been developed using large, clean data sets.
4. Choose tools that are appropriate for the intended use.
5. 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...

Printer-friendly versionSend to friendmore...