NutriSighT: Interpretable Transformer Model for Dynamic Prediction of Hypocaloric Enteral Nutrition in Mechanically Ventilated Patients.

Achieving adequate enteral nutrition among mechanically ventilated patients is challenging, yet critical. We developed NutriSighT, a transformer model using learnable positional coding to predict which patients would achieve hypocaloric nutrition between days 3-7 of mechanical ventilation. Using retrospective data from two large ICU databases (3,284 patients from AmsterdamUMCdb - development set, and 6,456 from MIMIC-IV - external validation set), we included adult patients intubated for at least 72 hours.

Physiological Data Collected from Wearable Devices Identify and Predict Inflammatory Bowel Disease Flares.

Background And Aims: Wearable devices capture physiological signals non-invasively and passively. Many of these parameters have been linked to inflammatory bowel disease (IBD) activity. We evaluated the associative ability of several physiological metrics with IBD flares and how they change before the development of flare.

Detection of neurologic changes in critically ill infants using deep learning on video data: a retrospective single center cohort study.

Background: Infant alertness and neurologic changes can reflect life-threatening pathology but are assessed by physical exam, which can be intermittent and subjective. Reliable, continuous methods are needed. We hypothesized that our computer vision method to track movement, pose artificial intelligence (AI), could predict neurologic changes in the neonatal intensive care unit (NICU).

The impact of common and rare genetic variants on bradyarrhythmia development.

To broaden our understanding of bradyarrhythmias and conduction disease, we performed common variant genome-wide association analyses in up to 1.3 million individuals and rare variant burden testing in 460,000 individuals for sinus node dysfunction (SND), distal conduction disease (DCD) and pacemaker (PM) implantation. We identified 13, 31 and 21 common variant loci for SND, DCD and PM, respectively.

Effect of Tiered Implementation of Clinical Decision Support System for Acute Kidney Injury and Nephrotoxin Exposure in Cardiac Surgery Patients.

Background:  Nephrotoxin exposure may worsen kidney injury and impair kidney recovery if continued in patients with acute kidney injury (AKI).

Objectives:  This study aimed to determine if tiered implementation of a clinical decision support system (CDSS) would reduce nephrotoxin use in cardiac surgery patients with AKI.

Methods:  We assessed patients admitted to the cardiac surgery intensive care unit at a tertiary care center from January 2020 to December 2021, and August 2022 to September 2023.

Generating credible referenced medical research: A comparative study of openAI's GPT-4 and Google's gemini.

Background: Amidst the increasing use of AI in medical research, this study specifically aims to assess and compare the accuracy and credibility of openAI's GPT-4 and Google's Gemini in their ability to generate medical research introductions, focusing on the precision and reliability of their citations across five medical fields.

Methods: We compared the two models, OpenAI's GPT-4 and Google's Gemini Ultra, across five medical fields, focusing on the credibility and accuracy of citations, alongside the analysis of introduction length and unreferenced data.

Results: Gemini outperformed GPT-4 in reference precision.

Large Language Models and Empathy: Systematic Review.

Background: Empathy, a fundamental aspect of human interaction, is characterized as the ability to experience another being's emotions within oneself. In health care, empathy is a fundamental for health care professionals and patients' interaction. It is a unique quality to humans that large language models (LLMs) are believed to lack.

The role of deep learning in diagnostic imaging of spondyloarthropathies: a systematic review.

Aim: Diagnostic imaging is an integral part of identifying spondyloarthropathies (SpA), yet the interpretation of these images can be challenging. This review evaluated the use of deep learning models to enhance the diagnostic accuracy of SpA imaging.

Methods: Following PRISMA guidelines, we systematically searched major databases up to February 2024, focusing on studies that applied deep learning to SpA imaging.

Deep Learning for Contrast Enhanced Mammography - A Systematic Review.

Background/aim: Contrast-enhanced mammography (CEM) is a relatively novel imaging technique that enables both anatomical and functional breast imaging, with improved diagnostic performance compared to standard 2D mammography. The aim of this study is to systematically review the literature on deep learning (DL) applications for CEM, exploring how these models can further enhance CEM diagnostic potential.

Methods: This systematic review was reported according to the PRISMA guidelines.

