Positive Technology Journal

"Raymond Deicken at the University of California at San Francisco and colleagues have been studying the amino acid Nacetylaspartate (NAA). They found that levels of NAA in the thalamus region of the brain are lower in people with schizophrenia than in those without.

To find out whether software could diagnose the condition from NAA levels, the team used a technique based on magnetic resonance imaging to measure NAA levels at a number of points within the thalamus of 18 people, half of whom had been diagnosed with schizophrenia. Antony Browne of the University of Surrey, UK, then analysed these measurements using an artificial neural network, a program that processes information by learning to recognise patterns in large amounts of data in a similar way to neurons in the brain.

Browne trained his network on the measurements of 17 of the volunteers to teach it which of the data sets corresponded to schizophrenia and which did not. He then asked the program to diagnose the status of the remaining volunteer, based on their NAA measurements. He ran the experiment 18 times, each time withholding a different person's measurements. The program diagnosed the patients with 100 per cent accuracy."