As stated in one of this week's readings, "A Different Game", the first step to making the most of the data is to improve the accuracy of the information. This is especially challenging in healthcare where many cases are similar but none are the same. Different conditions present differently, patients react differently to the same medications, and the ways in which data is stored and analyzed greatly vary. According to Dale Sanders, former CIO with the Northwestern University Medical Center, "there are too many variables and variations in healthcare delivery right now that add too much noise to the data to make comparative analytics as valuable as some pundits advocate."
In addition, Saunders claims that predictive analytics is not as effective without outcomes data. Saunders also suggests that we are not where we need to be with natural language processing in Healthcare. Even though it has been used in the industry as long as other forms of analytics, Saunders states that "there are fundamental gaps in our industry’s data ecosystem—missing pieces of the data puzzle—that inherently limit what we can achieve with NLP."
How can we close these gaps to improve the effectiveness of analytics in Healthcare?
http://www.economist.com/node/15557465
http://www.healthcatalyst.com/3-reasons-why-comparative-analytics-predictive-analytics-and-nlp-wont-solve-healthcares-problems/
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.