Depression Screening Research Articles

Background: Depressive symptoms independently double cardiovascular disease risk, yet routine depression screening remains uncommon in Indian outpatient settings despite a high prevalence of hypertension and diabetes. Chronic cardiometabolic conditions often stem from maladaptive self-soothing behaviors such as consuming calorie-dense foods and physical inactivity, which may serve as both cause and consequence of psychological distress. We hypothesized that patients with cardiometabolic risk factors would have higher rates of positive depression screens compared to those without such risk. Methods: A cross-sectional survey was conducted among adults (≥18 years) attending a North-Indian medical school-based outpatient clinic. After informed consent, demographic data, cardiometabolic risk factors (hypertension, diabetes, dyslipidemia), and depressive symptoms were documented. These symptoms were assessed using the Patient Health Questionnaire-2 (PHQ-2). The research team performed all screenings. Complete data from 113 patients were analyzed. Results: None of the 113 patients were screened for depression by their treating physicians. Thirty-five patients (31.0%, 95% CI: 23.2–40.0%) had at least one cardiometabolic risk factor. The overall incidence of positive PHQ-2 screens in the population was 13.3%. Positive screens (PHQ-2 ≥3) were significantly more common among patients with cardiometabolic risk factors (25.7%, 95% CI: 14.2–42.1%) compared to those without risk factors (7.7%, 95% CI: 3.6–15.8%; p=0.021; odds ratio=4.15). Depression prevalence increased from 7.7% in patients without risk factors to 10.3% with one risk factor and 40% with two or more risk factors (p-trend=0.03). Conclusions: Cardiometabolic risk factors are associated with a fourfold increase in positive depression screens among North-Indian outpatients. PHQ-2 positivity in this context likely reflects a cycle where psychological distress and harmful lifestyle behaviors reinforce each other, worsening both mental and physical health. Despite this elevated burden, provider-initiated mental health referrals were absent. Integrating automated PHQ-2 screening into electronic health records is feasible and addresses India’s substantial depression treatment gap. Embedding cognitive-behavioral therapy within this workflow could help patients break maladaptive cycles, improve emotional regulation, and enhance adherence to healthy behaviors, ultimately reducing morbidity and improving quality of life.

A 16-year-old-male presented in 2016 after a fall with a concussion due to dizziness. Chest X-ray showed a prominent cardiac silhouette. Further workup showed an echocardiogram with no left ventricular hypertrophy and mild left ventricular dilation. A Holter monitor recorded 1259 single PACs and 87 aberrantly conducted PACs. The patient was diagnosed with anxiety in 2017 and started on sertraline and later changed to fluoxetine. These medications were stopped at the end of 2022. In early 2023, he presented with symptomatic sinus bradycardia. A coronary angiogram revealed no obstructive CAD. MRI showed LV noncompaction towards the ventricular apex. Genetic testing showed a heterozygous HCN4 gene mutation. The HCN4 gene mutation variants affect the cyclic nucleotide-gated cardiac ion channels, potentially leading to arrhythmias. It is most associated with patients with sinus node dysfunction. Specific mutations have been known to also present with left ventricular noncompaction (like in our patient), sick sinus syndrome, and susceptibility to ventricular fibrillation. Emerging evidence suggests that HCN4 gene may have potential expression in the brain. It is known that the HCN1 and HCN2 genes are common in the brain, but they are finding that the HCN4 gene is used as an “on-off” button that can control the way neurons respond to synaptic input. This gene mutation, Gln375Ter, is associated with LV noncompaction or sinus node dysfunction. However, very few cases show an association of arrhythmias with mood disorders. There is evidence that the HCN4 gene may be associated with anxiety and depression because of its presence in the brain and specifically its location in the frontal cortex, and thalamocortical network. Our case illustrates how symptoms related to the mutation gradually emerged in the interval of presentation and diagnosis of the HCN4 gene mutation. For patients presenting with symptomatic bradycardia, screening for anxiety and depression using DSM-V criteria could be crucial in identifying a genetic basis for their condition. Given that the HCN4 gene mutation can manifest in diverse ways due to its expression in both the heart and brain, awareness of these potential symptoms can aid the care team in accurately diagnosing this mutation.

