ABSTRACT
BACKGROUND: Internet-based interventions produce comparable effectiveness rates as face-to-face therapy in treating depression. Still, more than half of patients do not respond to treatment. Machine learning (ML) methods could help to overcome these low response rates by predicting therapy outcomes on an individual level and tailoring treatment accordingly. Few studies implemented ML algorithms in internet-based depression treatment using baseline self-report data, but differing results hinder inferences on clinical practicability. This work compares algorithms using features gathered at baseline or early in treatment in their capability to predict non-response to a 6-week online program targeting depression. METHODS: Our training and test sample encompassed 1270 and 318 individuals, respectively. We trained random forest algorithms on self-report and process features gathered at baseline and after 2 weeks of treatment. Non-responders were defined as participants not fulfilling the criteria for reliable and clinically significant change on PHQ-9 post-treatment. Our benchmark models were logistic regressions trained on baseline PHQ-9 sum or PHQ-9 early change, using 100 iterations of randomly sampled 80/20 train-test-splits. RESULTS: Best performances were reached by our models involving early treatment characteristics (recall: 0.75-0.76; AUC: 0.71-0.77). Therapeutic alliance and early symptom change constituted the most important predictors. Models trained on baseline data were not significantly better than our benchmark. CONCLUSIONS: Fair accuracies were only attainable by involving information from early treatment stages. In-treatment adaptation, instead of a priori selection, might constitute a more feasible approach for improving response when relying on easily accessible self-report features. Implementation trials are needed to determine clinical usefulness.
ABSTRACT
BACKGROUND: In blended therapy, face-to-face psychotherapy and Internet-based interventions are combined. Blended therapy may be advantageous for patients and psychotherapists. However, most blended interventions focus on cognitive behavioral therapy or single disorders, making them less suitable for routine care settings. METHODS: In a randomized controlled trial, we will compare blended therapy and face-to-face therapy in routine care. We intend to randomize 1152 patients nested in 231 psychotherapists in a 1:1 ratio. Patients in the blended therapy group will receive access to a therapeutic online intervention (TONI). TONI contains 12 transdiagnostic online modules suited for psychodynamic, cognitive behavioral, and systemic therapy. Psychotherapists decide which modules to assign and how to integrate TONI components into the psychotherapeutic process to tailor treatment to their patients' specific needs. We will assess patients at baseline, 6 weeks, 12 weeks, and 6 months. Patients enrolled early in the trial will also complete assessments at 12 months. The primary outcomes are depression and anxiety at 6-month post-randomization, as measured by PHQ-8 and GAD-7. The secondary outcomes include satisfaction with life, level of functioning, personality traits and functioning, eating pathology, sexual problems, alcohol/drug use, satisfaction with treatment, negative effects, and mental health care utilization. In addition, we will collect several potential moderators and mediators, including therapeutic alliance, agency, and self-efficacy. Psychotherapists will also report on changes in symptom severity and therapeutic alliance. Qualitative interviews with psychotherapists and patients will shed light on the barriers and benefits of the blended intervention. Furthermore, we will assess significant others of enrolled patients in a sub-study. DISCUSSION: The integration of online modules which use a common therapeutic language and address therapeutic principles shared across therapeutic approaches into regular psychotherapy has the potential to improve the effectiveness of psychotherapy and transfer it into everyday life as well help save therapists' resources and close treatment gaps. A modular and transdiagnostic setup of the blended intervention also enables psychotherapists to tailor their treatment optimally to the needs of their patients. TRIAL REGISTRATION: German Clinical Trials Register (DRKS) DRKS00028536. Registered on 07.06.2022.