Pub Date : 2025-01-10DOI: 10.1038/s44220-024-00373-4
S. Parker Singleton, Brooke L. Sevchik, Simon N. Vandekar, Eric C. Strain, Sandeep M. Nayak, Robert H. Dworkin, J. Cobb Scott, Theodore D. Satterthwaite
Renewed interest in psychedelics as treatments for mental disorders has recently emerged, but substantial challenges remain in obtaining evidence from available data to inform clinical decision-making. This Comment explores the current landscape of clinical psychedelic research, highlighting the need for a systematic approach to evidence synthesis.
{"title":"An initiative for living evidence synthesis in clinical psychedelic research","authors":"S. Parker Singleton, Brooke L. Sevchik, Simon N. Vandekar, Eric C. Strain, Sandeep M. Nayak, Robert H. Dworkin, J. Cobb Scott, Theodore D. Satterthwaite","doi":"10.1038/s44220-024-00373-4","DOIUrl":"10.1038/s44220-024-00373-4","url":null,"abstract":"Renewed interest in psychedelics as treatments for mental disorders has recently emerged, but substantial challenges remain in obtaining evidence from available data to inform clinical decision-making. This Comment explores the current landscape of clinical psychedelic research, highlighting the need for a systematic approach to evidence synthesis.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 1","pages":"3-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941323","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 : 2025-01-09DOI: 10.1038/s44220-024-00371-6
Lauren Y. Atlas, Cristan Farmer, Jacob S. Shaw, Alison Gibbons, Emily P. Guinee, Juan Antonio Lossio-Ventura, Elizabeth D. Ballard, Monique Ernst, Shruti Japee, Francisco Pereira, Joyce Y. Chung
The COVID-19 pandemic’s impact on mental health is challenging to quantify because pre-existing risk, disease burden and public policy varied across individuals, time and regions. Longitudinal, within-person analyses can determine whether pandemic-related changes in social isolation impacted mental health. We analyzed time-varying associations between psychiatric vulnerability, loneliness, psychological distress and social distancing in a US-based study during the first year of the pandemic. We surveyed 3,655 participants about psychological health and COVID-19-related circumstances every 2 weeks for 6 months. We combined self-reports with regional social distancing estimates and a classifier that predicted probability of psychiatric diagnosis at enrollment. Loneliness and psychiatric vulnerability both impacted psychological distress. Loneliness and distress were also linked to social isolation and stress associated with distancing, and psychiatric vulnerability shaped how regional distancing affected loneliness across time. Public health policies should address loneliness when encouraging social distancing, particularly in those at risk for psychiatric conditions. In this new study, the authors analyzed data from a longitudinal US-based survey during the first year of the pandemic, focusing on social distancing, psychiatric vulnerability and loneliness in adults.
{"title":"Dynamic effects of psychiatric vulnerability, loneliness and isolation on distress during the first year of the COVID-19 pandemic","authors":"Lauren Y. Atlas, Cristan Farmer, Jacob S. Shaw, Alison Gibbons, Emily P. Guinee, Juan Antonio Lossio-Ventura, Elizabeth D. Ballard, Monique Ernst, Shruti Japee, Francisco Pereira, Joyce Y. Chung","doi":"10.1038/s44220-024-00371-6","DOIUrl":"10.1038/s44220-024-00371-6","url":null,"abstract":"The COVID-19 pandemic’s impact on mental health is challenging to quantify because pre-existing risk, disease burden and public policy varied across individuals, time and regions. Longitudinal, within-person analyses can determine whether pandemic-related changes in social isolation impacted mental health. We analyzed time-varying associations between psychiatric vulnerability, loneliness, psychological distress and social distancing in a US-based study during the first year of the pandemic. We surveyed 3,655 participants about psychological health and COVID-19-related circumstances every 2 weeks for 6 months. We combined self-reports with regional social distancing estimates and a classifier that predicted probability of psychiatric diagnosis at enrollment. Loneliness and psychiatric vulnerability both impacted psychological distress. Loneliness and distress were also linked to social isolation and stress associated with distancing, and psychiatric vulnerability shaped how regional distancing affected loneliness across time. Public health policies should address loneliness when encouraging social distancing, particularly in those at risk for psychiatric conditions. In this new study, the authors analyzed data from a longitudinal US-based survey during the first year of the pandemic, focusing on social distancing, psychiatric vulnerability and loneliness in adults.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 2","pages":"199-211"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44220-024-00371-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143381112","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 : 2025-01-08DOI: 10.1038/s44220-024-00359-2
Aaron Baird, Yusen Xia
