Prevalence of anxiety and depression among patients with glaucoma.

Purpose: This study aimed to determine the prevalence of anxiety and depression among patients with glaucoma compared to the average Brazilian prevalence (9.8% of anxiety and 5.8% of depression, according to the World Health Organization) and its correlation with the severity of the disease. Methods: This was a transversal, single-arm trial of patients from four glaucoma centers in São Paulo and Curitiba-Brazil. Patients comprised adults at least 18 years of age with glaucoma diagnosis under treatment for at least 6 months. All subjects of the study answered two questionnaires (PHQ-9 and GAD-7) to evaluate the presence of anxiety and depression, and the results were analyzed accordingly to clinical and demographic characteristics. Results: The protocol included a total of 210 patients. The average age was 61.6 ± 15.3 years, and the female gender was more common (68.86%). Primary open-angle glaucoma was the most common diagnosis (59.90%). The average IOP was 18.5 mmHg, and 1.5 anti-glaucoma drops were the mean treatment. The prevalence of depression and anxiety was 26.90 and 25.71%, respectively. Most patients with anxiety were classified as early glaucoma, while those with depression had severe glaucoma. Conclusion: This study found that the prevalence of anxiety and depression among patients with glaucoma is higher than in the general population in our country.

Exploring the relationship between earthquake exposure and severity of erectile dysfunction in southern part of Türkiye.

PURPOSE: This study aimed to explore the impact of psychological stress on erectile dysfunction (ED) in male patients following the Gaziantep-Kahramanmaras earthquake. The investigation aimed to establish correlations between earthquake-induced stress and changes in sexual function using International Index of Erectile Function (IIEF), Patient Health Questionnaire-9 (PHQ-9), and Generalized Anxiety Disorder-7 (GAD-7) scores. MATERIALS AND METHODS: A retrospective analysis was conducted on male ED patients from a Gaziantep urology clinic post-earthquake (March to August 2023). Patients with deteriorated erectile function post-earthquake (group 1) and those with pre-existing ED experiencing worsened symptoms post-earthquake (group 2) were included. Data collected encompassed sexual histories, IIEF scores, laboratory tests, and PHQ-9/GAD-7 evaluations. Patients were also evaluated mild and mild to moderate ED, moderate and severe ED according to IIEF erectile function. RESULTS: Seventy-six patients were evaluated (24 in group 1 and 52 in group 2). Significant reductions in total IIEF scores (58 to 40 in group 1 and 49 to 33 in group 2) were observed post-earthquake in both groups (p<0.001). PHQ-9/GAD-7 scores was 11.12±3.79/9.34±3.11 in mild and mild to moderate ED and 13.17±3.05/12.14±3.17 in moderate and severe ED (p=0.011, p<0.001, respectively). Negative correlations existed between PHQ-9/GAD-7 scores and IIEF erectile function (p<0.05) and total IIEF (p<0.05). CONCLUSIONS: This research suggests a plausible connection between the Gaziantep-Kahramanmaras earthquake and heightened ED cases. Psychological stress post-earthquake may contribute to worsened ED symptoms. Further investigations are warranted to comprehensively understand the interplay between natural disasters and sexual dysfunction, essential for optimizing patient care in challenging situations.

Depression Screening as a Part of the Employees' Annual Checkup Using a Two-Step Approach at King Khalid University Hospital, Riyadh, Saudi Arabia.

Introduction Health professionals experience high levels of work-related stress; hence, the study of depression among healthcare workers (HCWs) is essential to improve patient care, prevent burnout, and retain a skilled workforce as well as reduce stigma, enhance workplace productivity, and promote overall well-being. This study aimed to estimate the prevalence of depression and associated factors among HCWs at King Khalid University Hospital, Riyadh, Saudi Arabia. Methods We conducted a cross-sectional study among HCWs at King Khalid University Hospital. All healthcare workers required to renew their contract annually were given a Patient Health Questionnaire 2 (PHQ2) tool for screening for depression; if their score was three or more, a Patient Health Questionnaire 9 (PHQ9) tool was given along with additional questions including demographic, profession-related factors, and stressor presence in different life dimensions. Results In total, 69 HCWs filled out the screening survey (PHQ9). Most were females (n=57; 82.6%), with 36 (52.2%) aged 35 years or below. Five (7.2%) HCWs reported a family history of mental illness. The prevalence of major depressive disorders among HCWs was 29 (42%). Conclusions Younger HCWs who smoked and had no children were more susceptible to depression. Annual psychological screenings for HCWs could be beneficial for monitoring staff vulnerable to mental health disorders. We need a future multicenter study approach to confirm the prevalence of major depression in our region.

