Detailed contribution information
| Contribution title | Advancing Pediatric OCD Treatment with AI: Decoding Therapy Processes for ERP Success |
|---|---|
| Contribution code | D2.004 |
| Authors | |
| Form of presentation | Poster |
| Topic |
|
| Abstract |
Aims: Machine learning (ML) and artificial intelligence (AI) hold great promise for advancing mental health care by improving therapy delivery through enhanced personalization and scalability. In the context of cognitive-behavioral therapy (CBT), particularly Exposure and Response Prevention (ERP) for pediatric obsessive-compulsive disorder (OCD), AI tools could help analyze therapy sessions, offering therapists valuable insights to better tailor care. To achieve this, a foundational understanding of the therapeutic processes driving successful outcomes is essential. This study aims to build that foundation by identifying and coding key behavioral and relational components of effective ERP. Methods: Videotaped ERP sessions from 64 children and adolescents aged 8–17 are being manually coded for critical therapeutic processes. The coding focuses on treatment-specific behaviors and relational dynamics between the child and therapist. These high-quality, human-coded datasets will serve as the foundation for train |