Clinical Utility of Machine Learning and Longitudinal EHR Data
The widespread adoption of electronic health records in large health systems, combined with recent advances in data mining and machine learning methods, creates opportunities for the rapid acquisition and translation of knowledge for use in clinical practice. One area of great potential is in risk prediction of chronic progressive diseases from longitudinal medical records. In this Chapter, we illustrate this potential using a case study involving prediction of heart failure. Throughout, we discuss challenges and areas in need of further development.
KeywordsElectronic health records Hearth failure Machine learning Prediction models Text mining
- 5.Zhu J, Rosset S, Hastie T (2003) 1-norm support vector machines. Neural Inf Proc Sys 2003:16Google Scholar
- 7.IBM. Text analytics tools and runtime for IBM Language ware. Available at: http://www.alphaworks.ibm.com/tech/lrw2011
- 8.Apache UIMA. Available at: http://uima.apache.org/
- 11.Wang W, Yang J (2005) Mining sequential patterns from large data sets, series. Adv Database Sys 28Google Scholar