Publication
Publication: A Primer on Reinforcement Learning in Medicine for Clinicians
Artificial intelligence (AI) is reshaping healthcare, and reinforcement learning (RL) stands at the forefront of this transformation. A recent article in npj Digital Medicine highlights RL’s potential to revolutionize clinical decision-making by dynamically adapting treatments to individual patients. Unlike traditional AI models, RL continuously learns from interactions with the patient, optimizing care strategies in real…
Read MorePublication: Unraveling the Molecular Links Between COVID-19 and Long-Term Kidney Dysfunction
The impact of COVID-19 on kidney function extends far beyond the acute phase of infection, as highlighted in a recent study published in Kidney360. Researchers performed transcriptomic and proteomic analyses on blood samples from hospitalized patients with SARS-CoV-2, focusing on those who developed acute kidney injury (AKI). Their findings revealed that severe AKI is strongly…
Read MorePrespective: How AI is Revolutionizing Nephrology Clinical Trials
Artificial intelligence (AI) is set to reshape the landscape of clinical trials in nephrology, addressing longstanding challenges in trial design, patient recruitment, and outcome assessment. Recent advancements in machine learning and natural language processing (NLP) have demonstrated AI’s ability to streamline clinical trial planning, optimize patient identification through electronic health records (EHRs), and even create…
Read MorePublication: AI Model Enhances Glucose Control Post-Cardiac Surgery
Managing blood glucose levels in post-cardiac surgery patients is a critical challenge in intensive care units (ICUs), where fluctuations can lead to severe complications. Traditional insulin dosing protocols rely on clinician judgment and standardized guidelines, which, while effective, can lack precision for individual patient needs. A new AI-driven model, GLUCOSE, developed using distributional offline reinforcement…
Read MorePublication: Deep Learning Framework Enhances Disease Detection in Electronic Health Records
The rapid evolution of artificial intelligence in medicine is opening new frontiers for disease detection and diagnosis. A recent study introduces InfEHR, a novel deep learning framework designed to analyze electronic health records (EHRs) with unprecedented accuracy. Unlike traditional methods that rely on structured clinical data, InfEHR employs deep geometric learning, a cutting-edge technique that…
Read MorePublication: Bridging Human Expertise and Machine Precision
Recent research highlighted in a New England Journal of Medicine article emphasizes the transformative potential of augmented intelligence in healthcare. This innovative approach combines advanced algorithms with the nuanced judgment of clinicians, offering enhanced diagnostic accuracy and the promise of more personalized treatment plans. By integrating computational power with human oversight, the new model aims…
Read MorePublication: Exploring the Limitations of AI in Medical Code Extraction
Large language models (LLMs) are gaining traction in various specialized domains, but their capabilities are still being tested in highly technical fields such as medical coding. Our recent study investigates how effective these AI models are at extracting ICD-10-CM codes from clinical documentation compared to a human coder. We specifically analyzed six different LLMs, including…
Read MorePublication: Novel Intracranial Pressure Monitoring Using Non-Invasive Deep Learning Approach
A research study published as a preprint on February 27, 2024, by the AIMS Lab, showcases an innovative deep-learning approach that could redefine the field of intracranial pressure monitoring. In conditions like severe acute brain injuries (SABIs), including strokes and traumatic brain injuries, accurate measurement of intracranial pressure (ICP) can be significant for managing the…
Read MorePublication: Machine Learning Boosts Precision in Social Determinants of Health Analysis
Area-level social determinants of health (SDOH) based on patients’ ZIP codes or census tracts have been commonly used in research instead of individual SDOHs. However, using area-level SDOH measures as a substitute for individual SDOH measures may not be appropriate, especially in highly diverse urban neighbourhoods like New York City. On February 8, 2024, a…
Read MorePublication: Simulation – What Is the Impact of Predictive AI in the Health Care Setting?
Models built on machine learning in health care can be victims of their own success, according to researchers at the Icahn School of Medicine and the University of Michigan. Their study assessed the impact of implementing predictive models on the subsequent performance of those and other models. Their findings—that using the models to adjust how care is delivered…
Read More