ABSTRACT Background Approximately 280 million adults worldwide are diagnosed with depression. Undiagnosed and untreated patients with depression have a reduced quality of life and may lead to suicidal ideation. Increasing diagnostic and treatment access is critical, and community pharmacies are advantageously positioned to provide mental health services such as screening, treatment, and education. Patients visit community pharmacies more often than primary care providers, enabling regular depression screening and medication management. Despite their potential, few review articles comprehensively address the role of community pharmacy interventions in managing depression. The objective of this review is to systematically describe the current literature on depression interventions provided in community pharmacy settings. Methods Studies published in English that reported depression‐related interventions conducted in community pharmacy settings and by community pharmacists or students were included. PubMed and Web of Science databases were searched for published articles using keywords. Data were extracted and summarized on study design, setting, pharmacist interventions, patient demographics, and outcomes. Both experimental and observational studies were analyzed. Results Twenty‐three studies were included, comprising randomized and non‐randomized controlled trials, feasibility studies, cohort studies, and cross‐sectional analyses conducted across multiple countries. Interventions included pharmacist or student pharmacist‐led depression screenings, cognitive behavioral therapy, antidepressant adherence support, and referral services. Community pharmacists utilized tools such as the Patient Health Questionnaire‐9 (PHQ‐9) and Geriatric Depression Scale‐15 (GDS‐15) and provided mental health counseling. Studies demonstrated positive trends in adherence, depression symptom improvement, patient satisfaction, and screening reach. Barriers included lack of training, reimbursement mechanisms, and workflow integration. Conclusion Community pharmacies offer a promising, underutilized setting for depression screening and intervention. Pharmacist‐led services can support early identification of depression and medication adherence. Future work should standardize intervention protocols, assess long‐term outcomes, and address implementation barriers to scale these services in diverse practice settings.

The impact of neighborhood environment on adolescent anxiety and depression: A moderated mediation model involving screen time and family function.

Depression severity as a predictor of cardiovascular-kidney-metabolic syndrome progression and mortality: Results from two nationally representative cohort studies.

To systematically compare nurse-led versus traditional rehabilitation in improving clinical outcomes for stroke survivors. Systematic review and meta-analysis. Data were extracted from Cochrane, PubMed, Embase, and Web of Science (searched up to July 2024). Analyses with standardized mean differences (SMDs) and risk ratios (RRs) as the estimates were performed in Review Manager 5.4 and Stata 15.0. Randomized controlled trials investigating nurse-led stroke rehabilitation with outcomes such as mental component summary (MCS) and physical component summary (PCS) of quality of life, self-efficacy, National Institutes of Health Stroke Scale (NIHSS), stroke-specific quality of life (SS-QOL), Barthel Index (BI), Geriatric Depression Scale-15 (GDS-15), and pain were included. Sensitivity analyses and Grading of Recommendations Assessment, Development and Evaluation (GRADE) were performed. A total of 12 articles were included. The quality assessment indicated that most studies did not have a serious risk of bias. Nurse-led rehabilitation showed significant improvements in SS-QOL (SMD: 3.33, 95% CI: 1.26, 5.40; very low-quality evidence), depressive symptoms (GDS-15, SMD: -2.21; 95% CI: -2.80, -1.63; high-quality evidence), pain (SMD: -1.61; 95% CI: -2.14, -1.08; high-quality evidence), and BI (SMD: 0.24, 95% CI: 0.01, 0.48; low-quality evidence). However, there were no significant differences in MCS, PCS, self-efficacy, or NIHSS between the two groups. Sensitivity analysis showed that the results for SS-QOL and BI were unstable and should be interpreted with caution. Nurse-led rehabilitation is effective in improving psychological outcomes, particularly depression (GDS-15) and pain, although this high-quality evidence is based on a single study. Functional independence (BI) and SS-QOL are also improved, but the evidence for these outcomes is of low quality and highly unstable in sensitivity analyses. No significant benefits are found for other outcomes. The evidence quality varies, and future high-quality studies are needed to confirm these findings. Incorporating nurse-led rehabilitation into stroke guidelines and implementing standardized depression screening programs and non-pharmacological pain interventions in community rehabilitation could be beneficial for populations with depressive symptoms and chronic pain. This study adhered to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for transparent reporting of systematic reviews. This study did not include patient or public involvement in its design, conduct, or reporting.

Chronic Pain Prevalence, Characteristics, and Impact in United States Adults With Chronic Fatigue Syndrome/Myalgic Encephalomyelitis.

