scholarly journals Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-Based Therapy Sessions

10.2196/28244 ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. e28244
Author(s):  
Hannah A Burkhardt ◽  
George S Alexopoulos ◽  
Michael D Pullmann ◽  
Thomas D Hull ◽  
Patricia A Areán ◽  
...  
Keyword(s):  
Behavioral Activation ◽  
Depression Scale ◽  
Critical Factor ◽  
Longitudinal Assessment ◽  
Online Therapy ◽  
Online Chat ◽  
Patient Health ◽  
Automated Tools ◽  
Depression Symptomatology ◽  
Therapy Sessions

Background Behavioral activation (BA) is rooted in the behavioral theory of depression, which states that increased exposure to meaningful, rewarding activities is a critical factor in the treatment of depression. Assessing constructs relevant to BA currently requires the administration of standardized instruments, such as the Behavioral Activation for Depression Scale (BADS), which places a burden on patients and providers, among other potential limitations. Previous work has shown that depressed and nondepressed individuals may use language differently and that automated tools can detect these differences. The increasing use of online, chat-based mental health counseling presents an unparalleled resource for automated longitudinal linguistic analysis of patients with depression, with the potential to illuminate the role of reward exposure in recovery. Objective This work investigated how linguistic indicators of planning and participation in enjoyable activities identified in online, text-based counseling sessions relate to depression symptomatology over time. Methods Using distributional semantics methods applied to a large corpus of text-based online therapy sessions, we devised a set of novel BA-related categories for the Linguistic Inquiry and Word Count (LIWC) software package. We then analyzed the language used by 10,000 patients in online therapy chat logs for indicators of activation and other depression-related markers using LIWC. Results Despite their conceptual and operational differences, both previously established LIWC markers of depression and our novel linguistic indicators of activation were strongly associated with depression scores (Patient Health Questionnaire [PHQ]-9) and longitudinal patient trajectories. Emotional tone; pronoun rates; words related to sadness, health, and biology; and BA-related LIWC categories appear to be complementary, explaining more of the variance in the PHQ score together than they do independently. Conclusions This study enables further work in automated diagnosis and assessment of depression, the refinement of BA psychotherapeutic strategies, and the development of predictive models for decision support.

scholarly journals Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-Based Therapy Sessions (Preprint)

2021 ◽  
Author(s):  
Hannah A Burkhardt ◽  
George S Alexopoulos ◽  
Michael D Pullmann ◽  
Thomas D Hull ◽  
Patricia A Areán ◽  
...  
Keyword(s):  
Behavioral Activation ◽  
Depression Scale ◽  
Critical Factor ◽  
Longitudinal Assessment ◽  
Online Therapy ◽  
Online Chat ◽  
Patient Health ◽  
Automated Tools ◽  
Depression Symptomatology ◽  
Therapy Sessions

BACKGROUND Behavioral activation (BA) is rooted in the behavioral theory of depression, which states that increased exposure to meaningful, rewarding activities is a critical factor in the treatment of depression. Assessing constructs relevant to BA currently requires the administration of standardized instruments, such as the Behavioral Activation for Depression Scale (BADS), which places a burden on patients and providers, among other potential limitations. Previous work has shown that depressed and nondepressed individuals may use language differently and that automated tools can detect these differences. The increasing use of online, chat-based mental health counseling presents an unparalleled resource for automated longitudinal linguistic analysis of patients with depression, with the potential to illuminate the role of reward exposure in recovery. OBJECTIVE This work investigated how linguistic indicators of planning and participation in enjoyable activities identified in online, text-based counseling sessions relate to depression symptomatology over time. METHODS Using distributional semantics methods applied to a large corpus of text-based online therapy sessions, we devised a set of novel BA-related categories for the Linguistic Inquiry and Word Count (LIWC) software package. We then analyzed the language used by 10,000 patients in online therapy chat logs for indicators of activation and other depression-related markers using LIWC. RESULTS Despite their conceptual and operational differences, both previously established LIWC markers of depression and our novel linguistic indicators of activation were strongly associated with depression scores (Patient Health Questionnaire [PHQ]-9) and longitudinal patient trajectories. Emotional tone; pronoun rates; words related to sadness, health, and biology; and BA-related LIWC categories appear to be complementary, explaining more of the variance in the PHQ score together than they do independently. CONCLUSIONS This study enables further work in automated diagnosis and assessment of depression, the refinement of BA psychotherapeutic strategies, and the development of predictive models for decision support.

