By John Halamka and Paul Cerrato—Large language models like ChatGPT are finding their way into healthcare, business, and everyday life. The study of mechanistic interpretability may help us create safer, more trustworthy algorithms by…
Continue Reading
Millions of shift workers in the U.S. face an increased risk of depression, cancer, and metabolic disease, yet individual responses to shift work vary widely. We find that a conserved biological system of morning…
Continue Reading
News
Ambience Healthcare develops an AI medical coding model using OpenAI’s Reinforcement Fine-Tuning technology that can record and document clinical conversations, and identify and integrate relevant ICD-10 codes for more accurate billing. The company claims…
Continue Reading
This study introduces Glucose Level Understanding and Control Optimized for Safety and Efficacy (GLUCOSE), a distributional offline reinforcement learning algorithm for optimizing insulin dosing after cardiac surgery. Trained on 5228 patients, tested on 920,…
Continue Reading
This is a multi-institutional study to evaluate a head-and-neck CT auto-segmentation software across seven institutions globally. 11 lymph node levels and 7 organs-at-risk contours were evaluated in a two-phase study design. Time savings were…
Continue Reading
Background: Two-thirds of people aged 65 and older require help with daily activities such as eating, bathing, and getting in and out of bed or a chair. Walking-assist wearable robots have shown significant improvements…
Continue Reading
Background: The adoption of high-quality health apps has been slow, despite the myriad benefits associated with their use. This is partly due to concerns regarding the effectiveness, safety, and data privacy of such apps….
Continue Reading
Breakthrough Study Shows 400% Improvement in Detection Rates
A groundbreaking multimodal AI model has revolutionized delirium detection in hospitalized patients, delivering remarkable improvements in treatment outcomes. Published in JAMA Network Open, this innovative machine learning…
Digital therapeutics (DTx) provide innovative treatment options. In this study, we identified and compared approved DTx in China, the US, Germany, and Belgium. In total, 507 DTx applications were identified (US, 192; China, 235;…
Continue Reading
The complexities inherent in EHR data create discrepancies between real-world evidence and RCTs, posing substantial challenges in determining whether a treatment is likely to have a beneficial impact compared to the standard of care…
Continue Reading
