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.

CT-Based Body Composition Measures and Systemic Disease: A Population-Level Analysis Using Artificial Intelligence Tools in Over 100,000 Patients.

CT-based abdominal body composition measures have shown associations with important health outcomes. Artificial intelligence (AI) advances now allow deployment of tools that measure body composition in large patient populations. To assess associations of age, sex, and common systemic diseases on CT-based body composition measurements derived using a panel of fully automated AI tools in a population-level adult patient sample.

Utilizing domain knowledge to improve the classification of intravenous contrast phase of CT scans.

Multiple intravenous contrast phases of CT scans are commonly used in clinical practice to facilitate disease diagnosis. However, contrast phase information is commonly missing or incorrect due to discrepancies in CT series descriptions and imaging practices. This work aims to develop a classification algorithm to automatically determine the contrast phase of a CT scan.

Leveraging Professional Radiologists' Expertise to Enhance LLMs' Evaluation for AI-generated Radiology Reports.

In radiology, Artificial Intelligence (AI) has significantly advanced report generation, but automatic evaluation of these AI-produced reports remains challenging. Current metrics, such as Conventional Natural Language Generation (NLG) and Clinical Efficacy (CE), often fall short in capturing the semantic intricacies of clinical contexts or overemphasize clinical details, undermining report clarity. To overcome these issues, our proposed method synergizes the expertise of professional radiologists with Large Language Models (LLMs), like GPT-3.

Revisiting the Plasmodium falciparum druggable genome using predicted structures and data mining.

The identification of novel drug targets for the purpose of designing small molecule inhibitors is key component to modern drug discovery. In malaria parasites, discoveries of antimalarial targets have primarily occurred retroactively by investigating the mode of action of compounds found through phenotypic screens. Although this method has yielded many promising candidates, it is time- and resource-consuming and misses targets not captured by existing antimalarial compound libraries and phenotypic assay conditions.

Automated Classification of Body MRI Sequences Using Convolutional Neural Networks.

Rationale And Objectives: Multi-parametric MRI (mpMRI) studies of the body are routinely acquired in clinical practice. However, a standardized naming convention for MRI protocols and series does not exist currently. Conflicts in the series descriptions present in the DICOM headers arise due to myriad MRI scanners from various manufacturers used for imaging, wide variations in imaging practices across institutions, and technologist preferences.

Characterising the Time Course of the Dilatory Response of Healthy Retinal Arteries during Flicker-Light Provocation.

Introduction: The dilatory response of healthy retinal arterioles to flicker-light (FL) provocation appears to be biphasic. The vessel diameter rapidly increases (acute phase) over 5-10 s, then barely increases thereafter (maintenance phase) until FL cessation. This reaction is usually characterised at a single point by two parameters: maximum dilation (MD) relative to baseline diameter (MD, %) and time to MD (RT, s).

Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: A data-driven approach for improved classification.

In chest X-ray (CXR) image analysis, rule-based systems are usually employed to extract labels from reports for dataset releases. However, there is still room for improvement in label quality. These labelers typically output only presence labels, sometimes with binary uncertainty indicators, which limits their usefulness.

Deep Learning Segmentation of Ascites on Abdominal CT Scans for Automatic Volume Quantification.

Purpose: To evaluate the performance of an automated deep learning method in detecting ascites and subsequently quantifying its volume in patients with liver cirrhosis and ovarian cancer.

Materials And Methods: This retrospective study included contrast-enhanced and non-contrast abdominal-pelvic CT scans of patients with cirrhotic ascites and patients with ovarian cancer from two institutions, National Institutes of Health (NIH) and University of Wisconsin (UofW). The model, trained on The Cancer Genome Atlas Ovarian Cancer dataset (mean age, 60 years ± 11 [s.

Fully Automated and Explainable Measurement of Liver Surface Nodularity in CT: Utility for Staging Hepatic Fibrosis.

Rationale And Objectives: In the United States, cirrhosis was the 12th leading cause of death in 2016. Despite end-stage cirrhosis being irreversible, earlier stages of hepatic fibrosis can be reversed via early diagnosis and intervention. The objective is to investigate the utility of a fully automated technique to measure liver surface nodularity (LSN) for staging hepatic fibrosis (stages F0-F4).

Weakly supervised learning for subcutaneous edema segmentation of abdominal CT using pseudo-labels and multi-stage nnU-Nets.

Volumetric assessment of edema due to anasarca can help monitor the progression of diseases such as kidney, liver or heart failure. The ability to measure edema non-invasively by automatic segmentation from abdominal CT scans may be of clinical importance. The current state-of-the-art method for edema segmentation using intensity priors is susceptible to false positives or under-segmentation errors.

Unsupervised Multi-parametric MRI Registration Using Neural Optimal Transport.

