| 1. |
- Gogoulou, Evangelia, et al.
(author)
-
Predicting treatment outcome from patient texts : The case of internet-based cognitive behavioural therapy
- 2021
-
In: EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. - : Association for Computational Linguistics (ACL). - 9781954085022 ; , s. 575-580
-
Conference paper (peer-reviewed)abstract
- We investigate the feasibility of applying standard text categorisation methods to patient text in order to predict treatment outcome in Internet-based cognitive behavioural therapy. The data set is unique in its detail and size for regular care for depression, social anxiety, and panic disorder. Our results indicate that there is a signal in the depression data, albeit a weak one. We also perform terminological and sentiment analysis, which confirm those results. © 2021 Association for Computational Linguistics
|
|
| 2. |
- Carlbring, Per, et al.
(author)
-
Consensus statement on defining and measuring negative effects of Internet interventions
- 2014
-
Conference paper (peer-reviewed)abstract
- Background: Internet interventions have great potential for alleviating emotional distress, promoting mental health, and enhancing well-being. Numerous clinical trials have demonstrated their effectiveness for a number of psychiatric conditions, and interventions delivered via the Internet will likely become a common alternative to face-to-face treatment. Meanwhile, research has paid little attention to the negative effects associated with treatment, warranting further investigation of the possibility that some patients might deteriorate or encounter adverse events despite receiving best available care. Evidence from research of face-to-face treatment suggests that negative effects afflict 5-10% of all patients undergoing treatment in terms of deterioration.Objective: There is currently a lack of consensus on how to define and measure negative effects in psychotherapy research in general, leaving researchers without practical guidelines for monitoring and reporting negative effects in clinical trials. The current study therefore sought out to provide recommendations that could promote the study of negative effects in Internet interventions with the aim of increasing the knowledge of its occurrence and characteristics.Methods: Ten experts in the field of Internet interventions were invited to participate and share their perspective on how to explore negative effects, using the Delphi technique to facilitate a dialogue and reach an agreement. The authors discuss the importance of conducting research on negative effects in order to further the understanding of its incidence and different features.Results: Suggestions on how to classify and measure negative effects in Internet interventions are proposed, involving methods from both quantitative and qualitative research. Potential mechanisms underlying negative effects are also discussed, differentiating common factors shared with face-to-face treatments from those unique to treatments delivered via the Internet.Conclusions: We conclude that negative effects are to be expected and need to be acknowledged to a greater extent, advising researchers to systematically probe for negative effects whenever conducting clinical trials involving Internet interventions, as well as to share their findings in scientific journals.
|
|
| 3. |
- Gervind, Elisabet, et al.
(author)
-
The transference of research results to practise: Organization and implementation outcomes of iCBT in primary care – a mixed methods study using the RE-AIM framework
- 2022
-
In: SWESRII 2022.
-
Conference paper (other academic/artistic)abstract
- Background: Healthcare systems all over the world are working in dynamic and resource-constrained contexts. Implementation science plays a critical role in ensuring that costly research results are implemented and improve public health. Implementation of iCBT in regular care has given mixed results and has rarely been documented on the basis of a scientific framework for implementation research. Aim: The overall aim of the present study is to contribute to knowledge about how iCBT can be implemented and organized in primary care. The current study also explores naturalistic variability in two different organizational formats, concentrated and decentralized. Method: A mixed quantitative-qualitative design was used to identify factors that impact the implementation of iCBT across multiple levels, including patient, therapists, leaders and organization. The scientific framework RE-AIM with the dimensions reach (those in the target group participating in the program), effectiveness (effects after completion of the program), adoption (actors who accept the program), implementation (compliance with the program according to protocol), maintenance (sustainability over time) was used to evaluate the implementation. Results: 104 primary care centres participated in the study. Outcomes on patient-data (n=1979) were gathered between 2018 and 2021 from the quality register SibeR. Fifty-four iCBT-therapists, answered the NoMAD-questionnaire and fifteen leaders were interviewed. The materials are currently being analysed.
|
|
| 4. |
- Mahdi, Soheil, et al.
(author)
-
Short ADHD intervention (SAINT) : Psychological treatment for adults with ADHD
- 2023
-
Conference paper (other academic/artistic)abstract
- Objectives: SAINT is based on previous research on a CBT manual for adults with ADHD, now shortened to 5 individual-sessions with a follow-up session one month after treatment. It will be compared to an established self-help manual for adults with ADHD, provided through internet. Will SAINT produce an increased everyday function measured with AAQoL compared to control group? If so, is the increased function related to a higher adherence to treatment methods and homework in SAINT?Methods: A randomized controlled study design is applied where SAINT is compared to an active control condition. Asessments are made before treatment, during treatment, immediately after treatment, one month and three months after treatment. Both groups receive treatment during five weeks with a booster session one month after the fifth session. Outcome measures include everyday function, quality of life and ADHD symptoms, among others. The study is conducted in a specialist health care clinic in Stockholm.Results: To date, 71 participants have been randomized to one of two treatment conditions. 20 more participants will be recruited during 2023 and the final results will be analyzed in early 2024. Preliminary data on the outcome measures will be presented at the ADHD World Congress.Conclusions: In case of promising results, SAINT could be offered to patients immediately after diagnosis, thus increasing access to CBT for adults with ADHD.
|
|
| 5. |
- Rozental, Alexander, et al.
