https://jeroenvanschependom.be/tag/ai/AIWowchemy (https://wowchemy.com)en-usSat, 01 Jan 2022 00:00:00 +0000https://jeroenvanschependom.be/media/icon_hu898bad6a947579ff95e6bfac4d9757a2_264109_512x512_fill_lanczos_center_3.pnghttps://jeroenvanschependom.be/tag/ai/https://jeroenvanschependom.be/project/artificial-intelligence/Sat, 01 Jan 2022 00:00:00 +0000https://jeroenvanschependom.be/project/artificial-intelligence/<p>We study where artificial intelligence can genuinely add value in clinical neurology, with a focus on cognitive impairment, prognosis, and scalable analysis of multimodal data.</p> <h2 id="why-this-matters" style="font-size: 1.2rem; background: #FFB76B; background: linear-gradient(to right, #FFB76B 0%, #FFA73D 30%, #FF7C00 60%, #FF7F04 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Why this matters</h2> <p>AI is often presented as a universal solution in healthcare. Our work instead asks where machine learning is robust, clinically meaningful, and realistic in neurological disease.</p> <h2 id="current-directions" style="font-size: 1.2rem; background: #FFB76B; background: linear-gradient(to right, #FFB76B 0%, #FFA73D 30%, #FF7C00 60%, #FF7F04 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Current directions</h2> <ul> <li>AI for cognitive and clinical stratification</li> <li>Federated learning across distributed clinical datasets</li> <li>Methodological work on generalisability, bias, and clinical utility</li> </ul> <h2 id="earlier-work" style="font-size: 1.2rem; background: #FFB76B; background: linear-gradient(to right, #FFB76B 0%, #FFA73D 30%, #FF7C00 60%, #FF7F04 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Earlier work</h2> <p>One of my earlier explorations of AI in clinical care evaluated whether machine-learning approaches could detect metabolic syndrome in patients treated with antipsychotic medication. That work highlighted a recurring lesson in medical AI: apparent accuracy can depend strongly on the population under study.</p> <h2 id="on-ai-in-ms-care" style="font-size: 1.2rem; background: #FFB76B; background: linear-gradient(to right, #FFB76B 0%, #FFA73D 30%, #FF7C00 60%, #FF7F04 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">On AI in MS care</h2> <p>We have contributed to the debate on whether AI will transform multiple-sclerosis care in the coming decade. For me, the important question is not whether AI is fashionable, but whether it improves decisions, scales across centres, and remains interpretable enough for clinical use.</p> <h2 id="related-outputs" style="font-size: 1.2rem; background: #FFB76B; background: linear-gradient(to right, #FFB76B 0%, #FFA73D 30%, #FF7C00 60%, #FF7F04 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Related outputs</h2> <p>See the <a href="https://jeroenvanschependom.be/publication/">Publications</a> page for selected work on AI, federated learning, and digital biomarkers.</p>