621 Association of E-cigarette and Tobacco Use with Adolescent Sleep Quality

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A244-A244
Author(s):  
Clare Malhotra ◽  
Deepti Gunge ◽  
Ira Advani ◽  
Shreyes Boddu ◽  
Sedtavut Nilaad ◽  
...  
Keyword(s):  
Sleep Quality ◽  
Sleep Duration ◽  
Sleep Latency ◽  
Depression Scale ◽  
Mean Difference ◽  
Dual Use ◽  
Safe Alternative ◽  
Wake Time ◽  
Patient Health ◽  
Targeted Marketing

Abstract Introduction Recently, targeted marketing has encouraged teen e-cigarette vaping. Although e-cigarettes are often presented as a safe alternative to conventional tobacco, their toxicity is unclear. In adults, we have previously observed a link between dual usage of e-cigarettes and tobacco with increased sleep latency. We hypothesized an association between dual usage and increased sleep latency. Methods Participants were recruited to complete social media surveys. We performed three surveys: Survey 1 (n=47) in 2018, Survey 2 (n=1198) in 2019, and Survey 3 (n=564) in 2020. Surveys 1 and 2 had three sections: past and current inhalant use, the Pittsburgh Sleep Quality Index (PSQI), and the Leicester Cough Questionnaire (LCQ). Survey 3 did not include the LCQ, instead including the Hospital Anxiety and Depression Scale (HADS) and Patient Health Questionnaire (PHQ9). The adolescent data (aged 13–20 years; n=609) were isolated. Results Adolescents reported an increase in sleep duration with increasing age by one-way ANOVA. Males reported no change with increasing age, while, by Tukey’s multiple comparisons test, females got significantly more sleep at ages 19 and 20 than at age 14(p<0.01). There was no significant correlation between inhalant use and sleep duration. When broken down by gender, female dual users slept more than female nonsmokers,(p=0.01; mean difference=43.8 minutes; CI=0.11 to 1.36), while there was no difference in males. We observed a significant association between inhalant use and sleep(p=0.0008), with dual use correlated with a longer sleep latency than nonsmokers (mean difference=6.27 minutes; CI=1.40 to 11.13. We saw no correlation between inhalant use and anxiety or depression, nor between inhalant use and cough severity and prevalence. Conclusion In female adolescents, we observed a peak in sleep hours at age 19 but significantly less sleep in fourteen-year olds. College-aged females may have a later wake time relative to middle-school and high-school aged females. Dual inhalant use in females was associated with a long sleep duration, raising concern for sleep disruption caused by dual use. Dual use’s association with increased sleep latency raises concern for nicotine-induced wakefulness. Further data are required in order to define public health strategies. Support (if any) LCA is supported by NIH.

Psychometric Properties of the Dutch Version of the Signs of Depression Scale

2016 ◽  
Vol 27 (5) ◽  
pp. 617-637 ◽  
Author(s):  
Mariska J. van Dijk ◽  
Janneke M. de Man-van Ginkel ◽  
Thóra B. Hafsteinsdóttir ◽  
Marieke J. Schuurmans
Keyword(s):  
Psychometric Properties ◽  
Intraclass Correlation ◽  
Depression Scale ◽  
Cross Sectional Study ◽  
Cutoff Score ◽  
Stroke Patients ◽  
Dutch Version ◽  
Cross Sectional ◽  
Symptoms Of Depression ◽  
Patient Health

The early detection of depression after stroke is essential for the optimization of recovery in aphasic stroke patients. The purpose of this study was to evaluate the psychometric properties of the Signs of Depression Scale (SODS), a non-language-based screening instrument. We conducted a cross-sectional study in a sample of 58 stroke patients in a rehabilitation center. The internal consistency and interrater reliability were good (α = .71 and intraclass correlation coefficient [ICC] = .79). The pre-defined hypotheses confirmed the construct validity, and the correlation between the SODS and the Patient Health Questionnaire–9 (PHQ-9) was moderate ( rb = .32). At a cutoff score of ≥1, the sensitivity was 0.80, and the specificity was 0.39. These findings indicate that the SODS is appropriate to screen for depressive symptoms and can be used by nurses to identify symptoms of depression in patients with aphasia who require further assessment.

scholarly journals Short-term serial assessment of electronic patient-reported outcome for depression and anxiety in breast Cancer

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Jeeyeon Lee ◽  
Jin Hyang Jung ◽  
Wan Wook Kim ◽  
Byeongju Kang ◽  
Jungmin Woo ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Treatment Period ◽  
Depression Scale ◽  
Patient Reported Outcome ◽  
Depression And Anxiety ◽  
Short Term ◽  
Web Based ◽  
Patient Reported ◽  
Patient Health

Abstract Purpose The incidence of depression and anxiety is higher in patients with breast cancer than in the general population. We evaluated the degree of depression and anxiety and investigated the changes in patients with breast cancer during the treatment period and short-term follow-up period. Methods Overall, 137 patients with breast cancer were evaluated using the Patient Health Questionnaire 9-item depression scale (PHQ-9) and Generalized Anxiety Disorder scale (GAD-7). The scales were developed as a web-based electronic patient-reported outcome measure, and serial results were assessed before the operation, after the operation, in the post-treatment period, and in the 6-month follow-up period after surgery. Results The degree of depression and anxiety increased during treatment and decreased at 6-month follow-up, even if there were no statistical differences among the four periods (PHQ-9: p = 0.128; GAD-7: p = 0.786). However, daily fatigue (PHQ-9 Q4) and insomnia (PHQ-9 Q3) were the most serious problems encountered during treatment and at 6-month follow-up, respectively. In the GAD-7, worrying too much (Q3) consistently showed the highest scores during the treatment and follow-up periods. Of the patients, 7 (5.11%) and 11 (8.03%) patients had a worsened state of depression and anxiety, respectively, after treatment compared with before treatment. Conclusion Most factors associated with depression and anxiety improved after treatment. However, factors such as insomnia and worrying too much still disturbed patients with breast cancer, even at 6-month follow-up. Therefore, serial assessment of depression and anxiety is necessary for such patients.

