Embedded Files
Remember to follow me on Social Media!
Master of Electrical and Computer Engineering Capstone Project
IndurAITb: AI-Powered Smartphone-Based Tuberculosis Skin Test Interpretation
Video Pitch:
As the final capstone project for my master's at Rice, I developed IndurAITb, an AI-powered diagnostic app for the Tuberculosis Skin Test (TST). IndurAITb is a smartphone-based tool designed to make it easier and more accurate to interpret TSTs. These tests are used around the world to check if someone has been exposed to TB, but reading them correctly can be tricky and often depends on a healthcare worker’s judgment.
IndurAITb takes the guesswork out using artificial intelligence and computer vision to analyze the skin’s reaction directly from a short video. It spots the swelling (known as an “induration”) and measures it automatically, reducing human error and saving time. The app is lightweight, works offline, and can run on most mobile devices, making it perfect for use in rural or resource-limited settings.
By giving health workers a reliable, portable way to assess TSTs, IndurAITb can potentially improve TB screening and follow-up around the globe, especially where it’s needed most.
Applied Machine Learning and Data Science Capstone Project
Machine Learning for Predicting SIDS Outcomes
Video Pitch:
As part of my master's at Rice, my first capstone research involved applying machine learning to identify cardio-respiratory signatures that predict Sudden Infant Death Syndrome (SIDS) in mouse models.
By analyzing complex physiological datasets, my project discovered key patterns that could provide early indicators of mortality, ultimately contributing to advancements in predictive healthcare systems. Furthermore, the project achieved over 85% accuracy in predicting fatal outcomes by developing robust models to analyze these cardiorespiratory signatures.
This project integrated cutting-edge machine learning techniques with data science tools to process large-scale health data and reveal critical insights into cardio-respiratory interactions. This work contributes to the field of predictive healthcare by identifying critical early warning signals that can improve intervention strategies for infants at risk of SIDS. Its potential impact extends to real-time health monitoring systems that could be implemented in neonatal care units or even by family members through a user-friendly application.
Biomedical Engineering Capstone Project
Telemonitoring Ventricular Assist Device (TVAD)
Final Presentation:
This assignment involved developing a telemonitoring system for a Left Ventricular Assist Device (LVAD) as my bachelor's degree's final project, designed to monitor cardiac function in patients with heart failure.
By integrating physiological sensor data and applying machine learning techniques to predict device responsiveness, we analyzed the system to reduce latency by 10-15%, improving patient outcomes through more responsive monitoring.
The potential impact of this work lies in the enhancement of remote patient monitoring for cardiovascular healthcare, particularly for individuals who rely on LVADs for long-term heart support.
BIOMEDICAL ENGINEERING CAPSTONE PROJECT PRESENTATIONS IN CHRONOLOGICAL ORDER:
BIOMEDICAL ENGINEERING CAPSTONE PROJECT PRESENTATIONS IN CHRONOLOGICAL ORDER:
Page updated
Google Sites
Report abuse