Depression and anxiety are common mental health problems affecting around one in six adults. Treatments include therapy, telephone or group-based activities delivered by therapists. Treatment uses a "stepped care" model where most patients start with very brief treatments. If they remain unwell after this, they access longer and more intensive therapy. This model does not always work, as only one out of two patients fully recover.
The researchers have developed an artificial intelligence tool called "StratCare". It is designed to help health services to offer the best available treatment for each patient. StratCare is a computerised system that guides therapists on how to assess new patients. It asks a few questions about their symptoms, personality, and background. The system makes a recommendation about which treatment might be most effective for that person. This is either starting with brief therapy or starting with intensive therapy. The treatments are already used with depression in the National health Service (NHS). The patient can discuss with their therapist and decide whether to accept the recommendation. Otherwise, they can discuss trying other options. Previous research found that StratCare can help more people to recover from depression compared to the usual stepped care model.
The researchers will investigate if the StratCare tool works on a large scale in the NHS and if it helps patients in the long-term. The researchers will run a trial involving 1252 participants using NHS Talking Therapies services. Half will use the StratCare tool to make a treatment recommendation. The other half will follow the stepped care approach. The researchers will contact participants in the trial after 6, 12 and 18 months to see if their mood and quality of life has improved. The researchers will also interview therapists and participants to see what they think about treatment being guided by the StratCare tool.
Hypotheses:
* Stratified care will result in lower mean depression scores compared to usual stepped care (USC). * Stratified care will result in a statistically significant higher proportion of cases with reliable and clinically significant improvement in depression symptoms, compared to USC.
Primary Outcome:
Depressive symptoms, as measured by change on the Patient Health Questionnaire (PHQ-9), at 12 months post-enrolment.
18 years of age or older.
Patients who consent to share their de-identified clinical records for research purposes.
Patients assessed as eligible for psychological care in Talking Therapies based on clinical guidelines.
Patients with case-level depression symptoms (PHQ-9 ≥ 10).
None
Parallel
StratCare
DeviceThe StratCare app is a technology that collects data, processes inputs using a machine learning algorithm, and outputs a personalised treatment recommendation using automated decision rules. The inputs for the algorithm include patient-reported measures of depression, anxiety, functional impairment, personality traits, employment status and ethnic background. The algorithm calculates an expected prognosis (i.e., a probability of full remission of depression and anxiety symptoms after treatment), based on which patients are classified as standard (better expected prognosis) or complex cases. Standard cases are matched to low-intensity treatments and later have the option to move to high-intensity, whereas complex cases are matched directly to high-intensity treatments. In addition, the StratCare app is programmed to implement decision rules that ensure compliance with national clinical guidelines for the treatment allocation of patients with specific disorders.
Change in depressive symptoms from enrolment, as measured by the Patient Health Questionnaire (PHQ-9)
The PHQ-9 is a brief measure of depression symptoms, where each of 9 items is rated on a Likert scale from 0 to 3 representing symptom frequency in the last two weeks, yielding an overall severity score between 0 and 27. The cut-off ≥10 is recommended to screen for clinically significant depression symptoms, and a change of ≥6 points is indicative of statistically reliable change. The PHQ-9 has been extensively validated in primary care populations, with adequate sensitivity (88%) and specificity (88%) estimates for the detection of major depressive disorder using a cut-off score ≥10.
Change in anxiety symptoms from enrolment, as measured by the Generalised Anxiety Disorder Questionnaire (GAD-7)
GAD-7 is a seven-item measure of common anxiety symptoms. Each item is scored on a 0-3 scale and these are summed to give an overall severity rating (range 0-21). The GAD-7 has been found to be a reliable screening tool for anxiety disorders such as generalised anxiety, social phobia, post-traumatic stress and panic disorder. A cut-off score ≥8 in this measure has been shown to detect an anxiety disorder with adequate sensitivity (77%) and specificity (82%).
Change in Quality of Life (to derive Quality Adjusted Life Years) from enrolment, as measured by the EQ-5D-5L
The 5-level EQ-5D (EQ-5D-5L) measure is commonly used to derive Quality Adjusted Life Years (QALYs) in healthcare research and to ensure that cost-effectiveness analyses are comparable to other studies and health technologies. Each of the five domain items is rated on a five-point scale from 'no problems' to 'extreme problems', giving a five-digit number describing the patients' health state. Patient responses will be converted into utility values using UK population tariff. Self-rated health is measured on a visual analogue scale from 0-100, with 100 being 'the best health you can imagine'. We will use the validated mapping function to derive utility values for the EQ-5D-5L questionnaire. QALYs will be calculated using the trapezoidal rule for calculating the area-under-the-curve, from baseline to the 18-month follow-up.
Change in Quality of Life from enrolment, as measured by the Recovering Quality of Life Scale 10 item version (ReQoL-10)
The ReQoL-10 was informed by contributions of \>6,000 mental health service users. It has been developed specifically to assess quality of life in people with different mental health conditions and consists of 10 mental health questions and one physical health question. Each item is scored on a 0-4 scale and the 10 mental health scores are summed to give an overall score (range 0-40, 0 being poorest quality of life, 40 highest). A score of 24 or lower is considered as falling within the clinical range. An advantage of the ReQol-10 is that it captures a broad range of domains including meaningful activity, belonging and relationships, control and autonomy, hope, self-perception, well-being, and physical health.
Resource use across the trial duration, measured using an adapted Adult Service Use Schedule (AD-SUS)
Resource use data will include the following: (a) primary care consultations (e.g. appointments with physician and nurse practitioners); (b) Talking Therapies resource use (i.e. number of sessions at each step along the stepped care pathway - this is routinely collected for all Talking Therapies patients); (c) use of other mental health services (e.g. consultations with psychologists, psychiatrists, community psychiatric nurse); (d) hospital visits (e.g. emergency department visits, outpatient appointments and inpatient admissions); (e) use of medications; and (f) contacts with social care (e.g. social worker, home care worker, outreach worker).
Click on the lead sponsor to view all of their trials.
Rotherham Doncaster and South Humber NHS Foundation Trust
Lead sponsor
University of Sheffield
Collaborator
FSA Research Consulting Inc
Collaborator