Unidimensional or multidimensional? Revisiting the psychometrics of PHQ-9 and EPDS using bifactor model and item response theory in 2939 Chinese perinatal women.

BACKGROUND: Perinatal depression often goes undetected and untreated in low- and middle-income countries like China. Reliable screening tools can improve this situation. The Patient Health Questionnaire-9 (PHQ-9) and the Edinburgh Postnatal Depression Scale (EPDS), two widely used tools, often exhibit inconsistent factor structures, leading to debates regarding their unidimensionality versus multidimensionality and casting doubts on their psychometric properties. METHODS: Our study aimed to assess the utility of PHQ-9 and EPDS in Chinese perinatal women and to address the debate by employing the bifactor model and item response theory (IRT). We enrolled 2939 perinatal women from a maternity and infant health hospital serving all 16 districts of Shanghai. The bifactor model was used to examine the factor structure of PHQ-9 and EPDS, while IRT analysis evaluated the psychometric properties. RESULTS: The indices derived from the bifactor model indicated that both PHQ-9 and EPDS should be used as unidimensional measurements. All items in PHQ-9 and EPDS showed adequate discriminative ability and difficulty, but certain items require further refinement. PHQ-9 demonstrated better measurement precision at high levels of latent depression than EPDS. LIMITATIONS: These findings might not generalize to perinatal women in impoverished areas. The absence of clinical diagnoses limited the exploration of sensitivity and specificity. CONCLUSIONS: PHQ-9 and EPDS are effective tools for detecting depression in Chinese perinatal women and should be used as unidimensional tools. Our study expands upon existing psychometric findings related to PHQ-9 and EPDS, offering valuable insights for their application in research and clinical settings.

Non-Gaussian Liability Distribution for Depression in the General Population.

Unlike depression sum scores, the underlying risk for depression is typically assumed to be normally distributed across the general population. To assess the true empirical shape of depression risk, we created a continuous-valued estimate of the latent depression density, using the Davidian-Curve Item Response Theory (DC-IRT) and the National Health and Nutrition Examination Survey (NHANES) cohorts from 2005 to 2018 (n = 36,244 on the Nine-item Patient Health Questionnaire; PHQ-9). We conducted simulations to investigate the performance of DC-IRT for large samples and realistic items. The method can recover complex latent-risk distributions even when they are not evident from sum scores. However, estimation accuracy for different sample sizes depends on the method of model selection. In addition to full-data analysis, random samples of a few thousand observations were drawn for analysis. The latent shape of depression was left-skewed and bimodal in both investigations, indicating that the latent-normality assumption does not hold for depression.

Mobile sensing-based depression severity assessment in participants with heterogeneous mental health conditions.

Mobile sensing-based depression severity assessment could complement the subjective questionnaires-based assessment currently used in practice. However, previous studies on mobile sensing for depression severity assessment were conducted on homogeneous mental health condition participants; evaluation of possible generalization across heterogeneous groups has been limited. Similarly, previous studies have not investigated the potential of free-living audio data for depression severity assessment. Audio recordings from free-living could provide rich sociability features to characterize depressive states. We conducted a study with 11 healthy individuals, 13 individuals with major depressive disorder, and eight individuals with schizoaffective disorders. Communication logs and location data from the participants' smartphones and continuous audio recordings of free-living from a wearable audioband were obtained over a week for each participant. The depression severity prediction model trained using communication log and location data features had a root mean squared error (rmse) of 6.80. Audio-based sociability features further reduced the rmse to 6.07 (normalized rmse of 0.22). Audio-based sociability features also improved the F1 score in the five-class depression category classification model from 0.34 to 0.46. Thus, free-living audio-based sociability features complement the commonly used mobile sensing features to improve depression severity assessment. The prediction results obtained with mobile sensing-based features are better than the rmse of 9.83 (normalized rmse of 0.36) and the F1 score of 0.25 obtained with a baseline model. Additionally, the predicted depression severity had a significant correlation with reported depression severity (correlation coefficient of 0.76, p < 0.001). Thus, our work shows that mobile sensing could model depression severity across participants with heterogeneous mental health conditions, potentially offering a screening tool for depressive symptoms monitoring in the broader population.

