About
Concluded in February 2026, the ambitious AI-Mind project (Grant ID: 964220) was a pioneer in the new era of clinical AI research. During the five-year project period, the initiative successfully established one of the world's most comprehensive longitudinal datasets focused on Mild Cognitive Impairment (MCI) and dementia progression.
Collected through harmonised procedures across Norway, Finland, Italy, and Spain, the dataset covers over 1,000 individuals. It comprises more than 3,500 EEG recordings and digital cognitive assessments, 1,800 blood biomarker samples, and nearly 1,000 diagnostic conclusions. However, the existence of valuable data is only the first step; preparing such complex, sensitive information for clinical AI applications demands robust engineering combined with domain expertise.
In this talk, Dr. Hatlestad-Hall details how the AI-Mind project leveraged and collaborated with the Services for Sensitive Data (TSD) at the University of Oslo to build a comprehensive research platform for data curation, quality assurance, and AI model development. The talk will highlight critical lessons learned and identify essential focus areas for the future co-creation of research infrastructure that bridges the gap between clinical research and technology development.
00:00:00 Slide 1
00:00:40 Slide 2
00:08:42 Slide 3
00:14:15 Slide 4
00:25:21 Slide 5
00:26:32 Slide 6
00:31:35 Slide 7
00:34:18 Slide 8
00:35:25 Slide 9
The talk
Credits and licence
- Institution
- CERN
- Speaker
- Christoffer Hatlestad-Hall
- Year
- 2026
- Language
- English
- Subjects
- Computer science
- Source
- CERN
- Licence
- CERN, as CERN states it. CERN's terms
- Attribution
- © CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
- Who can watch
- CERN gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed