From data to targeted interventions: Paving the way to relieve the burden of mental-non-mental multimorbidity by a deep learning-informed translational network approach
Principal Investigator: Professor Gunther Meinlschmidt
Approved Research ID: 49658
Approval date: June 18th 2019
The multimorbidity of mental and non-mental disorders (MNMMM), which means that someone suffers from at least one mental and at least one non-mental disorder, is a common phenomenon at all stages of life. MNMMM has detrimental effects on patients, relatives, caregivers and society: it comes with more severe illnesses, more frailty and (re-)hospitalisation, longer and less effective treatments, reduced quality of life and life expectancy, and significantly higher direct and indirect health costs compared to individual disorders. Important barriers to innovations helping patients are the various manifestations of MNMMM and the difficulty to define and analyse MNMMM. Also, a lack of strategies to put theoretical knowledge into practice have prevented appropriate case management. In addition, these limitations have made it difficult to identify, validate and clinically apply biomarkers and valid mechanisms underlying MNMMM. In particular, our project supports the UK Biobank's stated mission to 'improve the prevention, diagnosis and treatment of a wide range of serious and life-threatening diseases'. To address the obstacles outlined above, we will analyse data from the UK Biobank and develop new analytical techniques. This way, we aim at identifying and validating biomarkers and mechanisms underlying common and harmful MNMMM networks. UKB analyses are planned to run for at least 3 years. The results are expected to provide strategies for the development of more accurate and personalized treatments leading to less psychosocial burden on patients and their families and lower health care costs for society. We also aim at promoting innovations that provide the basis for reducing the burden on MNMMM. New key variables derived from the UKB analyses will be fed back into the UKB dataset so that other researchers can benefit from our work.