scholarly journals Using Artificial Intelligence to Predict Change in Depression and Anxiety Symptoms in a Digital Intervention: Evidence from a Transdiagnostic Randomized Controlled Trial

2021 ◽  
Vol 295 ◽  
pp. 113618
Author(s):  
Nicholas C. Jacobson ◽  
Matthew D. Nemesure
2020 ◽  
Author(s):  
Maria Carolina Klos ◽  
Milagros Escoredo ◽  
Angie Joerin ◽  
Viviana Noemí Lemos ◽  
Michiel Rauws ◽  
...  

BACKGROUND The use of artificial intelligence based chatbots as an instrument of psychological intervention is emerging, however no studies have been reported in Latin America. OBJECTIVE This study aims to evaluate usage patterns and whether the use of a chatbot is effective for relieving depression and anxiety symptoms compared to a control group utilizing a psychoeducation book in Argentina. METHODS This was a randomized controlled trial study utilizing the chabot Tess throughout eight weeks. The initial sample consisted of 181 Argentinian college students ages 18 to 33, 87.2% female. Of those, 33 participants in the experimental condition and 30 in the control condition provided data on depressive symptoms at week eight, and 27 participants in the experimental condition and 23 in the control condition provided data on anxiety symptoms at week eight. Between and within group comparisons were analysed using Mann-Whitney U and Wilcoxon tests for depression symptoms, and Independent and Paired Samples t Tests to analyze anxiety symptoms. RESULTS There was no significant intergroup differences between the experimental group and the control group for depression and anxiety symptoms from baseline to week eight (P>.05). However, there were significant intragroup differences, where the experimental group showed a significant decrease in anxiety symptoms (P=.04) and no differences were observed for the control group (P=.33). No significant differences were found for depressive symptoms within the groups (P>.05). The effect size of the intervention was moderate for anxiety (d=.50) and small for depression (r=.09). In regards to participants engagement after eight weeks, there was an average of 472 exchanged messages (M=472.15; SD=249.52) and a higher number of messages exchanged with Tess was associated with positive feedback (F2,36=4.37; P=.02). CONCLUSIONS Students engaged a considerable amount of time exchanging messages with Tess and positive feedback was associated with higher numbers of messages exchanged. The initial results show promising evidence for the use of Tess for anxiety symptoms and a lower effect on depressive symptoms in Argentinian college students. Research on chatbots is still in its initial stages and further research is needed.


Healthcare ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 659
Author(s):  
Marouane Nassim ◽  
Haley Park ◽  
Elena Dikaios ◽  
Angela Potes ◽  
Sasha Elbaz ◽  
...  

Background: Between 20–50% of patients undergoing maintenance dialysis for end-stage kidney disease experience symptoms of depression and/or anxiety, associated with increased mortality, greater health care utilization, and decreased quality of life. It is unknown whether mindfulness-based interventions can improve depression and anxiety symptoms in patients receiving this treatment. Methods: We conducted an 8-week multicenter randomized controlled trial comparing a brief mindfulness intervention (BMI) vs. an active control (Health Enhancement Program [HEP]) in 55 patients receiving dialysis with symptoms of depression and/or anxiety. The primary outcome was change in Patient Health Questionnaire-9 (PHQ-9) depression scores, with a primary analysis in participants with baseline PHQ-9 ≥ 10, and a secondary analysis including all participants. The secondary outcome was change in Generalized Anxiety Disorder-7 (GAD-7) anxiety scores with corresponding primary and secondary analyses. Results: Both BMI and HEP reduced depressive symptoms, with no difference between trial arms (PHQ-9 change = −7.0 vs. −6.1, p = 0.62). BMI was more effective than HEP in reducing anxiety (GAD-7 change = −8.7 vs. −1.4, p = 0.01). Secondary analyses revealed no differences between arms. Conclusions: For patients undergoing dialysis, both BMI and HEP may be helpful interventions for depression symptoms, and BMI may be superior to HEP for anxiety symptoms. Mindfulness-based and other psychosocial interventions may be further evaluated in those undergoing dialysis as treatment options for symptoms of depression and anxiety.


