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 More

Publication: 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 More

Prespective: How AI is Revolutionizing Nephrology Clinical Trials

JASN

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 More

Publication: 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 More

Publication: 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 More

Publication: Bridging Human Expertise and Machine Precision

nejm AI

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 More

Publication: Exploring the Limitations of AI in Medical Code Extraction

Appl Clin Inform

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 More

Peripheral Transcriptomics in Acute and Long-Term Kidney Dysfunction in SARS-CoV2 Infection.

Link: https://doi.org/10.34067/KID.0000000727 Authors: Jayaraman, Pushkala; Rajagopal, Madhumitha; Paranjpe, Ishan; Suarez-Farinas, Mayte; Liharska, Lora; Thompson, Ryan; Del Valle, Diane Marie; Beckmann, Noam; Lund, Anina N; Gownivaripally, Pooja; Oh, Wonsuk; Gulamali, Faris F; Kauffman, Justin; Gonzalez-Kozlova, Edgar; Dellepiane, Sergio; Vasquez-Rios, George; Vaid, Akhil; Jiang, Joy; Fox, Ben; Sakhuja, Ankit; Chen, Steven; Kenigsberg, Ephraim; He, John Cijiang; Coca,…

Read More

Natural Language Processing Identifies Under-Documentation of Symptoms in Patients on Hemodialysis.

Link: https://doi.org/10.34067/KID.0000000694 Authors: Dai, Yang; Wen, Huei Hsun; Yang, Joanna; Gupta, Neepa; Rhee, Connie; Horowitz, Carol R; Mohottige, Dinushika; Nadkarni, Girish N; Coca, Steven; Chan, Lili Abstract: Patients on hemodialysis (HD) have a high burden of emotional and physical symptoms. These symptoms are often under-recognized. NLP can be used to identify patient symptoms from the…

Read More