An article published in the July issue of the Journal of the American Medical Association takes a look at how big data and predictive analytics are playing out in U.S. health care, and what challenges lie ahead for major breakthroughs in risk prediction.
The article’s authors write that machine learning algorithms have the potential to “derive meaning from unstructured data,” which could facilitate the “capture of substantial clinical information embedded in clinical notes.”
” … The growth in the availability of registries and claims data and the linkages between all these data sources have created a big data platform in health care, vast in both size and scope,” the authors write.
However, machine learning and prediction models aren’t likely to bring about a revolution any time soon, according to the article.
“It seems unlikely that incremental improvements in discriminative performance of the kind typically demonstrated in machine learning research will ultimately drive a major shift in clinical care,” the authors write.
Click here to read the full article on JAMA. (Subscription required)