The future is already here – it’s just not evenly distributed.

—William Gibson, quoted in The Economist, December 4, 2003

In America, we love personalization: personal computers, personal trainers, and more recently, personalized medicine. Because we especially prize individuality, the ground is fertile for developing services that cater to individualized preferences and needs. Personalized education is no exception; we have a growing drive to individualize and maximize how each student learns. Because the parallels between personalized medicine and personalized education are enlightening, let’s start with personalized medicine.

First of all, what is personalized medicine? Imagine for a moment that instead of taking medicine designed for the general population, you took therapy specifically catering to your genetic profile. Your doctor looked at your DNA, measured certain protein levels, and your doctor divined what drugs would work best for you. So far, measuring proteins in the body, such as erbB2 and EGFR, have successfully provided the basis for personalized cancer treatments that had better outcomes than treatments designed for a more general population of cancer patients. More than just for cancer, however, personalized medicine promises to use individuals’ genetic and other biological information to provide medical care with fewer side effects and higher rates of success. Thus, genetic and other biological information leads to the medical intervention in personalized medicine.

In its popular form, personalized education does not take a biological perspective. Instead, success stories in personalized education typically consist of software programs that are designed to provide the best amount, type, and rate of information for individual students’ cognitive, emotional, and social styles of learning. In order to do this, personalized educational systems typically draw from the insights of computer science, education, and behavioral-level psychology. Even one of the leaders in the field that has roots in cognitive science, Carnegie Learning, does not employ neuroscience. Neuroscience covers phenomena at a cellular or molecular level as opposed to cognitive science, which does not limit itself to models based in biology. Researchers at Carnegie Mellon University developed Carnegie Learning’s software program using a computer algorithm that adapts to the learner and responsively provides content based on the learner’s needs. Their software already enables over half a million students across the United States to learn mathematics more effectively. But what if they could take things a step farther?

Imagine using general neuroscience, not just cognitive science, to aid education. Just as an improved knowledge of DNA and proteins promises to revolutionize medicine, academia and industry alike predict that brain science will revolutionize education in the near future. With the frustration with current educational methods building, much of the necessary societal infrastructures of interest and funding are slowly lining up. What would this revolution ultimately look like? Whereas in personalized medicine, a doctor would measure your protein levels and look at your DNA in order to prescribe you the optimal treatment, in personalized education, a teacher would assess your neural profile in order to prescribe you the optimal curriculum. Now, this sounds good in theory, but how far away is the science in practice?

Progress So Far: Gathering Neural Data

In the analogy of personalized medicine as it relates to personalized education, what is personalized education’s equivalent of DNA and proteins? The answer may lie in a field at the intersection of neuroscience and computer science called neuroinformatics.

The neuroinformatics community was represented at the Society for Neuroscience conference in Washington, DC earlier this fall (which was attended by an astounding 31,000 people). Over the past few decades, technological advances in neuroimaging and increased data collection have resulted in so much data (especially from neuroimaging tools like fMRI) that some have claimed that neuroscience is a field that is data rich but theory poor.

Neuroinformatics tackles the mass of data by applying the tools of computer science to collecting, analyzing, and modeling the data. What kind of data does this encompass? Generally, it runs the gamut from molecular all the way up to behavioral levels. It maps and aims to visualize what regions of the brain connect, what differences exist between healthy and diseased brains, and (perhaps most relevantly) how the human brain functions under different circumstances (e.g., participants performing different tasks in fMRI machines).

A science coordinator from the Human Connectome project, Dr. Jennifer Elam, explained that with the help of a generous grant from the National Institute of Health, the project is taking the scans of 1200 healthy people’s brains and mapping their complete functional and structural connectivity. This could provide the basis for incredible insight into normal brain functioning. Ultimately, the project aims to determine how the parts of a human brain are interconnected and how their activities are interrelated under a variety of different experimental conditions.

Although not explicitly designed with applications for education in mind, this kind of information may ultimately provide the basis for the neuro-cognitive profiles needed to design biologically-based personalized education. If we know a student’s neuro-cognitive profile, we may be able to provide biologically-based interventions. Just as personalized medicine strives to prevent the negative side-effects of one-size-fits-all treatment, a neuroscience-based personalized education could prevent the negative effects of a one-size-fits-all education.

What kind of interventions might come out of such a paradigm shift? Already, the development of so-called smart drugs aim to improve professionals’ and students’ ability to stay alert and work longer, brain-machine interfaces have hooked into patients’ brains enabling locked-in patients to communicate with the outside world. Optogenetics has enabled neuroscientists to turn on and off neurons in mouse brains involved in motivation and learning—although it will be awhile before this is applied to humans. Algorithms exist that enable neuroscientists to read, with surprising accuracy, the stimuli patients lying in an fMRI scanner may be looking at. Neurofeedback, a brain-based form of biofeedback, has been used to treat ADHD.

These advancements represent windows into how neuroscience-based personalized learning may be implemented in the future. Perhaps smart drugs will be added to the stack of multi-vitamins children eat with their breakfast cereal. Perhaps executive education courses will provide some future version of the iPhone’s Siri in brain-machine interface form; all users would have to do is think “email the client” and it would be done. Perhaps optogenetics will enable students to learn concepts more quickly by activating the right neurons to fire at the right time in order to execute a task optimally. Perhaps fMRI “mind-reading” will enable educational technologists to design personalized, just-in-time curriculum. Perhaps neurofeedback will be integrated with adaptive learning systems in order to create extremely personalized curricula. Many questions remain about who should use these tools and have access to these tools. Should they only be used to help eliminate disorders or should they also be used to move baseline functioning from normal to superior? Ultimately, if personalized education is to follow a similar path as personalized medicine, much neuroinformatics research remains to be done. To a society in love with personalizing the world to fit our individual needs, what could be more useful than to study the very seat of our individuality: the brain. And in so doing, we may very well facilitate the act of study itself.

I am grateful to the following people and organizations: many thanks to Jorge Conde at Knome, Inc and Atul Singh of Fair Observer for making my attendance at the Society for Neuroscience conference possible, a big thanks to Jennifer Elam from the Human Connectome Project for thoughtfully answering my questions, and a major thanks to Leif Gibb, Ogi Ogas, Alex Rivest, Jehan deFonseka, my dad, George Ricker, and Barbara Lam, for all their thoughtful feedback, constructive criticism, and creative brainstorming throughout the writing process.

The views expressed in this article are the author’s own and do not necessarily reflect Fair Observer’s editorial policy.