Publications by authors named "L Coyle"
Article Synopsis
- The study discusses the limitations of using graph convolutional networks (GCN) for classifying natural language texts, particularly in terms of memory usage and distribution.
- It introduces a new model called FastMPN, which features a message passing architecture that allows for adjustable node embeddings and edge weights, improving the GCN's problem-solving ability.
- The FastMPN model was tested on extracting clinical data from cancer pathology reports, outperforming or matching existing models and training quickly on a large dataset using advanced hardware.
Background: A lag time between cancer case diagnosis and incidence reporting impedes the ability to monitor the impact of recent events on cancer incidence. Currently, the data submission standard is 22 months after a diagnosis year ends, and the reporting standard is 27.5 months after a diagnosis year ends.
View Article and Find Full Text PDFMachine learning and deep learning tools for the automated capture of cancer surveillance data.
J Natl Cancer Inst Monogr
August 2024
The National Cancer Institute and the Department of Energy strategic partnership applies advanced computing and predictive machine learning and deep learning models to automate the capture of information from unstructured clinical text for inclusion in cancer registries. Applications include extraction of key data elements from pathology reports, determination of whether a pathology or radiology report is related to cancer, extraction of relevant biomarker information, and identification of recurrence. With the growing complexity of cancer diagnosis and treatment, capturing essential information with purely manual methods is increasingly difficult.
View Article and Find Full Text PDFArticle Synopsis
- The study investigates the use of diuretics in treating bronchopulmonary dysplasia (BPD), a respiratory condition in premature infants, to evaluate their effectiveness.
- A systematic review was conducted, analyzing 13 studies from various databases, focusing on combinations of diuretics like spironolactone and furosemide and their impact on lung function.
- Results indicate that the effectiveness of diuretics for BPD is still unclear due to limited high-quality studies, suggesting a need for more rigorous randomized controlled trials to assess their safety and efficacy.