Mental health services and treatment are unfortunately subject to sociodemographic disparities. To address this issue, recent studies have begun to apply analytics methods—that is, artificial intelligence in general, machine learning and deep learning in particular—toward the identification of such disparities and, where possible, mitigation of bias within models used in mental health research. However, it is difficult to understand the scope and status of such research as it is spread across many journals and contexts of study. Here we conducted an analysis of articles in this area. We identified 40 articles from 2017 to July 2023 related to the use of analytics in the context of sociodemographic disparities in mental health. We find that prediction, clustering/grouping and fairness models were most often applied in the articles analyzed. A number of mental health-related sociodemographic disparities were identified in these articles, for example, associated with race/ethnicity, gender, age and socioeconomic status, but such findings were typically context dependent. Thus, we also provide suggestions in this Analysis on how to both enhance generalizability and embrace context-dependent findings, especially via the identification of heterogeneous treatment effects, model bias mitigation, use of generative artificial intelligence, incorporation of data from devices, and translation of findings into practice. In this study, the authors analyzed articles examining the use of artificial intelligence, machine learning and deep learning analytics for identifying sociodemographic disparities, such as in race/ethnicity and age, to make recommendations for improving models and generalizability.
{"title":"Applying analytics to sociodemographic disparities in mental health","authors":"Aaron Baird, Yusen Xia","doi":"10.1038/s44220-024-00359-2","DOIUrl":"10.1038/s44220-024-00359-2","url":null,"abstract":"Mental health services and treatment are unfortunately subject to sociodemographic disparities. To address this issue, recent studies have begun to apply analytics methods—that is, artificial intelligence in general, machine learning and deep learning in particular—toward the identification of such disparities and, where possible, mitigation of bias within models used in mental health research. However, it is difficult to understand the scope and status of such research as it is spread across many journals and contexts of study. Here we conducted an analysis of articles in this area. We identified 40 articles from 2017 to July 2023 related to the use of analytics in the context of sociodemographic disparities in mental health. We find that prediction, clustering/grouping and fairness models were most often applied in the articles analyzed. A number of mental health-related sociodemographic disparities were identified in these articles, for example, associated with race/ethnicity, gender, age and socioeconomic status, but such findings were typically context dependent. Thus, we also provide suggestions in this Analysis on how to both enhance generalizability and embrace context-dependent findings, especially via the identification of heterogeneous treatment effects, model bias mitigation, use of generative artificial intelligence, incorporation of data from devices, and translation of findings into practice. In this study, the authors analyzed articles examining the use of artificial intelligence, machine learning and deep learning analytics for identifying sociodemographic disparities, such as in race/ethnicity and age, to make recommendations for improving models and generalizability.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 1","pages":"124-138"},"PeriodicalIF":0.0,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941299","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 : 2025-01-08DOI: 10.1038/s44220-024-00353-8
Romain Icick, Alexey Shadrin, Børge Holen, Naz Karadag, Nadine Parker, Kevin S. O’Connell, Oleksandr Frei, Shahram Bahrami, Margrethe Collier Høegh, Trine Vik Lagerberg, Weiqiu Cheng, Tyler M. Seibert, Srdjan Djurovic, Anders M. Dale, Hang Zhou, Howard J. Edenberg, Joel Gelernter, Olav B. Smeland, Guy Hindley, Ole A. Andreassen
Alcohol use disorder (AUD) is highly heritable and burdensome worldwide. Genome-wide association studies can provide new evidence regarding the etiology of AUD. We report a multi-ancestry genome-wide association study focusing on a narrow AUD phenotype, using novel statistical tools in a total sample of 1,041,450 individuals (102,079 cases; European, 75,583; African, 20,689 (mostly African American); Hispanic American, 3,449; East Asian, 2,254; South Asian, 104; descent). Cross-ancestry functional analyses were performed with European and African samples. Thirty-seven genome-wide significant loci (105 variants) were identified, of which seven were novel for AUD and six for other alcohol phenotypes. Loci were mapped to genes, which show altered expression in brain regions relevant for AUD (striatum, hypothalamus and prefrontal cortex) and encode potential drug targets (GABAergic, dopaminergic and serotonergic neurons). African-specific analysis yielded a unique pattern of immune-related gene sets. Polygenic overlap and positive genetic correlations showed extensive shared genetic architecture between AUD and both mental and general medical phenotypes, suggesting that they are not only complications of alcohol use but also share genetic liability with AUD. Leveraging a cross-ancestry approach allowed identification of novel genetic loci for AUD and underscores the value of multi-ancestry genetic studies. These findings advance our understanding of AUD risk and clinically relevant comorbidities. This multi-ancestral meta-analysis of alcohol use disorder in over one million individuals identifies genome-wide significant risk variants from independent genomic loci and shared genetic architecture between alcohol use disorder and other mental and general medical conditions.
