Ïã¸ÛÁùºÏ²Ê

I would like to begin by thanking the Institute of Healthcare Engineering for their early-career travel award, which helped me attend the OHBM 2024 conference in Seoul, South Korea.

OHBM is an annual international conference dedicated to advancing the understanding of the anatomical and functional organisation of human brain using neuroimaging. It provides an excellent platform for the exchange of inspiring ideas and groundbreaking research across neuroimaging methods and applications. It is also a very well-organized conference that offers invaluable opportunities for career advancement and learning through its excellent sessions, symposiums, mentorship programs, and networking events, especially for early career researchers like myself.

Seoul was an exceptional conference venue. It was my first visit to South Korea, and I was deeply impressed by the rich Korean culture and warm hospitality. The conference beautifully showcased Korean heritage, featuring traditional musical-dance performances at the opening session, and offering attendees a taste of Seoul's vibrant cultural scene. The Korean influence was evident in various aspects of the event, from the thoughtfully arranged poster hall activities to the local symposium. Additionally, events like the 'Brain Mappers of Tomorrow' session were designed to engage Korean and other non-English speaking children and their parents in scientific processes, fostering critical thinking and a love for science. Exploring the city, I experienced the harmonious blend of ancient traditions and modern innovation that defines Seoul, making the conference not just an academic experience, but a cultural one as well.

This award enabled me to present my exciting new findings, AutoML-based model agnostic neuroimaging approach for improved Alzheimer’s disease classification, with the international brain mapping community. My poster received significant attention and was of great interest to both the neuroimaging and Alzheimer’s research communities. My work highlights a novel automated machine learning-based method for making patient-specific predictions of Alzheimer’s disease diagnosis and prognosis using neuroimaging data. Our autoML-multiverse approach is fully data-driven and it removes experimenter bias, eliminates arbitrary analytic choices, and improves prediction accuracy for clinically relevant outcomes.

Attending this conference allowed me to foster new collaborations and discuss potential new applications for my approach. It was an excellent venue to spark discussions and generate new ideas with researchers from around the world. The connections and insights gained will undoubtedly contribute to advancing my research and career. My thanks to IHE once again!