Precise deformable image registration of multi-parametric MRI sequences is necessary for radiologists in order to identify abnormalities and diagnose diseases, such as prostate cancer and lymphoma. Despite recent advances in unsupervised learning-based registration, volumetric medical image registration that requires considering the variety of data distributions is still challenging. To address the problem of multi-parametric MRI sequence data registration, we propose an unsupervised domain-transported registration method, called OTMorph by employing neural optimal transport that learns an optimal transport plan to map different data distributions.

Evaluation of GPT Large Language Model Performance on RSNA 2023 Case of the Day Questions.

Background GPT-4V (GPT-4 with vision, ChatGPT; OpenAI) has shown impressive performance in several medical assessments. However, few studies have assessed its performance in interpreting radiologic images. Purpose To assess and compare the accuracy of GPT-4V in assessing radiologic cases with both images and textual context to that of radiologists and residents, to assess if GPT-4V assistance improves human accuracy, and to assess and compare the accuracy of GPT-4V with that of image-only or text-only inputs.

Novel human iPSC models of neuroinflammation in neurodegenerative disease and regenerative medicine.

The importance of neuroinflammation in neurodegenerative diseases is becoming increasingly evident, and, in parallel, human induced pluripotent stem cell (hiPSC) models of physiology and pathology are emerging. Here, we review new advancements in the differentiation of hiPSCs into glial, neural, and blood-brain barrier (BBB) cell types, and the integration of these cells into complex organoids and chimeras. These advancements are relevant for modeling neuroinflammation in the context of prevalent neurodegenerative disorders, such as Alzheimer's disease (AD), Parkinson's disease (PD), and multiple sclerosis (MS).

Sensing data and methodology from the Adaptive DBS Algorithm for Personalized Therapy in Parkinson's Disease (ADAPT-PD) clinical trial.

Adaptive deep brain stimulation (aDBS) is an emerging advancement in DBS technology; however, local field potential (LFP) signal rate detection sufficient for aDBS algorithms and the methods to set-up aDBS have yet to be defined. Here we summarize sensing data and aDBS programming steps associated with the ongoing Adaptive DBS Algorithm for Personalized Therapy in Parkinson's Disease (ADAPT-PD) pivotal trial (NCT04547712). Sixty-eight patients were enrolled with either subthalamic nucleus or globus pallidus internus DBS leads connected to a Medtronic Percept PC neurostimulator.

Subcutaneous edema segmentation on abdominal CT using multi-class labels and iterative annotation.

Purpose: Anasarca is a condition that results from organ dysfunctions, such as heart, kidney, or liver failure, characterized by the presence of edema throughout the body. The quantification of accumulated edema may have potential clinical benefits. This work focuses on accurately estimating the amount of edema non-invasively using abdominal CT scans, with minimal false positives.

Whole-cell Rieske non-heme iron biocatalysts.

Rieske non-heme iron oxygenases (ROs) possess the ability to catalyze a wide range of reactions. Their ability to degrade aromatic compounds is a unique characteristic and makes ROs interesting for a variety of potential applications. However, purified ROs can be challenging to work with due to low stability and long, complex electron transport chains.

Intrapatient Changes in CT-Based Body Composition After Initiation of Semaglutide (Glucagon-Like Peptide-1 Receptor Agonist) Therapy.

The long-acting glucagon-like peptide-1 receptor agonist semaglutide is used to treat type 2 diabetes or obesity in adults. Clinical trials have observed associations of semaglutide with weight loss, improved control of diabetes, and cardiovascular risk reduction. The purpose of this study was to evaluate intrapatient changes in body composition after initiation of semaglutide therapy by applying an automated suite of CT-based artificial intelligence (AI) body composition tools.

Classification of Multi-Parametric Body MRI Series Using Deep Learning.

Multi-parametric magnetic resonance imaging (mpMRI) exams have various series types acquired with different imaging protocols. The DICOM headers of these series often have incorrect information due to the sheer diversity of protocols and occasional technologist errors. To address this, we present a deep learning-based classification model to classify 8 different body mpMRI series types so that radiologists read the exams efficiently.

Disparities and Medical Expenditure Implications in Pediatric Tele-Mental Health Services During the COVID-19 Pandemic in Mississippi.

Tele-mental health (TMH) services, including both mental and behavioral healthcare (MBH) services, emerged as a cornerstone in delivering pediatric mental healthcare during the coronavirus disease 2019 (COVID-19) pandemic, yet their utilization and effects on healthcare resource utilization (HCRU) and medical expenditures remain unclear. To bridge the gap, this study aims to investigate the association between TMH utilization and sociodemographic factors and assess its associated HCRU and medical expenditures within a pediatric population in Mississippi. Studying 1,972 insured pediatric patients who accessed outpatient MBH services at the study institution between January 2020 and June 2023, age, race, insurance type, rural residency, and household income were identified as key determinants of TMH utilization.