Introduction Chronic illness affects patients’ quality of life and often leads to underdiagnosed psychological issues, which can impact treatment adherence. This study aimed to assess quality of life in Tunisian patients with chronic diseases, screen for anxiety and depression, and evaluate their effect on medication adherence. Methods We conducted a cross-sectional study including 170 patients consulting at the National Social Security Fund for chronic conditions, from September to November 2022. Quality of life was assessed using the Short Form 12 Health Survey, anxiety and depression using the Hospital Anxiety and Depression scale, and treatment adherence using the Morisky, Green, and Levine scale. Results Among the 170 patients included in this study, 116 were women (68.2%), with a female-to-male ratio of 2.14. The mean age was 60 years and 5 months ± 9.85 years. The most common conditions were cardiovascular (71.7%), endocrine (64.7%), and pulmonary diseases (40.5%). The prevalences of depression and anxiety were 51.8% and 47%, respectively. Quality of life was impaired, with mean physical and mental scores of 35.05 ± 9.69 and 44.32 ± 11.13, respectively. Anxiety was more prevalent among women (p<0.001) and individuals under 60 years of age (p=0.009). Depression and anxiety were negatively correlated with quality of life. Depressive symptoms were associated with lower levels of treatment adherence (p=0.049). Conclusion Anxiety and depression were frequent among patients with chronic diseases and were associated with poorer quality of life and lower treatment adherence. These findings underscore the burden of psychological distress in this population and highlight its detrimental effects on both well-being and disease management.

Background Depressive disorder represents a major public health burden globally, yet the validity of the Patient Health Questionnaire-9 (PHQ-9)—a widely used depression screening tool—remains underexplored in Chinese psychiatric inpatient populations, particularly in age-stratified analyses. This study aimed to (1) validate the Chinese version of the PHQ-9 in Chinese psychiatric inpatients (contrasting with community-based findings) and (2) compare its psychometric properties between adolescent and adult inpatients. Methods This cross-sectional study enrolled 485 psychiatric inpatients (including 105 adolescents) from Shanxi Bethune Hospital. Participants completed the Chinese version of the PHQ-9. Analyses encompassed confirmatory factor analysis (CFA), Gaussian Graphical Model-based network analysis, and receiver operating characteristic (ROC) curve analysis to determine optimal diagnostic cutoff scores. Results Results showed the PHQ-9 had good internal consistency: Cronbach’s α = 0.876 (adolescents) and 0.883 (adults). CFA revealed no significant difference in fit between the unidimensional and two-factor (cognitive-affective vs. somatic) models in adolescents (Δχ²=0.79, p=0.374), with both models showing marginal fit (likely affected by small sample size). In adults, the two-factor model was preferred (Δχ²=6.49, p=0.011). The Network Comparison Test found no significant differences in network structure (M = 0.211, p=0.598) or global strength (S = 0.262, p=0.186) between age groups, but the adolescent network had poor stability (correlation stability coefficient = 0), limiting interpretation. ROC analysis identified age-specific optimal cutoffs exceeding the conventional threshold of 10: 15.5 for adolescents (sensitivity=0.84, specificity=0.47) and 14.5 for adults (sensitivity=0.79, specificity=0.66). Notably, 64.7% of the total sample scored ≥15 on the PHQ-9, while only 43.7% had a primary diagnosis of depressive disorder (ICD-11 6A7), indicating comorbid depressive symptoms contributed to higher cutoffs. Conclusion The findings of this study validate the structural validity and diagnostic validity of the PHQ-9 among Chinese adult psychiatric inpatients, while emphasizing that the interpretation of its factor structure in the adolescent population requires caution. The age-related symptom topological patterns indicated by network analyses are highly likely to be influenced by the insufficient size of the adolescent sample and need to be confirmed by subsequent studies. The results of the ROC curve highlight the clinical significance of formulating population-specific diagnostic cutoffs; however, the impact of comorbidity on the findings of this study must be taken into consideration.

