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.
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.