Christina Mack

Agentic AI in Healthcare: Opportunities, Challenges, and Future Directions

Mourad Gridach, Jay Nanavati, Khaldoun Zine El Abidine, Calum Yacoubian et autres

The integration of Agentic AI into healthcare marks a new era in medical automation and decision support. Leveraging autonomous reasoning, planning, and collaboration, these AI systems are transforming clinical workflows, diagnostics, and patient management. Recent advancements have led Agentic AI to evolve …

gb (code pays fourni par la source)

Anterior Cruciate Ligament Tear Location in National Football League Athletes Based on Magnetic Resonance Imaging

Robert H. Brophy, Jana Crain, Jonathan Baker, Richard M. Silverman et autres

Background: Anterior cruciate ligament (ACL) tears are common and often devastating injuries among elite athletes. While interest in ACL preservation has highlighted the importance of ACL tear location to treatment decision-making, there is limited data on ACL tear location in elite athletes. …

us (code pays fourni par la source)

A perspective for adapting generalist AI to specialized medical AI applications and their challenges

Zifeng Wang, Hanyin Wang, Benjamin Danek, Ying Li et autres

We introduce a framework to adapt large language models for medicine: (1) Modeling: breaking down medical workflows into manageable steps; (2) Optimization: optimizing model performance via advanced adaptations; and (3) System engineering: developing agent or chain systems. Furthermore, we describe varied use …

us, cn (code pays fourni par la source)

A study of calibration as a measurement of trustworthiness of large language models in biomedical natural language processing

Rodrigo de Oliveira, Matthew Garber, James M. Gwinnutt, Emaan Rashidi et autres

Objectives: To assess the calibration of 9 large language models (LLMs) within biomedical natural language processing (BioNLP) tasks, furthering understanding of trustworthiness and reliability in real-world settings. Materials and Methods: For each LLM, we collected responses and corresponding confidence scores for all …

gb, us (code pays fourni par la source)

Observed Versus Expected COVID-19 Infections Among National Football League Players During the 2020 Season

Anthony Casolaro, Dan Hanfling, Allen K. Sills, Thom Mayer et autres

BACKGROUND: The National Football League (NFL) and National Football League Players Association implemented a set of strict protocols for the 2020 season with the intent to mitigate COVID-19 risk among players and staff. In that timeframe, the league's 32 teams completed 256 …

us (code pays fourni par la source)

From text to insight: Methods for validation of NLP-extracted real-world oncology data using a human-in-the-loop electronic review tool.

Elizabeth Eldridge, Elizabeth Trowbridge, Julien Heidt, Nicholas Stemkowski et autres

e23291 Background: Natural Language Processing (NLP) for extraction of oncology-specific data-phenotypes from free-text in electronic medical records (EMR) is an efficient method for generating real-world data (RWD) for use in oncology research. NLP-extracted RWD enables rapid research outcomes to be examined across …

us (code pays fourni par la source)

Viral dynamics of acute SARS-CoV-2 infection and applications to diagnostic and public health strategies

Chaney C. Kalinich, Stephen M. Kissler, Nathan D. Grubaugh, Kristin Y. Shiue et autres

SARS-CoV-2 infections are characterized by viral proliferation and clearance phases and can be followed by low-level persistent viral RNA shedding. The dynamics of viral RNA concentration, particularly in the early stages of infection, can inform clinical measures and interventions such as test-based …

us (code pays fourni par la source)

Proposed Contents of a Real-World Data Quality and Relevance Package for Regulatory Submissions

Cynthia J. Girman, Christina Mack, Dana Y. Teltsch, Morgan A. Marks et autres

Real world data is increasingly used for regulatory decisions. Based on regulatory guidance documents on data quality and relevancy for real world data, TransCelerate released considerations for audit readiness in 2023. However, the content and level of detail for the actual documentation …

gb, us, fr (code pays fourni par la source)

Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions

Mourad Gridach, Jay Nanavati, Khaldoun Zine El Abidine, Christina Mack

The integration of Agentic AI into scientific discovery marks a new frontier in research automation. These AI systems, capable of reasoning, planning, and autonomous decision-making, are transforming how scientists perform literature review, generate hypotheses, conduct experiments, and analyze results. This survey provides …

Prevention of concussion and long‐term effects of repetitive traumatic brain injury: Unanimous consensus from the Cantu Concussion Summit

Robert C. Cantu, Allen K. Sills, Michael L. Alosco, Kristy B. Arbogast et autres

OBJECTIVE: The Cantu Concussion Summit aimed to gather clinicians and researchers to share findings and identify research gaps in brain injury and long-term cognitive disorders in athletes. DESIGN: The conference concluded with a discussion of ways to best mitigate the risk of …

us, ca (code pays fourni par la source)

A Study of Calibration as a Measurement of Trustworthiness of Large Language Models in Biomedical Research

Rodrigo de Oliveira, Matthew Garber, James M. Gwinnutt, Emaan S Rashidi et autres

ABSTRACT Objectives To assess the calibration of 9 large language models (LLMs) within biomedical natural language processing (BioNLP) tasks, furthering understanding of trustworthiness and reliability in real-world settings. Materials and Methods For each LLM, we collected responses and corresponding confidence scores for …

gb, us (code pays fourni par la source)

Core Concepts in Pharmacoepidemiology: Principled Use of Artificial Intelligence and Machine Learning in Pharmacoepidemiology and Healthcare Research

Kathryn Rough, Emaan Rashidi, Caroline G. Tai, Rachel M. Lucia et autres

Artificial intelligence (AI) and machine learning (ML) are important tools across many fields of health and medical research. Pharmacoepidemiologists can bring essential methodological rigor and study design expertise to the design and use of these technologies within healthcare settings. AI/ML-based tools also …

gb, us (code pays fourni par la source)