Background: Depression, obesity, and brain tumours represent significant public health challenges individually, but recent evidence says these conditions may share overlapping biological/ physiological pathways, which could cause compounding disease burden and complicating clinical management. Obesity has been associated with chronic systemic inflammation, hormonal imbalances, and neurobiological changes that increase vulnerability to mood disorders and certain cancers, including brain tumours. Depression is highly prevalent among patients with brain tumours and affects their quality of life, treatment adherence, and survival outcomes. However, the bidirectional interactions among obesity, depression, and brain tumours remain poorly understood. Objective: This systematic review aimed to synthesize the existing evidence on the interrelationship between depression, obesity, and brain tumours, exploring their shared pathophysiological mechanisms, epidemiological links, and clinical implications. Methods: A systematic search of the PubMed, Scopus, Web of Science, Science Direct, and PsycINFO databases was conducted for studies published between 2000 and 2025. Eligible studies included observational, experimental, and review articles that examined the association between depression, obesity, and brain tumours in adult populations. Quality assessment was performed using the Critical Appraisal Skills Program (CASP) checklist for observational studies, and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. Results and Discussion: A total of 35 studies met the inclusion criteria. Evidence suggests that obesity-related inflammatory markers, such as IL-6, TNF-α, and CRP, may contribute to the neuroinflammation implicated in both depressive symptoms and tumour progression. Furthermore, depression is both a psychological consequence of brain tumours and a potential prognostic factor for worse clinical outcomes. Few studies have explicitly explored the tripartite relationship, indicating a significant research gap. Addressing obesity, screening for depression, and understanding shared biological pathways can improve prevention, early intervention, and treatment outcomes for depression, obesity, and brain tumours. Conclusion: The available literature supports the interconnections among depression, obesity, and brain tumours, primarily through inflammatory and neuroendocrine pathways. However, integrated studies examining these three conditions concurrently are limited. Future research should prioritize longitudinal studies to clarify these relationships and inform multidisciplinary preventive and treatment strategies.

Two of the most actively studied modifiable lifestyle factors, exercise and video gaming, are regularly touted as easy and effective ways to enhance brain function and/or protect it from age-related decline. However, some critical lingering questions and methodological inconsistencies leave it unclear what aspects of brain health are affected by exercise and video gaming. In this cross-sectional global online study, we recruited over 1000 people and collected data about participants’ physical activity levels, time spent playing video games, mental health, and cognitive performance using tests of short-term memory, verbal abilities, and reasoning skills from the Creyos battery. The amount of regular physical activity was not significantly related to any measure of cognitive performance; however, more physical activity was associated with better mental health as indexed using the Patient Health Questionnaire (PHQ-2) and Generalized Anxiety Disorder (GAD-2) screeners for depression and anxiety. Conversely, we found that more time spent playing video games was associated with better cognitive performance but was unrelated to mental health. We conclude that exercise and video gaming have differential effects on the brain, which may help individuals tailor their lifestyle choices to promote mental and cognitive health, respectively, across the lifespan.

BackgroundPostpartum depression is common and leads to an increase in the risk of poorer maternal outcomes and suicide. Implementing effective screening and treatment for postpartum depression is an international public health priority.ObjectiveThis study aims to estimate the cost-effectiveness of implementing a strategy of Whooley screening followed by referral to Cognitive Behavioral Therapy (CBT) for women screened positive compared with the current Treatment as Usual (TAU) for women with postpartum depression in Hong Kong.MethodsA decision tree model was constructed to estimate the potential cost and utility benefits for Whooley screening followed by referral to CBT for women screened positive compared to TAU in Hong Kong. The model used healthcare costs, in Hong Kong Dollars (HKD), and quality-adjusted life years (QALYs) to estimate economic and health utility outcomes. We used two states (no depression/remission, and depression) modeled over the postpartum period. Deterministic, probabilistic sensitivity analyses and scenario analyses were conducted to explore the robustness of the results under the uncertainty around the model input parameters.ResultsThe base-case analysis suggested that Whooley screening followed by referral to CBT for women screened positive yielded an additional 0.014 QALYs compared to TAU and added HKD3193.15 to the cost per patient. Deterministic sensitivity analysis indicated that cost-effectiveness results were robust to utilities associated with depression, utilities associated with no depression/remission, and the probability of no improvement in depression for CBT. Probabilistic sensitivity analysis showed that Whooley screening followed by referral to CBT for women screened positive had a 100% likelihood of being more cost-effective than TAU at a willingness-to-pay (WTP) threshold of HKD422,191/QALY. Scenario analysis showed the important influence of patients’ acceptability and adherence to CBT on outcomes and revealed the impact of subsequent treatment costs on model results after considering subsequent treatment of false negative patients.ConclusionsWhooley screening followed by referral to CBT for women screened positive is estimated to be cost-effective in identifying and treating women with postpartum depression at an early stage compared to TAU. More research is required to assess this strategy’s feasibility, cost-benefit, and clinical effectiveness.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12888-025-07459-y.

