Artificial intelligence (AI) scribes can reduce the time physicians spend documenting patient visits by 69.1% during simulated primary care appointments, according to research led by University of Toronto PhD student LaShawn Murray. 

The study — published in the journal JAMIA Open, and co-authored with University of Toronto professor Enid Montague and Dr. Onil Bhattacharyya of Women’s College Hospital — involved nine physicians completing simulated patient encounters both with and without the use of AI scribes. These digital tools are capable of recording audio and using it to generate structured, regulatory-compliant clinical notes for a patient’s medical chart — the record physicians use to document their care. 

The researchers used video recordings of each appointment to analyze how physicians spent their time. They found that when the scribes were in use, the doctors spent significantly less time documenting. 

A team of NJIT researchers will map the infrastructure needed to support battery management across the state and region, identifying existing facilities and potential locations for battery collection, storage, dismantling, repurposing and recycling — and showing where New Jersey has the biggest gaps.

Smallholder farmers in sub-Saharan Africa adopt agricultural inputs including fertilizer at a low rate, contributing to low agricultural productivity. Previous research has shown that insufficient information and distrust in the quality of products for sale in local markets are among the reasons for low rates of fertilizer adoption and application. In a new study, University of Illinois Urbana-Champaign researchers examined the agricultural marketplace in Tanzania, finding that frequent turnover among local agro-dealers affect farmer perceptions of product quality and have implications for broader market functioning.

New analysis of almost 300,000 kilometres of Roman roads reveals a complex network shaped by people, places and landscapes, in which Rome was less central than is often assumed.

Open source software underpins much of the modern digital world, from mobile phones and automobiles to cloud computing and artificial intelligence. Now, the rapid adoption of AI is creating new opportunities to improve that software while placing growing pressure on the people responsible for maintaining and securing it, according to a new TechBrief from the Association for Computing Machinery’s Technology Policy Council  (TPC).

Artificial intelligence in medicine is rapidly moving beyond large language models, data analysis and prediction. One of its emerging applications is at the patient’s bedside, where AI can assist physicians with medical imaging and point-of-care ultrasound. On September 16 in Paris, this transition from discussing AI to testing its practical applications will be explored during the third Ultrasound in Nephrology training program.