Artificial Intelligence key to Universal Health Coverage
International Universal Health Coverage Day highlights need for medical innovation, says Triage Technologies Inc.
TORONTO, Dec. 12, 2018 (GLOBE NEWSWIRE) — Capping off a successful year, Triage Technologies Inc. (“Triage”) is proud to announce that its abstract, Improving Skin Condition Classification with a Question Answering Model, has been accepted by the ‘Medical Imaging meets NeurIPS’ workshop. The workshop, now in its second year, brings together professionals from around the world from the medical imaging computing and machine learning fields.
Artificial intelligence (AI) is currently at the forefront of healthcare innovation and Triage’s AI-enabled software achieved a scientific breakthrough in using AI to screen for skin disease with superhuman performance. In 2017, Triage was shown to outperform a panel of general practitioners and dermatologists in detecting high risk skin lesions. Currently Triage is capable of screening for hundreds of diseases with a smartphone camera, including skin cancer and other skin conditions.
The abstract, which was presented to the workshop this past Saturday in Montréal, Québec, demonstrates that by combining a question-answer (QA) model with a convolutional neural network (CNN) increases the accuracy up to 10% compared to the CNN alone, and more than 30% compared to the QA model alone.
“The conventional approach is to analyze the skin condition only based on a skin image. This can be done by a convolutional neural network,” said Amir-massoud Farahmand, faculty member at the Vector Institute for Artificial Intelligence in Toronto and co-author of the abstract. “This works to some extent, but the performance is not ideal.” Mohamed Akrout, co-author and Triage researcher from the University of Toronto, continued, “These results demonstrate that the proposed combination of the CNN and QA models can significantly improve the classification performance across a multiclass classification task.”
The acceptance of the abstract coincides with the World Health Organization’s International Universal Health Coverage Day on December 12, 2018.
“We firmly believe AI will play a pivotal role in the future of medicine,” said Tory Jarmain, co-author of the abstract and CEO and co-founder of Triage. “Not only can our platform improve medical outcomes by providing access to disease screening, but it also is a step in the direction of enabling low-cost universal health coverage around the world.”
To learn more about Triage or to schedule an interview, please contact:
Triage Technologies Inc. is a Toronto-based digital health company. Triage achieved a scientific breakthrough in using AI to achieve superhuman performance in detecting skin disease, including skin cancer and hundreds of other skin conditions, with the snap of a photo. Triage’s AI is available for free and is the first capable of screening for 1,000 diseases. Triage is partnered with, and advised by, leading medical experts including Dr. Amanda Oakley, founder of DermNet New Zealand, the world’s most popular dermatology website. For additional information please visit triage.com or download our press kit (https://www.triage.com/press-kit).
‘Medical Imaging meets NeurIPS’ is a new satellite workshop established in 2017. The workshop aims to bring researchers together from the medical image computing and machine learning communities. The objective is to discuss the major challenges in the field and opportunities for joining forces. This year the workshop will feature an oral and poster session where accepted works are presented. In addition, there will be a series of high-profile invited speakers from industry, academia, engineering and medical sciences giving an overview of recent advances, challenges, latest technology and efforts for sharing clinical data.