From the Crawford Lab: We have developed a set of text-mining algorithms to extract education and occupation, both important variables that describe socioeconomic status (SES), from electronic health records. The development and evaluation of the algorithm is described in PMC5147499, and the exclusion, jobs, and prefix lists developed for this algorithm can be found here. Detailed usage of the package can be found on the github site.
SES Text Mining Algorithms for Electronic Health Records
Posted in Software and Downloads.
Will Bush
William S. Bush, Ph.D., is a human geneticist and bioinformatician, and Assistant Professor within the Cleveland Institute for Computational Biology and the Department of Population and Quantitative Health Sciences at Case Western Reserve University.