{"title":"Identification of risk variants and cross-disorder pleiotropy through multi-ancestry genome-wide analysis of alcohol use disorder","authors":"Romain Icick, Alexey Shadrin, Børge Holen, Naz Karadag, Nadine Parker, Kevin S. O’Connell, Oleksandr Frei, Shahram Bahrami, Margrethe Collier Høegh, Trine Vik Lagerberg, Weiqiu Cheng, Tyler M. Seibert, Srdjan Djurovic, Anders M. Dale, Hang Zhou, Howard J. Edenberg, Joel Gelernter, Olav B. Smeland, Guy Hindley, Ole A. Andreassen","doi":"10.1038/s44220-024-00353-8","DOIUrl":"10.1038/s44220-024-00353-8","url":null,"abstract":"Alcohol use disorder (AUD) is highly heritable and burdensome worldwide. Genome-wide association studies can provide new evidence regarding the etiology of AUD. We report a multi-ancestry genome-wide association study focusing on a narrow AUD phenotype, using novel statistical tools in a total sample of 1,041,450 individuals (102,079 cases; European, 75,583; African, 20,689 (mostly African American); Hispanic American, 3,449; East Asian, 2,254; South Asian, 104; descent). Cross-ancestry functional analyses were performed with European and African samples. Thirty-seven genome-wide significant loci (105 variants) were identified, of which seven were novel for AUD and six for other alcohol phenotypes. Loci were mapped to genes, which show altered expression in brain regions relevant for AUD (striatum, hypothalamus and prefrontal cortex) and encode potential drug targets (GABAergic, dopaminergic and serotonergic neurons). African-specific analysis yielded a unique pattern of immune-related gene sets. Polygenic overlap and positive genetic correlations showed extensive shared genetic architecture between AUD and both mental and general medical phenotypes, suggesting that they are not only complications of alcohol use but also share genetic liability with AUD. Leveraging a cross-ancestry approach allowed identification of novel genetic loci for AUD and underscores the value of multi-ancestry genetic studies. These findings advance our understanding of AUD risk and clinically relevant comorbidities. This multi-ancestral meta-analysis of alcohol use disorder in over one million individuals identifies genome-wide significant risk variants from independent genomic loci and shared genetic architecture between alcohol use disorder and other mental and general medical conditions.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 2","pages":"253-265"},"PeriodicalIF":0.0,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143381086","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 : 2025-01-07DOI: 10.1038/s44220-024-00365-4
Wivine Blekic, Fabien D’Hondt, Arieh Y. Shalev, Katharina Schultebraucks
In recent years, the application of machine learning (ML) techniques in research on the prediction of post-traumatic stress disorder (PTSD) has increased. However, concerns regarding the clinical relevance and generalizability of ML findings hamper their implementation by clinicians and researchers. Here in this systematic review we examined (1) the extent to which pre-, peri- and post-traumatic risk factors identified using ML approaches coincide with the theoretical understanding of the disorder; (2) whether new insights were gained through ML techniques; and (3) whether ML findings, combined with previous research, enable an integrative model of PTSD risk encompassing both predictor categories and their theoretical relevance. We reviewed ML studies on PTSD risk factors in PubMed, Web of Science and Scopus. Studies were included if they specified when predictors and PTSD symptoms were collected in temporal relation to the traumatic event. A total of 30 studies with 12,908 participants (mean age 36.5 years) were included. After extracting the 15 most important predictors from all studies, we categorized them into pre-, peri- and post-trauma exposure predictors and examined their associations with established theoretical models of PTSD. Many studies exhibited a risk of bias, assessed using the prediction model risk of bias assessment tool (PROBAST). However, we found overlaps in identified predictors across studies, a concordance between data-driven results and theory-driven research, and underexplored predictors identified through ML. We propose an integrative model of PTSD risk that incorporates both data-driven and theory-driven findings and discuss future directions. We emphasize the importance of standards on how to apply and report ML approaches for mental health. This systematic review synthesizes evidence from 30 studies using machine learning approaches to identify predictors for post-traumatic stress disorder risk. The authors detect underexplored predictors and overlaps in predictors across studies and find an alignment between data-driven results and theory-based models.
