Misha Sadeghi, Robert Richer, Bernhard Egger, Lena Schindler-Gmelch, Lydia Helene Rupp, Farnaz Rahimi, Matthias Berking, Bjoern M. Eskofier
{"title":"Harnessing multimodal approaches for depression detection using large language models and facial expressions","authors":"Misha Sadeghi, Robert Richer, Bernhard Egger, Lena Schindler-Gmelch, Lydia Helene Rupp, Farnaz Rahimi, Matthias Berking, Bjoern M. Eskofier","doi":"10.1038/s44184-024-00112-8","DOIUrl":"10.1038/s44184-024-00112-8","url":null,"abstract":"Detecting depression is a critical component of mental health diagnosis, and accurate assessment is essential for effective treatment. This study introduces a novel, fully automated approach to predicting depression severity using the E-DAIC dataset. We employ Large Language Models (LLMs) to extract depression-related indicators from interview transcripts, utilizing the Patient Health Questionnaire-8 (PHQ-8) score to train the prediction model. Additionally, facial data extracted from video frames is integrated with textual data to create a multimodal model for depression severity prediction. We evaluate three approaches: text-based features, facial features, and a combination of both. Our findings show the best results are achieved by enhancing text data with speech quality assessment, with a mean absolute error of 2.85 and root mean square error of 4.02. This study underscores the potential of automated depression detection, showing text-only models as robust and effective while paving the way for multimodal analysis.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-14"},"PeriodicalIF":0.0,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00112-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880558","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}
Rosaura Orengo-Aguayo, Regan W. Stewart, Tania del Mar Rodríguez-Sanfiorenzo, Karen G. Martínez-González
{"title":"Implementation of trauma and disaster mental health awareness training in Puerto Rico","authors":"Rosaura Orengo-Aguayo, Regan W. Stewart, Tania del Mar Rodríguez-Sanfiorenzo, Karen G. Martínez-González","doi":"10.1038/s44184-024-00110-w","DOIUrl":"10.1038/s44184-024-00110-w","url":null,"abstract":"Climate change is disproportionately impacting youth mental health around the world. Using a Community-Based Participatory approach, three universities (one in South Carolina and two in Puerto Rico) partnered after the devastation of Hurricane Maria in 2017. We offered culturally and linguistically tailored trauma and disaster-informed mental health awareness training (e.g., Psychological First Aid (PFA), Trauma Informed Care (TIC), & Suicide & Crisis Management) to 9236 individuals and 652 Puerto Rican youth were identified and referred to mental health services as a result. The US Surgeon General featured our program as a promising model to help disaster-affected youth.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00110-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873620","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}
Marco Giurgiu, Irina Timm, Ulrich W. Ebner-Priemer, Florian Schmiedek, Andreas B. Neubauer
{"title":"Causal effects of sedentary breaks on affective and cognitive parameters in daily life: a within-person encouragement design","authors":"Marco Giurgiu, Irina Timm, Ulrich W. Ebner-Priemer, Florian Schmiedek, Andreas B. Neubauer","doi":"10.1038/s44184-024-00113-7","DOIUrl":"10.1038/s44184-024-00113-7","url":null,"abstract":"Understanding the complex relationship between sedentary breaks, affective well-being and cognition in daily life is critical as modern lifestyles are increasingly characterized by sedentary behavior. Consequently, the World Health Organization, with its slogan “every move counts”, emphasizes a central public health goal: reducing daily time spent in sedentary behavior. Previous studies have provided evidence that short sedentary breaks are feasible to integrate into daily life and can improve affective and cognitive parameters. However, observational studies do not allow for causal interpretation. To overcome this limitation, we conducted the first empirical study that integrated the within-person encouragement approach to test the causal effects of short 3-min sedentary breaks on affective and cognitive parameters in daily life. The results suggest that brief sedentary breaks may have a beneficial impact on valence and energetic arousal. Moreover, our methodological approach powerfully demonstrated the possibility of moving towards causal effects in everyday life.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00113-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873618","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":"Detecting and tracking depression through temporal topic modeling of tweets: insights from a 180-day study","authors":"Ranganathan Chandrasekaran, Suhas Kotaki, Abhilash Hosaagrahaara Nagaraja","doi":"10.1038/s44184-024-00107-5","DOIUrl":"10.1038/s44184-024-00107-5","url":null,"abstract":"Depression affects over 280 million people globally, yet many cases remain undiagnosed or untreated due to stigma and lack of awareness. Social media platforms like X (formerly Twitter) offer a way to monitor and analyze depression markers. This study analyzes Twitter data 90 days before and 90 days after a self-disclosed clinical diagnosis. We gathered 246,637 tweets from 229 diagnosed users. CorEx topic modeling identified seven themes: causes, physical symptoms, mental symptoms, swear words, treatment, coping/support mechanisms, and lifestyle, and conditional logistic regression assessed the odds of these themes occurring post-diagnosis. A control group of healthy users (284,772 tweets) was used to develop and evaluate machine learning classifiers—support vector machines, naive Bayes, and logistic regression—to distinguish between depressed and non-depressed users. Logistic regression and SVM performed best. These findings show the potential of Twitter data for tracking depression and changes in symptoms, coping mechanisms, and treatment use.