2019 ◽  
Author(s):  
Tayla McCloud ◽  
Rebecca Jones ◽  
Gemma Lewis ◽  
Vaughan Bell ◽  
Elias Tsakanikos

BACKGROUND Depression and anxiety symptoms are common among university students, but many do not receive treatment. This is often because of lack of availability, reluctance to seek help, and not meeting the diagnostic criteria required to access services. Internet-based interventions, including smartphone apps, can overcome these issues. However, a large number of apps are available, each with little evidence of their effectiveness. OBJECTIVE This study aims to evaluate for the first time the effectiveness of a self-guided mobile app, Feel Stress Free, for the treatment of depression and anxiety symptoms in students. METHODS A web-based randomized controlled trial compared a cognitive behavioral therapy (CBT)–based mobile app Feel Stress Free with a wait-list control. University students self-identified as experiencing symptoms of anxiety or depression and were randomized to 6 weeks of intervention (n=84) or control (n=84), unblinded. The app is self-guided and incorporates behavioral relaxation activities, mood tracking and thought challenging, and minigames. Participants completed the Hospital Anxiety and Depression Scale online at baseline and every fortnight. RESULTS At week 6, the primary end point, there was evidence that the Feel Stress Free app reduced depression symptoms (mean difference −1.56; 95% CI −2.67 to −0.44; <i>P</i>=.006) but only very weak evidence that it reduced anxiety symptoms (mean difference −1.36; 95% CI −2.93 to 0.21; <i>P</i>=.09). At week 4, there was evidence to support the effectiveness of the intervention for anxiety symptoms (mean difference −1.94; 95% CI −3.11 to −0.77; <i>P</i>=.001) and, though weaker, depression symptoms (mean difference −1.08; 95% CI −2.12 to −0.04; <i>P</i>=.04). At week 6, 83% (34/41) of participants indicated that they were using the app weekly or more frequently. CONCLUSIONS The Feel Stress Free app is a promising mobile intervention for treating symptoms of anxiety and depression in students and overcomes many of the barriers to traditional CBT. Further research is needed to establish its effectiveness at and beyond 6 weeks. CLINICALTRIAL ClinicalTrials.gov NCT03032952; https://clinicaltrials.gov/ct2/show/NCT03032952


10.2196/15418 ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. e15418
Author(s):  
Tayla McCloud ◽  
Rebecca Jones ◽  
Gemma Lewis ◽  
Vaughan Bell ◽  
Elias Tsakanikos

Background Depression and anxiety symptoms are common among university students, but many do not receive treatment. This is often because of lack of availability, reluctance to seek help, and not meeting the diagnostic criteria required to access services. Internet-based interventions, including smartphone apps, can overcome these issues. However, a large number of apps are available, each with little evidence of their effectiveness. Objective This study aims to evaluate for the first time the effectiveness of a self-guided mobile app, Feel Stress Free, for the treatment of depression and anxiety symptoms in students. Methods A web-based randomized controlled trial compared a cognitive behavioral therapy (CBT)–based mobile app Feel Stress Free with a wait-list control. University students self-identified as experiencing symptoms of anxiety or depression and were randomized to 6 weeks of intervention (n=84) or control (n=84), unblinded. The app is self-guided and incorporates behavioral relaxation activities, mood tracking and thought challenging, and minigames. Participants completed the Hospital Anxiety and Depression Scale online at baseline and every fortnight. Results At week 6, the primary end point, there was evidence that the Feel Stress Free app reduced depression symptoms (mean difference −1.56; 95% CI −2.67 to −0.44; P=.006) but only very weak evidence that it reduced anxiety symptoms (mean difference −1.36; 95% CI −2.93 to 0.21; P=.09). At week 4, there was evidence to support the effectiveness of the intervention for anxiety symptoms (mean difference −1.94; 95% CI −3.11 to −0.77; P=.001) and, though weaker, depression symptoms (mean difference −1.08; 95% CI −2.12 to −0.04; P=.04). At week 6, 83% (34/41) of participants indicated that they were using the app weekly or more frequently. Conclusions The Feel Stress Free app is a promising mobile intervention for treating symptoms of anxiety and depression in students and overcomes many of the barriers to traditional CBT. Further research is needed to establish its effectiveness at and beyond 6 weeks. Trial Registration ClinicalTrials.gov NCT03032952; https://clinicaltrials.gov/ct2/show/NCT03032952


Sign in / Sign up

Export Citation Format

Share Document