Pub Date : 2024-10-31DOI: 10.1038/s44220-024-00326-x
Francis Vergunst, Rachel Williamson, Alessandro Massazza, Helen L. Berry, Miranda Olff
Climate change is driving a suite of stressors that could increase the global mental health burden. In this Perspective we consider three mental health frameworks to evaluate this burden. The pathogenic framework focuses on symptom management in the presence or absence of mental disorders. The salutogenic framework emphasizes factors related to psychological wellbeing such as personal strengths, resilience and socio-environmental resources. The third approach—the dual-continuum or ‘complete state’ framework—considers mental disorders and psychological wellbeing simultaneously. Drawing on the cross-disciplinary literature, we find that the dual-continuum framework is a practical and empirically valid approach to evaluate climate-related impacts on mental health. This is because mental disorders and reduced wellbeing, though related, are conceptually and empirically distinct, and encompass different climate-related antecedents and psychosocial endpoints. Both are necessary to evaluate the full burden of climate change. In this Perspective, the authors present a framework for evaluating the burden of climate change to mental health that considers both mental disorders and psychological wellbeing.
{"title":"A dual-continuum framework to evaluate climate change impacts on mental health","authors":"Francis Vergunst, Rachel Williamson, Alessandro Massazza, Helen L. Berry, Miranda Olff","doi":"10.1038/s44220-024-00326-x","DOIUrl":"10.1038/s44220-024-00326-x","url":null,"abstract":"Climate change is driving a suite of stressors that could increase the global mental health burden. In this Perspective we consider three mental health frameworks to evaluate this burden. The pathogenic framework focuses on symptom management in the presence or absence of mental disorders. The salutogenic framework emphasizes factors related to psychological wellbeing such as personal strengths, resilience and socio-environmental resources. The third approach—the dual-continuum or ‘complete state’ framework—considers mental disorders and psychological wellbeing simultaneously. Drawing on the cross-disciplinary literature, we find that the dual-continuum framework is a practical and empirically valid approach to evaluate climate-related impacts on mental health. This is because mental disorders and reduced wellbeing, though related, are conceptually and empirically distinct, and encompass different climate-related antecedents and psychosocial endpoints. Both are necessary to evaluate the full burden of climate change. In this Perspective, the authors present a framework for evaluating the burden of climate change to mental health that considers both mental disorders and psychological wellbeing.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 11","pages":"1318-1326"},"PeriodicalIF":0.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1038/s44220-024-00333-y
Gökhan Aydogan, Christian C. Ruff
The tendency to engage in risky behavior relates to genetic predispositions and brain structure, but the molecular pathways linking genes to neuroanatomical changes remain elusive. A recent study reveals how specific gene expression patterns shape brain structures associated with risk-taking, suggesting a mechanistic pathway from genes to maladaptive behavior.
{"title":"New insights from gene expression patterns on the neurobiological basis of risky behavior","authors":"Gökhan Aydogan, Christian C. Ruff","doi":"10.1038/s44220-024-00333-y","DOIUrl":"10.1038/s44220-024-00333-y","url":null,"abstract":"The tendency to engage in risky behavior relates to genetic predispositions and brain structure, but the molecular pathways linking genes to neuroanatomical changes remain elusive. A recent study reveals how specific gene expression patterns shape brain structures associated with risk-taking, suggesting a mechanistic pathway from genes to maladaptive behavior.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 11","pages":"1273-1274"},"PeriodicalIF":0.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1038/s44220-024-00318-x
Ran Goldblatt, Nathalie Holz, Garrett W. Tate, Kari Sherman, Selamawit Ghebremicael, Soumitra S. Bhuyan, Yazan A. Al-Ajlouni, Sara Santillanes, Ghermay Araya, Shermaine Abad, Megan M. Herting, Wesley K. Thompson, Bishal Thapaliya, Ram Sapkota, Jiayuan Xu, Jingyu Liu, The environMENTAL consortium, Gunter Schumann, Vince D. Calhoun
Although numerous studies over the past decade have highlighted the influence of environmental factors on mental health, globally applicable data on physical surroundings such as land cover and urbanicity are still limited. The urban environment is complex and composed of many interacting factors. To understand how urban living affects mental health, simultaneous measures of multiple environmental factors need to be related to symptoms of mental illness, while considering the underlying brain structure and function. So far, most studies have assessed individual urban environmental factors, such as greenness, in isolation and related them to individual symptoms of mental illness. We have refined the satellite-based ‘Urban Satellite’ (UrbanSat) measures, consisting of 11 satellite-data-derived environmental indicators, and linked them through residential addresses with participants of the Adolescent Brain Cognitive Development (ABCD) Study. The ABCD Study is the largest ongoing longitudinal and observational study exploring brain development and child health, involving 11,800 children, assessed at 9–16 years of age, from 21 sites across the USA. Here we describe linking of the ABCD Study data with UrbanSat variables, including each subject’s residential address at their baseline visit, including land cover and land use, nighttime lights and population characteristics. We also highlight and discuss important links of the satellite-data variables to the default mode network clustering coefficient and cognition. This comprehensive dataset provides an important tool for advancing neurobehavioral research on urbanicity during the critical developmental periods of childhood and adolescence. In this Perspective, the authors present a model of assessing urban environmental factors’ impact on mental health by using UrbanSat measures and data from adolescents in the ABCD Study.