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00107-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142790458","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":"Exploring digital use, happiness, and loneliness in Japan with the experience sampling method","authors":"Yijun Chen, Xiaochu Zhang, Rei Akaishi","doi":"10.1038/s44184-024-00108-4","DOIUrl":"10.1038/s44184-024-00108-4","url":null,"abstract":"Smartphones have become an integral part of modern life, raising concerns about their impact on mental health, especially among young people. However, previous studies yielded inconsistent results, possibly due to neglecting the possibility of interactions between offline and online communications. To explore potential interactions among different communication modes (online vs. offline) and communication types (private vs. public), we adopted the experience sampling method to track 418 Japanese individuals over 21 days and analyzed the data using multilevel models and psychometric network models. The findings revealed that digital use has only small direct effects on happiness and loneliness, especially through public (one-to-many) online communication. The increased digital use reduced offline communication time, indirectly influencing loneliness to a large degree. Overall, this study highlights the indirect effects of decreased face-to-face communication and the significant role of one-to-many online communication, which may explain a part of the diverse findings on this issue.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00108-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142790481","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}
Nicholas J. Dobbins, Jacqueline Chipkin, Tim Byrne, Omar Ghabra, Julia Siar, Mitchell Sauder, R. Michael Huijon, Taylor M. Black
{"title":"Deep learning models can predict violence and threats against healthcare providers using clinical notes","authors":"Nicholas J. Dobbins, Jacqueline Chipkin, Tim Byrne, Omar Ghabra, Julia Siar, Mitchell Sauder, R. Michael Huijon, Taylor M. Black","doi":"10.1038/s44184-024-00105-7","DOIUrl":"10.1038/s44184-024-00105-7","url":null,"abstract":"Violence, verbal abuse, threats, and sexual harassment of healthcare providers by patients is a major challenge for healthcare organizations around the world, contributing to staff turnover, distress, absenteeism, reduced job satisfaction, and worsening mental and physical health. To enable interventions prior to possible violent episodes, we trained two deep learning models to predict violence against healthcare workers 3 days prior to violent events for case and control patients. The first model is a document classification model using clinical notes, and the second is a baseline regression model using largely structured data. Our document classification model achieved an F1 score of 0.75 while our model using structured data achieved an F1 of 0.72, both exceeding the predictive performance of a psychiatry team who reviewed the same documents (0.5 F1). To aid in the explainability and understanding of risk factors for violent events, we additionally trained a named entity recognition classifier on annotations of the same corpus, which achieved an overall F1 of 0.7. This study demonstrates the first deep learning model capable of predicting violent events within healthcare settings using clinical notes, surpassing the first published baseline of human experts. We anticipate our methods can be generalized and extended to enable intervention at other hospital systems.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00105-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142788036","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":"Development of the psychopathological vulnerability index for screening at-risk youths: a Rasch model approach","authors":"Yujing Liao, Haitao Shen, Wenjie Duan, Shanshan Cui, Chunxiu Zheng, Rong Liu, Yawen Jia","doi":"10.1038/s44184-024-00106-6","DOIUrl":"10.1038/s44184-024-00106-6","url":null,"abstract":"Accumulating research on mental health emphasizes the general factor of psychopathology (p-factor) that unites various mental health issues. This study develops a psychopathological vulnerability assessment for youths, evaluating its psychometric properties and clinical utility. An umbrella review conceptualized multifactor psychopathological vulnerability, leading to a 57-item pool. A total of 11,224 individuals participated in this study. The resulting 22-item psychopathological vulnerability index (PVI) fitted the unidimensional Rasch model, demonstrating a person separation reliability of 0.78 and a Cronbach’s alpha of 0.84. Cut-off points of 11 and 5, derived from latent class analysis, were used to distinguish vulnerable and high-protection populations. The PVI’s concurrent and predictive hit rates ranged from 36.00% to 53.57% in clinical samples. The PVI concretized the vulnerability–stress model for identifying at-risk youths and may facilitate universal interventions by integrating the theoretical foundations of bifactor S-1 models with key symptoms from network models for theoretically grounded approaches.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-16"},"PeriodicalIF":0.0,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11612436/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142775310","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}
