Electronic Health Records Reveal Significant Familial Cancer Risk, but Genetic Testing Remains Underutilized
Electronic health record (EHR) data can effectively identify patients with familial risk for hereditary breast and ovarian cancer, but a substantial proportion of these high-risk individuals have not undergone genetic testing.
Comparison of Physician Experience in Clinical Decision Support: Evaluating the Impact of a Specialized Large Language Model (Ask Avo) versus a General-Purpose Model (ChatGPT-4)
Specialized large language models designed for clinical applications, such as Ask Avo, can significantly improve physician experience in terms of trustworthiness, actionability, relevance, comprehensiveness, and user-friendly format compared to general-purpose models like ChatGPT-4.
Automated Liver Function Testing Platform Improves Chronic Liver Disease Diagnosis and Management in Primary Care
The iLFT platform can enhance the diagnosis and management of chronic liver disease in primary care settings by automating further testing and providing recommendations based on liver function test results.
Reinforcing Explainability in ChatGPT's Breast Cancer Risk Assessment through Embedding Clinical Guidelines
This research explores the integration of generative AI, specifically ChatGPT, with breast cancer risk assessment guidelines to enhance the explainability and transparency of the decision-making process.
Implementing a New Kidney Function Equation Without Race Adjustment Did Not Modify Nephrology Referrals and Visits Within a Healthcare System
Implementing a new eGFR equation without race adjustment did not change rates of nephrology referrals and visits within a single healthcare system, despite lowering eGFR estimates for patients documented as Black or African American.
Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation to Improve Oxygen Delivery and Avoid Lung Injury
The core message of this article is to develop an interpretable reinforcement learning methodology to optimize mechanical ventilation strategies that can increase blood oxygen levels (SpO2) while explicitly discouraging aggressive ventilator settings known to cause lung injuries.
Generating Faithful and Complete Summaries of Patient Hospital Stays from Electronic Health Records
Generating hospital-course summaries that accurately and comprehensively represent the patient's medical history and care during a hospital stay is critical for continuity of care and patient safety, but is a challenging task due to the large volume of documentation in electronic health records.
Comprehensive Corpus of Annotated Medical Imaging Reports and Advanced Information Extraction Using BERT-based Language Models
This study introduces a novel annotated corpus, CAMIR, which combines granular event-based annotations with concept normalization to comprehensively capture clinical findings from radiology reports. Two BERT-based information extraction models, mSpERT and PL-Marker++, are developed and evaluated on the CAMIR dataset, demonstrating performance comparable to human-level agreement.
Exploring Semantic Information in Disease: Data Augmentation Techniques for Chinese Disease Name Normalization
Novel data augmentation techniques enhance disease name normalization performance by respecting structural invariance and hierarchy properties.
© 2024 by Linnk AI