Date of Completion

Spring 5-1-2024

Thesis Advisor(s)

Hugo Posada-Quintero, Patrick Kumavor

Honors Major

Biomedical Engineering

Disciplines

Artificial Intelligence and Robotics | Biomedical Devices and Instrumentation | Databases and Information Systems | Electrical and Electronics | Signal Processing

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that negatively affects a patient’s cognitive and communication aptitude and, therefore, can severely impact that patient’s quality of life. Because of this, early diagnosis is paramount. In recent studies, electroretinography (ERG), which is a measure of the retina’s electrical response to a brief flash of light into the eye, has shown promise in detecting ASD. Access to these scans can provide early diagnosis, improving well-being. Current ERG devices are very expensive due to their on board processing capabilities. This paper aims to create an ERG device using a smartphone as the main computing component as well as the stimulus flash source. Along with an inexpensive custom PCB with electrode connections and 3D printed body, this device improves accessibility to this tool through reducing cost. As for the software, a mobile application was developed to provide stimulus flash and read the signal from the external circuit. In addition, this application houses an Amazon Web Services (AWS) based database. This database allows for easily accessible data from each reading for research purposes. In addition, a binary classification Support Vector Machines (SVM) machine learning algorithm was developed to provide instant ASD diagnostic capabilities. Results: The device shows promise for capturing ERG signals with relative consistency. In addition, the database allows for a streamlined data storing process. Lastly, the SVM algorithm was found to have 66.2% accuracy.

Download

Share

COinS