Prevalence and Risk by Age and Sex of Sleep Dysregulation and Depressive Episodes in Bipolar and Depressive Disorders in a Community Survey in Sardinia, Italy.

Background/Objectives: Sleep disturbances often accompany mood disorders and persistent insomnia after mood symptoms have resolved may be a marker of poor outcome. The association between sleep symptoms and mood disorders seems to change with age and sex. This study aims to assess the frequency of depressive episodes and sleep disorders in the general population through an agile screening questionnaire and to evaluate the association of depressive episodes and sleep symptoms by sex and age categories. Methods: 774 women and 728 men from Sardinia aged > 16 years old were enrolled. The Patient Health Questionnaire (PHQ-9) was administered through a computer-assisted telephonic interview. Results: The frequency of depressive episodes was double in women (10.6% vs. 4.4%; p < 0.0001), with the highest values in women > 75 yo (17.4%). The frequency of sleep dysregulation was double in women (18.7% vs. 9.6%; p < 0.0001), with the highest values in women > 75 yo (35.9%) and the lowest in the group of men > 75 yo. The group of young males showed the lowest frequency of depressive episodes (1.4%) and a frequency of sleep dysregulation (9.1%) similar to that of the other groups of age and sex. Sleep dysregulation without depressive episodes presented a higher distribution in the elderly, both in males (20.7%) and in females (18.5%). No significative differences were found across sex and age groups in the distribution of depressive episodes without sleep dysregulation. Conclusions: The use of an agile screener such as PHQ9 in the general population and/or in populations at risk can be a valuable tool in finding those individuals in whom sleep dysregulation may represent an early warning signal, one that may be thoroughly evaluated to identify and treat possible sleep disorders early.

The Indirect Effect of Future Anxiety on the Relationship between Self-Efficacy and Depression in a Convenience Sample of Adults: Revisiting Social Cognitive Theory.

Background/Objectives: Depression and anxiety are prevalent disorders, particularly during emerging adulthood. Uncertainty about the future, exacerbated by unstable times, can lead to heightened future anxiety in this group. This study aimed to examine the complex associations of depression symptoms, future anxiety, and self-efficacy in adults from Poland. Additionally, we investigated age and gender differences in depression symptoms, future anxiety, and self-efficacy. Methods: A cross-sectional online survey study was performed in 2023 in Poland using snowball sampling. A convenience sample of 284 adults participated in this study, ranging in age between 18 and 65 years old (M = 32.18, SD = 11.87), including 95 men (33.45%) and 189 (66.55%) women, and also 157 (55.63%) emerging adults (18-28 years old) and 126 (44.37%) middle-aged adults (29-65 years old). The Patient Health Questionnaire (PHQ-9), Dark Future Scale (DFS-5), and Generalized Self-Efficacy Scale (GSES) were used to measure depression, future anxiety, and self-efficacy, respectively. Results: A 2-way ANOVA showed that both emerging adults and women scored significantly higher in depression symptoms and future anxiety than middle-aged adults and men, respectively. Furthermore, women scored lower in self-efficacy than men. Analyses revealed that there was a positive correlation between depression and future anxiety. Self-efficacy was negatively correlated with depression and future anxiety. Self-efficacy and future anxiety accounted for 48% of depression variance, controlling for age and gender. Future anxiety was found to be a partial mediator of the relationship between self-efficacy and depression. Conclusions: This study significantly advances the understanding of mental health in adults, grounded in social cognitive theories, revealing that low self-efficacy heightens future anxiety, thereby exacerbating depression symptoms in the Polish adult population, independent of age and gender. Emerging adults and women need psychological support to reduce depression and future anxiety. Women, in particular, should be the main focus of interventions to boost self-efficacy. Implementing targeted preventive measures and support systems can mitigate the challenges faced by emerging adults and women.

Unveiling the interoception impairment in various major depressive disorder stages.