{"title":"Linking neuroimaging and mental health data from the ABCD Study to UrbanSat measurements of macro environmental factors","authors":"Ran Goldblatt, Nathalie Holz, Garrett W. Tate, Kari Sherman, Selamawit Ghebremicael, Soumitra S. Bhuyan, Yazan A. Al-Ajlouni, Sara Santillanes, Ghermay Araya, Shermaine Abad, Megan M. Herting, Wesley K. Thompson, Bishal Thapaliya, Ram Sapkota, Jiayuan Xu, Jingyu Liu, The environMENTAL consortium, Gunter Schumann, Vince D. Calhoun","doi":"10.1038/s44220-024-00318-x","DOIUrl":"10.1038/s44220-024-00318-x","url":null,"abstract":"Although numerous studies over the past decade have highlighted the influence of environmental factors on mental health, globally applicable data on physical surroundings such as land cover and urbanicity are still limited. The urban environment is complex and composed of many interacting factors. To understand how urban living affects mental health, simultaneous measures of multiple environmental factors need to be related to symptoms of mental illness, while considering the underlying brain structure and function. So far, most studies have assessed individual urban environmental factors, such as greenness, in isolation and related them to individual symptoms of mental illness. We have refined the satellite-based ‘Urban Satellite’ (UrbanSat) measures, consisting of 11 satellite-data-derived environmental indicators, and linked them through residential addresses with participants of the Adolescent Brain Cognitive Development (ABCD) Study. The ABCD Study is the largest ongoing longitudinal and observational study exploring brain development and child health, involving 11,800 children, assessed at 9–16 years of age, from 21 sites across the USA. Here we describe linking of the ABCD Study data with UrbanSat variables, including each subject’s residential address at their baseline visit, including land cover and land use, nighttime lights and population characteristics. We also highlight and discuss important links of the satellite-data variables to the default mode network clustering coefficient and cognition. This comprehensive dataset provides an important tool for advancing neurobehavioral research on urbanicity during the critical developmental periods of childhood and adolescence. In this Perspective, the authors present a model of assessing urban environmental factors’ impact on mental health by using UrbanSat measures and data from adolescents in the ABCD Study.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 11","pages":"1285-1297"},"PeriodicalIF":0.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-28DOI: 10.1038/s44220-024-00339-6
Sandra Baez, Laura Castro-Aldrete, Gabrielle B. Britton, Agustin Ibañez, Antonella Santuccione-Chadha
Gender inequality substantially impacts society, disproportionately disadvantaging women, especially in the global south. This inequality correlates with brain health outcomes for women, including a higher risk of cognitive decline and dementia. Here we highlight how sex-linked biology and gender disparities affect women’s brain health in the global south through various pathways, such as a differential exposomes, health behaviors and gender biases in research and healthcare systems. Alzheimer’s disease and other brain health conditions exemplify how sex-specific risk factors and gender-related health barriers interact to influence brain health. We advocate for incorporating sex/gender considerations in research, policy and clinical practice to improve brain health interventions in the global south. Additionally, we propose using the patient and public involvement framework to effectively tailor health strategies that address these factors. This Perspective discusses how gender disparities affect women’s brain health in the global south and proposes strategies to improve brain health outcomes by incorporating sex and gender considerations in research, policy and clinical practice and using the patient and public involvement framework.