近年来，机器学习（ML）技术在创伤后应激障碍（PTSD）预测研究中的应用越来越多。然而，对临床相关性和ML发现的普遍性的担忧阻碍了临床医生和研究人员的实施。在这篇系统综述中，我们检查了(1)使用ML方法确定的创伤前、创伤周围和创伤后风险因素与对该障碍的理论认识相吻合的程度；(2)是否通过ML技术获得了新的见解；(3) ML研究结果与以往的研究相结合，是否能够建立一个包括预测因子类别及其理论相关性的创伤后应激障碍风险综合模型。我们回顾了PubMed、Web of Science和Scopus中关于PTSD危险因素的ML研究。如果研究明确了何时收集预测因子和PTSD症状与创伤性事件的时间关系，则纳入研究。共纳入30项研究，12908名参与者（平均年龄36.5岁）。在从所有研究中提取出15个最重要的预测因子后，我们将它们分为创伤前、创伤中和创伤后暴露预测因子，并检查它们与已建立的创伤后应激障碍理论模型的关联。许多研究显示存在偏倚风险，使用预测模型偏倚风险评估工具（PROBAST）进行评估。然而，我们发现不同研究中确定的预测因素存在重叠，数据驱动的结果和理论驱动的研究之间存在一致性，以及通过ML确定的未被探索的预测因素。我们提出了一个整合数据驱动和理论驱动结果的PTSD风险综合模型，并讨论了未来的发展方向。我们强调关于如何应用和报告ML方法用于心理健康的标准的重要性。本系统综述综合了来自30项研究的证据，这些研究使用机器学习方法来识别创伤后应激障碍风险的预测因素。作者发现了研究中未充分开发的预测因子和预测因子的重叠，并发现了数据驱动结果和基于理论的模型之间的一致性。
{"title":"A systematic review of machine learning findings in PTSD and their relationships with theoretical models","authors":"Wivine Blekic, Fabien D’Hondt, Arieh Y. Shalev, Katharina Schultebraucks","doi":"10.1038/s44220-024-00365-4","DOIUrl":"10.1038/s44220-024-00365-4","url":null,"abstract":"In recent years, the application of machine learning (ML) techniques in research on the prediction of post-traumatic stress disorder (PTSD) has increased. However, concerns regarding the clinical relevance and generalizability of ML findings hamper their implementation by clinicians and researchers. Here in this systematic review we examined (1) the extent to which pre-, peri- and post-traumatic risk factors identified using ML approaches coincide with the theoretical understanding of the disorder; (2) whether new insights were gained through ML techniques; and (3) whether ML findings, combined with previous research, enable an integrative model of PTSD risk encompassing both predictor categories and their theoretical relevance. We reviewed ML studies on PTSD risk factors in PubMed, Web of Science and Scopus. Studies were included if they specified when predictors and PTSD symptoms were collected in temporal relation to the traumatic event. A total of 30 studies with 12,908 participants (mean age 36.5 years) were included. After extracting the 15 most important predictors from all studies, we categorized them into pre-, peri- and post-trauma exposure predictors and examined their associations with established theoretical models of PTSD. Many studies exhibited a risk of bias, assessed using the prediction model risk of bias assessment tool (PROBAST). However, we found overlaps in identified predictors across studies, a concordance between data-driven results and theory-driven research, and underexplored predictors identified through ML. We propose an integrative model of PTSD risk that incorporates both data-driven and theory-driven findings and discuss future directions. We emphasize the importance of standards on how to apply and report ML approaches for mental health. This systematic review synthesizes evidence from 30 studies using machine learning approaches to identify predictors for post-traumatic stress disorder risk. The authors detect underexplored predictors and overlaps in predictors across studies and find an alignment between data-driven results and theory-based models.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 1","pages":"139-158"},"PeriodicalIF":0.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941353","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 : 2025-01-07DOI: 10.1038/s44220-024-00352-9
Raluca Petrican, Sidhant Chopra, Ashlea Segal, Nick Fallon, Alex Fornito
Premature reproductive aging is linked to heightened stress sensitivity and psychological maladjustment across the life course. However, the brain dynamics underlying this relationship are poorly understood. Here, to address this issue, we analyzed multimodal data from female participants in the Adolescent Brain and Cognitive Development (longitudinal, N = 441; aged 9–12 years) and Human Connectome-Aging (cross-sectional, N = 130; aged 36–60 years) studies. Age-specific intrinsic functional brain network dynamics mediated the link between reproductive aging and perceptions of greater interpersonal adversity. The adolescent profile overlapped areas of greater glutamatergic and dopaminergic receptor density, and the middle-aged profile was concentrated in visual, attentional and default mode networks. The two profiles showed opposite relationships with patterns of functional neural network variability and cortical atrophy observed in psychosis versus major depressive disorder. Our findings underscore the divergent patterns of brain aging linked to reproductive maturation versus senescence, which may explain developmentally specific vulnerabilities to distinct disorders. Age-specific intrinsic functional brain network dynamics mediates the link between female reproductive aging and perceptions of interpersonal adversity in adolescence and middle adulthood.
