De-identification of patient notes with recurrent neural networks
Conclusion: Our findings support the use of ANNs for de-identification of patient notes, as they show better performance than previously published systems while requiring no manual feature engineering.
Source: Journal of the American Medical Informatics Association - Category: Information Technology Authors: Dernoncourt, F., Lee, J. Y., Uzuner, O., Szolovits, P. Tags: Research and Applications Source Type: research
More News: Databases & Libraries | Electronic Health Records (EHR) | Health Insurance | HIPAA | Information Technology | Insurance