Print This Post
Call For Collaborators: AI and machine learning for multimodal precision brain health interventions
Artificial intelligence and machine learning are increasingly used to integrate multimodal data, including cognitive measures, fluid and imaging biomarkers, digital device data, genomics and demographic factors, to generate personalised brain health profiles. These approaches are beginning to inform targeted prevention and intervention strategies. However, there is currently no clear methodological guidance on how multimodal data should be combined, validated and translated into precision brain health interventions.
We are undertaking a structured review to identify and synthesise ongoing and planned interventional studies that incorporate both a personalised component and an AI or machine learning framework. Our objectives are to:
- Characterise the algorithms and modelling strategies used or proposed for multimodal integration.
- Examine approaches to internal and external validation, transportability and calibration.
- Evaluate strengths, limitations and recurrent methodological weaknesses.
- Develop practical recommendations and methodological guidance for AI enabled personalised brain health interventions.
We are seeking contributors with expertise in either:
- Artificial intelligence and machine learning methods relevant to multimodal data integration, or
- Brain health research involving multimodal datasets such as cognitive, biomarker, imaging, digital or genetic data.
This project is a new initiative of the DEMON Network and is being developed as an international collaborative effort bringing together researchers across disciplines and countries. It presents an opportunity to contribute to a coordinated, international effort aimed at shaping emerging methodological standards for precision brain health, with clear scientific and translational impact.
If you are interested in contributing, please contact Dr Daria Jensen at jensen@cbs.mpg.de
DEMON Network
