{"id":5016,"date":"2023-02-24T08:56:24","date_gmt":"2023-02-24T06:56:24","guid":{"rendered":"https:\/\/dev.umfst.ro\/?p=5016"},"modified":"2024-08-13T15:47:13","modified_gmt":"2024-08-13T12:47:13","slug":"machine-learning-gives-nuanced-view-of-alzheimers-stages","status":"publish","type":"post","link":"https:\/\/umfst.ro\/fr\/blog\/machine-learning-gives-nuanced-view-of-alzheimers-stages\/","title":{"rendered":"Machine Learning Gives Nuanced View of Alzheimer\u2019s Stages"},"content":{"rendered":"

A Cornell-led collaboration used machine learning to pinpoint the most accurate means, and timelines, for anticipating the advancement of Alzheimer\u2019s disease in people who are either cognitively normal or experiencing mild cognitive impairment.<\/p>\n\n\n\n

The modeling showed that predicting the future decline into dementia for individuals with mild cognitive impairment is easier and more accurate than it is for cognitively normal, or asymptomatic, individuals. At the same time, the researchers found that the predictions for cognitively normal subjects is less accurate for longer time horizons, but for individuals with mild cognitive impairment, the opposite is true.<\/p>\n\n\n\n

\"\"
Lorem ipsum<\/figcaption><\/figure>\n\n\n\n

The modeling also demonstrated that magnetic resonance imaging (MRI) is a useful prognostic tool for people in both stages, whereas tools that track molecular biomarkers, such as positron emission tomography (PET) scans, are more useful for people experiencing mild cognitive impairment.<\/p>\n\n\n\n

The team\u2019s paper, \u201cMachine Learning Based Multi-Modal Prediction of Future Decline Toward Alzheimer\u2019s Disease: An Empirical Study<\/a>,\u201d published Nov. 16 in PLOS ONE. The lead author is Batuhan Karaman, a doctoral student in the field of electrical and computer engineering.<\/p>\n\n\n\n

\n

<\/p>\n<\/blockquote>\n\n\n\n

Alzheimer\u2019s disease can take years, sometimes decades, to progress before a person exhibits symptoms. Once diagnosed, some individuals decline rapidly but others can live with mild symptoms for years, which makes forecasting the rate of the disease\u2019s advancement a challenge.<\/p>\n\n\n\n

<\/div>\n\n\n\n

This is how a subtitle fits in the page<\/h2>\n\n\n\n

\u201cWhen we can confidently say someone has dementia, it is too late. A lot of damage has already happened to the brain, and it\u2019s irreversible damage,\u201d said senior author Mert Sabuncu<\/a>, associate professor of electrical and computer engineering in the College of Engineering and Cornell Tech, and of electrical engineering in radiology at Weill Cornell Medicine.<\/p>\n\n\n\n

\n
\"Lorem
Lorem ipsum Lorem ipsum<\/figcaption><\/figure>\n\n\n\n
\"\"
Lorem ipsum Lorem ipsum<\/figcaption><\/figure>\n\n\n\n
\"\"
Lorem ipsum Lorem ipsum<\/figcaption><\/figure>\n\n\n\n
\"\"
Lorem ipsum Lorem ipsum<\/figcaption><\/figure>\n
Lorem ipsum<\/figcaption><\/figure>\n\n\n\n

\u201cWe really need to be able to catch Alzheimer\u2019s disease early on,\u201d Sabuncu said, \u201cand be able to tell who\u2019s going to progress fast and who\u2019s going to progress slower, so that we can stratify the different risk groups and be able to deploy whatever treatment options we have.\u201d<\/p>\n\n\n\n

Clinicians often focus on a single \u201ctime horizon\u201d \u2013 usually three or five years \u2013 to predict Alzheimer\u2019s progression in a patient. The timeframe can seem arbitrary, according to Sabuncu, whose lab specializes in analysis of biomedical data \u2013 particularly imaging data, with an emphasis on neuroscience and neurology.<\/p>\n\n\n\n

Sabuncu and Karaman partnered with longtime collaborator and co-author Elizabeth Mormino of Stanford University to use neural-network machine learning that could analyze five years\u2019 worth of data about individuals who were either cognitively normal or had mild cognitive impairment. The data, captured in a study by the Alzheimer\u2019s Disease Neuroimaging Initiative, encompassed everything from an individual\u2019s genetic history to PET and MRI scans.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Another subtitle to split the page<\/h2>\n\n\n\n

\u201cWhat we were really interested in is, can we look at these data and tell whether a person will progress in upcoming years ?\u201d Sabuncu said. \u201cAnd importantly, can we do a better job in forecasting when we combine all the follow-up datapoints we have on individual subjects?\u201d<\/p>\n\n\n\n

The researchers discovered several notable patterns. For example, predicting a person will move from being asymptomatic to exhibiting mild symptoms is much easier for a time horizon of one year, compared to five years. However, predicting if someone will decline from mild cognitive impairment into Alzheimer\u2019s dementia is most accurate on a longer timeline, with the \u201csweet spot\u201d being about four years.<\/p>\n\n\n\n

\u201cThis could tell us something about the underlying disease mechanism, and how temporally it is evolving, but that\u2019s something we haven\u2019t probed yet,\u201d Sabuncu said.<\/p>\n\n\n\n

Regarding the effectiveness of different types of data, the modeling showed that MRI scans are most informative for asymptomatic cases and are particularly helpful for predicting if someone\u2019s going to develop symptoms over the next three years, but less helpful for forecasting for people with mild cognitive impairment. Once a patient has developed mild cognitive impairment, PET scans, which measure certain molecular markers such as the proteins amyloid and tau, appear to be more effective.<\/p>\n\n\n\n

\n