A foundation model for human-AI collaboration in medical literature mining.

Systematic literature review is essential for evidence-based medicine, requiring comprehensive analysis of clinical trial publications. However, the application of artificial intelligence (AI) models for medical literature mining has been limited by insufficient training and evaluation across broad therapeutic areas and diverse tasks. Here, we present LEADS, an AI foundation model for study search, screening, and data extraction from medical literature.

Recommending Clinical Trials for Online Patient Cases using Artificial Intelligence.

Clinical trials are crucial for assessing new treatments; however, recruitment challenges-such as limited awareness, complex eligibility criteria, and referral barriers-hinder their success. With the growth of online platforms, patients, caregivers, and family members increasingly post medical cases on social media and health communities, while physicians publish case reports accessible on platforms like PubMed-collectively expanding recruitment pools beyond traditional clinical trial pathways. Recognizing this potential, we utilized TrialGPT, a framework that leverages a large language model, to match 50 online patient cases (collected from case reports and social media) to clinical trials and evaluate performance against traditional keyword-based searches.

Beyond Multiple-Choice Accuracy: Real-World Challenges of Implementing Large Language Models in Healthcare.

Large language models (LLMs) have gained significant attention in the medical domain for their human-level capabilities, leading to increased efforts to explore their potential in various healthcare applications. However, despite such a promising future, there are multiple challenges and obstacles that remain for their real-world uses in practical settings. This work discusses key challenges for LLMs in medical applications from four unique aspects: operational vulnerabilities, ethical and social considerations, performance and assessment difficulties, and legal and regulatory compliance.

Endoscopists' knowledge, perceptions, and attitudes toward the use of artificial intelligence in endoscopy: a systematic review.

Background And Aims: Artificial intelligence (AI) is rapidly evolving in the field of GI endoscopy. This systematic review aims to summarize the current perspectives of endoscopists on AI in endoscopy and to identify its challenges.

Methods: Electronic databases were searched to identify studies conducted on endoscopists' opinions on the use of AI in endoscopy.

Exploring beyond diagnoses in electronic health records to improve discovery: a review of the phenome-wide association study.

Objective: The phenome-wide association study (PheWAS) systematically examines the phenotypic spectrum extracted from electronic health records (EHRs) to uncover correlations between phenotypes and exposures. This review explores methodologies, highlights challenges, and outlines future directions for EHR-driven PheWAS.

Materials And Methods: We searched the PubMed database for articles spanning from 2010 to 2023, and we collected data regarding exposures, phenotypes, cohorts, terminologies, replication, and ancestry.

The West Catching Up With the East: High-Magnification NBI Is Accurate for the Diagnosis of Gastric Neoplasia in a Western Population.

Background And Aim: Accurate endoscopic prediction of histology is key to recognition of early gastric neoplasia and selection of appropriate resection techniques. Narrow-band imaging with magnification (M-NBI) has proven to be highly accurate for gastric lesions in eastern countries; however, we sought to examine whether it can be effectively utilized in the west where evidence is scarce.

Methods: This is an analysis of a prospective database of gastric lesions at a single Australian center from 2009 to 2023.

Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators.

Although large language models (LLMs) have been assessed for general medical knowledge using licensing exams, their ability to support clinical decision-making, such as selecting medical calculators, remains uncertain. We assessed nine LLMs, including open-source, proprietary, and domain-specific models, with 1,009 multiple-choice question-answer pairs across 35 clinical calculators and compared LLMs to humans on a subset of questions. While the highest-performing LLM, OpenAI o1, provided an answer accuracy of 66.

Demystifying Large Language Models for Medicine: A Primer.

Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this primer paper, we propose an actionable guideline to help healthcare professionals more efficiently utilize LLMs in their work, along with a set of best practices.

Herpes simplex virus encephalitis: An atypical presentation of delirium.

Herpes simplex encephalitis (HSE) is the most common cause of infectious encephalitis. Our case is of a 75-year-old woman who presented with dysuria and altered mental status. Our case addresses the difficulties in diagnosis and highlights the importance of early recognition of HSE and its associated neurological sequelae.

Evaluating resources composing the PheMAP knowledge base to enhance high-throughput phenotyping.

Objective: A previous study, PheMAP, combined independent, online resources to enable high-throughput phenotyping (HTP) using electronic health records (EHRs). However, online resources offer distinct quality descriptions of diseases which may affect phenotyping performance. We aimed to evaluate the phenotyping performance of single resource-based PheMAPs and investigate an optimized strategy for HTP.

Utilizing Electroencephalography Measurements for Comparison of Task-Specific Neural Efficiencies: Spatial Intelligence Tasks.

Spatial intelligence is often linked to success in engineering education and engineering professions. The use of electroencephalography enables comparative calculation of individuals' neural efficiency as they perform successive tasks requiring spatial ability to derive solutions. Neural efficiency here is defined as having less beta activation, and therefore expending fewer neural resources, to perform a task in comparison to other groups or other tasks.

A Proof of Concept Study of Function-Based Statistical Analysis of fNIRS Data: Syntax Comprehension in Children with Specific Language Impairment Compared to Typically-Developing Controls.

Functional near infrared spectroscopy (fNIRS) is a neuroimaging technology that enables investigators to indirectly monitor brain activity in vivo through relative changes in the concentration of oxygenated and deoxygenated hemoglobin. One of the key features of fNIRS is its superior temporal resolution, with dense measurements over very short periods of time (100 ms increments). Unfortunately, most statistical analysis approaches in the existing literature have not fully utilized the high temporal resolution of fNIRS.