Year: 2020
Type: conference-paper
Abstract: Artificial intelligence (AI) has the potential to transform medical research and eventually the practice of healthcare.The recent coalescence of vast amounts of data, accelerated computing, deep learning, and other machine learning techniques has yielded remarkable results across research discovery and translational medicine.AI has emerged as a promising tool to improve patient outcomes and reduce the cost by providing insights from data across medical domains, from condition detection, diagnosis, and treatment response prediction.However, there remain challenges to overcome.The development of AI methods requires huge amounts of high-quality curated data.In fact, the volume of high-quality data used in model training can be directly correlated to model quality.The first major challenge to the fundamental use of AI in medicine is the lack of standard and accessible data readily for computational use.This challenge is comprised of not only storage needs, but also efforts in data transmission, metadata curation, and distributed processing, all adhering to privacy and policy preserving requirements.
Source: TigerPrints (Clemson University)
Author: V. K. Cody Bumgardner
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W3047776323