PurposeThis study aims to investigate the topological structure of symptoms and positive psychological variables in stroke survivors through the network analysis method.Patients and MethodsThis is a cross-sectional study. A total of 622 Chinese stroke patients were recruited from six diverse tertiary general hospitals in Tianjin, China, from February to September 2024. The Assessment of Daily Living scale (ADL), Pittsburgh Sleep Quality Index (PSQI), Numerical Rating Scale (NRS), Mini-Mental State Examination (MMSE), Self-Rating Anxiety Scale (SAS), and Self-Rating Depression Scale (SDS) were employed to assess the distress caused by symptoms in these patients. Positive psychological constructs were quantified via the Herth Hope Index (HHI), Perceived Social Support Scale (PSSS), and General Self-Efficacy Scale (GSES). Network analysis was employed to investigate the interplay between these positive psychological variables and the distress associated with stroke symptoms.Results“Cognitive impairment’’ and “Functional disability” (MMSE-ADL, edge weight = −0.610) had the strongest negative connection. “Anxiety” and “Depression” (SAS-SDS, edge weight = 0.556) had the strongest positive connection. Depression (SDS) demonstrated the highest strength centrality, indicating its role as the most interconnected symptom. Family support (PSSS-1) emerged as the most central positive psychology variable, with the highest closeness and betweenness scores, acting as a critical bridge between psychological and somatic symptom clusters.ConclusionDepression and family support are pivotal nodes in stroke symptom networks. Integrating family-centered interventions with early depression screening may disrupt symptom propagation and improve outcomes. These findings underscore the need for multicomponent strategies addressing both psychological and social determinants of recovery in stroke care.

Depression is a common comorbidity in dementia, with prevalence ranging from 20 to 60% across different countries. This study examined whether depressive symptom severity levels differ by dementia characteristics and country of residence in people living with dementia. This cross-sectional analysis used baseline data from 376 participants in the HOMESIDE trial. Linear regression models examined differences in depressive symptom severity levels by dementia stage, type, severity, and country. In this sample (57% male, mean age 76.6 years), depressive symptom scores were higher for people with severe cognitive impairment than those with mild dementia (MMSE 24–30) (adjusted mean difference: 3.78, 95% CI 1.60–5.96). Mean depressive symptom severity was lower in Norway, Germany, and United Kingdom compared to Australia, with no significant difference for Poland. No apparent differences by dementia type or stage were found. Depressive symptom severity levels differed by cognitive impairment severity and country. Cross-national differences likely reflect a complex interplay of healthcare systems, cultural factors, family support structures, and societal approaches to dementia care. Regular depressive symptom screening is recommended, particularly for severe dementia.Trial registration: ACTRN12618001799246 (Australian New Zealand Clinical Trials Registry) and NCT03907748 (ClinicalTrials.gov).Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-20385-z.

Background:Depression negatively affects how a person feels, thinks, or behaves; is associated with impaired functioning in social and work settings; and can be associated with thoughts of suicide. This update of the 2013 Canadian Task Force on Preventive Health Care guideline provides an evidence-based recommendation about instrument-based screening for depression.Methods:For this update, we commissioned a systematic review on benefits and harms of instrument-based screening (i.e., using a screening tool) for depression among adults. The systematic review covered relevant literature from October 2018 to May 2020, updated to January 2025 for trials, and to March 2025 for trial registries. We examined patient values and preferences via patient engagement surveys and focus groups; we engaged content experts and other interest holders at key points throughout the project. We used the Grading of Recommendations, Assessment, Development and Evaluation approach to determine the certainty of evidence for each outcome and strength of the recommendation; adhered to the Guidelines International Network principles of managing competing interests; and followed Appraisal of Guidelines for Research and Evaluation, and Guidance for Reporting Involvement of Patients and the Public reporting guidance.Recommendations:We recommend against screening all adults aged 18 years and older for depression using questionnaires (strong recommendation, very low-certainty evidence), based on evidence suggesting that depression screening using a screening tool has little to no effect on health. This recommendation does not apply to adults with a personal history, current diagnosis, or clinical suspicion of a diagnosis of depression or another mental health disorder. It does apply to those who may be at an elevated risk of depression.Interpretation:The recommendation against screening adults for depression using a screening tool emphasizes the importance of good clinical care, where clinicians ask about their patients’ well-being and remain vigilant for symptoms and signs of depression.