Extracting International Classification of Diseases Codes from Clinical Documentation using Large Language Models.

Background: Large language models (LLMs) have shown promise in various professional fields, including medicine and law. However, their performance in highly specialized tasks, such as extracting ICD-10-CM codes from patient notes, remains underexplored.

Objective: The primary objective was to evaluate and compare the performance of ICD-10-CM code extraction by different LLMs with that of human coder.

Disagreements in Medical Ethics Question Answering Between Large Language Models and Physicians.

Importance: Medical ethics is inherently complex, shaped by a broad spectrum of opinions, experiences, and cultural perspectives. The integration of large language models (LLMs) in healthcare is new and requires an understanding of their consistent adherence to ethical standards.

Objective: To compare the agreement rates in answering questions based on ethically ambiguous situations between three frontier LLMs (GPT-4, Gemini-pro-1.

Benchmarking Large Language Models for Extraction of International Classification of Diseases Codes from Clinical Documentation.

Background: Healthcare reimbursement and coding is dependent on accurate extraction of International Classification of Diseases-tenth revision - clinical modification (ICD-10-CM) codes from clinical documentation. Attempts to automate this task have had limited success. This study aimed to evaluate the performance of large language models (LLMs) in extracting ICD-10-CM codes from unstructured inpatient notes and benchmark them against human coder.

A Primer on Reinforcement Learning in Medicine for Clinicians.

Reinforcement Learning (RL) is a machine learning paradigm that enhances clinical decision-making for healthcare professionals by addressing uncertainties and optimizing sequential treatment strategies. RL leverages patient-data to create personalized treatment plans, improving outcomes and resource efficiency. This review introduces RL to a clinical audience, exploring core concepts, potential applications, and challenges in integrating RL into clinical practice, offering insights into efficient, personalized, and effective patient care.

A strategy for cost-effective large language model use at health system-scale.

Large language models (LLMs) can optimize clinical workflows; however, the economic and computational challenges of their utilization at the health system scale are underexplored. We evaluated how concatenating queries with multiple clinical notes and tasks simultaneously affects model performance under increasing computational loads. We assessed ten LLMs of different capacities and sizes utilizing real-world patient data.

Applications of ChatGPT in Heart Failure Prevention, Diagnosis, Management, and Research: A Narrative Review.

Heart failure (HF) is a leading cause of mortality, morbidity, and financial burden worldwide. The emergence of advanced artificial intelligence (AI) technologies, particularly Generative Pre-trained Transformer (GPT) systems, presents new opportunities to enhance HF management. In this review, we identified and examined existing studies on the use of ChatGPT in HF care by searching multiple medical databases (PubMed, Google Scholar, Medline, and Scopus).

Assessing Retrieval-Augmented Large Language Model Performance in Emergency Department ICD-10-CM Coding Compared to Human Coders.

Background: Accurate medical coding is essential for clinical and administrative purposes but complicated, time-consuming, and biased. This study compares Retrieval-Augmented Generation (RAG)-enhanced LLMs to provider-assigned codes in producing ICD-10-CM codes from emergency department (ED) clinical records.

Methods: Retrospective cohort study using 500 ED visits randomly selected from the Mount Sinai Health System between January and April 2024.

Advancing Clinical Practice: The Potential of Multimodal Technology in Modern Medicine.

Multimodal technology is poised to revolutionize clinical practice by integrating artificial intelligence with traditional diagnostic modalities. This evolution traces its roots from Hippocrates' humoral theory to the use of sophisticated AI-driven platforms that synthesize data across multiple sensory channels. The interplay between historical medical practices and modern technology challenges conventional patient-clinician interactions and redefines diagnostic accuracy.

Automated Identification of Heart Failure With Reduced Ejection Fraction Using Deep Learning-Based Natural Language Processing.

Background: The lack of automated tools for measuring care quality limits the implementation of a national program to assess guideline-directed care in heart failure with reduced ejection fraction (HFrEF).

Objectives: The authors aimed to automate the identification of patients with HFrEF at hospital discharge, an opportunity to evaluate and improve the quality of care.

Methods: The authors developed a novel deep-learning language model for identifying patients with HFrEF from discharge summaries of hospitalizations with heart failure at Yale New Haven Hospital during 2015 to 2019.