(author)
-
Consensus statement on defining and measuring negative effects of Internet interventions
- 2014
-
In: Oral Abstracts from the 7th Scientific Meeting of the International Society for Research on Internet Interventions. ; , s. 39-39
-
Conference paper (other academic/artistic)abstract
- Purpose: Internet interventions provide a potential for promoting mental health and alleviating emotional distress. A large number of clinical trials have demonstrated their efficacy for several psychiatric conditions, and Internet interventions will likely become a common and valuable alternative within the regular health care. In the meantime, research has paid little attention to the possibility that some treatments might be associated with different types of negative effects. Evidence from face-to-face treatments suggests that 5-10% of all patients deteriorate despite receiving best available care. In addition, other forms of negative effects may exist as well, e.g., social stigmatization, interpersonal difficulties, and decreased self-esteem. However, a lack of agreement on how to define and measure negative effects has left researchers without practical guidelines for monitoring and reporting deterioration and adverse events in clinical trials, warranting a consensus for conducting research on negative effects.Method: The objective of the current paper is to provide recommendations that could promote the study of negative effects in Internet interventions. Ten leading experts in the field of Internet interventions were invited to participate and share their perspective on how to explore negative effects, using the Delphi technique to facilitate a dialogue and reach an agreement.Results: The importance of conducting further research on negative effects is discussed, and suggestions on how to classify and measure negative effects are provided, involving methods from quantitative and qualitative research. Potential mechanisms underlying negative effects are also presented, differentiating factors shared with face-to-face treatments from those unique to treatments delivered via the Internet.Conclusion: Negative effects should be expected and need to be recognized to a greater extent, and researchers are advised to systematically probe for negative effects whenever conducting clinical trials involving Internet interventions, as well as to share their findings in scientific journals.
|
|
| 6. |
- Safinianaini, Negar, et al.
(author)
-
Gated hidden markov models for early prediction of outcome of internet-based cognitive behavioral therapy
- 2019
-
In: 17th Conference on Artificial Intelligence in Medicine, AIME 2019. - Cham : Springer Verlag. - 9783030216412 - 9783030216429 ; , s. 160-169
-
Conference paper (peer-reviewed)abstract
- Depression is a major threat to public health and its mitigation is considered to be of utmost importance. Internet-based Cognitive Behavioral Therapy (ICBT) is one of the employed treatments for depression. However, for the approach to be effective, it is crucial that the outcome of the treatment is accurately predicted as early as possible, to allow for its adaptation to the individual patient. Hidden Markov models (HMMs) have been commonly applied to characterize systematic changes in multivariate time series within health care. However, they have limited capabilities in capturing long-range interactions between emitted symbols. For the task of analyzing ICBT data, one such long-range interaction concerns the dependence of state transition on fractional change of emitted symbols. Gated Hidden Markov Models (GHMMs) are proposed as a solution to this problem. They extend standard HMMs by modifying the Expectation Maximization algorithm; for each observation sequence, the new algorithm regulates the transition probability update based on the fractional change, as specified by domain knowledge. GHMMs are compared to standard HMMs and a recently proposed approach, Inertial Hidden Markov Models, on the task of early prediction of ICBT outcome for treating depression; the algorithms are evaluated on outcome prediction, up to 7 weeks before ICBT ends. GHMMs are shown to outperform both alternative models, with an improvement of AUC ranging from 12 to 23%. These promising results indicate that considering fractional change of the observation sequence when updating state transition probabilities may indeed have a positive effect on early prediction of ICBT outcome.
|
|
| 7. |
- Karlsson-Good, Magnus, 1988-, et al.
(author)
-
Increasing accessibility to iCBT for depression : A randomised controlled trial of condensed versus standard length treatment
- 2023
-
Conference paper (other academic/artistic)abstract
- Background: Research show that internet-based CBT (iCBT) is an effective treatment for depression. However, little is known about how length of treatment text material affect outcomes. Accessibility to treatment would improve if treatment could be presented with less text, especially for patients with ADHD symptoms and lower reading speed.Objective: The aim of this study was to test the hypothesis that a Condensed treatment would be non-inferior to a Full-length treatment. We further hypothesized that a Condensed treatment would be extra helpful for participants with a low reading speed and more ADHD symptoms.Method: A single-blind randomised controlled trial was conducted (N = 267) comparing two versions of guided iCBT for depression; Full-length (60 000 words) and Condensed (30 000 words). Estimated between-group effect sizes and their confidence intervals were compared to a pre-determined non-inferiority margin (Cohen’s d = 0.4). Moderation analyses of reading speed and ADHD symptoms were conducted, as well as comparisons of treatment engagement and knowledge acquisition.Results: The Condensed version of iCBT was non-inferior at endpoint for depressive symptoms, anxiety symptoms, and quality of life compared to the Full-length version. There was a significant interaction effect between reading speed and treatment version. No significant differences between the treatment versions were found on measures of treatment engagement or knowledge acquisition.Conclusion: A condensed version of iCBT for depression can be used with non-inferior results. A condensed treatment might be extra helpful for patients with lower reading speed. Given a high degree of missing data, these results need to be replicated.
|
|