{"title":"Functional brain network dynamics mediate the relationship between female reproductive aging and interpersonal adversity","authors":"Raluca Petrican, Sidhant Chopra, Ashlea Segal, Nick Fallon, Alex Fornito","doi":"10.1038/s44220-024-00352-9","DOIUrl":"10.1038/s44220-024-00352-9","url":null,"abstract":"Premature reproductive aging is linked to heightened stress sensitivity and psychological maladjustment across the life course. However, the brain dynamics underlying this relationship are poorly understood. Here, to address this issue, we analyzed multimodal data from female participants in the Adolescent Brain and Cognitive Development (longitudinal, N = 441; aged 9–12 years) and Human Connectome-Aging (cross-sectional, N = 130; aged 36–60 years) studies. Age-specific intrinsic functional brain network dynamics mediated the link between reproductive aging and perceptions of greater interpersonal adversity. The adolescent profile overlapped areas of greater glutamatergic and dopaminergic receptor density, and the middle-aged profile was concentrated in visual, attentional and default mode networks. The two profiles showed opposite relationships with patterns of functional neural network variability and cortical atrophy observed in psychosis versus major depressive disorder. Our findings underscore the divergent patterns of brain aging linked to reproductive maturation versus senescence, which may explain developmentally specific vulnerabilities to distinct disorders. Age-specific intrinsic functional brain network dynamics mediates the link between female reproductive aging and perceptions of interpersonal adversity in adolescence and middle adulthood.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 1","pages":"104-123"},"PeriodicalIF":0.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44220-024-00352-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941321","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 : 2025-01-06DOI: 10.1038/s44220-024-00360-9
James A. Naifeh, Emily R. Edwards, Kate H. Bentley, Sarah M. Gildea, Chris J. Kennedy, Andrew J. King, Evan M. Kleiman, Alex Luedtke, Thomas H. Nassif, Matthew K. Nock, Nancy A. Sampson, Nur Hani Zainal, Murray B. Stein, Vincent F. Capaldi, Robert J. Ursano, Ronald C. Kessler
The value of population screening for suicide risk remains unclear. The US Army’s annual medical examination, the Periodic Health Assessment (PHA), screens for suicidality and other mental and physical health problems. Here in our 2014–2019 cohort study we used PHA and Army administrative data (n = 1,042,796 PHAs from 452,473 soldiers) to develop a model to predict 6-month nonfatal and fatal suicide attempts (SAs). The model was designed to establish eligibility for a planned high-risk SA prevention intervention. The PHA suicide risk screening questions had limited value, as 95% of SAs occurred among soldiers who denied suicidality. However, a simple least absolute shrinkage and selection operator (LASSO) penalized regression model that included a wide range of administrative predictors had good test sample discrimination (0.794 (standard error 0.009) area under the receiver operating characteristic curve) and calibration (integrated calibration index 0.0001). The 25% of soldiers at highest predicted risk accounted for 69.5% of 6-month SAs, supporting use of the model to target preventive interventions. A machine learning model incorporating a wide range of administrative medical and demographic data from the US Army outperformed suicide risk screening questions in predicting suicide attempts over the 6 month period following soldiers’ annual medical examinations.
