The role of pre-existing knowledge and knowledge acquisition in internet-based cognitive-behavioural therapy for eating disorders
- Authors: Linardon, Jake , Broadbent, Jaclyn , Shatte, Adrian , Fuller-Tyszkiewicz, Matthew
- Date: 2022
- Type: Text , Journal article
- Relation: Computers in Human Behavior Vol. 134, no. (2022), p.
- Full Text: false
- Reviewed:
- Description: Knowledge is a relevant concept in internet-based cognitive-behaviour therapy (I-CBT), yet little research has sought to understand the role of knowledge in I-CBT for eating disorders. This study addressed this gap. Data were analysed from 293 participants enrolled in a RCT of I-CBT for eating disorder symptoms. A test assessing knowledge of CBT principles and eating disorders was administered before and after I-CBT. Participants had high knowledge to begin with, correctly answering 72% of items. A significant increase in knowledge scores and knowledge confidence was observed after ICBT. While no relationship between the degree of knowledge gain and the degree of symptom improvement emerged, an increase in confidence in one's knowledge was associated with greater symptom improvement. Higher baseline knowledge levels predicted lower likelihood of drop-out and a higher likelihood of adherence, but were unrelated to symptom-level improvement. Findings suggest that while new knowledge can be acquired through I-CBT, the degree of knowledge gain alone is not sufficient to explain improvement in symptoms. Pre-existing knowledge levels may be an important prognostic indicator of patient progress and compliance to I-CBT. Ensuring that patients can correctly apply the key I-CBT skills may be more important than knowledge gain. © 2022 Elsevier Ltd
Classification of Twitter users with eating disorder engagement : learning from the biographies
- Authors: Abuhassan, Mohammad , Anwar, Tarique , Fuller-Tyszkiewicz, Matthew , Jarman, Hannah , Shatte, Adrian , Liu, Chengfei , Sukunesan, Suku
- Date: 2023
- Type: Text , Journal article
- Relation: Computers in Human Behavior Vol. 140, no. (2023), p.
- Full Text: false
- Reviewed:
- Description: Individuals with an Eating Disorder (ED) are typically reluctant to seek help via traditional means (e.g., psychologists). However, recent evidence suggests that many individuals seek assistance via social media for weight and diet related concerns. Sophisticated approaches are needed to better distinguish those who may be in need of help for an ED from those who are simply commenting on ED in online social environments. In order to facilitate effective communication between individuals with or at-risk of an ED and healthcare professionals, this research exploits a deep learning model to differentiate the users with ED engagement (e.g., ED sufferers, healthcare professionals or communicators) over social media. For this purpose, a collection of Twitter data is compiled using Twitter application programming interface (API) on the Australian Research Data Commons (ARDC) Nectar research cloud. After collecting 1,400,000 Twitter biographies in total, a subset of 4000 biographies are annotated manually. This annotation enables the differentiation of users engaged with ED-focused language on social media into five categories: ED-user, healthcare professional, communicator, healthcare professional-communicator, and other. Based on these annotated categories, a predictive deep learning model based on bidirectional encoder representations from transformers (BERT) and long short-term memory (LSTM) is developed. The model achieves an F1 score of 98.19% and an accuracy of 98.37%. It demonstrates the viability of detecting the individuals with possible ED risk and distinguishes them from other categories using their biography data. We further conducted a network analysis for investigating the communication network between these categories. Our analysis shows that ED-users are more secretive and self-protective, whereas the healthcare professionals and communicators frequently interact with each other and a wide range of other people. To the best of our knowledge, our research is the first of its kind for identifying the different user categories engaged with ED-focused communications on social media. © 2022
Effects of participant's choice of different digital interventions on outcomes for binge-spectrum eating disorders : a pilot doubly randomized preference trial
- Authors: Linardon, Jake , Shatte, Adrian , Messer, Mariel , McClure, Zoe , Fuller-Tyszkiewicz, Matthew
- Date: 2023
- Type: Text , Journal article
- Relation: Behavior Therapy Vol. 54, no. 2 (2023), p. 303-314
- Full Text: false
- Reviewed:
- Description: It is unclear whether offering individuals a choice between different digital intervention programs affects treatment outcomes. To generate initial insights, we conducted a pilot doubly randomized preference trial to test whether offering individuals with binge-spectrum eating disorder a choice between two digital interventions is causally linked with superior outcomes than random assignment to these interventions. Participants with recurrent binge eating were randomized to either a choice (n = 77) or no-choice (n = 78) group. Those in the choice group could choose one of the two digital programs, while those in the no-choice group were assigned a program at random. The two digital interventions (a broad and a focused program) took 4 weeks to complete, were based on cognitive-behavioral principles and have demonstrated comparable efficacy, but differ in scope, content, and targeted change mechanisms. Most participants (79%) allocated to the choice condition chose the broad program. While both groups experienced improvements in primary (Eating Disorder Examination Questionnaire global scores and number of binge eating episodes over the past month) and secondary outcomes (dietary restraint, body image concerns, etc.), no significant between-group differences were observed. The two groups did not differ on dropout rates, nor on most indices of intervention engagement. Findings provide preliminary insights towards the role of client preferences in digital mental health interventions for eating disorders. Client preferences may not determine outcomes when digital interventions are based on similar underlying principles, although larger trials are needed to confirm this. © 2023