1
|
Walter U, Pennig S, Kottmann T, Bleckmann L, Röschmann-Doose K, Schlee W. Randomized controlled trial of a smartphone-based cognitive behavioral therapy for chronic tinnitus. PLOS DIGITAL HEALTH 2023; 2:e0000337. [PMID: 37676883 PMCID: PMC10484427 DOI: 10.1371/journal.pdig.0000337] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/17/2022] [Accepted: 07/25/2023] [Indexed: 09/09/2023]
Abstract
Tinnitus, the phantom perception of sounds, generates distress and anxiety in those affected. Cognitive behavioral treatment approaches reproducibly help patients in managing chronic tinnitus. This study systematically evaluated the usefulness of a tinnitus app (with areas of attention and relaxation, mindfulness, acceptance, self-efficacy), which is prescribed for a total of nine months. One hundred eighty-seven participants with chronic tinnitus were equally randomized to an intervention arm that used a smartphone-based intervention -marketed as Kalmeda Tinnitus app-. and a control arm with delayed onset of treatment by 3 months. The first 3 months of a 9-months prescribed intervention have been analyzed as primary outcome. The Tinnitus Questionnaire (TQ) was used as primary endpoint to determine the reduction of tinnitus distress. Following intervention, there was a statistically significant and clinically relevant reduction of the TQ sum score in the intervention group compared to the control group (p<0.001, Cohen's d effect size = 1.1). The secondary parameters, Patient Health Questionnaire-9 (PHQ9) and Perceived-Stress-Questionnaire (PSQ20) scores improved significantly in the intervention group whereas the Self Efficacy-Optimism-Pessimism short form (SWOP-K9) scores remained unchanged in both groups. Patients reported no treatment-related side effects. Taken together, use of this Tinnitus app lead to a significant decrease in tinnitus distress and a clinically relevant effect in the patients´ self-reported everyday management.
Collapse
Affiliation(s)
- Uso Walter
- ENT Practice Walter & Zander, Duisburg and mynoise GmbH, Duisburg, Germany
| | | | | | | | | | - Winfried Schlee
- Eastern Switzerland University of Applied Sciences, St. Gallen, Switzerland
- Clinic and Polyclinic for Psychiatry and Psychotherapy, University of Regensburg, Regensburg, Germany
| |
Collapse
|
2
|
Rodrigo H, Beukes EW, Andersson G, Manchaiah V. Predicting the Outcomes of Internet-Based Cognitive Behavioral Therapy for Tinnitus: Applications of Artificial Neural Network and Support Vector Machine. Am J Audiol 2022; 31:1167-1177. [PMID: 36215687 PMCID: PMC9907438 DOI: 10.1044/2022_aja-21-00270] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022] Open
Abstract
PURPOSE Internet-based cognitive behavioral therapy (ICBT) has been found to be effective for tinnitus management, although there is limited understanding about who will benefit the most from ICBT. Traditional statistical models have largely failed to identify the nonlinear associations and hence find strong predictors of success with ICBT. This study aimed at examining the use of an artificial neural network (ANN) and support vector machine (SVM) to identify variables associated with treatment success in ICBT for tinnitus. METHOD The study involved a secondary analysis of data from 228 individuals who had completed ICBT in previous intervention studies. A 13-point reduction in Tinnitus Functional Index (TFI) was defined as a successful outcome. There were 33 predictor variables, including demographic, tinnitus, hearing-related and treatment-related variables, and clinical factors (anxiety, depression, insomnia, hyperacusis, hearing disability, cognitive function, and life satisfaction). Predictive models using ANN and SVM were developed and evaluated for classification accuracy. SHapley Additive exPlanations (SHAP) analysis was used to identify the relative predictor variable importance using the best predictive model for a successful treatment outcome. RESULTS The best predictive model was achieved with the ANN with an average area under the receiver operating characteristic value of 0.73 ± 0.03. The SHAP analysis revealed that having a higher education level and a greater baseline tinnitus severity were the most critical factors that influence treatment outcome positively. CONCLUSIONS Predictive models such as ANN and SVM help predict ICBT treatment outcomes and identify predictors of outcome. However, further work is needed to examine predictors that were not considered in this study as well as to improve the predictive power of these models. SUPPLEMENTAL MATERIAL https://doi.org/10.23641/asha.21266487.
