PM.20.025 – Personalized treatment for mental disorders: using routine data for shared decision making and precision medicine
Mental disorders are highly prevalent and create an enormous societal and personal burden. However, current treatments mostly have limited effects. Moreover, there is large heterogeneity between client experiences and outcomes in mental health care. Finally, to maximize treatment outcomes there is an urgent need for shared decision making between patients and mental healthcare providers. These aspects together demand advanced methodology and innovative thinking to bring the mental healthcare field forward by improving patient outcomes and increasing the efficiency of mental healthcare. The overall aim of our proposal will be to personalize care for patients with mental disorders by utilizing routinely collected data and taking an innovative perspective on patient outcomes. We will achieve this overall aim by: 1) Building a data-infrastructure integrating different types of data (e.g. electronic medical records, routine outcome monitoring databases, claims data, social media, ecological momentary assessments); 2) (Re-)defining outcome measures to optimally capture aspects relevant to patients with mental disorders; 3) Developing innovative algorithms using data at both the individual and aggregate level to identify the optimal combination of treatments for a specific patient to support shared decision making; 4) Creating dynamic models to make up-to-date predictions of outcomes in individual patients with mental disorders by monitoring their disease trajectories; 5) Assessing the effectiveness and cost-effectiveness of personalized mental healthcare using these data driven approaches combined with shared decision making; 6) Implementing these new approaches in mental healthcare into routine care by providing tools that can be incorporated into existing electronic environments. 7) Showing the potential of our approach by applying it to three different showcases (schizophrenia, depression, trauma disorder). Thus, our project will result in efficient use of routinely collected data to improve the prognosis of patients with mental disorders by tailoring their treatment to their specific needs and preferences, thereby supporting patient orchestrated care.
mental disorders, personalised care, prediction modelling, real world data, shared decision making
GGZ Friesland, GGZ inGeest, RGOc (Rob Giel Onderzoekscentrum), Rijksuniversiteit Groningen (RUG), Trimbos Institute, UMCG
|Organisation||Vrije Universiteit Amsterdam (VU)|
|Name||Prof. dr. Judith E. Bosmans|