Classification of Spontaneous Speech of Individuals with Dementia Based on Automatic Prosody Analysis Using Support Vector Machines (SVM)

AAAI Conferences

Analysis of spontaneous speech is an important tool for clinical linguists to diagnose various dementia types that affect the language processing areas. Prosody is affected by some dementia types, most notably Parkinson's disease (PD, degradation of voice quality, unstable pitch), Alzheimer's disease (AD, monotonic pitch), and the non-fluent type of Primary Progressive Aphasia (PPA-NF, hesitant, non-fluent speech). Prosodic features can be computed efficiently by software. In this study, we evaluate the performance of a SVM classifier that is trained on prosodic features only. The limitation to only prosody yields baseline results that can be used in a later stage to evaluate the added effect of variables of (morpho) syntax. The goal is to distinguish different dementia types based on the recorded speech. Results show that the classifier can distinguish some dementia types (PPA-NF, AD), but not others (PD, PPA-SD).


Daydreaming brain network used in autopilot

BBC News

The part of the brain associated with daydreaming also allows us to perform tasks on autopilot, a study has found. A collection of brain regions known as the "default mode network" (DMN) is active when we are daydreaming or thinking about the past or future. Cambridge University researchers found it also allows us to switch to autopilot once we are familiar with a task, such as driving a familiar route. There is even hope the findings can help people with mental illness. Previous research has found the DMN is more active during states of rest, and that it can behave abnormally in conditions such as Alzheimer's disease, schizophrenia and attention deficit hyperactivity disorder (ADHD).


Children conceived in the winter are at greater risk of autism and dyslexia: Mother's lack of vitamin D affects development of baby's brain

Daily Mail - Science & tech

Babies conceived in winter are more likely to develop learning difficulties, a major study suggests. Scientists think lack of exposure to sunlight in the early stages of pregnancy may affect brain development. A study of more than 800,000 school children in Scotland showed 8.9 per cent of children conceived in January to March had learning disabilities, compared to 7.6 per cent of those conceived between July and September. One in five people in Britain have low levels of the vitamin D - which is produced by the skin when it soaks up the sun's rays. The vitamin is particularly important during pregnancy, and is already known to affect the way a baby's bones grow in the womb.


A gene discovery may help cure Parkinson's disease

Daily Mail - Science & tech

A'master switch' in the brain could prevent Parkinson's disease, scientists have revealed. The breakthrough could pave the way for a drug that potentially cures the condition by stopping brain cells from dying. By turning on proteins that boost the energy of neurons, it would protect them from destruction, a study found. A'switch' in the brain that boosts the energy of neurons may help prevent Parkinson's disease Researchers from the University of Leicester found that a gene known as ATF4 plays a key role in the onset of Parkinson's in fruit flies. Acting as a switch, ATF4 helps to control the energy stations of cells - known as mitochondria - including neurons.


Innovative AI Breath Analyzer Diagnoses Diseases by "Smell"

#artificialintelligence

Imagine being able to know if you have Parkinson's disease, multiple sclerosis, liver failure, Crohn's diseases, pulmonary hypertension, chronic kidney disease, or any number of cancers based on a simple, non-invasive test of your breath. Breath analyzers to detect alcohol have been around for well over half a century--why not apply the same concept to detect diseases? A global team of scientists from universities in Israel, France, Latvia, China and the United States have developed an artificial intelligence (AI) system to detect 17 diseases from exhaled breath with 86 percent accuracy. The research team led by Professor Hassam Haick of the Technion-Israel Institute of Technology collected breath samples from 1404 subjects with either no disease (healthy control) or one of 17 different diseases. The disease conditions include lung cancer, colorectal cancer, head and neck cancer, ovarian cancer, bladder cancer, prostate cancer, kidney cancer, gastric cancer, Crohn's disease, ulcerative colitis, irritable bowel syndrome, idiopathic Parkinson's, atypical Parkinson ISM, multiple sclerosis, pulmonary hypertension, pre-eclampsia toxemia, and chronic kidney disease.