BACKGROUND: The intricate pathophysiological mechanisms of major depressive disorder (MDD) necessitate the development of comprehensive early indicators that reflect the complex interplay of emotional, physical, and cognitive factors. Despite its potential to fulfill these criteria, interoception remains underexplored in MDD. This study aimed to evaluate the potential of interoception in transforming MDD's clinical practices by examining interoception deficits across various MDD stages and analyzing their complex associations with the spectrum of depressive symptoms. METHODS: This study included 431 healthy individuals, 206 subclinical depression individuals, and 483 MDD patients. Depressive symptoms and interoception function were assessed using the PHQ-9 and MAIA-2, respectively. RESULTS: Interoception dysfunction occurred in the preclinical phase of MDD and further impaired in the clinical stage. Antidepressant therapies showed limited efficacy in improving interoception and might damage some dimensions. Interoceptive dimensions might predict depressive symptoms, primarily enhancing negative thinking patterns. The predictive model based on interoception was built with random split verification and demonstrated good discrimination and predictive performance in identifying MDD. CONCLUSIONS: Early alterations in the preclinical stage, multivariate associations with depressive symptoms, and good discrimination and predictive performance highlight the importance of interoception in MDD management, pointing to a paradigm shift in diagnostic and therapeutic approaches.

Safety and effectiveness of vortioxetine in patients with major depressive disorder in a real-life clinical setting in India: results from an interventional, flexible-dose study.

OBJECTIVE: Vortioxetine has demonstrated safety and efficacy in improving symptoms of major depressive disorder (MDD), including overall functioning in real-world settings. This is the first study in a real-life clinical setting in India to evaluate effectiveness and safety of vortioxetine in patients with MDD. METHODS: This interventional, open-label study consisted of a 12-week treatment period with flexible doses of vortioxetine (5-20 mg/day) in adult patients (aged 18-65 years) with a confirmed MDD diagnosis. Effectiveness outcomes included change from baseline to week 12 in Patient Health Questionnaire-9 (PHQ-9) and Clinical Global Impression-Severity (CGI-S) scores, along with CGI-Improvement (CGI-I) scores at week 12, using a mixed model for repeated measures. Adverse events (AEs) were recorded for safety outcome assessments. RESULTS: Of 395 patients who received vortioxetine, 42.3% were women mean age 38.9 years; 322 patients completed the study. Significant improvement in depressive symptoms was observed in change from baseline to week 12 least squares (LS) mean (SE) PHQ-9 total score (-9.36 [0.276]; p<.0001) and CGI-S score (-2.14 [0.065]; p<.0001). LS mean (SE) CGI-I score showed significant improvement at week 12 (1.93 [0.067]; p<.0001). Subgroup analysis across age, sex, disease severity, and body mass index showed significant improvements in depression symptoms and severity. A total of 35.4% (n = 140) of patients experienced treatment-emergent AEs (mostly mild-moderate); nausea and pruritus were the most frequent (6.6%, n = 26 each). CONCLUSION: Safety and effectiveness of vortioxetine in improving symptoms of MDD over a 12-week period was demonstrated in a real-life clinical setting in India. CLINICAL TRIAL REGISTRATION INFORMATION: Open-label, flexible-dose study of vortioxetine in patients with major depressive disorder in India; Clinical Trials.gov ID: NCT04288895; https://www.clinicaltrials.gov/study/NCT04288895.

Detecting depression severity using weighted random forest and oxidative stress biomarkers.

This study employs machine learning to detect the severity of major depressive disorder (MDD) through binary and multiclass classifications. We compared models that used only biomarkers of oxidative stress with those that incorporate sociodemographic and health-related factors. Data collected from 830 participants, based on the Patient Health Questionnaire (PHQ-9) score, inform our analysis. In binary classification, the Random Forest (RF) classifier achieved the highest Area Under the Curve (AUC) of 0.84 when all features were included. In multiclass classification, the AUC improved from 0.84 with only oxidative stress biomarkers to 0.88 when all characteristics were included. To address data imbalance, weighted classifiers, and Synthetic Minority Over-sampling Technique (SMOTE) approaches were applied. Weighted random forest (WRF) improved multiclass classification, achieving an AUC of 0.91. Statistical tests, including the Friedman test and the Conover post-hoc test, confirmed significant differences between model performances, with WRF using all features outperforming others. Feature importance analysis shows that oxidative stress biomarkers, particularly GSH, are top ranked among all features. Clinicians can leverage the results of this study to improve their decision-making processes by incorporating oxidative stress biomarkers in addition to the standard criteria for depression diagnosis.

