Journal of psychopathology and clinical science最新文献

{"title":"Fine-tuning large language models for detecting negative self-referential language in smartphone text among youth with depression.","authors":"Isaac N Treves, Lilian Y Li, Libby Hod, Adela Schwartz, Paul A Bloom, Jamaal Spence, Alexander Saul Rosenberg, Katherine Durham, Xuhai Xu, Esha Trivedi, David Pagliaccio, Nicholas B Allen, Stewart A Shankman, Randy P Auerbach","doi":"10.1037/abn0001159","DOIUrl":"https://doi.org/10.1037/abn0001159","url":null,"abstract":"<p><p>Adolescent smartphone language provides a lens into negative self-referential thinking, which is central to major depressive disorder (MDD). Prior studies have linked language features, including negative sentiment and first-person pronouns, to mood and depression, suggesting that naturalistic language may identify who is at risk and when that risk is greatest. However, studies of adolescent smartphone social communication have typically relied on rule-based models not validated for heterogeneous, context-sensitive language. To address this gap, we determined whether transformer models, including large language models, optimized detection of depression risk in extensive adolescent smartphone text data. In this study, 223 adolescents (Mage = 16.43 years, current MDD = 37, remitted MDD = 103, healthy controls = 83) installed a smartphone app, which prompted participants to provide mood ratings once a day and acquired all keyboard inputs over 12 months (mean text entries per participant = 17,683). Ten thousand text entries were double-coded for entry-level sentiment (positive, neutral, negative) and self-reference for training and testing traditional rule-based approaches (VADER, pronoun counts) and transformer approaches, including GPT-4-mini. In the full data set, between-participant associations with depressive symptoms and within-participant relations to daily mood and depressive episodes were examined. Fine-tuned transformer models best aligned with human-coded sentiment labels (F1GPT4-MINI = .84, F1VADER = .59) and accurately detected self-reference (F1T5-BASE = .97). Adolescents with current and remitted MDD exhibited more transformer-based negative self-referential language than healthy controls (ORs = 1.38, 1.26). Increased negative self-referential language predicted worse next-day mood (β = -.033, p < .001) and a higher likelihood of next-week depressive episodes (OR = 1.66, 95% confidence interval [1.06, 2.62], p = .028), although the association with depressive episodes was not robust to sensitivity analyses. Transformer models may be integrated into digital mental health care to detect when youth are at risk for depression. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13483330/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large language models can supplement the assessment of clinical high risk for psychosis.","authors":"Luz Maria Alliende, Rob Voigt, Maeve Hoffman, Gregory P Strauss, Lauren M Ellman, Elaine F Walker, Philip Corlett, Jason Schiffman, Scott W Woods, Albert Powers, Steven M Silverstein, James A Waltz, Richard Zinbarg, Shuo Chen, Trevor F Williams, Joshua Kenney, James M Gold, Vijay A Mittal","doi":"10.1037/abn0001160","DOIUrl":"10.1037/abn0001160","url":null,"abstract":"<p><p>Capturing psychosis risk before illness onset is an ongoing challenge for psychosis-spectrum studies. Natural language processing (NLP) tools can harness information embedded in the notes generated during clinical interviews to obtain more objective markers of psychosis risk; for this project, we used readily available assessor notes. The following project acts as proof of concept on the usefulness of AI-based tools to capture latent psychosis risk information. We used assessor notes for 2,077 Structured Interview for Psychosis-risk Syndromes interviews as input for different AI-based NLP models to produce metrics for psychosis risk, namely, a trained encoder-only model (ModernBERT), and zero-shot and few-shot instantiation of two decoder-only models (Large Language Model Meta AI Version 4 [LLaMA-4] and GPT-4.1 mini). AI-based risk metrics were compared with gold-standard ratings of clinical high risk for psychosis (CHR). The AI-based risk metrics' relationship to traditional psychosis risk scores (Shanghai-At-Risk-for-Psychosis [SHARP] and North American Prodrome Longitudinal Study [NAPLS]) was also assessed. Finally, we explored the added benefit of adding AI-based risk metrics to models predicting future participant conversion. All models performed above chance in classifying interview notes for the presence or absence of CHR syndromes. The trained encoder model performed the best out of all models determining the presence of CHR syndromes (accuracy = 82.67%, κ = .63). Positive CHR classification by the encoder model resulted in a 0.69 and 0.85 standard deviation increase in SHARP and NAPLS risk scores (<i>p</i> < .001). A 1 standard deviation increase in decoder-generated risk scores increased traditional risk scores between 0.24 and 0.47 standard deviations (all <i>p</i>s < .001). In exploratory analyses, decoder-generated risk scores incrementally improved models predicting conversion including SHARP but not NAPLS risk scores. Although our results need to be considered in the context of one consortium, AI-based NLPs show potential as an aid for the diagnosis of CHR syndromes, evaluating psychosis risk, and even predicting future conversion, even with suboptimal but readily available inputs (i.e., assessor notes). Future projects could use AI-based tools' potential in augmenting psychosis risk screenings and risk predictors. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13449246/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large language model applications for real-time clinical mental health assessment: Current potential and future directions.","authors":"Katie Aafjes-van Doorn, Francine Cheng Ty, Antonia Yuxin Hua, Chunlin An, Anna Van Meter","doi":"10.1037/abn0001155","DOIUrl":"10.1037/abn0001155","url":null,"abstract":"<p><p>Large language models (LLMs) have shown increasing promise in the mental health field. LLMs are especially well suited to play a role in the labor-intensive, costly process of clinical assessment, as they can interact with a patient or participant directly to conduct a mental health assessment. We conducted a preregistered scoping review to (a) describe the unique capabilities of LLMs for clinical assessment, (b) determine the current state of the field in applying LLMs to directly assess patient/participant mental health (including screening, diagnosis, and monitoring of symptoms), and (c) highlight future research to facilitate the application of LLMs. We included work published in both Chinese and English. Only 10 studies met criteria for direct LLM-based mental health assessment. The evidence base was recent and heterogeneous: Four studies focused primarily on diagnostic interviewing or classification, five on symptom or severity assessment, and one on task-based multimodal depression assessment. Studies varied across text, voice, and multimodal formats, and depression was the dominant target. Across studies, stronger performance tended to be reported in tools that used structured interviewing logic, domain-specific adaptation, and clinically anchored reference standards. However, the evidence base remains small, with many studies employing limited validation procedures, and heavily weighted toward early-stage or nonjournal publications. The limited pace of academic validation means that, at present, LLMs are best understood as emerging assessment-support tools rather than replacements for clinical evaluation. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148665294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond a single predictor: Is there a synergistic effect of autistic and attention-deficit/hyperactivity disorder traits on creativity? Commentary on Taylor et al. (2025).","authors":"Maria Clara da Cruz Brandão, Marcos Antônio da Silva Araújo, Ana Elisa Toscano","doi":"10.1037/abn0001135","DOIUrl":"10.1037/abn0001135","url":null,"abstract":"<p><p>This commentary proposes that the heightened creativity often observed in neurodivergent populations may emerge from a unique synergy between autistic and attention-deficit/hyperactivity disorder traits rather than being driven by attention-deficit/hyperactivity disorder alone. We suggest that future research should directly compare comorbid groups against those with single-diagnosis profiles to better understand how these distinct cognitive styles interact to produce creative outcomes. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":"727-728"},"PeriodicalIF":4.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A meta-analysis of heart rate variability and psychopathology: An investigation guided by the hierarchical taxonomy of psychopathology framework.","authors":"Tam Pham,Carly J Johnco,Ana Neves,Wilson P H Lim,Gladys J Heng,Rachel Ygnacio,Miriam K Forbes","doi":"10.1037/abn0000936","DOIUrl":"https://doi.org/10.1037/abn0000936","url":null,"abstract":"Although low resting heart rate variability (HRV) is associated with various forms of psychopathology, patterns of specificity and nonspecificity in the apparent transdiagnostic nature of resting HRV have not been systematically investigated. Existing research is dominated by disorder-specific studies, limiting conclusions about whether HRV reductions reflect mechanisms unique to particular diagnoses or a broader transdiagnostic vulnerability. Using the Hierarchical Taxonomy of Psychopathology framework, this Stage 2 Registered Report synthesized evidence from 430 studies and 732 effect sizes (N = 62,264) to quantify associations between resting HRV and psychopathology at multiple levels of specificity-from individual disorders to higher order spectra and superspectra. Across the hierarchy, lower resting HRV emerged as a robust correlate of most domains of psychopathology. For example, at the disorder level, lower resting HRV was significantly associated with schizophrenia, bipolar disorder, autism, generalized anxiety, panic disorder, borderline personality, posttraumatic stress disorder, and major depression, but not with obsessive-compulsive disorder, social anxiety, and attention-deficit/hyperactivity disorder. Psychotic conditions showed the strongest associations across all levels of the hierarchy, but sensitivity analyses indicated that these associations are likely influenced by study design and sample characteristics. Together with consistent moderator effects showing stronger HRV-psychopathology associations in samples with higher symptom severity, we conclude that decrements in resting HRV represent a transdiagnostic marker of systemic dysregulation reflecting illness severity rather than disorder-specific autonomic signatures. (PsycInfo Database Record (c) 2026 APA, all rights reserved).","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":"19 1","pages":"729-761"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148565036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Humanizing \"multimodal\" digital phenotyping of serious mental illness.","authors":"Alex S Cohen, Michael