Major Depressive Disorder: Early Prediction of Non-response to Antidepressant Therapy Via a Mobile Digital Scale

Major Depressive Disorder (MDD) is a debilitating disease characterized by a depressed mood, diminished interests, impaired cognitive function and vegetative symptoms, such as disturbed sleep or appetite. MDD occurs about twice as often in women than it does in men and affects about 6% of the adult population worldwide each year. Standard symptoms scales like the Hamilton Depression Rating Scale or the Montgomery-asberg Depression Rating Scale, the Self-Report 16-item Quick Inventory of Depressive Symptomatology were initially developed for the evaluation of a therapeutic intervention or a pharmacological treatment and are routinely used by clinicians in the assessment of Treatment Resistant Depression (TRD) occurrence. In parallel, patient-reported outcomes have gained increasing importance and are widely recommended by health authorities in the assessment of depression. The same institutions insist on the collection of real-world data to provide clinicians with ecological measurements. It has been demonstrated that an early response to an AntiDepressant (AD) treatment can be seen as early as week 2 and is not related to a placebo-effect. While there is no consensus on the exact cut-off values, several factors emerge as early predictors of a later treatment response, such as: * Improvement in emotional processing of happy facial expressions after 1 week of treatment, * Circa 20% improvement in Hamilton Depression Rating Scale-17 item (HDRS-17) at week 2. The hypothesis is therefore that repeated, systematic and real-time, contextualized and multimodal collection of depressive symptoms from patients at home will establish a threshold score that can predict a subsequent response to their treatment. REDRESS was inspired by several standard depression scales used and recommended by the French Health Authority, augmented with digital active and passive activity monitoring, speech analysis and emotional processing assessment. Another important assumption is that hones