Collapse
Affiliation(s)
- Hansapani Rodrigo
- School of Mathematical and Statistical Sciences, University of Texas Rio Grande Valley, Edinburg,Virtual Hearing Lab, Collaborative initiative between Lamar University, Beaumont, TX, and University of Pretoria, South Africa
| | - Eldré W. Beukes
- Virtual Hearing Lab, Collaborative initiative between Lamar University, Beaumont, TX, and University of Pretoria, South Africa,Vision and Hearing Sciences Research Centre, School of Psychology and Sport Science, Anglia Ruskin University, Cambridge, United Kingdom
| | - Gerhard Andersson
- Department of Behavioral Sciences and Learning, Department of Biomedical and Clinical Sciences, Linköping University, Sweden,Department of Clinical Neuroscience, Division of Psychiatry, Karolinska Institute, Stockholm, Sweden
| | - Vinaya Manchaiah
- Virtual Hearing Lab, Collaborative initiative between Lamar University, Beaumont, TX, and University of Pretoria, South Africa,Department of Otolaryngology–Head and Neck Surgery, University of Colorado School of Medicine, Aurora,UCHealth Hearing and Balance, University of Colorado Hospital, Aurora,Department of Speech-Language Pathology and Audiology, University of Pretoria, South Africa,Department of Speech and Hearing, School of Allied Health Sciences, Manipal, India
| |
Collapse
|
3
|
Beukes EW, Andersson G, Manchaiah V. Patient Uptake, Experiences, and Process Evaluation of a Randomized Controlled Trial of Internet-Based Cognitive Behavioral Therapy for Tinnitus in the United States. Front Med (Lausanne) 2021; 8:771646. [PMID: 34869490 PMCID: PMC8635963 DOI: 10.3389/fmed.2021.771646] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2021] [Accepted: 10/04/2021] [Indexed: 11/21/2022] Open
Abstract
Introduction: An internet-based cognitive behavioral therapy (ICBT) offers a way to increase access to evidence-based tinnitus care. To increase the accessibility of this intervention, the materials were translated into Spanish to reach Spanish as well as English speakers. A clinical trial indicated favorable outcomes of ICBT for tinnitus for the population of the United States. In view of later dissemination, a way to increase the applicability of this intervention is required. Such understanding is best obtained by considering the perspectives and experiences of participants of an intervention. This study aimed to identify the processes that could facilitate or hinder the clinical implementation of ICBT in the United States. Methods: This study evaluated the processes regarding enrolment, allocation, intervention delivery, the outcomes obtained, and the trial implementation. The study sample consisted of 158 participants who were randomly assigned to the experimental and control group. Results: Although the recruitment was sufficient for English speakers, recruiting the Spanish participants and participants belonging to ethnic minority groups was difficult despite using a wide range of recruitment strategies. The allocation processes were effective in successfully randomizing the groups. The intervention was delivered as planned, but not all the participants chose to engage with the materials provided. Compliance for completing the outcome measures was low. The personal and intervention factors were identified as barriers for the implementation whereas the facilitators included the support received, being empowering, the accessibility of the intervention, and its structure. Conclusion: An understanding regarding the factors contributing to the outcomes obtained, the barriers and facilitators of the results, engagement, and compliance were obtained. These insights will be helpful in preparing for the future dissemination of such interventions. Clinical Trial Registration: www.ClinicalTrials.gov, identifier: NCT04004260. Registered on 2 July 2019.
