LongITools

Dynamic longitudinal exposome trajectories in cardiovascular and metabolic non-communicable diseases

OBJECTIVES

Develop machine learning tools based on full resolution exposome data for cardio-metabolic risk prediction
Establish an open-source toolbox for analysing longitudinal biomedical data including multi-source and multi-type exposome data
Implement defined user and clinical requirements and pilot test a mobile application for cardio-metabolic monitoring

ROLES

Develop a catalogue of longitudinal multi-dimensional datasets under a FAIR (findable, accessible, interoperable and re-usable) data infrastructure
Develop, implement and advance epidemiological, statistical and computational methodologies to incorporate the longitudinal dimensions in exposome-wide associations and cross-omic studies of health and disease
Explore and unravel, using data-driven methods, the association between environmental exposures and the risk of cardio-metabolic disease across the life-course
Implement, pilot and demonstrate new healthcare applications for personal risk assessment and public health and policy planning
Perform economic and econometric assessments to identify the health and cost benefits of time-dependent investments in addressing the impact of environmental exposures across the life course

PARTNERS

NO.	INSTITUTION	COUNTRY
1	Imperial College London	United Kingdom
2	Erasmus MC	Nederland
3	Beta Technology	United Kingdom
4	University of Eastern Finland	Finland
5	Chalmers University of Technology	Sweden
6	University Medical Center Groningen	Nederland
7	National Institute of Medical Research	France
8	University College London	United Kingdom
9	University of Utrecht	Nederland
10	University of Surrey	United Kingdom
11	Amsterdam Medical Center	Nederland
12	University of Oslo	Norway
13	University of Bristol	United Kingdom
14	Universitat Pompeu Fabra	Spain
15	AB-Acus	Italy
16	Cynexo	Italy
17	University of Rome	Italy