AI could improve Alzheimer’s diagnosis, study finds

Artificial intelligence has changed everything from film making on cybersecurityand it may also be poised to make major medical breakthroughs that have puzzled researchers for decades.

The use of AI in medicine has been growing in recent years, especially in the diagnosis of diseases and disorders. There are more and more doctors rely on deep learninga machine learning method modeled on artificial neural networks to learn by example as the human brain does, to help detect potentially life-threatening situations which are easy to forget, such as cancer, heart disease, and so on. asymptomatic cases of COVID-19.

But the next breakthrough for AI in medicine may be in the diagnosis of Alzheimer’s, the devastating disease that causes irreversible cognitive decline and dementia, for which treatment and reliable early detection have eluded researchers. medicine. of the century since the discovery of the disease.

Researchers at Massachusetts General Hospital recently tested deep learning methods in Alzheimer’s detection, and found that not only was deep learning more accurate than comparative AI models that were not trained in analyzing many variables together, it was also able to identify Alzheimer’s cases regardless of the causes. which often complicates early detection, as does a patient’s age. The findings are reported in a study published last week in PLOS ONEa scientific and medical journal.

The researchers trained a deep learning model with thousands of brain scan images collected from more than 10,000 people, with and without Alzheimer’s disease. The study then tested the model against real-world clinical data on Alzheimer’s diagnoses.

The deep learning model was able to identify Alzheimer’s cases with a 90.2% accuracy rate, about five percentage points higher than simpler AI models that don’t rely on deep learning. learning system. The AI ​​model performed better regardless of when and where patients were diagnosed with Alzheimer’s, as well as how old they were at the time.

“This is one of the only studies that uses routinely collected MRIs of the brain to try to detect dementia,” Matthew Leming, a research associate at Massachusetts General Hospital and lead author of the study, said in a statement. “Our results—with cross-site, cross-time, and cross-population generalizability—make a strong case for the clinical use of this diagnostic technology.”

A 90% accuracy rate of Alzheimer’s diagnosis can leapfrog and surpass human clinical diagnosis rates, which, according to a 2017 studystand at 77%.

AI’s big medical splash

While AI-powered search engines developed by OpenAI, Microsoftand Google have grabbed most of the headlines about artificial intelligence recently as they promised interfere with the search and how we workmachine learning may have potentially life-saving medical applications.

More than 7 million people admitted to US emergency rooms each year are misdiagnosed, according to the a study in December through the Department of Health and Human Services. That study found that nearly 3 million ER patients suffered adverse effects from misdiagnosis, while more than 370,000 suffered permanent disability or death.

Misdiagnosis is also an economic burden, because the elimination of incorrect tests and treatments as well as malpractice cases arising from wrong diagnoses can add to the environment. $100 billion per year to save, according to the Society to Improve Diagnosis in Medicine, a nonprofit.

Doctors and doctors say that AI holds important promise in efforts to improve diagnostic methods, although many of the same AI issues found elsewhere, such as the potential for true mistakes and racial prejudices, also appeared in medical research. A Literature review on AI in medical diagnosis published last year found that the technology holds promise in fields including cancer, diabetes, and Alzheimer’s diagnosis, although it recommended more research to improve AI’s accuracy in identifying medical issues.

A major role in Alzheimer’s research

But if future research makes AI and deep learning more widely used in diagnosis, it could be a game changer for Alzheimer’s, which is one of the most difficult diseases to predict and treat. diagnosed.

Alzheimer’s is the most common type of dementia among the elderly, afflicting about 44 million worldwide. But it is only one form of a large family of dementia-related conditions, which can easily be mistaken for Alzheimer’s.

A 2017 study of more than 900 people found that up to one in four Alzheimer’s patients were misdiagnosed, with a roughly split between false positives and false negatives. Alzheimer’s tendency for misdiagnosis depends on the number of its symptoms overlaps with other common neurological disorders, including Lewy body or frontotemporal dementia. The chances of misdiagnosis increasing ageaccording to the American Academy of Neurology, which states that Alzheimer’s disease and other dementing diseases “can be easily misdiagnosed in the elderly.”

Predicting a patient with Alzheimer’s is not easier than diagnosing it, since more than 90% of Alzheimer’s cases are considered “rarely”—which is seen in patients with no family history of the disease. Because of these difficulties, there are almost nothing reliable early screening models for Alzheimer’s, with most cases diagnosed after symptoms of brain damage appear.

The Massachusetts General Hospital study did not address whether deep learning could help predict Alzheimer’s, but other studies seem to suggest that AI may have an important role to play there as well.

An AI model developed at the University of Florida has been able to tap into electronic health records to predict which patients are at high risk of developing Alzheimer’s. up to five years before diagnosis, the university announced last week. While the researchers recommend more testing before doctors start using AI prediction tools, they know that AI models can help with early diagnosis and reduce the severity of disease in the long run. term.

Learn how to navigate and build trust in your business with The Trust Factor, a weekly newsletter that examines what leaders need to succeed. Sign up here.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *