1
|
Desrivières S, Zhang Z, Robinson L, Whelan R, Jollans L, Wang Z, Nees F, Chu C, Bobou M, Du D, Cristea I, Banaschewski T, Barker G, Bokde A, Grigis A, Garavan H, Heinz A, Bruhl R, Martinot JL, Martinot MLP, Artiges E, Orfanos DP, Poustka L, Hohmann S, Millenet S, Fröhner J, Smolka M, Vaidya N, Walter H, Winterer J, Broulidakis M, van Noort B, Stringaris A, Penttilä J, Grimmer Y, Insensee C, Becker A, Zhang Y, King S, Sinclair J, Schumann G, Schmidt U. Machine learning models for diagnosis and risk prediction in eating disorders, depression, and alcohol use disorder. RESEARCH SQUARE 2024:rs.3.rs-3777784. [PMID: 38352452 PMCID: PMC10862965 DOI: 10.21203/rs.3.rs-3777784/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 02/20/2024]
Abstract
This study uses machine learning models to uncover diagnostic and risk prediction markers for eating disorders (EDs), major depressive disorder (MDD), and alcohol use disorder (AUD). Utilizing case-control samples (ages 18-25 years) and a longitudinal population-based sample (n=1,851), the models, incorporating diverse data domains, achieved high accuracy in classifying EDs, MDD, and AUD from healthy controls. The area under the receiver operating characteristic curves (AUC-ROC [95% CI]) reached 0.92 [0.86-0.97] for AN and 0.91 [0.85-0.96] for BN, without relying on body mass index as a predictor. The classification accuracies for MDD (0.91 [0.88-0.94]) and AUD (0.80 [0.74-0.85]) were also high. Each data domain emerged as accurate classifiers individually, with personality distinguishing AN, BN, and their controls with AUC-ROCs ranging from 0.77 to 0.89. The models demonstrated high transdiagnostic potential, as those trained for EDs were also accurate in classifying AUD and MDD from healthy controls, and vice versa (AUC-ROCs, 0.75-0.93). Shared predictors, such as neuroticism, hopelessness, and symptoms of attention-deficit/hyperactivity disorder, were identified as reliable classifiers. For risk prediction in the longitudinal population sample, the models exhibited moderate performance (AUC-ROCs, 0.64-0.71), highlighting the potential of combining multi-domain data for precise diagnostic and risk prediction applications in psychiatry.
Collapse
|
2
|
Yang Y, Tian M, Liu Y, Qiu S, Hu Y, Yang Y, Wang C, Xu Z, Lin L. Effects of Impulsivity and Interpersonal Problems on Adolescent Depression: A Cross-Lagged Study. Behav Sci (Basel) 2024; 14:52. [PMID: 38247704 PMCID: PMC10813366 DOI: 10.3390/bs14010052] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 12/28/2023] [Accepted: 01/05/2024] [Indexed: 01/23/2024] Open
Abstract
The dynamic changes over time in the relationships between impulsivity, interpersonal problems, and depression warrant further exploration. This study delves into the roles of impulsivity and interpersonal issues in the progression of adolescent depression over a year, using a sample of 271 Chinese adolescents (51.7% male, Mage = 12.60 ± 0.69). At three time points, impulsivity levels were assessed with the Chinese version of the Barratt Impulsiveness Scale-11, interpersonal problems with the Adolescent Self-Rating Life Events Check List, and depression with the Center for Epidemiologic Studies Depression Scale. Results revealed that both impulsivity and interpersonal problems serve as risk factors for depression, but the primary risk factor shifted over time. In early middle school stages, impulsivity was the predominant risk factor, while in later stages, interpersonal problems became the primary risk factor. These findings carry significant implications for directing prevention efforts and interventions for adolescent depression.
Collapse
Affiliation(s)
- Yanan Yang
- Key Research Base of Humanities and Social Sciences of the Ministry of Education, Academy of Psychology and Behavior, Tianjin Normal University, Tianjin 300387, China
- Center of Cooperative Innovation for Assessment and Promotion of National Mental Health under Ministry of Education, Tianjin Normal University, Tianjin 300387, China
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Mingyangjia Tian
- Key Research Base of Humanities and Social Sciences of the Ministry of Education, Academy of Psychology and Behavior, Tianjin Normal University, Tianjin 300387, China
- Center of Cooperative Innovation for Assessment and Promotion of National Mental Health under Ministry of Education, Tianjin Normal University, Tianjin 300387, China
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Yu Liu
- Intelligent Laboratory of Child and Adolescent Mental Health and Crisis Intervention of Zhejiang Province, Zhejiang Normal University, Jinhua 321004, China
- Department of Psychology, Zhejiang Normal University, Jinhua 321004, China
| | - Shaojie Qiu
- Faculty of Psychology, Beijing Normal University, Beijing 100875, China
| | - Yuan Hu
- Key Research Base of Humanities and Social Sciences of the Ministry of Education, Academy of Psychology and Behavior, Tianjin Normal University, Tianjin 300387, China
- Center of Cooperative Innovation for Assessment and Promotion of National Mental Health under Ministry of Education, Tianjin Normal University, Tianjin 300387, China
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Yang Yang
- Collaborative Innovation Center of Assessment Toward Basic Education Quality, Beijing Normal University, Beijing 100875, China
| | - Chenxu Wang
- Collaborative Innovation Center of Assessment Toward Basic Education Quality, Beijing Normal University, Beijing 100875, China
| | - Zhansheng Xu
- Key Research Base of Humanities and Social Sciences of the Ministry of Education, Academy of Psychology and Behavior, Tianjin Normal University, Tianjin 300387, China
- Center of Cooperative Innovation for Assessment and Promotion of National Mental Health under Ministry of Education, Tianjin Normal University, Tianjin 300387, China
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Lin Lin
- Key Research Base of Humanities and Social Sciences of the Ministry of Education, Academy of Psychology and Behavior, Tianjin Normal University, Tianjin 300387, China
- Center of Cooperative Innovation for Assessment and Promotion of National Mental Health under Ministry of Education, Tianjin Normal University, Tianjin 300387, China
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| |
Collapse
|
3
|
Byrne P. Premature mortality of people with severe mental illness: a renewed focus for a new era. Ir J Psychol Med 2023; 40:74-83. [PMID: 35357297 DOI: 10.1017/ipm.2022.3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
This perspective article applies public health principles to improve the physical health of selected populations with mental disorders. Two preventable adverse outcomes, poorer physical health and premature mortality, are described across mental disorders. Evidence of the lifetime effects of adverse childhood experiences and inequalities is presented: these are the 'causes of the causes'. Seven drivers of physical disorders are illustrated that drive preventable deaths and as doctors, psychiatrists must lead from the front to reverse rising mortality. Evidence supports universal and selective interventions and even the most difficult challenges such as weight gain and opioid misuse are an opportunity for psychiatry to engage with individual patients and their organisations, public health colleagues, health systems and beyond. Interventions complement and do not replace existing clinical practices that reduce self-harm and prevent suicide. Mental health teams already do most of the work in this arena, and the case is made to refocus on physical health with task sharing. The top 10 recommendations within a personalised medicine framework are listed in this paper as a starting point.
Collapse
Affiliation(s)
- Peter Byrne
- Department of Psychological Medicine, Royal London Hospital, London, UK
- Public Mental Health Implementation Centre, Royal College of Psychiatrists, London, UK
| |
Collapse
|
4
|
Rong Y, Chen N, Dong J, Li Q, Yue X, Hu L, Wei P. Expectations of immediate and delayed reward differentially affect cognitive task performance. Neuroimage 2022; 262:119582. [PMID: 35995376 DOI: 10.1016/j.neuroimage.2022.119582] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2022] [Revised: 08/11/2022] [Accepted: 08/18/2022] [Indexed: 10/31/2022] Open
Abstract
The current study used a modified Monetary Incentive Delay task to examine the neural mechanisms underlying anticipating and receiving an immediate or delayed reward and examined the influence of pursuing these rewards on cognitive task performance. A pre-cue indicating the potential of gaining a monetary reward (immediate-, delayed-, vs. no-reward) was followed by a target stimulus requiring a fast and accurate response. Then, response-contingent feedback was presented indicating whether or not the participant would receive the corresponding reward. Linear mixed-effect models revealed the fastest behavioural responses and the strongest neural activity, as reflected in event-related-potentials and event-related-spectral-perturbation responses, for immediate reward, followed by delayed reward, with the slowest behavioural responses and the weakest neural activities observed in the no-reward condition. Expectations related to the cue-P3 component and the cue-delta activities predicted behavioural performance, especially in the immediate reward condition. Moreover, exploratory analyses revealed that depression moderated the relationship between target-locked neural activity and behavioural performance in the delayed reward condition, with lower neural activity being related to worse behavioural performance amongst participants scoring high on depression. These results indicate that differential value representations formed through delay discounting directly affect neural responses in reward processing and directly influence the effort invested in the current task, which is reflected by behavioural responses and is in agreement with the expected value of control theory.
