Search

Introduction Children with septo-optic-pituitary dysplasia (SOD) may experience a range of visual impairments and hormonal dysfunctions beyond developmental delay/intellectual disability. The literature describes sleep fragmentation, circadian rhythm disruptions and reduced sleep efficiency. These manifestations are believed to be closely linked to both structural and functional abnormalities associated with SOD, potentially disrupting the natural circadian rhythm. Both anomalies in midline brain structures and decreased visual input could potentially impact melatonin secretion, although a distinct melatonin profile for SOD patients has yet to be identified. Furthermore, the specific contribution of these factors to sleep disturbances in SOD remains unexplored. The aim of this study is to evaluate the quality of sleep and its characteristics, along with the melatonin profile, among paediatric patients diagnosed with SOD. A comparison will be made between these findings and those of children with isolated bilateral visual impairment, as well as patients with agenesis of the corpus callosum.Methods and analysis Participants aged between 3 and 18 years previously diagnosed with SOD will be recruited prospectively. Each participant will be assessed at baseline and at each follow-up visit scheduled to evaluate the clinical course. Sleep quality and daytime sleepiness changes will be tracked using actigraphic assessment, standardised sleep questionnaires and a sleep EEG. Additionally, plasma and salivary melatonin profiles will be assessed for each participant.Ethics and dissemination This study has been approved by local Ethics Committee (N°0049187/23). The study findings will be shared through publication in an international peer-reviewed journal and presented at both national and international conferences.Trial registration number NCT06262152.

The digitization of healthcare records has revolutionized medical research and patient care, with electronic health records (EHRs) containing a wealth of structured and unstructured data. Extracting valuable information from unstructured clinical text presents a significant challenge, necessitating automated tools for efficient data mining. Natural language processing (NLP) methods have been pivotal in this endeavor, aiming to extract crucial clinical concepts embedded within free-form text. Our research addresses the imperative for robust biomedical entity extraction, focusing specifically on inflammatory bowel disease (IBD). Leveraging novel domain-specific pre-training and entity-aware masking strategies with contrastive learning, we fine-tune and adapt a general language model to be better adapted to IBD-related information extraction scenarios. Our named entity recognition (NER) tool streamlines the retrieval process, supporting annotation, correction, and visualization functionalities. In summary, we developed a comprehensive pipeline for clinical Dutch NER encompassing an efficient domain adaptation strategy with domain-aware masking and model fine-tuning enhancements, and an end-to-end entity extraction tool, significantly advancing medical record curation and clinical workflows.