Greater Dublin
I am a Machine Learning Engineer and Medical Student with a focus on leveraging artificial intelligence in the era of digital data abundance. My goal is to support healthcare professionals in delivering more accurate and personalized treatments. With a background in biomedical engineering, I am committed to exploring how AI can be harnessed to make a positive impact on healthcare.
Developing AI models for echocardiogram analysis. Preprint forthcoming.
Project: Development and validation of AI-driven solutions for elite athlete injury management (EliteAI). Objective: Developed a novel approach combining Artificial Intelligence and Diffusion MRI to enhance the accuracy of diagnosing and managing serious muscle injuries in elite athletes. Key Contributions: • Designed and implemented an image classifier prototype to objectively assess MRI scans and predict return-to-play timelines for injured athletes. • Led efforts in deep learning model training, including object detection, classification, and segmentation for muscle injury identification. • Applied advanced techniques for data curation, anonymization, and preprocessing to ensure high-quality inputs for model training.
Overview: During my time as a research assistant under Prof. Madeleine Lowery, I worked to advance a Deep Brain Stimulation (DBS) system, focusing on preparing it for pre-clinical animal trials. My main tasks involved implementing and testing closed-loop stimulation control algorithms. Key Responsibilities: • Control Algorithm Implementation: Programmed the system’s firmware and developed several closed-loop control algorithms, including On-Off, Dual-Threshold, and Proportional-Integral Amplitude and Frequency Modulation controls. • Firmware Development: Reprogrammed the system’s firmware to enable switching between different stimulation pulses. • System Performance Testing: Measured system delays and optimized it for real-time closed-loop stimulation. Achievements and Impact: • Contributed to the development of a DBS system capable of implementing closed-loop stimulation with minimal delays, paving the way for pre-clinical trials involving animal models with Parkinson’s disease. • Supported the research published in "On-Off and Proportional Closed-Loop Adaptive Deep Brain Stimulation Reduces Motor Symptoms in Freely Moving Hemiparkinsonian Rats" (Evers et al., Neuromodulation: Technology at the Neural Interface, 2024), which demonstrates the effectiveness of adaptive DBS in reducing motor symptoms in parkinsonian rats and highlights the potential of closed-loop systems.
Project Focus: Analyzed noise and spurious signals in nonlinear fractional-N frequency synthesizers (Phase Locked Loops), with a focus on improving system accuracy and performance. Key Responsibilities: • Conducted measurements in an ESD-protected RF laboratory using real-time spectrum analyzers to evaluate synthesizer behavior. • Developed detailed technical reports on research progress and findings, contributing to ongoing analysis and system optimization. • Contributed to a research paper on the impact of MASH DDSM quantization noise, which was presented at the IEEE International Conference on Electronics, Circuits, and Systems (ICECS).