Talk by Alberto Blanco Garcés with the title Multi-label deep neural classification of health records in Spanish

Alberto Blanco Garcés visitor at DSV/Stockholm university from the University of the Basque country gave today a Zoomtalk with the title Multi-label deep neural classification of health records in Spanish. 
 
Abstract
The seminar is about clinical text mining, a field of Natural Language Processing applied to biomedical informatics. The aim is to classify Electronic Health Records with respect to the International Classification of Diseases, which is the foundation for the identification of international health statistics and the standard for reporting diseases and health conditions. Within the framework of data mining, the goal is the multi-label classification, as each health record has assigned multiple International Classification of Diseases codes. We present our research advances and results by applying Deep Learning methods to EHRs in Spanish, exploring techniques such as Feed-forward Neural Networks, Recurrent Neural Networks and Transformers. 
 
The talk was recorded here
 
The best results using 110 labels gave at most an F-score of 0.40 using as input 2.553 different ICD-10 codes distributed over 22,907 Electronic Health Records, see also Blanco et al 2020.

About Hercules

I am a professor working at DSV-Stockholm University, I perform research in natural language processing and information retrieval, the last ten years I have been working on text mining on electronic patient records to build useful tools to improve health. Hercules homepage
This entry was posted in At DSV, Data and Text Mining, Event, Health Informatics, Language Technology, Presentation, SYSLAB, Visit. Bookmark the permalink.