Publications
We work hard to attract, retain, and support the most outstanding faculty.
2025
2025
2025
2025
2025
2025
BACKGROUND
Detailed intervention reporting is essential to interpretation, replication, and eventual translation of music-based interventions (MBIs) into practice. Despite availability of (RG-MBI, published 2011), multiple reviews reveal sustained problems with reporting quality and consistency. To address this, we convened an interdisciplinary expert panel to update and improve the utility and validity of the existing guidelines using a rigorous Delphi approach. The resulting updated checklist includes 12-items across eight areas considered essential to ensure transparent reporting of MBIs.
METHODS
The purpose of this explanation and elaboration document is to facilitate consistent understanding, use, and dissemination of the revised RG-MBI. Members of the interdisciplinary expert panel collaborated to create the resulting guidance statement.
RESULTS
This guidance statement offers: (1) the scope and intended use of the RG-MBI, (2) an explanation for each checklist item, with examples from published studies, and (3) two published studies with annotations indicating where the authors reported each checklist item.
CONCLUSION
Broader uptake of the RG-MBIs by study authors, editors, and peer reviewers will lead to better reporting of MBI trials, and in turn facilitate greater replication of research, improve cross-study comparisons and meta-analyses, and increase implementation of findings.
View on PubMed2025
2025
BACKGROUND
Delirium is a common condition affecting hospitalized older adults, often leading to adverse outcomes. Nevertheless, delirium frequently goes unrecognized due to various clinical and systemic challenges. We aimed to develop and evaluate a deep-learning natural language processing (NLP) model trained on Brazilian Portuguese clinical notes, aiming to improve the identification of delirium symptoms in electronic health records (EHR) and to facilitate the detection of delirium.
METHODS
We extracted free-text clinical notes from 500 hospitalizations of older adults at a tertiary care hospital in São Paulo, Brazil, for annotation and analysis. Delirium symptoms were identified and labeled by expert clinicians using a structured protocol. The deep learning model BERTimbau was employed alongside a classical Random Forest approach for comparison, with performance metrics derived from F1 scores. We also developed the CAM-BERT framework, an algorithmic approach to categorize potential delirium cases by aligning symptoms classified by the model with CAM criteria.
RESULTS
The BERTimbau model showcased superior performance, with an F1-macro score of 77 % compared to the baseline model's 39 %. It achieved F1 scores of around 90 % for identifying confusion and disorganized thinking. For the CAM-BERT framework, which mapped detected symptoms to CAM criteria, the overall F1-macro score was 83 %. The agreement with expert chart review yielded a Cohen's kappa coefficient of 0.72.
CONCLUSIONS
The study highlights the potential of artificial intelligence, particularly NLP, in supporting the recognition of delirium in non-English-speaking clinical settings. Further research is needed to validate the model's applicability across diverse healthcare environments.
View on PubMed2025
2025