Non-obvious correlations to disease management unraveled by Bayesian artificial intelligence analyses of CMS data
作者：
Highlights：
• Data-driven Bayesian networks based analysis has been performed on health care data.
• Summarized, healthcare provider level data was used for this analysis.
• Novel hypothesis linking diagnosis codes was proposed based on findings from Bayesian networks approach.
• Potential mechanisms were explored to explain novel hypothesis.
• This paper demonstrates the ability of artificial intelligence methods to advance medical research.
摘要
•Data-driven Bayesian networks based analysis has been performed on health care data.•Summarized, healthcare provider level data was used for this analysis.•Novel hypothesis linking diagnosis codes was proposed based on findings from Bayesian networks approach.•Potential mechanisms were explored to explain novel hypothesis.•This paper demonstrates the ability of artificial intelligence methods to advance medical research.
论文关键词：
论文评审过程：Received 25 July 2016, Revised 1 November 2016, Accepted 7 November 2016, Available online 17 November 2016, Version of Record 22 November 2016.
论文官网地址：https://doi.org/10.1016/j.artmed.2016.11.001
