Health Life

A.I. tool provides more accurate flu forecasts

Credit: Stevens Institute of Technology

Predicting influenza outbreaks just got a little easier, thanks to a new A.I.-powered forecasting tool developed by researchers at Stevens Institute of Technology.

By incorporating location data, the A.I. system is able to outperform other state-of-the-art forecasting methods, delivering up to an 11% increase in accuracy and predicting influenza outbreaks up to 15 weeks in advance.

Past forecasting tools have sought to spot patterns by studying the way infection rates change over time but Yue Ning, who led the work at Stevens, and her team used a graph neural network to encode flu infections as interconnected regional clusters. That allows their algorithm to tease out patterns in the way influenza infections flow from one region to another, and also to use patterns spotted in one region to inform its predictions in other locations.

“Capturing the interplay of space and time lets our mechanism identify hidden patterns and predict influenza outbreaks more accurately than ever before,” said Ning, an associate professor of computer science. “By enabling better resource allocation and public health planning, this tool will have a big impact on how we cope with .”

Ning and her team trained their A.I. tool using real-world state and regional data from the U.S. and Japan, then tested its forecasts against historical flu data. Other models can use past data to forecast flu outbreaks a week or two in advance, but incorporating allows far more robust predictions over a period of several months. Their work is reported in the Oct. 19—23 Proceedings of the 29th ACM International Conference on Information and Knowledge Management.

“Our model is also extremely transparent—where other A.I. forecasts use ‘black box’ algorithms, we’re able to explain why our system has made specific predictions, and how it thinks outbreaks in

Health article

When Unwanted Thoughts Intrude | NIH News in Health

November 2020






Print this issue







Understanding Obsessive-Compulsive Disorder

It’s common to worry about things like germs or to double check that the stove is turned off. But for people with obsessive-compulsive disorder (OCD), these thoughts and behaviors are so severe that they interfere with daily life.

OCD is a mental health condition that causes repeated unwanted thoughts, called obsessions. This can trigger compulsions—the urge to do things over and over to deal with the troubling thoughts. You don’t need to have both to have OCD.

Many people with OCD have a fear of germs or contamination. This can lead to obsessive thoughts about things being “dirty.” Some people may feel a need for things to be symmetrical or in a perfect order. Worries about harm to yourself or others are also common. In some cases, these unwanted thoughts can be violent or disturbing.

“An obsession is an intrusive, distressing thought that usually kids or adults with OCD are able to recognize as a fear that doesn’t make a ton of sense,” explains Dr. Kate Fitzgerald, an OCD expert at the University of Michigan. “But these intrusive thoughts tend to cause them much anxiety.”

People with OCD may develop rituals meant to relieve their anxiety from the thoughts. This could involve behaviors like excessive handwashing or cleaning, arranging things in a certain order, or compulsive counting.

Many of us are a little “obsessive.” So when is there cause for concern? The biggest sign is if these thoughts or habits are making it hard to function in your day-to-day life, explains Fitzgerald.

This can mean problems with family, work, or school. Spending more than one hour a day on thoughts or behaviors can indicate a