scholarly journals Analysis and Design of Social Presence in a Computer-Mediated Communication System

2021 ◽  
Vol 12 ◽  
Author(s):  
Hiroki Kojima ◽  
Dominique Chen ◽  
Mizuki Oka ◽  
Takashi Ikegami
Keyword(s):  
Social Presence ◽  
Subjective Experience ◽  
Computer Mediated Communication ◽  
Critical Factor ◽  
Transfer Entropy ◽  
Phone Call ◽  
Interaction Patterns ◽  
Online Chat ◽  
Analysis And Design ◽  
Statistical Measures

Social presence, or the subjective experience of being present with another existing person, varies with the interaction medium. In general, social presence research has mainly focused on uni-directional aspects of each exchanged message, not on bidirectional interactions. Our primary purpose is to introduce such bidirectional evaluation by quantifying the degree of social presence with a few statistical measures. To this end, we developed a software called “TypeTrace” that records all keystrokes of online chat interactants and reenacts their typing actions and analyzed the results from different chat conditions, mainly focusing on the characterization of bi-directional interactions. We also compared the chat interaction patterns with the patterns from phone call datasets to investigate the difference of live communication in different media. The hypothesis of the experiment was that either richness or concurrency of communication is important for organizing social presence. Richness is defined by the variety of information at a time in communication and the concurrency is the number of temporal thread being processed at the same time. Our results show that when we merely increase the richness of information by presenting the typing process, the cognition of others' presence does not significantly increase. However, when the information concurrency is augmented by introducing the transmission of realtime text, we found that the transfer entropy between the interactants becomes considerably higher, and the social presence and emotional arousal, intimacy increased. High transfer entropy was also observed in the phone call dataset. This result shows that the mere augmentation of information richness does not necessarily lead to increased social presence, and concurrent communication is another critical factor for fostering vivid conversation in digital environments.

Abstract 30: Role For Adverse Childhood Experiences And Depression In Preeclampsia

Hypertension ◽  
2021 ◽  
Vol 78 (Suppl_1) ◽  
Author(s):  
Monica C Myers ◽  
Mark K Santillan ◽  
Debra S Brandt ◽  
Amy K Stroud ◽  
Julie A Vignato ◽  
...  
Keyword(s):  
Postpartum Depression ◽  
Adverse Childhood Experiences ◽  
Depression Scale ◽  
Severe Depression ◽  
Late Pregnancy ◽  
Physical And Mental Health ◽  
Childhood Experiences ◽  
Adverse Experiences ◽  
Adverse Childhood ◽  
Patient Health

Hypertensive diseases are associated with adverse experiences in childhood as well as depression. In order to determine if these associations were present in women with preeclampsia (PreE), a particularly devastating hypertensive disease in pregnancy, the scores from three questionnaires: Adverse Childhood Experiences (ACE), Edinburgh Postnatal Depression Scale (EPDS), and the Patient Health Questionnaire-9 (PHQ-9) were compared between women with PreE (n=32) and women without PreE (n=46) between 9 and 48 months postpartum (IRB# 201808705). ACE scores are calculated by summing an individual’s affirmative responses to specific adverse experiences during childhood. In our study, the average ACE score of individuals with PreE was higher than that of women without PreE (1.69 vs. 1.02, P=.04). We also divided women into groups based on whether their ACE score was ≤3 or ≥4 due to evidence that individuals who have experienced ≥4 ACEs are at greatest risk for physical and mental health conditions. Among our participants, 80% of women with an ACE score ≥4 (n=10) had PreE while only 35.3% of women with a score ≤3 (n=68) developed the condition (P=0.01). As well, the odds of having PreE were higher in those with ACE scores ≥4, compared with those with scores ≤3 (OR= 7.34; 95% CI = 1.44, 37.33). In a subset of participants, scores were available from EPDS, survey that identifies women who have postpartum depression 6 weeks after birth, and from the PHQ-9, another assessment for depression. Among our participants, the average EPDS score was higher in women with PreE than women without PreE (6.38, n=21 vs. 3.71, n=42 P=0.01), indicating more severe symptoms of postpartum depression in women who also had PreE. In addition, the average PHQ-9 score among women with PreE was higher than that of women without PreE (3.71, n=15 vs 1.86, n=37 P=.02) with a higher score indicating more severe depression. The average PHQ-9 score was also higher in women who had ACE scores ≥4 than women with scores ≤3 (4.00, n=4 vs. 2.27, n=48 P=.01) indicating that women with more adverse childhood events were more likely to experience depression. Together, these findings indicate that PreE may be associated with adverse events during childhood as well as depression in late pregnancy and/or postpartum.

Sign in / Sign up

Export Citation Format

Share Document