{"title":"Predicting suicide attempts among US Army soldiers using information available at the time of periodic health assessments","authors":"James A. Naifeh, Emily R. Edwards, Kate H. Bentley, Sarah M. Gildea, Chris J. Kennedy, Andrew J. King, Evan M. Kleiman, Alex Luedtke, Thomas H. Nassif, Matthew K. Nock, Nancy A. Sampson, Nur Hani Zainal, Murray B. Stein, Vincent F. Capaldi, Robert J. Ursano, Ronald C. Kessler","doi":"10.1038/s44220-024-00360-9","DOIUrl":"10.1038/s44220-024-00360-9","url":null,"abstract":"The value of population screening for suicide risk remains unclear. The US Army’s annual medical examination, the Periodic Health Assessment (PHA), screens for suicidality and other mental and physical health problems. Here in our 2014–2019 cohort study we used PHA and Army administrative data (n = 1,042,796 PHAs from 452,473 soldiers) to develop a model to predict 6-month nonfatal and fatal suicide attempts (SAs). The model was designed to establish eligibility for a planned high-risk SA prevention intervention. The PHA suicide risk screening questions had limited value, as 95% of SAs occurred among soldiers who denied suicidality. However, a simple least absolute shrinkage and selection operator (LASSO) penalized regression model that included a wide range of administrative predictors had good test sample discrimination (0.794 (standard error 0.009) area under the receiver operating characteristic curve) and calibration (integrated calibration index 0.0001). The 25% of soldiers at highest predicted risk accounted for 69.5% of 6-month SAs, supporting use of the model to target preventive interventions. A machine learning model incorporating a wide range of administrative medical and demographic data from the US Army outperformed suicide risk screening questions in predicting suicide attempts over the 6 month period following soldiers’ annual medical examinations.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 2","pages":"242-252"},"PeriodicalIF":0.0,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143381081","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 : 2025-01-06DOI: 10.1038/s44220-024-00364-5
Junseok K. Lee, Marion Rouault, Valentin Wyart
Compulsivity has been associated with variable behavior under uncertainty. However, previous work has not distinguished between two main sources of behavioral variability: the stochastic selection of choice options that do not maximize expected reward (choice variability) and random noise in the reinforcement learning process that updates option values from choice outcomes (learning variability). Here we study the relation between dimensional compulsivity and behavioral variability using a computational model that dissociates its two sources. Across two independent datasets (137 and 123 participants), we found that compulsivity is associated with more frequent switches between options, triggered by increased choice variability, but no change in learning variability. This effect of compulsivity on the ‘trait’ component of choice variability is observed even in conditions where this source of behavioral variability yields no cognitive benefits. These findings indicate that compulsive individuals make variable and suboptimal choices under uncertainty, but do not hold degraded representations of option values. Lee et al. find that compulsivity is associated with choice variability under uncertainty, resulting in frequent switching between choice options but no alteration in the ability to learn from the positive or negative outcomes of these choices.