{"title":"Enhancing brain health in the global south through a sex and gender lens","authors":"Sandra Baez, Laura Castro-Aldrete, Gabrielle B. Britton, Agustin Ibañez, Antonella Santuccione-Chadha","doi":"10.1038/s44220-024-00339-6","DOIUrl":"10.1038/s44220-024-00339-6","url":null,"abstract":"Gender inequality substantially impacts society, disproportionately disadvantaging women, especially in the global south. This inequality correlates with brain health outcomes for women, including a higher risk of cognitive decline and dementia. Here we highlight how sex-linked biology and gender disparities affect women’s brain health in the global south through various pathways, such as a differential exposomes, health behaviors and gender biases in research and healthcare systems. Alzheimer’s disease and other brain health conditions exemplify how sex-specific risk factors and gender-related health barriers interact to influence brain health. We advocate for incorporating sex/gender considerations in research, policy and clinical practice to improve brain health interventions in the global south. Additionally, we propose using the patient and public involvement framework to effectively tailor health strategies that address these factors. This Perspective discusses how gender disparities affect women’s brain health in the global south and proposes strategies to improve brain health outcomes by incorporating sex and gender considerations in research, policy and clinical practice and using the patient and public involvement framework.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 11","pages":"1308-1317"},"PeriodicalIF":0.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-28DOI: 10.1038/s44220-024-00343-w
Shawn A. Rhoads, Xiaosi Gu, Joseph M. Barnby
Social factors have an outsized role in the progression and treatment of psychiatric conditions, but existing computational models often neglect social context. We propose that integrating social features into computational frameworks will shed light into the complexity of mental health, and provide guidelines for model design.
{"title":"Advancing computational psychiatry through a social lens","authors":"Shawn A. Rhoads, Xiaosi Gu, Joseph M. Barnby","doi":"10.1038/s44220-024-00343-w","DOIUrl":"10.1038/s44220-024-00343-w","url":null,"abstract":"Social factors have an outsized role in the progression and treatment of psychiatric conditions, but existing computational models often neglect social context. We propose that integrating social features into computational frameworks will shed light into the complexity of mental health, and provide guidelines for model design.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 11","pages":"1268-1270"},"PeriodicalIF":0.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-28DOI: 10.1038/s44220-024-00338-7
Sarah E. Chang, Dylan E. Hughes, Jinhan Zhu, Mahnoor Hyat, Sullivan D. Salone, Zachary T. Goodman, Joshua L. Roffman, Nicole R. Karcher, Leanna M. Hernandez, Jennifer K. Forsyth, Carrie E. Bearden
Attention problems are among the earliest precursors of schizophrenia. In this longitudinal cohort study, we examine relationships between cognitive and neuropsychiatric polygenic scores (PGSs), psychosis-spectrum symptoms and attention-related phenotypes in adolescence (ABCD; n = 11,855; mean baseline age 9.93 ± 0.6). Across three biennial visits, greater attentional variability and altered functional connectivity were associated with severity of psychotic-like experiences (PLEs). In European-ancestry youth, neuropsychiatric and cognitive PGSs were associated with greater PLE severity (R2 = 0.026–0.035) and greater attentional variability (R2 = 0.100–0.109). Notably, the effect of broad neurodevelopmental PGS on PLEs weakened over time, whereas schizophrenia PGS did not. Attentional variability partially mediated relationships between multiple PGSs and PLEs, explaining 4–16% of these associations. Finally, PGSs parsed by developmental coexpression modules were significantly associated with PLE severity, though effect sizes were larger for genome-wide PGSs. Findings implicate broad neurodevelopmental liability in the pathophysiology of psychosis-spectrum symptomatology in adolescence; attentional variability may link risk variants to symptoms. Using data from the Adolescent Brain Cognitive Development Study, the authors find an association between neuropsychiatric and cognitive polygenic scores and psychotic-like experience severity, and reveal a mediating role of attentional variability.
