International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 03 | Mar 2024
p-ISSN: 2395-0072
www.irjet.net
Alzheimer’s Disease Prediction Using Darwin Dataset P V S R Abhinav1, G.Venkata Adharsh2, Prudhvi Reddy3, Peddireddy Sneha Latha Reddy4, Dr. B, Jaidan5 1,2,3,4 Student, GITAM(Deemed to be University), Visakhapatnam ,Andhra Pradesh, India.
5Associate Professor, GITAM(Deemed to be University), Visakhapatnam, Andhra Pradesh
---------------------------------------------------------------------***--------------------------------------------------------------------Abstract— The DARWIN dataset is a valuable resource The paper discusses the composition of the DARWIN for researchers and healthcare professionals interested in using handwriting analysis for early detection of Alzheimer's disease. It includes a diverse collection of handwriting samples from Alzheimer's patients and a matched control group. The dataset comprises data from 174 participants at different stages of the disease, allowing researchers to understand the evolution of handwriting characteristics as the disease progresses. This dataset addresses the lack of standardized protocols and sufficient data in Alzheimer's research, providing a comprehensive resource to explore the potential of handwriting analysis for early detection. The control group offers a valuable comparison for studying Alzheimer's-related handwriting changes.
dataset, the tasks completed by participants, and the clinical and demographic information associated with the handwriting samples. It highlights the dataset's value in enhancing our understanding of Alzheimer's disease and advancing the development of early diagnosis tools and interventions.
Keywords— darwin dataset, handwriting, alzheimer’s
However, diagnosing Alzheimer's disease in clinical practice remains challenging. The disease's subtle symptoms make it difficult to identify until it worsens. Traditional diagnostic methods, such as neuroimaging scans and cognitive evaluations, may not accurately detect the disease's early stages or differentiate it from other neurodegenerative conditions or age-related mental decline. Thus, there is a need for novel diagnostic tools that can detect Alzheimer's disease early on.
Early diagnosis of Alzheimer's disease is crucial for several reasons. It allows for prompt actions to reduce symptoms and the spread of the disease, improving overall quality of life. It also enables individuals and their families to make informed decisions about end-of- life care, financial arrangements, and long-term care planning, reducing the burden on caregivers.
1. Introduction 1.1 Introduction Alzheimer's disease and various neurodegenerative illnesses, such as dementia, are a growing concern worldwide. These conditions lead to the gradual decrease of neuro cells in the brain, resulting in the loss of movement and cognitive abilities. Early diagnosis is crucial to provide timely therapies and improve the quality of life for patients. Handwriting analysis has emerged as a promising method for detecting and tracking Alzheimer's disease in its early stages. This noninvasive and cost-effective technique could identify potential signs of the disease by analyzing subtle changes in cognitive function and fine motor coordination. However, there are challenges in the field, including the need for a standardized technique and limited research data.
Handwriting analysis offers a potential solution. Studies show that individuals with Alzheimer's disease exhibit noticeable changes in their handwriting, reflecting underlying neurodegenerative processes. Advanced analytical tools, such as computer vision and machine learning algorithms, can extract quantitative data from handwriting samples and identify unique patterns associated with early-stage disease. When combined with current diagnostic techniques, handwriting analysis could improve sensitivity and specificity in Alzheimer's diagnosis. However, there are obstacles to implementing handwriting analysis in clinical settings. The lack of standardized procedures for evaluating and analyzing handwriting in Alzheimer's disease is a significant challenge. Harmonizing data collection methods, creating normative benchmarks, and validating assessment instruments are necessary to ensure research findings' accuracy and repeatability.
To address these issues, the DARWIN dataset (Dataset for handwriting Analysis in Alzheimer's Disease) has been created. This comprehensive collection of handwriting samples from individuals with Alzheimer's disease and a matched control group aims to facilitate research and provide valuable resources to researchers, doctors, and healthcare professionals. The dataset will aid in exploring handwriting characteristics and their potential application in early diagnosis.
© 2024, IRJET
|
Impact Factor value: 8.226
Further studies are needed to validate the diagnostic value of handwriting analysis. Long-term investigations tracking
|
ISO 9001:2008 Certified Journal
|
Page 959