Psychology

99% accuracy diagnosing ADHD through machine learning

Machine learning could replace complicated testing used to identify ADHD.

 

Researchers designed a novel method for diagnosing attention deficit hyperactivity disorder (ADHD) with 99% accuracy using brain scans. 

 

ADHD symptoms such as restlessness, an inability to focus, and/or anxiety can vary widely between persons and even change day to day in an individual. These shifting symptoms make physicians only able to reach a diagnosis through rigorous behavioral testing.

 

Chris McNorgan’s team at the University at Buffalo sidestepped this issue by utilizing machine learning techniques. They had a computer analyze the brain scans of patients with ADHD. After collecting data on what ADHD looks like in the brain, the computer was then able to detect the presence of ADHD with almost perfect accuracy.

 

Researchers believe this development could allow ADHD to be diagnosed more efficiently, leading to improved treatment.

McNorgan, C., Judson, C., Handzlik, D., & Holden, J. G. (2020). Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections. Frontiers in Physiology, 11, 583005. https://doi.org/10.3389/fphys.2020.583005

 

Ecology

Native Americans show researchers how to fight wildfires with fire

Ancient Native American farming practices could help prevent wildfires in today’s communities.

 

The Jemez peoples’ history of success at living in the wildfire prone areas of New Mexico informed researchers’ possible design improvements for fire proofing modern communities.

 

Wildfires plague the United States, especially in the west where 50,000 structures have been demolished in just California since 2018.

 

An interdisciplinary team of archaeologists, paleoecologists, and ecologicalists led by Christopher Roos of Southern Methodist University researched the history of the Jemez model and shed light on its effectiveness. By keeping the immediate area around the village free of trees and setting small preemptive fires, the Jemez people cleared areas likely to cause wildfires, leaving fertile farmland behind.

 

If adopted today, especially with tribal collaboration, researchers believe these practices could provide a sustainable way to coexist with wildfires.

 

Roos, C. I., Swetnam, T. W., Ferguson, T. J., Liebmann, M. J., Loehman, R. A., Welch, J. R., Margolis, E. Q., Guiterman, C. H., Hockaday, W. C., Aiuvalasit, M. J., Battillo, J., Farella, J., & Kiahtipes, C. A. (2021). Native American fire management at an ancient wildland-urban interface in the Southwest United States. Proceedings of the National Academy of Sciences of the United States of America, 118(4). https://doi.org/10.1073/pnas.2018733118