Self-Administered Interventions Based on Natural Language Processing Models for Reducing Depressive and Anxiety Symptoms: Systematic Review and Meta-Analysis.

BACKGROUND: The introduction of natural language processing (NLP) technologies has significantly enhanced the potential of self-administered interventions for treating anxiety and depression by improving human-computer interactions. Although these advances, particularly in complex models such as generative artificial intelligence (AI), are highly promising, robust evidence validating the effectiveness of the interventions remains sparse. OBJECTIVE: The aim of this study was to determine whether self-administered interventions based on NLP models can reduce depressive and anxiety symptoms. METHODS: We conducted a systematic review and meta-analysis. We searched Web of Science, Scopus, MEDLINE, PsycINFO, IEEE Xplore, Embase, and Cochrane Library from inception to November 3, 2023. We included studies with participants of any age diagnosed with depression or anxiety through professional consultation or validated psychometric instruments. Interventions had to be self-administered and based on NLP models, with passive or active comparators. Outcomes measured included depressive and anxiety symptom scores. We included randomized controlled trials and quasi-experimental studies but excluded narrative, systematic, and scoping reviews. Data extraction was performed independently by pairs of authors using a predefined form. Meta-analysis was conducted using standardized mean differences (SMDs) and random effects models to account for heterogeneity. RESULTS: In all, 21 articles were selected for review, of which 76% (16/21) were included in the meta-analysis for each outcome. Most of the studies (16/21, 76%) were recent (2020-2023), with interventions being mostly AI-based NLP models (11/21, 52%); most (19/21, 90%) delivered some form of therapy (primarily cognitive behavioral therapy: 16/19, 84%). The overall meta-analysis showed that self-administered interventions based on NLP models were significantly more effective in reducing both depressive (SMD 0.819, 95% CI 0.389-1.250; P<.001) and anxiety (SMD 0.272, 95% CI 0.116-0.428; P=.001) symptoms compared to various control conditions. Subgroup analysis indicated that AI-based NLP models were effective in reducing depressive symptoms (SMD 0.821, 95% CI 0.207-1.436; P<.001) compared to pooled control conditions. Rule-based NLP models showed effectiveness in reducing both depressive (SMD 0.854, 95% CI 0.172-1.537; P=.01) and anxiety (SMD 0.347, 95% CI 0.116-0.578; P=.003) symptoms. The meta-regression showed no significant association between participants' mean age and treatment outcomes (all P>.05). Although the findings were positive, the overall certainty of evidence was very low, mainly due to a high risk of bias, heterogeneity, and potential publication bias. CONCLUSIONS: Our findings support the effectiveness of self-administered NLP-based interventions in alleviating depressive and anxiety symptoms, highlighting their potential to increase accessibility to, and reduce costs in, mental health care. Although the results were encouraging, the certainty of evidence was low, underscoring the need for further high-quality randomized controlled trials and studies examining implementation and usability. These interventions could become valuable components of public health strategies to address mental health issues. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD42023472120; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023472120.

Sex differences in entrapment in a multinational sample: a network analysis perspective.

Background: The concept of entrapment has been highlighted as a transdiagnostic element that manifests itself in disorders such as depression, anxiety, and suicidal ideation. Although research has been conducted in different contexts independently, a comprehensive multi-country study to assess gender differences in entrapment through network analysis has not yet been carried out. The objective of this study was to evaluate the entrapment network in men and women at the multinational level. Methods: A sample of 2,949 participants, ranging in age from 18 to 73 years from six countries (Germany, Iran, Spain, Slovakia, El Salvador, and Peru), was considered. They completed the entrapment scale. A network analysis was performed for both men and women to identify the connectivity between indicators and the formation of clusters and domains, in addition to the centrality assessment in both sex groups. Results: The study findings revealed the presence of a third domain focused on external interpersonal entrapment in the network of men and women. However, in relation to the interconnectivity between domains, variations were evidenced in both networks, as well as in centrality, it was reported that men present a greater generalized entrapment in various aspects of life, while women tend to experience a more focused entrapment in expressions of intense emotional charge. Conclusion: The multinational study identified variations in the structure of entrapment between genders, with three domains (internal, external, and external-interpersonal) and differences in the interaction of indicators and groupings, as well as discrepancies in centrality.

Structure and factorial invariance of the Grit-Original scale and convergent validity of the network with job satisfaction and happiness.

Background: The concept of Grit refers to a person's ability to maintain perseverance and passion in the pursuit of long-term objectives. However, research on the applicability of the Grit-Original scale (Grit-O) in the Latin American context is limited. Objective: This instrumental design study aimed to analyze the structure of this scale and its factorial invariance in relation to gender, as well as to examine its convergent validity with job satisfaction and happiness. Methods: A sample of 364 Peruvian workers that were selected through non-probabilistic convenience sampling in 2021. Results: The results of the confirmatory factor analysis showed that the two-dimensional structure of 12 items presented adequate goodness-of-fit indices. Additionally, the instrument is invariant between men and women. Likewise, the convergent relationship between the Grit scale, job satisfaction, and happiness variables was confirmed, which supports the validity of the instrument in the study context. Conclusion: The findings of the study confirm that the GRIT-O is a measure with adequate psychometric properties in the Peruvian context.

Factorial and network structure of the Reynolds Adolescent Depression Scale (RADS-2) in Peruvian adolescents.

Depression in young people is considered a public health problem, given that it affects their personal, social, and academic lives; therefore, early detection of depressive symptoms is of importance for a favorable prognosis. This study aimed to estimate the psychometric properties of the second edition of the Reynolds Adolescent Depression Scale (RADS-2) in Peruvian adolescents. The sample was composed of 917 Peruvian adolescents, aged 13 to 18 years (M = 15,241, SD = 1,020), who were selected from two public educational institutions in Metropolitan Lima. Confirmatory factor analysis supported the 25-item model with the four-dimensional structure and its overall and interdimensional reliability. This structure was found to be gender invariant. Finally, network analysis was performed to assess the relationships and centralities of the depressive symptoms of the validated version of the RADS-2. The results show that the RADS-2 measure is a consistent and reliable test that yields valid results in the Peruvian adolescent context.