PETRUSHKA is aimed at developing and subsequently testing a personalised approach to the pharmacological treatment of major depressive disorder in adults, which can be used in everyday NHS clinical settings.

We have collected data from patients with major depressive disorder, obtained from diverse datasets, including randomised trials as well as real-world registries (registers that hold routinely collected NHS data from the UK). These data summarise the most reliable and most up-to-date scientific evidence about benefits and adverse effects of antidepressants for depression and have been used to inform the PETRUSHKA prediction model to produce individualised treatment recommendations. The prediction model underpins a web-based decision support tool (the PETRUSHKA tool) which incorporates the patient's and clinician's preferences in order to rank treatment options and tailor the treatment to each patient.

This trial will recruit participants from the NHS within primary care in England and investigate whether the use of the PETRUSHKA tool is better than 'usual care' treatment in terms of adherence to antidepressant treatment, clinical response and quality of life, and its cost-effectiveness over a 6-months follow up.

The PETRUSHKA tool, employs a bespoke algorithm to identify the best antidepressant for each individual patient. The algorithm: (a) is based on a prediction model which uses a combination of advanced analytics (statistics) and machine learning methods (artificial intelligence); (b) uses a dataset which is a combination of real-world data (QResearch: https://www.qresearch.org/) from over 1 million primary care patients with depression in England and Wales, and individual participant data from about 40,000 patients recruited in randomised controlled trials; (c) incorporates preferences from patients and clinicians (especially about adverse events); (d) generates a ranked list of personalised treatment recommendations that will inform the clinical discussion between clinicians and patients, and the final treatment decision. The clinical decision aid tool is implemented in the form of a web-based application, accessible from any computer or tablet.

Inclusion Criteria:

• Aged 18 - 74 years inclusive;
• Willing and able to give informed consent for participation in the trial;
• Clinical diagnosis of depression (either single episode or recurrent), for which an antidepressant is clinically indicated;
• Willing to start antidepressant treatment as monotherapy;
• Able to read/understand and/or complete self-administered questionnaires online in English;
• Willing to meet any clinical requirements related to taking a specific medication

Exclusion Criteria:

• Prescribed any antidepressant in the preceding 4 weeks;
• Current or historical diagnosis of ADHD, Alcohol/Substance Use Disorder, bipolar disorder, dementia, eating disorders, mania/hypomania, OCD, PTSD, psychosis/schizophrenia, Treatment Resistant Depression (having tried 2 or more antidepressants for the same depressive episode at adequate dose and time);
• Diagnosis of arrhythmias (including Q-T prolongation, heart block), recent MI, poorly controlled epilepsy, acute porphyrias;
• Require urgent mental care or admission (including suicidal intent/plans);
• Concurrently enrolled in another investigational medicinal product (IMP) trial or an interventional trial about depression;
• Participants who are currently pregnant, planning pregnancy or lactating;
• Has a medical, social or other condition which, in the investigator's opinion , may make the participant unable to comply with all the trial requirements (e.g., terminal illness - motor neuron disease).

Assessors will be blind when administering rating scales at week 8 and 24, and statisticians will be blind to the allocated treatment during analysis.