In this work we present two datasets for the development of virtual patients and the first evaluation results. We firstly introduce a Spanish corpus of medical dialogue questions annotated with intents, built upon prior research in French. We also propose a second dataset of dialogues using a novel annotation approach that involves doctor questions, patient answers, and corresponding clinical records, organized as triples of the form (clinical report, question, patient answer). This way, the doctor-patient conversation is modeled as a question-answering system that tries to find responses to questions taking a clinical record as input. This approach can help to eliminate the need for manually structured patient records, as commonly used in previous studies, thereby expanding the pool of diverse virtual patients available. Leveraging these annotated corpora, we develop and assess an automatic system designed to answer medical dialogue questions posed by medical students to simulated patients in medical exams. Our approach demonstrates robust generalization, relying solely on medical records to generate new patient cases. The two datasets and the code will be freely available for the research community.

Research on language technology for the development of medical applications is currently a hot topic in Natural Language Understanding and Generation. Thus, a number of large language models (LLMs) have recently been adapted to the medical domain, so that they can be used as a tool for mediating in human-AI interaction. While these LLMs display competitive performance on automated medical texts benchmarks, they have been pre-trained and evaluated with a focus on a single language (English mostly). This is particularly true of text-to-text models, which typically require large amounts of domain-specific pre-training data, often not easily accessible for many languages. In this paper, we address these shortcomings by compiling, to the best of our knowledge, the largest multilingual corpus for the medical domain in four languages, namely English, French, Italian and Spanish. This new corpus has been used to train Medical mT5, the first open-source text-to-text multilingual model for the medical domain. Additionally, we present two new evaluation benchmarks for all four languages with the aim of facilitating multilingual research in this domain. A comprehensive evaluation shows that Medical mT5 outperforms both encoders and similarly sized text-to-text models for the Spanish, French, and Italian benchmarks, while being competitive with current state-of-the-art LLMs in English.

The aim of this paper is to present our approach (IxaMed) in the PharmacoNER 2019 task. The task consists of identifying chemical, drug, and gene/protein mentions from clinical case studies written in Spanish. The evaluation of the task is divided in two scenarios: one corresponding to the detection of named entities and one corresponding to the indexation of named entities that have been previously identified. In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings. We have achieved our best result (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records (50M words) with contextual string embeddings of Wikipedia and Electronic Health Records. On the other hand, for the indexation of the named entities we have used the Levenshtein distance obtaining a 85.34 F-Score as our best result.

The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation. We report F1 results for 6 languages: Basque (0.853), English (0.919), French (0.907), German (0.913), Portuguese (0.926) and Spanish (0.868 and 0.769). Finally, we also pursued an error analysis based on clause typology for Basque and Spanish, in order to understand the performance of the segmenter.