In older and senile age, the prevalence of night-time sleep disturbances increases significantly (up to 30–48%), which is associated with both physiological changes in sleep and medical and behavioural factors.Objective: to identify clinical and social factors contributing to sleep disorders in older people and establish their relationship with internal organ diseasesMaterials and methods. The study included 1,002 patients aged 60–90 who underwent a comprehensive geriatric examination, screening for sleep disorders (Pittsburgh Sleep Quality Index) and depression (Geriatric Depression Scale), as well as a neuropsychological examination. An analysis of clinical and social factors and an analysis of associations with somatic diseases were performed, and sleep disorder phenotypes were identified by data clustering (UMAP + K-means).Results. A decrease in sleep efficiency with age (p<0.001) was identified, while sleep duration remained unchanged within the age range studied. Presomnic disturbances (prevalence – 9.6%) were associated with female gender, lower income, education and physical activity level, intrasomnic disturbances (prevalence – 12.3%) were associated with cardiovascular diseases, body mass index, having a partner, introversion, and taking walks. Common predictors for both falling asleep and staying asleep were pain syndrome, depression, and geriatric syndromes of asthenia and sarcopenia. Cluster analysis identified five phenotypes that differed not only in their sleep disturbance patterns but also in their clinical and social characteristics, subjective attitudes toward sleep, and ageing profiles with varying risks of developing geriatric syndromes.Conclusion. Clear clinical and social correlates have been identified in elderly patients: presomnic disturbances are associated with female gender and socio-economic factors, while intrasomnic disturbances are predominantly associated with somatic pathology. Of particular importance is the identification of five discrete phenotypes of sleep disorders, each characterised by a unique combination of clinical parameters, ageing pro- file, and risk of geriatric syndromes.

ObjectiveThis systematic review and meta-analysis examined the prevalence of depression among individuals with diabetes and identified associated risk factors.MethodsFive databases (PubMed, Web of Science, Cochrane, ProQuest, Embase) were searched for observational studies reporting depression prevalence and multivariable-adjusted risk factors in diabetic populations. Two reviewers independently screened and extracted data. Analyses were conducted using R software.ResultsThirty-nine studies involving 17,486 diabetic patients were included. The pooled prevalence of depression was 35% (95% CI: 30%–41%). Risk factors included age ≤60 years, female sex, being single, unemployment, physical inactivity, anxiety, limited social support, poor medication adherence, complications (neuropathy, nephropathy, retinopathy, foot ulcers), physical disability, insulin therapy, combined insulin–oral treatment, and fasting glucose ≥126 mg/dL.ConclusionDepression affects over one-third of diabetic patients and is associated with sociodemographic, psychological, and clinical factors. Our study provides updated global evidence and identifies specific high-risk profiles (e.g., females, those with complications, or on combination therapy), supporting the need for targeted screening beyond general recommendations. These findings support the integration of standardized depression screening tools such as the PHQ-9 into routine diabetes care, particularly in resource-limited settings. For patients with identified risk factors, regular follow-up screening is recommended to enable early detection and timely intervention. Routine screening and timely intervention are essential, especially for high-risk groups. Longitudinal studies are needed to clarify causal links and inform targeted prevention.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/, identifier CRD420250656589.

