npj Digital Medicine
An online open-access journal dedicated to publishing research in all aspects of digital medicine, including the clinical application and implementation of digital and mobile technologies, virtual healthcare, and novel applications of artificial intelligence and informatics.
Our lives can be seen as a series of events unfolding over time, and this can be modeled using Transformers, an AI architecture that has been highly successful in large language models. In our npj Digital Medicine article we explore how they can be applied to personalized healthcare journeys.
Providing quality of care feedback using Bayesian Machine Learning in Urology
A better method of measuring the quality of care delivered in specialities that lack the proper funding for comprehensive quality indicators developed by clinical quality registries using Bayesian machine learning and large administrative datasets.
Results and Implications for Generative AI in a Large Introductory Biomedical and Health Informatics Course
We compared student hoework and final exam scores with 6 large-language model (LLM) systems in a large online introductory course in biomedical and health informatics. All of the LLMs scored between the 50th and 75th percentiles of students, raising questions about student assessment in higher ed.
Pregnancy tracking with wearables
Pregnancies are often only tracked every couple of weeks at best, and have historically been understudied. Using wearable devices, people can measure and even share their pregnancy experiences anywhere in high resolution. Communities can fill historical oversights for research and for empowerment.
A single wearable sensor combined with machine learning estimates step length in older adults and patients with neurological disorders
We applied machine learning tools to estimate step length from features derived from a single, wearable, lower back sensor in older adults and people with altered gait patterns. Our results highlight the advantages of using machine learning for step length estimation and other related tasks.
Smart Clinics in Ophthalmology: Automatic Fundus Fluorescein Angiography Image Interpretation with Large Language Models
FFA-GPT is an automated system for ophthalmic image interpretation that enables both report generation and interactive question answering for fundus fluorescein angiography images.
Effectiveness of DialBetesPlus, a self-management support system for diabetic kidney disease: Randomized controlled trial
We conducted a large RCT of the DialBetesPlus mHealth intervention. In this trial, we applied the intervention to patients in Japan with diabetic kidney disease. DialBetesPlus seeks to change patient behavior by helping them meet the lifestyle guidelines given to them by their physicians.