i2b2 data-warehouse could be a useful tool to support the enrollment phase of clinical studies. The aim of this work is to evaluate its performance on two clinical trials. We developed also an i2b2 extension to help in suggesting eligible patients for a study. The work showed good results in terms of ability to implement inclusion/exclusion criteria, but also in terms of identified patients actually enrolled and high number of patients suggested as potentially enrollable.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3233/SHTI210217 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Examining the Generalizability of Pretrained De-identification Transformer Models on Narrative Nursing Notes.
Appl Clin Inform
March 2024
Department of Biomedical Informatics, Columbia University, New York, New York, United States.
Background: Narrative nursing notes are a valuable resource in informatics research with unique predictive signals about patient care. The open sharing of these data, however, is appropriately constrained by rigorous regulations set by the Health Insurance Portability and Accountability Act (HIPAA) for the protection of privacy. Several models have been developed and evaluated on the open-source i2b2 dataset.
View Article and Find Full Text PDFImproving large language models for clinical named entity recognition via prompt engineering.
J Am Med Inform Assoc
September 2024
Section of Biomedical Informatics and Data Science, School of Medicine, Yale University, New Haven, CT, United States.
Importance: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets.
View Article and Find Full Text PDFProtected Health Information Recognition by Fine-Tuning a Pre-training Transformer Model.
Healthc Inform Res
January 2022
Department of Computer Engineering, Gachon University, Seongnam, Korea.
Objective: De-identifying protected health information (PHI) in medical documents is important, and a prerequisite to deidentification is the identification of PHI entity names in clinical documents. This study aimed to compare the performance of three pre-training models that have recently attracted significant attention and to determine which model is more suitable for PHI recognition.
Methods: We compared the PHI recognition performance of deep learning models using the i2b2 2014 dataset.
A Context-Enhanced De-identification System.
ACM Trans Comput Healthc
January 2022
George Mason University, Fairfax, VA, USA.
Many modern entity recognition systems, including the current state-of-the-art de-identification systems, are based on bidirectional long short-term memory (biLSTM) units augmented by a conditional random field (CRF) sequence optimizer. These systems process the input sentence by sentence. This approach prevents the systems from capturing dependencies over sentence boundaries and makes accurate sentence boundary detection a prerequisite.
View Article and Find Full Text PDFEvaluation of Three Feasibility Tools for Identifying Patient Data and Biospecimen Availability: Comparative Usability Study.
JMIR Med Inform
July 2021
Institute for Medical Informatics and Biometry, Carl Gustav Carus Faculty of Medicine, Technische Universität Dresden, Dresden, Germany.
Background: To meet the growing importance of real-word data analysis, clinical data and biosamples must be timely made available. Feasibility platforms are often the first contact point for determining the availability of such data for specific research questions. Therefore, a user-friendly interface should be provided to enable access to this information easily.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!