Abstract Artificial general intelligence (AGI) and artificial intelligence-generated content (AIGC) technologies are transforming mental health care by enabling early diagnosis, personalized treatment, and innovative therapeutic interventions. This systematic review evaluates the applications, benefits, and challenges of AGI and AIGC in diagnosing and managing depression and related disorders. A comprehensive literature search was conducted across PubMed, PsycINFO, EMBASE, Scopus, and Web of Science, with the last update on June 2, 2024. Studies were included if they assessed the role of AGI or AIGC in screening, diagnosis, treatment, or monitoring of depression. Exclusion criteria included non-English publications, review articles, and studies unrelated to artificial intelligence (AI) applications in mental health. Risk of bias was evaluated using standardized assessment tools, and findings were synthesized qualitatively. Of 246 identified articles, 34 met the inclusion criteria. Key findings indicate that AGI enhances diagnostic accuracy by integrating multimodal data (e.g. neuroimaging, wearable devices, and behavioral analysis), whereas AI-driven tools improve treatment personalization and real-time monitoring. AI-assisted psychotherapy and drug discovery models show promise in optimizing mental health interventions. However, challenges remain regarding algorithmic bias, data privacy, regulatory compliance, and ethical concerns. AGI and AIGC offer transformative potential in mental health care, improving diagnostic precision and personalized treatment strategies. However, further research is required to validate AI-driven interventions, mitigate bias, and establish ethical frameworks for clinical integration. Ensuring equitable access and robust validation will be essential for the responsible adoption of AI in psychiatry.

BackgroundInsomnia is a significant independent risk factor for depression and suicidality. However, these conditions often go undetected, particularly in individuals presenting with sleep complaints. This study aimed to develop and validate machine learning (ML) models for the indirect screening of suicidal ideation (SI) and depression and to specifically evaluate their performance in a population reporting at least subthreshold insomnia.MethodsData were obtained from a Slovenian nationwide community sample (N = 2,989) via an online questionnaire. Logistic regression models were developed to predict SI (measured by SIDAS) and moderate-to-severe depression (measured by DASS-21) via indirect predictors, including socio-demographics, life satisfaction, behavioral changes, and 14 coping strategies from the Brief COPE inventory. The model performance was tested on a validation sample, which was stratified into groups with (Insomnia Severity Index [ISI] score ≥ 8; n = 917) and without (ISI < 8; n = 819) insomnia symptoms.ResultsThe models demonstrated strong and consistent predictive performance across both groups. The area under the receiver operating characteristic curve (AUROC) for the SI model was 0.78 in the insomnia group and 0.80 in the non-insomnia group. For the depression model, the AUROCs were 0.79 and 0.82, respectively. The minimal difference in performance indicates that the models are robust and equally effective regardless of the presence of insomnia.ConclusionOur findings demonstrate that ML models using indirect questions can effectively screen for both suicidality and depression simultaneously. The models' robust performance in individuals with insomnia highlights their potential as feasible, ethical, and efficient tools for early detection. Given that sleep complaints are a common reason for seeking healthcare, this approach offers a critical opportunity for timely intervention in a high-risk population, potentially reducing preventable morbidity and mortality associated with suicide and depression.

Depression and anxiety affect 10%-20% of the population, are leading causes of nonfatal disease, and are underdiagnosed globally. Mental health can play a significant role in surgical outcomes, including treatment of degenerative spinal conditions. Understanding the relationships between mental health and spinal surgery outcomes is critical for optimizing perioperative care. Consecutive patients without a prior diagnosis of anxiety or depression and scheduled to undergo single-level lumbar fusion surgery were prospectively administered a quality of life survey, the EQ-5D tool (n = 1771). The EQ-5D anxiety/depression score (EAS) (subscore range 1-3) was calculated for each patient. Coarsened exact matching was used to perform a 1:1 match of patients with the highest EAS to those with the lowest EAS while controlling for patient characteristics known to impact outcomes. Primary outcomes included intraoperative durotomy, length of stay, discharge disposition, and 30- and 90-day emergency department (ED) visits, readmissions, reoperations, and mortality. After exactly matching patients with an EAS of 3 and 1, an elevated risk of anxiety and depression (EAS 3, n = 85 vs EAS 1, n = 85) was associated with significantly increased duration of hospital stay (4.03 days vs 3.23 days, p < 0.001), nonhome discharge (OR 3.28 [95% CI 1.40-7.66], p = 0.004), 30- and 90-day readmission (OR 5.0 [1.10-22.82], p = 0.021 and OR 3.66 [1.02-13.14], p = 0.033, respectively), and 90-day ED visits (OR 9.0 [1.14-71.03], p = 0.011). No significant differences in durotomy rates or 30- or 90-day reoperation rates existed between cohorts. Risk of undiagnosed depression and anxiety, as measured by the EAS, is associated with greater odds of short-term postoperative healthcare utilization, but not rate of durotomy or reoperation. Depression and anxiety screening tools, such as the EAS, may help guide targeted risk-mitigation strategies among patients undergoing spinal fusion surgery.