Development and preliminary evaluation of a suicidal risk assessment protocol in a randomised controlled trial using the Patient Health Questionnaire (PHQ-9).

BACKGROUND: Participants in research trials often disclose severe depression symptoms, including thoughts of self-harm and suicidal ideation, in validated self-administered questionnaires such as the Patient Health Questionnaire (PHQ-9). However, there is no standard protocol for responding to such disclosure, and the opportunity to support people at risk is potentially missed. We developed and evaluated a risk assessment protocol for the IBD-BOOST randomised controlled trial (ISRCTN71618461 09/09/2019). METHODS: Participants completed the PHQ-9 at baseline and 6-month and 12-month follow-ups. The trial database automatically alerted the research team to risk assess participants. Trial researchers, trained in the protocol, contacted participants by telephone, completed the risk assessment, and signposted participants to appropriate professional services. RESULTS: Seven hundred eighty participants were randomised in the trial; 41 required risk assessment. One participant declined assessment, so 40 risk assessments were completed. Twenty-four participants were assessed as low-risk and 16 participants as medium-risk, with 12 declaring previous suicide attempts. None were rated as high-risk. Trial participants expressed appreciation for being contacted, and all except two wished to receive information about professional support services. Trial risk assessors reported positive experiences of conducting the risk assessment with suggestions for improvement, which resulted in minor modifications to the protocol. DISCUSSION: Our evaluation demonstrated that it was viable for a research trial team to successfully conduct a risk-assessment protocol for trial participants reporting thoughts of self-harm, with training and support from senior colleagues. Resources are required for training and delivery, but it is not unduly onerous. Trial participants appeared to find completing the assessment acceptable.

Prevalence of subthreshold depression and its related factors in Chinese college students: A cross-sectional study.

Objective: To investigate the prevalence of subthreshold depression among Chinese college students and to explore the related factors. Methods: The research subjects were Chinese college students participating in the "2022 Psychology and Behavior Investigation of Chinese Residents (PBICR-2022)". Data on respondents' general characteristics, quality of life, perceived pressure, family communication, perceived social support, self-efficacy, and depression status were gathered. To investigate the association between each variable and the risk of subthreshold depression, statistical analyses, including chi-square tests and rank sum tests were conducted. Furthermore, a binary stepwise logistic regression was employed to establish the regression model of the factors related to subthreshold depression among Chinese college students. Results: A prevalence of subthreshold depression of about 39.7 % was found among the 8934 respondents. Logistic regression analysis revealed that respondents who are female, have chronic diseases, are in debt, experience significant impacts from epidemic control policies, have lower self-assessed quality of life, experience challenges in family communication, perceive lower social support, have lower self-efficacy, and feel higher perceived pressure are more likely to develop subthreshold depression compared to the control group. (P < 0.05). Conclusion: The prevalence rate of subthreshold depression among Chinese college students was found to be approximately 40 %. Female college students suffering from chronic diseases, with households in debt, greatly impacted by epidemic control policies, and experiencing high perceived stress, may be at risk for subthreshold depression among Chinese college students. On the other hand, strong family communication, perceived social support, and self-efficacy were identified as potential protective factors. In order to facilitate timely screening, diagnosis, and treatment of subthreshold depression in Chinese college students, it is crucial for the government, local communities, colleges, and families to prioritize the mental health of college students and implement targeted measures accordingly.

Serum neurofilament light chain levels are associated with depression among US adults: a cross-sectional analysis among US adults, 2013-2014.