{"title":"Attention-mediated genetic influences on psychotic symptomatology in adolescence","authors":"Sarah E. Chang, Dylan E. Hughes, Jinhan Zhu, Mahnoor Hyat, Sullivan D. Salone, Zachary T. Goodman, Joshua L. Roffman, Nicole R. Karcher, Leanna M. Hernandez, Jennifer K. Forsyth, Carrie E. Bearden","doi":"10.1038/s44220-024-00338-7","DOIUrl":"10.1038/s44220-024-00338-7","url":null,"abstract":"Attention problems are among the earliest precursors of schizophrenia. In this longitudinal cohort study, we examine relationships between cognitive and neuropsychiatric polygenic scores (PGSs), psychosis-spectrum symptoms and attention-related phenotypes in adolescence (ABCD; n = 11,855; mean baseline age 9.93 ± 0.6). Across three biennial visits, greater attentional variability and altered functional connectivity were associated with severity of psychotic-like experiences (PLEs). In European-ancestry youth, neuropsychiatric and cognitive PGSs were associated with greater PLE severity (R2 = 0.026–0.035) and greater attentional variability (R2 = 0.100–0.109). Notably, the effect of broad neurodevelopmental PGS on PLEs weakened over time, whereas schizophrenia PGS did not. Attentional variability partially mediated relationships between multiple PGSs and PLEs, explaining 4–16% of these associations. Finally, PGSs parsed by developmental coexpression modules were significantly associated with PLE severity, though effect sizes were larger for genome-wide PGSs. Findings implicate broad neurodevelopmental liability in the pathophysiology of psychosis-spectrum symptomatology in adolescence; attentional variability may link risk variants to symptoms. Using data from the Adolescent Brain Cognitive Development Study, the authors find an association between neuropsychiatric and cognitive polygenic scores and psychotic-like experience severity, and reveal a mediating role of attentional variability.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 12","pages":"1518-1531"},"PeriodicalIF":0.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142778609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-25DOI: 10.1038/s44220-024-00357-4
Dirk H. M. Pelt, Philippe C. Habets, Christiaan H. Vinkers, Lannie Ligthart, Catharina E. M. van Beijsterveldt, René Pool, Meike Bartels
{"title":"Author Correction: Building machine learning prediction models for well-being using predictors from the exposome and genome in a population cohort","authors":"Dirk H. M. Pelt, Philippe C. Habets, Christiaan H. Vinkers, Lannie Ligthart, Catharina E. M. van Beijsterveldt, René Pool, Meike Bartels","doi":"10.1038/s44220-024-00357-4","DOIUrl":"10.1038/s44220-024-00357-4","url":null,"abstract":"","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 12","pages":"1543-1543"},"PeriodicalIF":0.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44220-024-00357-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142778608","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}
Pub Date : 2024-10-25DOI: 10.1038/s44220-024-00330-1
Sachin R. Pendse, Logan Stapleton, Neha Kumar, Munmun De Choudhury, Stevie Chancellor
The field of digital mental health is advancing at a rapid pace. Passively collected data from user engagements with digital tools and services continue to contribute insights into mental health and illness. As the field of digital mental health grows, a concerning norm has been established—digital service users are given little say over how their data are collected, shared or used to generate revenue for private companies. Given a long history of service-user exclusion from data collection practices, we propose an alternative approach that is attentive to this history: the consent-forward paradigm. This paradigm embeds principles of affirmative consent in the design of digital mental health tools and services, which may strengthen trust around individual choices and needs, and proactively protect users from unexpected harm. In this Perspective, we outline practical steps to implement this paradigm, toward ensuring that people searching for care have the safest experiences possible. In this Perspective, the authors discuss a consent-forward paradigm that embeds principles of affirmative consent in the design of digital mental health tools and services and protects users from unexpected harm.
{"title":"Advancing a consent-forward paradigm for digital mental health data","authors":"Sachin R. Pendse, Logan Stapleton, Neha Kumar, Munmun De Choudhury, Stevie Chancellor","doi":"10.1038/s44220-024-00330-1","DOIUrl":"10.1038/s44220-024-00330-1","url":null,"abstract":"The field of digital mental health is advancing at a rapid pace. Passively collected data from user engagements with digital tools and services continue to contribute insights into mental health and illness. As the field of digital mental health grows, a concerning norm has been established—digital service users are given little say over how their data are collected, shared or used to generate revenue for private companies. Given a long history of service-user exclusion from data collection practices, we propose an alternative approach that is attentive to this history: the consent-forward paradigm. This paradigm embeds principles of affirmative consent in the design of digital mental health tools and services, which may strengthen trust around individual choices and needs, and proactively protect users from unexpected harm. In this Perspective, we outline practical steps to implement this paradigm, toward ensuring that people searching for care have the safest experiences possible. In this Perspective, the authors discuss a consent-forward paradigm that embeds principles of affirmative consent in the design of digital mental health tools and services and protects users from unexpected harm.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 11","pages":"1298-1307"},"PeriodicalIF":0.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-24DOI: 10.1038/s44220-024-00335-w
Shirley B. Wang, Ruben D. I. Van Genugten, Yaniv Yacoby, Weiwei Pan, Kate H. Bentley, Suzanne A. Bird, Ralph J. Buonopane, Alexis Christie, Merryn Daniel, Dylan DeMarco, Adam Haim, Lia Follet, Rebecca G. Fortgang, Flynn Kelly-Brunyak, Evan M. Kleiman, Alexander J. Millner, Onyinye Obi-Obasi, J. P. Onnela, Narise Ramlal, Jordyn R. Ricard, Jordan W. Smoller, Tida Tambedou, Kelly L. Zuromski, Matthew K. Nock
Suicide risk is highest immediately after psychiatric hospitalization, but the field lacks methods for identifying which patients are at greatest risk, and when. We built personalized models predicting suicidal thoughts after psychiatric hospital visits (N = 89 patients), using ecological momentary assessment (EMA; average EMA responses per participant = 311). We built several idiographic models, including baseline autoregressive and elastic net models (using single train/test split) and Gaussian process (GP) models (using an iterative rolling-forward prediction method). Simple GP models provided the best prediction of suicidal urges (R2average = 0.17), outperforming baseline autoregressive (R2average = 0.10) and elastic net (R2average = 0.06) models. Similarly, simple GP models provided the best prediction of suicidal intent (R2average = 0.12) compared to autoregressive (R2average = 0.08) and elastic net (R2average = 0.04). Here we show that idiographic prediction of suicidal thoughts is possible, although the accuracy is currently modest. Building GP models that iteratively update and learn symptom dynamics over time could provide important information to inform the development of just-in-time adaptive interventions. Using ecological monetary assessment, this study presents findings from idiographic models built to predict suicidal ideation in individuals after psychiatric hospitalization.
精神病患者住院后立即自杀的风险最高，但该领域缺乏识别哪些患者以及何时自杀风险最高的方法。我们利用生态瞬间评估（EMA；每位参与者的平均 EMA 反应 = 311）建立了预测精神病院就诊后自杀想法的个性化模型（N = 89 名患者）。我们建立了多个特异性模型，包括基线自回归模型和弹性网模型（使用单一训练/测试分割）以及高斯过程（GP）模型（使用迭代滚动前向预测方法）。简单的 GP 模型对自杀冲动的预测效果最好（R2average = 0.17），优于基线自回归模型（R2average = 0.10）和弹性网模型（R2average = 0.06）。同样，与自回归模型（R2 平均值 = 0.08）和弹性网模型（R2 平均值 = 0.04）相比，简单的 GP 模型对自杀意向的预测效果最好（R2 平均值 = 0.12）。我们在此表明，对自杀意念进行特异性预测是可能的，尽管其准确性目前并不高。建立能随着时间推移迭代更新和学习症状动态的 GP 模型，可为及时适应性干预措施的开发提供重要信息。本研究采用生态货币评估方法，介绍了为预测精神病患者住院后的自杀意念而建立的特异性模型的研究结果。
{"title":"Building personalized machine learning models using real-time monitoring data to predict idiographic suicidal thoughts","authors":"Shirley B. Wang, Ruben D. I. Van Genugten, Yaniv Yacoby, Weiwei Pan, Kate H. Bentley, Suzanne A. Bird, Ralph J. Buonopane, Alexis Christie, Merryn Daniel, Dylan DeMarco, Adam Haim, Lia Follet, Rebecca G. Fortgang, Flynn Kelly-Brunyak, Evan M. Kleiman, Alexander J. Millner, Onyinye Obi-Obasi, J. P. Onnela, Narise Ramlal, Jordyn R. Ricard, Jordan W. Smoller, Tida Tambedou, Kelly L. Zuromski, Matthew K. Nock","doi":"10.1038/s44220-024-00335-w","DOIUrl":"10.1038/s44220-024-00335-w","url":null,"abstract":"Suicide risk is highest immediately after psychiatric hospitalization, but the field lacks methods for identifying which patients are at greatest risk, and when. We built personalized models predicting suicidal thoughts after psychiatric hospital visits (N = 89 patients), using ecological momentary assessment (EMA; average EMA responses per participant = 311). We built several idiographic models, including baseline autoregressive and elastic net models (using single train/test split) and Gaussian process (GP) models (using an iterative rolling-forward prediction method). Simple GP models provided the best prediction of suicidal urges (R2average = 0.17), outperforming baseline autoregressive (R2average = 0.10) and elastic net (R2average = 0.06) models. Similarly, simple GP models provided the best prediction of suicidal intent (R2average = 0.12) compared to autoregressive (R2average = 0.08) and elastic net (R2average = 0.04). Here we show that idiographic prediction of suicidal thoughts is possible, although the accuracy is currently modest. Building GP models that iteratively update and learn symptom dynamics over time could provide important information to inform the development of just-in-time adaptive interventions. Using ecological monetary assessment, this study presents findings from idiographic models built to predict suicidal ideation in individuals after psychiatric hospitalization.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"2 11","pages":"1382-1391"},"PeriodicalIF":0.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：