Yu Jin, Yinjie Fan, Jian He, Amanda Wilson, Yi Li, Jiaqi Li, Yajun Bu, Yuanyuan Wang
{"title":"Symptomatic associations and sexual differences in depression and communication","authors":"Yu Jin, Yinjie Fan, Jian He, Amanda Wilson, Yi Li, Jiaqi Li, Yajun Bu, Yuanyuan Wang","doi":"10.1038/s44184-024-00098-3","DOIUrl":"10.1038/s44184-024-00098-3","url":null,"abstract":"Previous studies have explored the associations between parental and offspring’s depression and parent-child communication. However, few studies have investigated their symptomatic associations and potential sex differences. Therefore, this study aims to examine their associations and sex differences in parents and offspring. Based on the China Family Panel Studies (CFPS)-2020 study, depressive symptoms and parent-child communication were measured by the 8-item Center for Epidemiologic Studies Depression Scale (CESD-8) and independent questions, respectively. Network analysis was used to investigate the associations and to compare the sex differences of parents and offspring. A total of 1710 adolescents were included after cleaning process (N = 28,530). There were significantly stronger associations in boys’ “anhedonia” and “arguments with parents”, and in girls’ “happiness” and parents’ “joyfulness”. Furthermore, there were same-sex depression associations between children and parents (e.g., boys’ “despair”–fathers’ “joyfulness”; girls’ “anhedonia”–mothers’ “loneliness”). These results would help us to better understand the in depression and communication nuanced associations and to develop effective strategies for improving parental and offspring’s mental health.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00098-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142758096","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}
Judith Cukor, Zhenxing Xu, Veer Vekaria, Fei Wang, Mark Olfson, Samprit Banerjee, Gregory Simon, George Alexopoulos, Jyotishman Pathak
{"title":"Longitudinal trajectories of symptom change during antidepressant treatment among managed care patients with depression and anxiety","authors":"Judith Cukor, Zhenxing Xu, Veer Vekaria, Fei Wang, Mark Olfson, Samprit Banerjee, Gregory Simon, George Alexopoulos, Jyotishman Pathak","doi":"10.1038/s44184-024-00104-8","DOIUrl":"10.1038/s44184-024-00104-8","url":null,"abstract":"Despite the high correlation between anxiety and depression, little remains known about the course of each condition when presenting concurrently. This study aimed to identify longitudinal patterns during antidepressant treatment in patients with depression and anxiety, and evaluate related factors associated with these patterns. By analyzing longitudinal self-report Patient Health Questionnaire-9 (PHQ-9) and General Anxiety Disorder-7 (GAD-7) scores that tracked courses of depression and anxiety over a three-month window among the 577 adult participants, six depression and six anxiety trajectory subgroups were computationally derived using group-based trajectory modeling. Three depression subgroups showed symptom improvement, while three showed nonresponses. Similar patterns were observed in the six anxiety subgroups. Multinomial regression was used to associate patient characteristics with trajectory subgroup membership. Compared to patients in the remission group, factors associated with depressive symptom nonresponse included older age and lower depression severity.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00104-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142737666","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":"Impact of pandemic-related worries on mental health in India from 2020 to 2022","authors":"Youqi Yang, Anqi Sun, Lauren Zimmermann, Bhramar Mukherjee","doi":"10.1038/s44184-024-00101-x","DOIUrl":"10.1038/s44184-024-00101-x","url":null,"abstract":"This study examines how pandemic-related worries affected mental health in India’s adults from 2020 to 2022. Using data from the Global COVID-19 Trends and Impact Survey (N = 2,576,174), it explores the associations between worry variables (financial stress, food insecurity, and COVID-19-related health worries) and self-reported symptoms of depression and anxiety. Our analysis, based on complete cases (N = 747,996), used survey-weighted models, adjusting for demographics and calendar time. The study finds significant associations between these worries and mental health outcomes, with financial stress being the most significant factor affecting both depression (adjusted odds ratio, aOR: 2.36; 95% confidence interval, CI: [2.27, 2.46]) and anxiety (aOR: 1.91; 95% CI: [1.81, 2.01])). Models with interaction terms revealed gender, residential status, and calendar time as effect modifiers. This study demonstrates that social media platforms like Facebook can effectively gather large-scale survey data to track mental health trends during public health crises.","PeriodicalId":74321,"journal":{"name":"Npj mental health research","volume":" ","pages":"1-13"},"PeriodicalIF":0.0,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44184-024-00101-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142692158","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}