BACKGROUND: Serum neurofilament light chain (sNfL) has been identified as a biomarker for neurologic diseases. However, sNfL remains unknown to be responsible for depression. AIMS: The aim of this research was to explore the relationship between sNfL levels and depression in US adults. METHODS: In this cross-sectional survey of the general population, we investigated representative data involving 10,175 participants from the 2013-2014 cycle of the National Health and Nutrition Examination Survey (NHANES). Depression was diagnosed using the Patient Health Questionnaire-9 (PHQ-9). The effect of related factors on depression was analyzed by conducting a univariate analysis. Stratified analysis was utilized to detect the stability and sensitivity of the relationship. After adjusting for race, education, marital status, smoking status, body mass index (BMI), sleep duration, income, and a history of hypertension, sedentary behavior and stroke, multivariable linear regression was performed to demonstrate the correlation between sNfL and depression. RESULTS: A total of 1301 individuals between the ages of 20 and 75 were involved in this investigation, of which 108 (8.3%) were diagnosed with depression. A significant positive correlation between sNfL and depression among adults in the US was observed by conducting univariable analyses. After adjusting for confounding factors, the multivariate analyses indicated that elevated sNfL levels might play a pivotal role in the development of depression (odds ratio (OR) = 3.0; 95% confidence interval (CI): (1.5, 6.1), P = 0.002). CONCLUSION: These results indicated that sNfL is closely linked to depression in a nationally representative individual. However, further studies are needed to confirm the biological mechanism as well as the clinical implications of sNfL and depression.

Mental health and academic performance of college students: Knowledge in the field of mental health, self-control, and learning in college.

The aim of this research is to analyze the impact of mental health on the academic performance of junior and senior students studying in a university setting during the 2022-2023 academic year, in the post-COVID period. The study was conducted in Beijing, China, with the participation of 600 students, including 300 first-year students and 300 fifth-year students. DASS (Depression, Anxiety, and Stress Scale) and PHQ-9 (Patient Health Questionnaire-9) questionnaires were employed to measure mental health. The DASS assesses symptoms of depression, anxiety, and stress, while the PHQ-9 specifically evaluates depression severity. Academic performance was evaluated using a 12-point scale, which incorporated various criteria such as exam scores, coursework performance, and participation in extracurricular activities. The research was conducted across five faculties of the university from 2022 to 2023. In the study, fifth-year students demonstrated a higher level of mental health compared to first-year students, with an average DASS score of 27.1 and 24.2, respectively. Interestingly, despite this, first-year students achieved higher academic performance indicators, with an average score of 8.2 compared to 9.8 in fifth-year students. Correlation analysis revealed significant associations between stress, depression, and anxiety levels with academic performance (stress: r = -0.25, p < 0.001; depression: r = -0.20, p = 0.003; anxiety: r = -0.18, p = 0.008). These findings highlight the critical importance of addressing students' mental well-being, particularly in later academic years. Recommendations include implementing support programs and developing online resources for students.

Comparison of Patient Health Questionnaire-9, Edinburgh Postnatal Depression Scale and Hospital Anxiety and Depression - Depression subscale scores by administration mode: An individual participant data differential item functioning meta-analysis.

Administration mode of patient-reported outcome measures (PROMs) may influence responses. We assessed if Patient Health Questionnaire-9 (PHQ-9), Edinburgh Postnatal Depression Scale (EPDS) and Hospital Anxiety and Depression Scale - Depression subscale (HADS-D) item responses and scores were associated with administration mode. We compared (1) self-administration versus interview-administration; within self-administration (2) research or medical setting versus private; and (3) pen-and-paper versus electronic; and within interview-administration (4) in-person versus phone. We analysed individual participant data meta-analysis datasets with item-level data for the PHQ-9 (N = 34,529), EPDS (N = 16,813), and HADS-D (N = 16,768). We used multiple indicator multiple cause models to assess differential item functioning (DIF) by administration mode. We found statistically significant DIF for most items on all measures due to large samples, but influence on total scores was negligible. In 10 comparisons conducted across the PHQ-9, EPDS, and HADS-D, Pearson's correlations and intraclass correlation coefficients between latent depression symptom scores from models that did or did not account for DIF were between 0.995 and 1.000. Total PHQ-9, EPDS, and HADS-D scores did not differ materially across administration modes. Researcher and clinicians who evaluate depression symptoms with these questionnaires can select administration methods based on patient preferences, feasibility, or cost.

Large Language Models Versus Expert Clinicians in Crisis Prediction Among Telemental Health Patients: Comparative Study.

