The potential for AI to diagnose and even predict the onset of serious medical conditions is being demonstrated in pioneering research.
More reliable predictions
Starting with Alzheimer’s disease, the most common cause of dementia, a new algorithm is able to predict its onset with 84 percent accuracy. The author of the research, Sulantha Sanjeewa, a computer scientist at McGill University in Canada, believes it could help to slow or one day even stop the onset of debilitating symptoms which can include memory loss and difficulties with thinking, problem-solving or language.
“If you can tell from a group of individuals who is the one that will develop the disease, one can better test new medications that could be capable of preventing the disease,” said co-lead study author Dr. Pedro Rosa-Neto, an associate professor of neurology, neurosurgery, and psychiatry, also at McGill University.
Patients who are deemed at risk of developing Alzheimer’s could be prioritised for new trials of treatments which aim to slow its progress. Clinical trials run between 18 and 24 months but if those selected for treatment never go on to develop Alzheimer’s than it’s difficult to determine whether it was effective.
While still in its early stages, the findings suggest the AI’s ability to analyse brain scans offer more reliable predictions than humans alone. It was trained by being shown PET scans of nearly 200 patients up to 24 months before they developed the disease. This was compared with their scans after which showed the buildup of amyloid in areas of their brain – a protein often present in patients with cognitive impairment.
The study’s findings were published online in July in the journal Neurobiology of Aging.
Able to predict the severity of symptoms
Schizophrenia affects just 1.2 percent of the American population (around 3.2 million people) but it has severe effects. The inability to distinguish what is real, something often characterised by the condition, can pose a danger both to the individual and others.
Groundbreaking research conducted by IBM and the University of Alberta could soon help doctors diagnose the onset of the disease. It can even determine the severity of symptoms using a simple MRI scan and a neural network built to look at blood flow within the brain.
“This unique, innovative multidisciplinary approach opens new insights and advances our understanding of the neurobiology of schizophrenia, which may help to improve the treatment and management of the disease,” says Dr. Serdar Dursun, a Professor of Psychiatry & Neuroscience at the University of Alberta.
The neural network behind the AI was trained on a dataset of 95 fMRI images from the Function Biomedical Informatics Research Network. Both scans of patients with schizophrenia and those of a healthy control group were included. From this data, it was possible for the neural network to build a predictive model able to correctly determine those with schizophrenia with 74 percent accuracy.
“We’ve discovered a number of significant abnormal connections in the brain that can be explored in future studies,” Dursun continued, “and AI-created models bring us one step closer to finding objective neuroimaging-based patterns that are diagnostic and prognostic markers of schizophrenia.”
Furthermore, the model was able to predict the severity of symptoms once they set in. With this information, treatment options can be planned ahead of time as well as getting conscious authorisation from the individual to restrain them if needed to protect themselves and others.
Both pieces of research provide an exciting look at how AI can be used to predict and diagnose medical conditions, and hopefully provide more effective treatment.
What are your thoughts on the use of AI to diagnose and predict medical conditions? Let us know in the comments.
Interested in hearing industry leaders discuss subjects like this and sharing their use-cases? Attend the co-located AI & Big Data Expo events with upcoming shows in Silicon Valley, London and Amsterdam to learn more. Co-located with the IoT Tech Expo, Blockchain Expo and Cyber Security & Cloud Expo so you can explore the future of enterprise technology in one place.