New AI method can support real-time management of infectious diseases
For the past 25 years, one discipline has been revolutionizing epidemiology: phylodynamics. By using genetic sequences, scientists can study how pathogens evolve. Thanks to mathematics, these data can be coherently organized into phylogenetic trees, with each branch representing a chain of transmission and each leaf representing an individual infection.
The article discusses a new artificial intelligence method that can support real-time management of infectious diseases. Phylodynamics, a discipline that has been revolutionizing epidemiology over the past 25 years, uses genetic sequences to study how pathogens evolve. By organizing these data into phylogenetic trees, scientists can trace the transmission chains and relationships between pathogens.
Parameters such as the rate of pathogen spread, infection duration, and geographic origin can be estimated using these trees. However, conventional epidemiological models are limited by data complexity and volume. Scientists at INRAE have developed a deep learning artificial intelligence method called neural posterior estimation (NPE) to address these limitations.
Using a dataset of 72 genomes from the 2014 Ebola outbreak in Sierra Leone, the team demonstrated that NPE produces robust estimates similar to traditional inference methods. This marks the first use of NPE in a phylodynamic application. The rapid calibration of models and the ability to incorporate large volumes of diverse data make NPE a promising tool for real-time epidemic and epizootic management. Detailed online tutorials are available to enable others to replicate this type of analysis.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
