no code implementations • LREC 2022 • Anastasios Lamproudis, Aron Henriksson, Hercules Dalianis
Here, an empirical investigation is carried out in which various strategies for adapting a generic language model to the clinical domain are compared to pretraining a pure clinical language model.
2 code implementations • RANLP 2021 • Alberto Blanco, Sonja Remmer, Alicia Pérez, Hercules Dalianis, Arantza Casillas
We introduce a multi-label text classifier with per-label attention for the classification of Electronic Health Records according to the International Classification of Diseases.
no code implementations • RANLP 2021 • Anastasios Lamproudis, Aron Henriksson, Hercules Dalianis
The use of pretrained language models, fine-tuned to perform a specific downstream task, has become widespread in NLP.
no code implementations • RANLP 2021 • Sonja Remmer, Anastasios Lamproudis, Hercules Dalianis
A tool that automatically assigns ICD codes to free-text clinical notes could save time and reduce erroneous coding.
no code implementations • BioNLP (ACL) 2022 • Thomas Vakili, Hercules Dalianis
However, the records may also contain information that can reveal the identity of the patients.
no code implementations • NoDaLiDa 2021 • Synnøve Bråthen, Wilhelm Wie, Hercules Dalianis
To assess such tools, gold standards - annotated clinical text - must be available.
no code implementations • NoDaLiDa 2021 • Mila Grancharova, Hercules Dalianis
So far, however, no attempts have been made at applying BERT for NERC on Swedish EPR data.
no code implementations • NoDaLiDa 2021 • Hanna Berg, Hercules Dalianis
This paper describes a freely available web-based demonstrator called HB Deid.
no code implementations • EMNLP (Louhi) 2020 • Hanna Berg, Aron Henriksson, Hercules Dalianis
The impact of de-identification on data quality and, in particular, utility for developing models for downstream tasks has been more thoroughly studied for structured data than for unstructured text.
no code implementations • LREC 2022 • Thomas Vakili, Anastasios Lamproudis, Aron Henriksson, Hercules Dalianis
The impact of the de-identification techniques is assessed by training and evaluating the models using six clinical downstream tasks.
no code implementations • LREC 2020 • Maria Bampa, Hercules Dalianis
The experimental findings suggest that the clinical text in EHRs includes information that can capture data beyond the ones that are found in a structured format.
no code implementations • LREC 2020 • Hanna Berg, Hercules Dalianis
An abundance of electronic health records (EHR) is produced every day within healthcare.
no code implementations • WS 2019 • Hanna Berg, Taridzo Chomutare, Hercules Dalianis
This article presents experiments with pseudonymised Swedish clinical text used as training data to de-identify real clinical text with the future aim to transfer non-sensitive training data to other hospitals.
no code implementations • RANLP 2017 • Rebecka Weegar, Jan F Nyg{\aa}rd, Hercules Dalianis
In this article we present a system that extracts information from pathology reports.
no code implementations • LREC 2012 • Maria Skeppstedt, Maria Kvist, Hercules Dalianis
Named entity recognition of the clinical entities disorders, findings and body structures is needed for information extraction from unstructured text in health records.