Jul 29 2020
According to a new study by researchers at the University of Sheffield artificial intelligence (AI) could enable faster diagnosis of Alzheimer’s disease and improve patient prognosis.
Image Credit: University of Sheffield.
Performed at the University of Sheffield’s Neuroscience Institute, the new research investigates how the regular use of AI in healthcare could help mitigate the economic impact and time involved in the treatment of common neurodegenerative diseases such as Alzheimer’s and Parkinson’s, for the NHS.
For several neurological disorders, age is the main risk factor. Worldwide, populations have been living longer than ever before, therefore, the number of people suffering from a neurodegenerative disease is predicted to increase like never before.
It is estimated that the number of people living with Alzheimer’s alone will increase to 115 million by 2050, which poses a real challenge for the health system.
Reported in the Nature Reviews Neurology journal, the new study describes how AI technologies such as machine learning algorithms, can identify neurodegenerative disorders—which make a portion of the brain to die—before worsening of the progressive symptoms. This can increase the chances of benefits for patients from successful disease-modifying treatment.
Most neurodegenerative diseases still do not have a cure and in many cases are diagnosed late due to their molecular complexity. Widespread implementation of AI technologies can help, for example, predict which patients showing mild cognitive impairment will go on to develop Alzheimer’s disease, or how severely their motor skills will decline over time.
Dr Laura Ferraiuolo, Study Lead Author, University of Sheffield
“AI-powered technologies can also be used to help patients communicate their symptoms remotely and in the privacy of their own homes, which will be an enormous benefit to patients with mobility issues,” added Dr Laura Ferraiuolo.
It is feasible to train machine learning algorithms to identify changes brought about by diseases in patient movement information, medical images, speech recordings, or footage displaying patient behavior, all of which make the AI a valuable diagnostic aid.
For instance, trained professionals in radiology departments can use it to analyze images more quickly and underscore crucial results for an instant follow-up.
Moreover, algorithms can listen to patients’ speech and analyze their vocabulary and other semantic features to evaluate their cognitive function. Information included in genetic profiles or electronic health records can also be used by machine learning to recommend the ideal treatments for individual patients.
The study is the outcome of a long-term close partnership between BenevolentAI, a biotech company, and a research team from the University of Sheffield’s Neuroscience Institute, Monika Myszczynska, Dr Richard Mead, and Dr Guillaume Hautbergue.
Using AI in clinical settings can lead to savings in the NHS by reducing the necessity of patients affected by debilitating diseases, like MND, to travel to clinic—which is very relevant during the current pandemic—and the time patients and physicians spend in clinic.
Monika Myszczynska, Study First Author, University of Sheffield
“It is too early to talk about outcomes in terms of treatments but, in this study, we examined how machine learning methods can be used to identify the best course of treatment for patients based on their disease progression or how it could be used to identify new therapeutic targets and drugs,” added Myszczynska.
Further research will now focus on the improvement of current diagnostic technologies, as well as a generation of new algorithms to make the use of AI in prognosis prediction and drug discovery a reality. AI feeds on data, therefore generation of international consortia and collaborations are the key to these future endeavours.
Monika Myszczynska, Study First Author, University of Sheffield
The study is part of the research by the University of Sheffield’s Neuroscience Institute, the goal of which is to bring scientists and academics from different specialties together to convert scientific discoveries conducted in the lab into pioneering treatments that will be advantageous to patients living with neurodegenerative disorders.
Journal Reference:
Myszczynska, M. A., et al. (2020) Applications of machine learning to diagnosis and treatment of neurodegenerative diseases. Nature Reviews Neurology. doi.org/10.1038/s41582-020-0377-8.
Source: https://www.sheffield.ac.uk/