Predicting relapse of depression and anxiety after Cognitive Behavioural Therapy
Lead Research Organisation:
University of Sheffield
Department Name: Psychology
Abstract
The sample will consist of 300 adults who have undergone CBT recently. The participants will be recruited via multiple IAPT (i.e. Improving Access to Psychological Therapies) psychological therapy services that offer CBT for depression and anxiety. These services are associated with a practice research network that has a history of collecting data from CBT clients ("Northern IAPT Practice Research Network", n.d.).
Organisations
People |
ORCID iD |
| Jaime Delgadillo (Primary Supervisor) | |
| Benjamin Lorimer (Student) |
Studentship Projects
| Project Reference | Relationship | Related To | Start | End | Student Name |
|---|---|---|---|---|---|
| ES/P000746/1 | 01/10/2017 | 30/09/2027 | |||
| 1939177 | Studentship | ES/P000746/1 | 01/10/2017 | 07/10/2021 | Benjamin Lorimer |
| Description | We found that adopting a machine learning approach can help facilitate the prediction of relapse of depression and anxiety after low-intensity cognitive behavioural therapy in psychotherapy services. Predictive indices of the developed models indicated adequate prognostic value in the context of mental healthcare, and show potential for the use of this methodology to enable improved estimations of relapse risk. The developed models also identified young age, unemployment, and higher post-treatment symptoms as being important risk factors for relapse. Unemployment in particular was a highly potent risk factor, with almost every single unemployed patient in one study being found to relapse. However, replications with larger samples are required, and investigations into relapse following high-intensity CBT are also needed. |
| Exploitation Route | The findings from our research are directly relevant to therapists, mental health practitioners, and mangers of psychotherapy services. Relapse is a major problem in mental healthcare, and it is important to attempt to prevent its occurrence. An understanding of what patients are at risk of relapse could allow for these patients to be targeted with relapse prevention interventions. Prognostic models, similar to those developed in our research, could be applied in services to identify these "at-risk" individuals. Furthermore, awareness of individual risk factors (young age, unemployment, higher post-treatment symptoms) could guide how therapists focus on and provide their relapse prevention within-sessions. |
| Sectors | Healthcare |