Transformers for extracting breast cancer information from Spanish clinical narratives.

The wide adoption of electronic health records (EHRs) offers immense potential as a source of support for clinical research. However, previous studies focused on extracting only a limited set of medical concepts to support information extraction in the cancer domain for the Spanish language. Building on the success of deep learning for processing natural language texts, this paper proposes a transformer-based approach to extract named entities from breast cancer clinical notes written in Spanish and compares several language models. To facilitate this approach, a schema for annotating clinical notes with breast cancer concepts is presented, and a corpus for breast cancer is developed. Results indicate that both BERT-based and RoBERTa-based language models demonstrate competitive performance in clinical Named Entity Recognition (NER). Specifically, BETO and multilingual BERT achieve F-scores of 93.71% and 94.63%, respectively. Additionally, RoBERTa Biomedical attains an F-score of 95.01%, while RoBERTa BNE achieves an F-score of 94.54%. The findings suggest that transformers can feasibly extract information in the clinical domain in the Spanish language, with the use of models trained on biomedical texts contributing to enhanced results. The proposed approach takes advantage of transfer learning techniques by fine-tuning language models to automatically represent text features and avoiding the time-consuming feature engineering process.

Presence of the Eucalyptus snout beetle in Ecuador and potential invasion risk in South America.

Eucalyptus snout beetles are a complex of at least eight cryptic species (Curculionidae: Gonipterus scutellatus complex), native to mainland Australia and Tasmania, that defoliate Eucalyptus trees and are considered important pests. Since the 19th century, three species of the complex have been introduced to other continents. Here, we document the presence of Eucalyptus snout beetles in Ecuador. We used DNA data for species identification and unambiguously demonstrated that the Ecuadorian specimens belong to the species Gonipterus platensis, which has low genetic diversity compared with other species in the complex. We analyzed G. platensis' potential distribution in South America with ecological niche models and found several areas of high to intermediate climatic suitability, even in countries where the pest has not been registered, like Peru and Bolivia. Accurate identification of species in the G. scutellatus complex and understanding of their potential distribution are essential tools for improved management and prevention tactics.

Los gorgojos del eucalipto son un complejo de al menos ocho especies crípticas (Curculionidae: complejo Gonipterus scutellatus), nativos de Australia continental y Tasmania, que defolian árboles de eucalipto y son considerados como plagas de importancia. Desde el siglo 19, tres especies de este complejo se han introducido a otros continentes. En este trabajo reportamos la presencia de gorgojos del eucalipto en Ecuador. Usamos datos genéticos para la identificación específica y demostramos claramente que los especímenes ecuatorianos pertenecen a la especie Gonipterus platensis, la cual tiene baja diversidad genética comparada con otras especies en el complejo. Analizamos la distribución potencial de G. platensis en América del Sur con modelos de nicho ecológico y encontramos varias áreas con idoneidad ambiental alta a intermedia, incluso en países donde esta especie no ha sido registrada, como Perú y Bolivia. La correcta identificación de las especies del complejo Gonipterus scutellatus y una mejor comprensión de su distribución potencial constituyen herramientas fundamentales para optimizar medidas de manejo y prevención.

Catalog of the invertebrate type specimens hosted at the Pontificia Universidad Católica del Ecuador and Escuela Politécnica Nacional natural history collections.

This work updates the invertebrate type specimen catalog published by Donoso et al. (2009). The catalog is increased by 2281 type specimens (from 454 species or subspecies) to a total of 4180 type specimens (from 770 species or subspecies) hosted at the Pontificia Universidad Católica del Ecuador and Escuela Politécnica Nacional natural history collections. The new material adds 307 holotypes, 1910 paratypes, and 64 allotypes. It provides original information from four phyla (Arthropoda, Mollusca, Nemata, and Platyhelminthes), eight classes, 21 orders, 73 families, and 156 genera. This updated catalog includes a map showing the type localities in the country, a list of the 71 new type specimens (from 23 species or subspecies) from other countries hosted at both museums, corrections to the previous catalog published by Donoso et al. (2009), and label information from each new specimen.