EDAD: Early Diagnosis of Alzheimer's Disease Utilizing Low-Cost Plasma Peptide Extraction, Atmospheric Pressure Mass Spectrometer, and Support Vector Machine-Based Classification of Amyloid-Beta Species
ISEF · 2025 Translational Medical Science
Overview
Conventional methods for Alzheimer's Disease (AD) early diagnosis are often considered not cost-effective and sometimes invasive. Although recent AD studies focus on blood biomarker-based methods, a less expensive and non-invasive way, these methods still require high clinical expertise. To address these limitations, this study aimed to develop EDAD, a diagnostic device to automatically detect, quantify, and classify blood biomarkers, specifically amyloid-beta species, to predict AD prognosis in patients assisted by support vector machines (SVMs). The device was tested in-silico using COMSOL Multiphysics to determine the capability of the inner casing to retain its particle velocity and denoise mass spectra using its novel rotating annular cylinder mechanism. A biuret test of the peptide binding assay (PBA) and calibration test of the amyloid-beta species-specific quadrupole mass spectrometer (QMS) was done to determine its ability to extract proteins and to prepare for actual testing. The rotating mechanism resulted in an x-axis mean free path after 10 seconds at 300 RPM, and the inner casing constriction resulted in an increased velocity for the ions. In its actual testing, EDAD analyzed 48 plasma samples from four (4) different population groups based on their AD prognosis. EDAD classified forty-seven (47) samples correctly, showing a specificity of 92.3% and sensitivity of 100%, significantly higher than conventional screening tests such as Amyloid-PET scan and ELISA kits. Additionally, the cost analysis shows that EDAD is significantly more cost-effective than Amyloid PET scan and ELISA Kits, making it a more cost-effective and efficient alternative for early AD diagnosis.
Competition history
- ISEF 2025
Resources
Related projects
ISEF · 2020
Developing a Pre-Risk Assessment Incorporating Machine-Learning and Biomarkers to Diagnose Alzheimer's Disease
ISEF · 2018
Detection of Early-Stage Alzheimer's Disease via Hierarchical Classification of Proteomic and Clinical Profiles
ISEF · 2025
Non-Invasive Blood-Based Early Alzheimer's Detection Using Sex-Specific Brain-Blood Graph Reinforcement Learning
ISEF · 2021
Experimental Detection System for Senile Dementia- A Novel, Systematic Approach Using Metabolomics, Bioinformatics, and Circuitry to Develop a Biosensor Through Metabolomic Electrical Resistance Analysis for Detection of Early Onset Alzheimer’s
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair