July 9, 2013

Data Mining for Human Cognition

Alex Woodie

Lumosity hopes to advance the study of human cognition with a new project that will leverage big data collected from its popular website. Launched earlier this month, the Human Cognition Project will mine data collected from 40 million Lumosity users over the past six years, with the goal of conducting scientific studies on brain development and learning theory that would be difficult to undertake in the lab.

Since launching in 2007, Lumosity has attracted plenty of attention on the Web with its quirky ads that tout the capability of its online games to make your brain stronger. There may be some debate whether the games actually make you smarter. But with a study recently published in the journal, Frontiers in Neuroscience, there’s little doubt that the San Francisco, California company is serious about advancing the understanding of human cognition.

“New technologies and research platforms have the potential to transform the speed, scale, efficiency, and range of topics in which neuroscience research is conducted,” said P. Murali Doraiswamy, Professor of Psychiatry at DukeUniversityMedicalCenter and co-author of the study. “This study is interesting because it brings to light the possibilities of what we can uncover by taking a big data approach to cognitive performance research.”

The study gave a small teaser of the type of research the company hopes to accomplish with its massive dataset. In the first study, the researchers attempt to measure performance on quizzes against how much sleep the quiz-takers got the night before, and how much alcohol they consumed. Cognitive performance across three areas–speed, memory, and flexibility–topped out with seven hours of sleep, and with one or two drinks. Brain performance decreased with each additional drink, the study says.

In the second study published in Frontiers in Neuroscience, the researchers sought to answer how age affects one’s learning ability. The study matched a Lumosity user’s age against results from tests that measure for two types of intelligence, including “fluid intelligence,” which is roughly equal to problem solving ability, and “crystallized intelligence,” which draws on one’s accumulated knowledge and skills.

The result is good news for the aged across the world. “Although raw cognitive performance peaks in young adulthood, the lifelong accumulation of knowledge compensates such that older adults can still perform at a high level,” the company says.

What makes the Human Cognition Project so potentially promising is the massive scale of the project. In the first study, the researchers were working with data culled from between 127,000 to 162,000 Lumosity users. Granted, much of the data is self-reported, and there is no way to do controlled experiments. But the scale of the undertaking opens up new possibilities in terms of the types of questions that can be studied, the number and demographics of participants, and the speed at which research can be carried out, Lumosity says.

“The goal of the Human Cognition Project is to rapidly and efficiently advance our understanding of the brain,” said Daniel Sternberg, Ph.D, a Data Scientist at Lumosity and lead author of the study. “We’re excited for the potential that big data holds for conducting large-scale, collaborative, global research on human cognition.”

Related Items:

Interplay between Research, Big Data & HPC

Rethinking Loyalty Programs with a Big Data Brain

Saving Lives of Premature Babies with Real-Time Analytics