D Masucci, Ole E Granrud, Kiara K Warren, Aubree T Corporandy, Ashley N Zollicoffer, Gregory P Strauss","doi":"10.1037/abn0001134","DOIUrl":"10.1037/abn0001134","url":null,"abstract":"<p><p>Developing digital technologies for quantifying symptoms of serious mental illness (SMI) has been a focus of research for over 7 decades. Recent efforts have focused on multimodal feature integration, which captures conceptually distinct behavioral domains. We evaluated links between nonverbal digital features and human-rated negative symptoms, with the expectation that their relationship would depend on verbal information (i.e., be moderated by language emotional tone). We believe this better approximates how humans integrate verbal and nonverbal information when making clinical ratings. Mobile video diaries were evaluated for people with SMI, those at clinical high risk for developing SMI, and control groups (<i>N</i>s = 48, 20, 36, and 21, respectively; <i>K</i> videos = 902, 440, 602, and 399, respectively). We identified six features (i.e., capturing positive and neutral facial expressions, vocal intonation and emphasis, and speaking pause length and articulation rate) that showed acceptable reliability (final <i>N</i> and <i>K</i> for video/audio analysis = 109/912 and 120/2,200, respectively), but most features failed to show acceptable reliability. Videos were behaviorally rated for alogia and blunted vocal and facial affect. Relationships between nonverbal features and human ratings were dependent on verbal tone, but only when verbal tone was positive in valence. For example, behaviorally rated alogia was associated with longer pauses, but primarily when language had a positive tone. These results support a relatively novel approach to multimodal digital phenotyping, one that emphasizes using multimodal features to provide \"context\" in the way that humans likely interpret and integrate multimodal streams of information. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":"889-900"},"PeriodicalIF":4.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13374719/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148058711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intimate relationship distress and incidence of major depression in a U.S. probability sample: A preregistered propensity score analysis.","authors":"Mark A Whisman, Pia E Sellery, Savannah M Boyd, David A Sbarra","doi":"10.1037/abn0001131","DOIUrl":"10.1037/abn0001131","url":null,"abstract":"<p><p>Poor intimate relationship quality is prospectively associated with elevated levels of depressive symptoms and higher incidence of a major depressive episode. Propensity score matching analyses, which statistically equate people in the exposure sample (e.g., people in distressed relationships) with a comparison sample (e.g., people in nondistressed relationships), provide a complementary means to traditional covariate analyses for addressing confounding in observational research, thereby enhancing the ability to evaluate potential causal associations. In this preregistered study, propensity score matching analyses were conducted using a probability sample of married adults in the United States aged 50 years and older who participated in 2014/2016 or 2016/2018 waves of the Health and Retirement Study and who were (a) not depressed at baseline and (b) continuously married at baseline and 2-year follow-up. Women (<i>n</i> = 407) and men (<i>n</i> = 525) in distressed relationships were matched with an equal number of women and men in nondistressed relationships on the propensity to experience relationship distress. Women and men in distressed relationships were significantly more likely than propensity-matched women and men in nondistressed relationships to meet criteria for a past-year major depressive episode at follow-up. In the full sample of women (<i>n</i> = 2,273) and men (<i>n</i> = 2,345), similar results were obtained for covariate analyses using the propensity score as well as traditional covariate analyses examining covariates independently. Findings provide strong support for the perspective that relationship distress is causally associated with depression and support the use of couple-based interventions for preventing and treating depression in middle-aged and older adults. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":"796-805"},"PeriodicalIF":4.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transactional relations between attentional biases for affective stimuli and depressive symptoms in offspring of mothers with and without major depressive disorder.","authors":"Kelly A Gair, Leslie A Brick, Brandon E Gibb","doi":"10.1037/abn0001132","DOIUrl":"10.1037/abn0001132","url":null,"abstract":"<p><p>Attentional biases toward depression-relevant stimuli (e.g., sad faces) are thought to contribute to the development and maintenance of depression, but research in youth is limited and primarily cross-sectional. Therefore, it remains unclear whether such biases are risk factors for, versus consequences of, depression (or both), and whether these links may be stronger among youth already at risk for depression due to a family history of the disorder. To address these questions, the present multiwave longitudinal study followed 242 mothers and their offspring (ages 8-14; 51.65% girls, 81.40% non-Hispanic White) over 2 years with assessments every 6 months (five assessments total) to examine prospective relations between attentional biases (measured via a dot-probe eye-tracking task) and depressive symptoms in youth. Of the mothers, 123 had a history of major depressive disorder (MDD) during their child's life and the rest had no lifetime history of MDD. Using random intercepts cross-lagged panel models, we found that depressive symptoms predicted prospective changes in attentional biases, but not the reverse, and the pattern of attentional bias change differed based on maternal history of MDD. Specifically, among offspring of mothers with MDD, higher depressive symptoms at a given assessment predicted future increases in attentional bias to sad faces, whereas among offspring of never depressed mothers, higher depressive symptoms predicted subsequent decreases in attentional bias to happy faces. These findings suggest that experiences of depression may contribute to different patterns of attention to emotional cues based on maternal history of MDD. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":"774-784"},"PeriodicalIF":4.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13155365/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large language models detect amplified abstract interpretation in trait anxiety.","authors":"Jihyun K Hur, Wisteria Deng, Harsimran Kaur, Jutta Joormann, Tyrone D Cannon","doi":"10.1037/abn0001154","DOIUrl":"https://doi.org/10.1037/abn0001154","url":null,"abstract":"<p><p>Research on the relation of interpretation biases to internalizing symptoms has primarily focused on emotional valence (i.e., negativity bias), leaving other aspects of cognitive processing underexplored. Guided by dual-coding theory (Kousta et al., 2011; Paivio, 1991), we examined how the balance between abstract versus concrete elaboration shapes social interpretations in adults with varying levels of trait anxiety and depressive symptoms. A confirmatory sample of 158 U.S. participants wrote interpretations of 24 ambiguous social images (12 negative, 12 nonnegative) presented with gradually decreasing blur (Stage 1 = 80% blur, Stage 2 = 20%, Stage 3 = 0%). Large language model (Generative Pre-Trained Transformer-4.1) analyses were used to compute emotional valence and the proportion of abstract versus concrete language in each response. Trait anxiety symptoms emerged as robust correlates of language-based interpretation biases. As preregistered, both trait anxiety and depressive symptoms correlated with more negative interpretations. This pattern was stronger for negative than nonnegative scenarios, replicating previous findings of negativity bias. In addition, in exploratory analyses, individuals high in trait anxiety, but not depressive symptoms, showed an amplified increase in abstract relative to concrete language across stages. The result held even when accounting for lexicon-based abstractness measures. These results extend valence-based theories by suggesting that trait anxiety symptoms are associated with amplified abstraction during social interpretations. Large language model-derived linguistic indices provide a nuanced, automated method for capturing dual-coding dynamics in natural language, broadening avenues to probe latent cognitive processing patterns in psychopathology. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148594914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explaining GPTs' schema of depression: A machine behavior analysis.","authors":"Adithya V Ganesan, Vasudha Varadarajan, Yash Kumar Lal, Veerle C Eijsbroek, Katarina Kjell, Oscar N E Kjell, Tanuja Dhanasekaran, Elizabeth C Stade, Johannes C Eichstaedt, Ryan L Boyd, H Andrew Schwartz, Lucie Flek","doi":"10.1037/abn0001144","DOIUrl":"10.1037/abn0001144","url":null,"abstract":"<p><p>The use of large language models (LLMs) such as ChatGPT (GPT-4/GPT-5) for mental health is growing rapidly, including their use to assess and help people with mood disorders, such as depression. However, we have a limited understanding of the schema of mental disorders in these language models, that is, how they internally associate and interpret the symptoms. In this work, we used contemporary measurement theory to decode how GPT-4 and GPT-5 interrelate depressive symptoms, providing an explanation of how large language models behave in clinical applications. First, we evaluated whether these models can reliably detect depressive constructs, finding that GPT-4 (a) demonstrated strong convergent validity with standard instruments and expert judgments (<i>r</i> = .70-.81). We mapped the model's internal schema of depression, showing that it (b) organized symptoms into an interconnected network (symptom correlations <i>r</i> = .23-.78) that largely aligned with the established clinical literature. However, it (c) underemphasized the relationship between <i>suicidality</i> and other symptoms while overemphasizing the importance of <i>psychomotor symptoms.</i> Finally, the associations (d) suggested novel hypotheses for symptom mechanisms, for instance, indicating that <i>sleep</i> and <i>fatigue</i> are broadly influenced by other depressive symptoms, whereas <i>worthlessness/guilt</i> is selectively associated with <i>depressed mood</i>. GPT-5 showed slightly lower convergence with self-report, which our analysis attributed to changes in the relationships among symptoms. These insights provide a generalizable, empirical foundation for understanding language models' mental health assessments across models and disorders. (PsycInfo Database Record (c) 2026 APA, all rights reserved).</p>","PeriodicalId":73914,"journal":{"name":"Journal of psychopathology and clinical science","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13682761/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148594845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}