What is it about?

Establish a connection between minute details of the speech and ascertain which factors of speech exhibit the strongest relation with an Alzheimer patient’s speech

Featured Image

Why is it important?

Alzheimer's disease (AD) is a neurodegenerative disease that affects nearly 50 million individuals across the globe and is one of the leading causes of deaths globally. It is projected that by 2050, the number of people affected by the disease would more than double. Consequently, the growing advancements in technology beg the question, can technology be used to predict Alzheimer's for a better and early diagnosis? In this paper, we focus on this very problem. Specifically, we have trained both ML models and neural networks to predict and classify participants based on their speech patterns. We computed a number of linguistic variables using DementiaBank's Pitt Corpus, a database consisting of transcripts of interviews with subjects suffering from multiple neurodegenerative diseases

Perspectives

Alzheimer’s disease is by far the most common type of dementia, accounting for about 70% of all dementia cases, worldwide. It is a progressive and irreversible neurodegenerative disease that causes brain cells to degenerate and die, thereby debasing the mental faculties of the patient. AD has no ubiquitous definition and is often associated with symptoms like memory loss, language deterioration, mood changes, impaired judgment, and loss of initiative. In this paper, we propose a non-invasive method of predicting and distinguishing AD from other neurodegenerative diseases. We have trained ML models using the speech (audio) transcripts of individuals with different neurodegenerative diseases. This paper also studies the impact of speech features on model predictions. More formally, the paper studies which of the myriad speech features are the most relevant in making accurate predictions for the trained models (and hence in diagnosis of AD)

Veeky Baths
BITS Pilani Goa Campus

Read the Original

This page is a summary of: ML-Based Analysis to Identify Speech Features Relevant in Predicting Alzheimer's Disease, March 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3532213.3532244.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page