Collapse
Affiliation(s)
- Eldre W. Beukes
- Department of Speech and Hearing Sciences, Lamar University, Beaumont, TX, United States
- Vision and Hearing Sciences Research Centre, School of Psychology and Sport Sciences, Anglia Ruskin University, Cambridge, United Kingdom
- Virtual Hearing Lab, a Collaborative Initiative Between Lamar University, Beaumont, TX, United States, and the University of Pretoria, Pretoria, South Africa
| | - Gerhard Andersson
- Department of Behavioral Sciences and Learning, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
- Division of Psychiatry, Department of Clinical Neuroscience, Karolinska Institute, Stockholm, Sweden
| | - Vinaya Manchaiah
- Department of Speech and Hearing Sciences, Lamar University, Beaumont, TX, United States
- Virtual Hearing Lab, a Collaborative Initiative Between Lamar University, Beaumont, TX, United States, and the University of Pretoria, Pretoria, South Africa
- Department of Speech-Language Pathology and Audiology, University of Pretoria, Pretoria, South Africa
- Department of Speech and Hearing, School of Allied Health Sciences, Manipal Academy of Higher Education, Manipal, India
| |
Collapse
|
4
|
Rodrigo H, Beukes EW, Andersson G, Manchaiah V. Exploratory Data Mining Techniques (Decision Tree Models) for Examining the Impact of Internet-Based Cognitive Behavioral Therapy for Tinnitus: Machine Learning Approach. J Med Internet Res 2021; 23:e28999. [PMID: 34726612 PMCID: PMC8596228 DOI: 10.2196/28999] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2021] [Revised: 08/29/2021] [Accepted: 09/12/2021] [Indexed: 01/07/2023] Open
Abstract
Background There is huge variability in the way that individuals with tinnitus respond to interventions. These experiential variations, together with a range of associated etiologies, contribute to tinnitus being a highly heterogeneous condition. Despite this heterogeneity, a “one size fits all” approach is taken when making management recommendations. Although there are various management approaches, not all are equally effective. Psychological approaches such as cognitive behavioral therapy have the most evidence base. Managing tinnitus is challenging due to the significant variations in tinnitus experiences and treatment successes. Tailored interventions based on individual tinnitus profiles may improve outcomes. Predictive models of treatment success are, however, lacking. Objective This study aimed to use exploratory data mining techniques (ie, decision tree models) to identify the variables associated with the treatment success of internet-based cognitive behavioral therapy (ICBT) for tinnitus. Methods Individuals (N=228) who underwent ICBT in 3 separate clinical trials were included in this analysis. The primary outcome variable was a reduction of 13 points in tinnitus severity, which was measured by using the Tinnitus Functional Index following the intervention. The predictor variables included demographic characteristics, tinnitus and hearing-related variables, and clinical factors (ie, anxiety, depression, insomnia, hyperacusis, hearing disability, cognitive function, and life satisfaction). Analyses were undertaken by using various exploratory machine learning algorithms to identify the most influencing variables. In total, 6 decision tree models were implemented, namely the classification and regression tree (CART), C5.0, GB, XGBoost, AdaBoost algorithm and random forest models. The Shapley additive explanations framework was applied to the two optimal decision tree models to determine relative predictor importance. Results Among the six decision tree models, the CART (accuracy: mean 70.7%, SD 2.4%; sensitivity: mean 74%, SD 5.5%; specificity: mean 64%, SD 3.7%; area under the receiver operating characteristic curve [AUC]: mean 0.69, SD 0.001) and gradient boosting (accuracy: mean 71.8%, SD 1.5%; sensitivity: mean 78.3%, SD 2.8%; specificity: 58.7%, SD 4.2%; AUC: mean 0.68, SD 0.02) models were found to be the best predictive models. Although the other models had acceptable accuracy (range 56.3%-66.7%) and sensitivity (range 68.6%-77.9%), they all had relatively weak specificity (range 31.1%-50%) and AUCs (range 0.52-0.62). A higher education level was the most influencing factor for ICBT outcomes. The CART decision tree model identified 3 participant groups who had at least an 85% success probability following the undertaking of ICBT. Conclusions Decision tree models, especially the CART and gradient boosting models, appeared to be promising in predicting ICBT outcomes. Their predictive power may be improved by using larger sample sizes and including a wider range of predictive factors in future studies.
Collapse
Affiliation(s)
- Hansapani Rodrigo
- School of Mathematical and Statistical Sciences, University of Texas Rio Grande Valley, Edinburgh, TX, United States.,Virtual Hearing Lab, Beaumont, TX, United States
| | - Eldré W Beukes
- Virtual Hearing Lab, Beaumont, TX, United States.,Department of Speech and Hearing Sciences, Lamar University, Beaumont, TX, United States.,Department of Vision and Hearing Sciences, School of Psychology and Sport Science, Anglia Ruskin University, Cambridge, United Kingdom
| | - Gerhard Andersson
- Department of Behavioral Sciences and Learning, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden.,Department of Clinical Neuroscience, Division of Psychiatry, Karolinska Institute, Stockholm, Sweden
| | - Vinaya Manchaiah
- Virtual Hearing Lab, Beaumont, TX, United States.,Department of Speech and Hearing Sciences, Lamar University, Beaumont, TX, United States.,Department of Speech and Hearing, School of Allied Health Sciences, Manipal Academy of Higher Education, Karnataka, India.,Department of Speech-Language Pathology and Audiology, University of Pretoria, Gauteng, South Africa
| |
Collapse
|