COLUMBIA, MARYLAND - Fundamental research marches forward every day in every field. Applications of the results from such pure research requires additional time and effort - to implement, validate, deploy, and monitor its use in the real world. Clinical trials acquire a whole new dimension when testing artificial intelligence (AI) algorithms versus testing drug treatments on cohorts of test subjects. In many cases, the results of basic research coming out today are the precursors to the great advances in medical, clinical, and healthcare applications of AI that will emerge in coming years.
Predicting Emerging Infectious Diseases
Most infectious diseases afflicting humans originate in other animals. These ‘zoonotic jumping viruses’ are the subject of new predictive modeling research using AI and machine learning (ML). The likelihood of a virus jumping species can now be estimated using inferences from its genome sequence with the aid of AI that can sift through millions of potential zoonotic candidates to find the ‘one in a million’ likely to do so. The key to this advancement is: millions of high-risk viruses exist, but the genomic sequencing throughput of labs cannot keep up. AI and ML algorithms are trained on closely-related viruses whose more complete genomic sequences include characteristics of the limited genomic sequence information for individual candidates in the massive sample of potential zoonotic viruses. With that accelerated ‘triage’ of candidate viruses, highlighted by AI, laboratory sequencing can be initiated on the most worrisome cases.
AI models are now only taking preliminary steps in this area of predictive research. Nevertheless, these early findings are promisingly good, pointing favorably to AI’s potential to provide early alerts of emerging infectious diseases.
The content herein is subject to copyright by The Yuan. All rights reserved. The content of the services is owned or licensed to The Yuan. The copying or storing of any content for anything other than personal use is expressly prohibited without prior written permission from The Yuan, or the copyright holder identified in the copyright notice contained in the content.