James Zou team: New paper recently published in the Harvard Data Science Review discussing how data science can benefit from large language models (LLMs) hdsr.mitpress.mit.edu/pub/pqiufdew/r. Congratulations to James and team!
DBDS’ Nigam Shah: Healthcare Leaders and UK Government Discuss Safe Deployment of AI
Healthcare leaders are currently engaged in vigorous discussions about the potential risks and responsibilities that come with the deployment of artificial intelligence (AI) in the sector. While some segments of the public fear dystopian scenarios akin to those seen in science fiction narratives, with robots taking control, healthcare professionals deem these anxieties exaggerated. Nonetheless, they stress the necessity for safe and responsible implementation of AI technologies.
DBDS’ Lu Tian will deliver the inaugural keynote Lai Lecture on 3/8 in the 7th International Symposium on Statistical Innovation for Medical Product Development honoring late Tze L. Lai for his contributions in innovative clinical trial design. isbiostat.org.
Daniel L. Rubin in Journal of Clinical Medicine: Segmentation-Assisted Fully Convolutional Neural Network Enhances Deep Learning Performance to Identify Proliferative Diabetic Retinopathy
Abstract
With the progression of diabetic retinopathy (DR) from the non-proliferative (NPDR) to proliferative (PDR) stage, the possibility of vision impairment increases significantly. Therefore, it is clinically important to detect the progression to PDR stage for proper intervention. We propose a segmentation-assisted DR classification methodology, that builds on (and improves) current methods by using a fully convolutional network (FCN) to segment retinal neovascularizations (NV) in retinal images prior to image classification.
Read more here: https://www.mdpi.com/2077-0383/12/1/385