{"title":"Compulsivity is linked to suboptimal choice variability but unaltered reinforcement learning under uncertainty","authors":"Junseok K. Lee, Marion Rouault, Valentin Wyart","doi":"10.1038/s44220-024-00364-5","DOIUrl":"10.1038/s44220-024-00364-5","url":null,"abstract":"Compulsivity has been associated with variable behavior under uncertainty. However, previous work has not distinguished between two main sources of behavioral variability: the stochastic selection of choice options that do not maximize expected reward (choice variability) and random noise in the reinforcement learning process that updates option values from choice outcomes (learning variability). Here we study the relation between dimensional compulsivity and behavioral variability using a computational model that dissociates its two sources. Across two independent datasets (137 and 123 participants), we found that compulsivity is associated with more frequent switches between options, triggered by increased choice variability, but no change in learning variability. This effect of compulsivity on the ‘trait’ component of choice variability is observed even in conditions where this source of behavioral variability yields no cognitive benefits. These findings indicate that compulsive individuals make variable and suboptimal choices under uncertainty, but do not hold degraded representations of option values. Lee et al. find that compulsivity is associated with choice variability under uncertainty, resulting in frequent switching between choice options but no alteration in the ability to learn from the positive or negative outcomes of these choices.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 2","pages":"229-241"},"PeriodicalIF":0.0,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143381088","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 : 2025-01-06DOI: 10.1038/s44220-024-00367-2
Christopher Lucasius, Mai Ali, Tanmay Patel, Deepa Kundur, Peter Szatmari, John Strauss, Marco Battaglia
Machine learning (ML) is becoming a tool of choice to analyze high-dimensional datasets pertaining to mental health. Given the rapid integration of ML into research and clinical settings, this article provides a functional overview of a common ML pipeline used for the assessment and prediction of psychiatric disorders. Developing such a construct entails building a data infrastructure, collecting and preprocessing data, training and testing models and interpreting their results. Practical considerations pertaining to data management and preprocessing are first presented. We then describe considerations and best practices for model selection on the basis of the psychiatric disorder and the data modalities available for analysis. A critical analysis of existing works utilizing ML methods for psychiatric disorder assessment, prediction and causal associations is also provided. Last, future ML trends in psychiatry are highlighted. To reinforce learning, the Supplementary Note links to an interactive Jupyter Notebook that offers practical examples and hands-on interaction with a sample dataset. This Review provides a comprehensive overview of the principles, processes and procedures in the application of machine learning for psychiatry and mental health research.
{"title":"A procedural overview of why, when and how to use machine learning for psychiatry","authors":"Christopher Lucasius, Mai Ali, Tanmay Patel, Deepa Kundur, Peter Szatmari, John Strauss, Marco Battaglia","doi":"10.1038/s44220-024-00367-2","DOIUrl":"10.1038/s44220-024-00367-2","url":null,"abstract":"Machine learning (ML) is becoming a tool of choice to analyze high-dimensional datasets pertaining to mental health. Given the rapid integration of ML into research and clinical settings, this article provides a functional overview of a common ML pipeline used for the assessment and prediction of psychiatric disorders. Developing such a construct entails building a data infrastructure, collecting and preprocessing data, training and testing models and interpreting their results. Practical considerations pertaining to data management and preprocessing are first presented. We then describe considerations and best practices for model selection on the basis of the psychiatric disorder and the data modalities available for analysis. A critical analysis of existing works utilizing ML methods for psychiatric disorder assessment, prediction and causal associations is also provided. Last, future ML trends in psychiatry are highlighted. To reinforce learning, the Supplementary Note links to an interactive Jupyter Notebook that offers practical examples and hands-on interaction with a sample dataset. This Review provides a comprehensive overview of the principles, processes and procedures in the application of machine learning for psychiatry and mental health research.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 1","pages":"8-18"},"PeriodicalIF":0.0,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941305","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 : 2025-01-03DOI: 10.1038/s44220-024-00362-7
The role and effects of traumatic brain injury (TBI) on the development of chronic long-term health conditions are unclear. This umbrella review of existing systematic reviews and meta-analyses synthesizes the effects of TBI on risk of physical and mental health disorders and discusses implications for research and clinical management.
{"title":"Physical and mental health after traumatic brain injury","authors":"","doi":"10.1038/s44220-024-00362-7","DOIUrl":"10.1038/s44220-024-00362-7","url":null,"abstract":"The role and effects of traumatic brain injury (TBI) on the development of chronic long-term health conditions are unclear. This umbrella review of existing systematic reviews and meta-analyses synthesizes the effects of TBI on risk of physical and mental health disorders and discusses implications for research and clinical management.","PeriodicalId":74247,"journal":{"name":"Nature mental health","volume":"3 1","pages":"6-7"},"PeriodicalIF":0.0,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941315","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：