BACKGROUND: Due to recent advances in artificial intelligence, large language models (LLMs) have emerged as a powerful tool for a variety of language-related tasks, including sentiment analysis, and summarization of provider-patient interactions. However, there is limited research on these models in the area of crisis prediction. OBJECTIVE: This study aimed to evaluate the performance of LLMs, specifically OpenAI's generative pretrained transformer 4 (GPT-4), in predicting current and future mental health crisis episodes using patient-provided information at intake among users of a national telemental health platform. METHODS: Deidentified patient-provided data were pulled from specific intake questions of the Brightside telehealth platform, including the chief complaint, for 140 patients who indicated suicidal ideation (SI), and another 120 patients who later indicated SI with a plan during the course of treatment. Similar data were pulled for 200 randomly selected patients, treated during the same time period, who never endorsed SI. In total, 6 senior Brightside clinicians (3 psychologists and 3 psychiatrists) were shown patients' self-reported chief complaint and self-reported suicide attempt history but were blinded to the future course of treatment and other reported symptoms, including SI. They were asked a simple yes or no question regarding their prediction of endorsement of SI with plan, along with their confidence level about the prediction. GPT-4 was provided with similar information and asked to answer the same questions, enabling us to directly compare the performance of artificial intelligence and clinicians. RESULTS: Overall, the clinicians' average precision (0.7) was higher than that of GPT-4 (0.6) in identifying the SI with plan at intake (n=140) versus no SI (n=200) when using the chief complaint alone, while sensitivity was higher for the GPT-4 (0.62) than the clinicians' average (0.53). The addition of suicide attempt history increased the clinicians' average sensitivity (0.59) and precision (0.77) while increasing the GPT-4 sensitivity (0.59) but decreasing the GPT-4 precision (0.54). Performance decreased comparatively when predicting future SI with plan (n=120) versus no SI (n=200) with a chief complaint only for the clinicians (average sensitivity=0.4; average precision=0.59) and the GPT-4 (sensitivity=0.46; precision=0.48). The addition of suicide attempt history increased performance comparatively for the clinicians (average sensitivity=0.46; average precision=0.69) and the GPT-4 (sensitivity=0.74; precision=0.48). CONCLUSIONS: GPT-4, with a simple prompt design, produced results on some metrics that approached those of a trained clinician. Additional work must be done before such a model can be piloted in a clinical setting. The model should undergo safety checks for bias, given evidence that LLMs can perpetuate the biases of the underlying data on which they are trained. We believe that LLMs hold promise for augmenting the identification of higher-risk patients at intake and potentially delivering more timely care to patients.

Assessing the Relationship Between Vitiligo and Major Depressive Disorder Severity: Cross-Sectional Study.

BACKGROUND: Vitiligo, a common dermatological disorder in Saudi Arabia, is associated with significant psychological impacts. This study explores the relationship between vitiligo and the severity of major depressive disorder (MDD), highlighting the broader implications on mental health among affected individuals. OBJECTIVE: We aim to assess the prevalence and predictors of depression among adult patients with vitiligo, and to examine the relationship between MDD severity and vitiligo. METHODS: Using a cross-sectional design, the research used the vitiligo area severity index and the Patient Health Questionnaire-9 to measure the extent of vitiligo and depression severity, respectively. This study involved 340 diagnosed patients with vitiligo from various health care settings. Logistic and ordinal regression analysis were applied to evaluate the impact of sociodemographic variables and vitiligo types on MDD severity. RESULTS: The prevalence of MDD was 58.8% (200/340) of participants. Depression severity varied notably: 18.2% (62/340) of patients experienced mild depression, 17.9% (61/340) moderate, 11.8% (40/340) moderately severe, and 10.9% (37/340) severe depression. Female patients had higher odds of severe depression than male patients (adjusted odds ratio [aOR] 3.14, 95% CI 1.93-5.1; P<.001). Age was inversely related to depression severity, with patients aged older than 60 years showing significantly lower odds (aOR 0.1, 95% CI 0.03-0.39; P<.001). Lower income was associated with higher depression severity (aOR 10.2, 95% CI 3.25-31.8; P<.001). Vitiligo types also influenced depression severity; vulgaris (aOR 5.3, 95% CI 2.6-10.9; P<.001) and acrofacial vitiligo (aOR 2.8, 95% CI 1.5-5.1; P<.001) were significantly associated with higher depression levels compared to focal vitiligo. CONCLUSIONS: The findings suggest that vitiligo contributes to an increased risk of severe depression, highlighting the need for integrated dermatological and psychological treatment approaches to address both the physical and mental health aspects of the disease.