Listen Up

Friday, July 5, 2024

Alzheimer's: AI tool may help predict risk with almost 80% accuracy




Continuing our series of diagnosing and treatment of Alzheimer's disease, the Health Train Express research team discovered this new knowledge base for A.D.

Alzheimer's disease (AD) is the most common cause of dementia and has a long prodromal phase, during which subtle cognitive changes occur. Mild cognitive impairment (MCI) is a stage between normal cognition and AD. Individuals with MCI are at higher risk of developing AD with a 3% to 15% conversion rate of MCI to AD every year.12 Therefore, accurately predicting the progression of MCI to AD can assist physicians in making decisions regarding patient treatment, participation in cognitive rehabilitation programs, and selection for clinical trials involving new drugs.3

Dementia directly affects more than 55 million peopleTrusted Source worldwide, and up to 70% of those people have Alzheimer’s disease, which is characterized by a loss of brain cells associated with the toxic buildup of two proteins, amyloidTrusted Source and tauTrusted Source.

The most common symptoms of Alzheimer’s disease are memory loss, cognitive deficits, problems with speaking, recognition, spatial awareness, reading, or writing, and significant changes in personality and behavior. Since Alzheimer’s is progressive, these symptoms are usually mild at first and tend to become more severe over time. With no cure for the disease, patients and caregivers must approach treatment with medication, lifestyle changes, and support groups. 
AI model may predict Alzheimer’s by analyzing speech patterns


  • Researchers at Boston University say they have designed an artificial intelligence tool that can predict with nearly 80% accuracy whether someone is at risk for developing Alzheimer’s disease based on their speech patterns.
  • The ability to identify potential cognitive decline early has significant potential for mitigating the progression of Alzheimer’s, experts say.
  • However, the sample size used was small, and experts caution that such a tool is not meant to be leaned on as an exclusive method.

  This is from the Alzheimer's Disease Association in the Journal of Alzheimer's

INTRODUCTION

Identification of individuals with mild cognitive impairment (MCI) who are at risk of developing Alzheimer's disease (AD) is crucial for early intervention and selection of clinical trials.

METHODS

We applied natural language processing techniques along with machine learning methods to develop a method for automated prediction of progression to AD within 6 years using speech. The study design was evaluated on the neuropsychological test interviews of n = 166 participants from the Framingham Heart Study, comprising 90 progressive MCI and 76 stable MCI cases.

RESULTS

Our best models, which used features generated from speech data, age, sex, and education level, achieved an accuracy of 78.5% and a sensitivity of 81.1% to predict MCI-to-AD progression within 6 years.

DISCUSSION

The proposed method offers a fully automated procedure, providing an opportunity to develop an inexpensive, broadly accessible, and easy-to-administer screening tool for MCI-to-AD progression prediction, facilitating the development of remote assessment.

Highlights

  • Voice recordings from neuropsychological exams coupled with basic demographics can lead to strong predictive models of progression to dementia from mild cognitive impairment.
  • The study leveraged AI methods for speech recognition and processed the resulting text using language models.
  • The developed AI-powered pipeline can lead to a fully automated assessment that could enable remote and cost-effective screening and prognosis for Alzheimer's disease.

The prevalence of AD increases annually due to the long-term survival of patients, and it produces an increasing expense for long-term care.

Detecting Alzheimer's Disease at an early stage may improve possible treatments.

Detecting early AD could Improve the quality of life for patients and caregivers.

Clinical trials for AD are ongoing by the NIH and have yielded mixed results.

Treatment with either gantenerumab or solanezumab, two monoclonal antibodies, did not slow down cognitive decline in people who have a type of early-onset dementia called dominantly inherited Alzheimer’s disease (DIAD), according to a recent study. However, gantenerumab did reduce some biomarkers of the disease. The study, which was funded in part by NIA, was published in Nature Medicine on June 21. DIAD is a rare form of Alzheimer’s disease. It is an inherited condition caused by mutations in certain genes. People who have DIAD often start having symptoms of dementia, such as confusion and problems with memory, reasoning, and judgment, between the ages of 30 and 50. Currently, there is no treatment to prevent or slow down the disease. In the study, researchers led by a team at Washington University School of Medicine in St. Louis tested whether gantenerumab or solanezumab can effectively treat this condition. This study was part of the Dominantly Inherited Alzheimer Network Trials Unit (DIAN-TU). 

Biomarkers for AD

Cerebrospinal fluid (CSF) biomarkers, developed first by Fujirebio more than 25 years ago, have evolved over time from research to specialized diagnostic testing, and from use by early adopters to widespread routine testing today.

Assessing a patient’s CSF allows the detection of four proteins associated with Alzheimer’s disease: two forms of beta-amyloid (Aβ1-42 and Aβ1-40) proteins and two forms of Tau (Total Tau and hyperphosphorylated-Tau) proteins. In Alzheimer’s disease amyloid proteins (Aβ1-42 and Aβ1-42/Aβ1-40 ratio) decline to abnormally low levels. The Aβ1-42 levels and the Aβ1-42/Aβ1-40 ratio may decline long before disease symptoms are manifested. Although still considered a research tool in the US, high total Tau and phospho-Tau levels may also be observed in Alzheimer’s Disease.


There is an urgent clinical need for low-invasive, affordable techniques to assess the risk of Alzheimer's pathology in patients, that could help refer individuals to specialists for confirmatory testing. Plasma-based biomarkers for the two amyloid (Aβ1-42 and Aβ1-40) proteins and for the phospho-Tau protein are already available from Fujirebio for fully automated testing (for research use only). Research continues at the Fujirebio Neurology Center of Excellence, which has led, for example, to the release of new assays from CSF for two promising biomarkers, NPTX2 and sTREM2, and amyloid, both of which are available for research use.  Amyloid is an abnormal protein composed of peptides or peptide fragments.

Amyloid Protein Structure

Histopathology of Amyloid Protein in Brain

MMP-9 is associated with Alzheimer's. MMP can be found in CSF (and/or plasma, Ca clear, colorless fluid that surrounds and protects the brain and spinal cord of vertebratesI. t'Several lines of evidence indicate that there may be an inflammatory component to the pathology of AD. Matrix metalloproteinases (MMPs) remodel the pericellular environment by regulating the cleavage of extracellular matrix proteins, cell surface components, neurotransmitter receptors, and growth factors. The confused abilities of several MMPs to degrade amyloid precursor protein (APP) lead to aggregation of Aβ, as well as the increased expression of MMPs in postmortem brain tissue of AD patients, indicating that MMPs play an important role in the pathogenesis of AD. Their activities are determined through the induction of transcription by inflammatory mediators, through posttranslational modification by free radicals or cytokines and through inhibitory proteins such as tissue inhibitors of metalloproteinases (TIMPs) [].
 roduced by ependymal cells in the brain's ventricles and flows through the subarachnoid spaces of the cranium and spine. CSF has several important functions, including:

Ongoing. Clinical Trials and Research can be found on Pubmed and ClinicalTrials.gov 

The use of PET scans and history combined can afford more specific possibilities.  A positron emission tomography (PET) scan is a nuclear medicine procedure that uses a scanner to create detailed images of the body. The scan measures metabolic activity in body tissues by injecting a small amount of radioactive glucose (sugar) into a vein. The patient then lies on a table that slides through the PET machine while wearing a headrest and white strap to help keep them still. The scanner creates pictures of areas inside the body where the glucose is taken up, with brighter spots indicating higher activity. 

Research is ongoing by many pharma companies. Biogen, Eli Lilly, and Eisai: Three Companies That May Ride the Advancement in Alzheimer's.




No comments: