Papers by Hercules Dalianis
Downstream Task Performance of BERT Models Pre-Trained Using Automatically De-Identified Clinical Data (2022.lrec-1)
Copied to clipboard
| Challenge: | Automatic de-identification systems introduce errors due to their imperfect precision and may negatively impact the utility of the de-identified dataset. |
| Approach: | They propose to de-identifie a large clinical corpus in Swedish by removing entire sentences containing sensitive data or by replacing sensitive words with realistic surrogates. |
| Outcome: | The proposed models are safe to distribute to other academic researchers and reduce privacy risks. |
Data-Constrained Synthesis of Training Data for De-Identification (2025.acl-long)
Copied to clipboard
| Challenge: | sensitive domains lack widely available datasets due to privacy risks . recent studies have focused on evaluating the privacy of the synthetic text . |
| Approach: | They domain-adapt LLMs to clinical domain and generate synthetic clinical texts . they then generate NER models that can be annotated with tags for PII . |
| Outcome: | The proposed model performs better than the original model using smaller datasets. |
A Semi-supervised Approach for De-identification of Swedish Clinical Text (2020.lrec-1)
Copied to clipboard
| Challenge: | An abundance of electronic health records (EHRs) is produced every day within healthcare. |
| Approach: | They propose a semi-supervised method for automatically creating high-quality training data for de-identification using annotated data for training and annotations that are costly in time and human resources. |
| Outcome: | The proposed method improves recall from 84.75% to 89.20% without sacrificing precision to the same extent, dropping from 95.73% to 94.20%. |
Evaluating Pretraining Strategies for Clinical BERT Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing generic language models in specialized domains may be sub-optimal due to domain differences. |
| Approach: | They propose various strategies for adapting a generic language model to the target domain and various forms of vocabulary modifications to fine-tune it. |
| Outcome: | The proposed strategies outperform a general-domain language model but little difference in performance between the models. |
Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text (D19-62)
Copied to clipboard
| Challenge: | Several ethical and scientific issues arise regarding the balance between maintaining patient confidentiality and the need for wider application of trained models. |
| Approach: | They propose to use pseudonymised clinical text as training data to de-identify real clinical text in other hospitals. |
| Outcome: | The proposed model performed better for some PHI information than the standard model and poor performance on Location and Health Care Unit information. |