Depression is the leading cause of disability. Treatment of depression is based on stepped care, which is provided on a trial-and-error basis. Only 30-50% of patients benefit from each treatment step, resulting in prolonged treatment trajectories with avoidable burden for patients and costs for society. In line with the NWA route Personalised medicine and knowledge agendas of professional and patient organisations, we aim to personalise the treatment using biomarkers (question 095). We and others have recently shown that treatment outcome can be predicted for individual patients with ~80% accuracy using machine learning analysis of neuroimaging data. This means that our methods could potentially double the current 30-50% treatment success rate to 80%. However, earlier proof-of-concept studies were performed for single treatments and may not generalize to the Dutch clinical population. Our primary question therefore is whether we can develop biomarkers that enable treatment selection, which is pivotal for clinical use. We will obtain clinical, neuroimaging (EEG/MRI), and (epi)genetic markers of patients with major depressive disorder before their treatment. For biomarker development, we will recruit patients who received indications for a wide range of current treatment steps, including treatment with psychotherapy, pharmacotherapy and neurostimulation. We will set up an interdisciplinary consortium for the recruitment of patients and collection of data, measure treatment success from the patient’s perspective, and use state-of-the-art machine learning to develop multimodal biomarkers that incorporate clinical data to optimize predictive accuracy. In the prospective validation phase, biomarkers will be implemented in randomised controlled trials to evaluate the efficacy and cost-effectiveness of biomarker-based treatment. The development of a treatment selection biomarker panel would be a scientific breakthrough, enabling a societal breakthrough to personalise the treatment of depression. This will shorten the treatment trajectory for patients, lower patient burden and health care demand, and reduce costs for society.
