{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Tech Tomorrow","title":"Could AI and data science help us find a cure for Alzheimer’s with Prof. Alejo Nevado-Holgado","html":"","width":"100%","height":180,"duration":1507,"description":"An estimated 55 million people worldwide are living with dementia, of which Alzheimer’s is the most common form. This number continues to rise as global populations age. Despite the scale of the problem and large amounts of funding, no one has been able to find a cure. Could it be that data science, rather than medicine, holds the answers to tackling this disease?\nIn this episode of Tech Tomorrow, David Elliman speaks with Alejo Nevado-Holgado, Associate Professor of Psychiatry at the University of Oxford and member of the Big Data Institute. He leads AI research within the Computational and Molecular Neuroscience Laboratory, an interdisciplinary team spanning AI, biochemistry, and bioinformatics.\nThe conversation explores how advanced computational methods are using vast biological and clinical datasets, including genomics, transcriptomics, proteomics, stem cell imaging, brain scans, and electronic health records. This integrated approach aims to uncover disease mechanisms, identify new drug targets, and advance more personalized treatments, all supported by high-performance computing.\nA key challenge in Alzheimer’s research is the difficulty of accessing and studying the brain. The blood-brain barrier limits treatment delivery, while the disease develops over decades before symptoms appear. The discussion also highlights ongoing scientific uncertainty about whether hallmark features such as amyloid plaques and tau tangles are causes of the disease or downstream effects.\nThe episode examines how AI can support early detection through blood-based biomarkers and why it is particularly effective in analysing complex, high-dimensional data such as molecular structures and genomic information. The importance of combining diverse datasets, such as population-scale biobanks and drug discovery data, is emphasised as essential for progress.\nHowever, challenges remain, including the need for explainable AI systems and more complete longitudinal health data. The...","thumbnail_url":"https://img.transistorcdn.com/pZGeZGCvOw_Nv7lFAAlALqQyorlxskmKcY0c0BIVihc/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS85NmFm/OWY2NWVkNWNjY2Rh/N2U4NDNlOGRiYmY5/NzgwOC5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}