UK study reveals that Artificial Intelligence can help healthcare providers diagnose Alzheimer’s earlier and improve patient prognosis.
Due to people living longer than ever before, the number of people diagnosed with a neurodegenerative disease like Alzheimer’s or Parkinson’s is expected to rise to 115 million by 2050. This will pose a challenge for the healthcare system as they struggle to treat and support these patients. Scientists at the University of Sheffield’s Neuroscience Institute have been studying how the use of artificial intelligence and machine learning in health care can help reduce the time and cost of these diseases, which cause memory loss and cognitive decline, place on hospitals and other medical facilities.
“It is too early to talk about the 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,” said Monika Myszczynska, a scientist from the University of Sheffield.
The study was published in the journal Nature Reviews Neurology and focused on how AI technologies like machine learning could be used to detect neurodegenerative disorders before symptoms worsen. The earlier the disease is detected the better the chances of patients benefitting from treatment that slows down the progression and reduces the severity of symptoms. AI technologies can also be used to allow patients to communicate their symptoms to their healthcare providers from the comfort and privacy of their own homes, a big benefit for those with mobility or speech issues.
Machine learning algorithms can detect changes in medical images, speech recordings, patient movement data, and footage giving examples of the patients’ behavior that can be attributed to the disease, allow doctors to make earlier diagnoses. The algorithms can also listen to patients’ speech and assess their cognitive function by analyzing vocabulary and other semantic data, and access data in electronic health records or genetic profiles to determine the best treatment options for each patient.
“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,” said lead author of the study, Dr. Laura Ferraiuolo from the University of Sheffield.