ATHENS - Imagine if one were suffering from paralysis and could control a motorized wheelchair or prosthetic limb through thought alone. This scenario is now becoming reality thanks to the development of brain-computer interfaces (BCIs).

BCIs, sometimes also called brain-machine interfaces, are direct communication pathways between the brain’s electrical activity and external devices, most commonly computers or robotic limbs. BCIs can be classified into three main groups: non-invasive, semi-invasive and invasive. Invasive BCIs are implanted directly into the gray matter of the brain during neurosurgery to capture data (brain signals). Partially invasive BCI devices are implanted inside the skull but rest outside the brain rather than within the gray matter. Non-invasive BCIs detect brain signals through electrodes placed on the scalp. These are considered the safest and cheapest types of devices, but they can only capture ‘weaker’ human brain signals due to the obstruction caused by the skull.

There are several ways of developing a noninvasive BCI, including electroencephalography (EEG), magnetoencephalography (MEG), and magnetic resonance tomography (MRT). An EEG-based brain-computer interface is the most preferred type of BCI for study. EEG signals are processed and decoded in control signals, which a computer or robotic device can readily perceive.¹

Artificial intelligence (AI), which can advance the analysis and decoding of neural activity, has turbocharged the field of BCIs. When AI works within BCIs, internal parameters are constantly provided to algorithms in the form of pulse durations and amplitudes, stimulation frequencies, energy consumption by the device, stimulation or recording densities, and electrical properties of the neural tissues.² After receiving this information, AI algorithms can then cut through the data noise and produce in real time the desired functional outcomes.