Collapse
Affiliation(s)
- Yachao Rong
- Beijing Key Laboratory of Learning and Cognition and School of Psychology, Capital Normal University, Beijing, 100048, China
| | - Ningxuan Chen
- Beijing Key Laboratory of Learning and Cognition and School of Psychology, Capital Normal University, Beijing, 100048, China
| | - Jiarui Dong
- Beijing Key Laboratory of Learning and Cognition and School of Psychology, Capital Normal University, Beijing, 100048, China
| | - Qi Li
- Beijing Key Laboratory of Learning and Cognition and School of Psychology, Capital Normal University, Beijing, 100048, China
| | - Xiaodong Yue
- Beijing Key Laboratory of Learning and Cognition and School of Psychology, Capital Normal University, Beijing, 100048, China
| | - Li Hu
- Key Laboratory of Mental Health, Institute of Psychology, Chinese Academy of Sciences, Beijing, 100101, China; Department of Psychology, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Ping Wei
- Beijing Key Laboratory of Learning and Cognition and School of Psychology, Capital Normal University, Beijing, 100048, China.
| |
Collapse
|
5
|
Zhang J, Li K, Xue Y, Feng Z. Network Analysis of the Relationship Between Trait Depression and Impulsiveness Among Youth. Front Psychiatry 2022; 13:916332. [PMID: 35782437 PMCID: PMC9247242 DOI: 10.3389/fpsyt.2022.916332] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/09/2022] [Accepted: 05/13/2022] [Indexed: 12/02/2022] Open
Abstract
Objective Both impulsiveness and trait depression are the trait-level risk factors for depressive symptoms. However, the two traits overlap and do not affect depressive symptoms independently. This study takes impulsiveness and trait depression into a whole construct, aiming to find the complex associations among all facets and explore their relative importance in a trait network. It can help us find the key facets that need consideration in preventing depression. Materials and Methods We used the Barratt Impulsiveness Scale (BIS) and Trait Depression Scale (T-DEP) as measuring tools, conducted network analysis, and applied the Graphic Least Absolute Shrinkage and Selection Operator (GLASSO) algorithm to estimate the network structure and compute the linkage and centrality indexes. The accuracy and stability of the indexes were estimated through bootstrapping. All the computations were performed by R script and packages. Results We found that "trait anhedonia" was connected with "non-planning" and "cognitive" impulsiveness, while "trait dysthymia" was connected with "motor" impulsiveness. "Cognitive" impulsiveness had a statistically significant higher expected influence than "motor" impulsiveness and had the trend to be dominant in the network. "Trait dysthymia" had a statistically significant higher bridge expected influence than "cognitive" impulsiveness and had the trend to be the key facet linking impulsiveness with trait depression. "Non-only children" had higher network global strength than "only children." All indexes were accurate and stable. Conclusion The present study confirms the complex associations among facets of trait depression and impulsiveness, finding that "cognitive" impulsiveness and "trait dysthymia" are the two key factors in the network. The results imply that different facets of impulsiveness should be considered respectively regarding anhedonia and dysthymia. "Cognitive" impulsiveness and "trait dysthymia" are critical to the prevention of depression.
Collapse
Affiliation(s)
| | | | | | - Zhengzhi Feng
- Department of Medical Psychology, Army Medical University, Chongqing, China
| |
Collapse
|
6
|
Di Rosa E, Mapelli D, Ronconi L, Macchia E, Gentili C, Bisiacchi P, Edelstyn N. Anxiety predicts impulsive-compulsive behaviours in Parkinson's disease: Clinical relevance and theoretical implications. J Psychiatr Res 2022; 148:220-229. [PMID: 35134729 DOI: 10.1016/j.jpsychires.2022.01.052] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/25/2021] [Revised: 01/13/2022] [Accepted: 01/26/2022] [Indexed: 10/19/2022]
Abstract
Patients with Parkinson's disease (PD) often present symptoms of anxiety, depression and apathy. These negative affect manifestations have been recently associated with the presence of impulsive compulsive behaviours (ICBs). However, their relation with the use of dopamine replacement therapy (DRT), a renewed risk factor for ICBs, is still not fully understood. Elucidating the role of these different ICBs predictors in PD could inform both prevention/intervention recommendations as well as theoretical models. In the present study, we have analysed data collected in 417 PD patients, 50 patients with Parkinsonian symptoms but with scan without evidence of dopaminergic deficit (SWEDD), and 185 healthy controls (HC). We examined each patient's clinical profile over a two-year time window, investigating the role of both negative affect and DRT on ICBs. Results confirmed the presence of higher levels of anxiety in both the clinical groups, and of higher level of ICBs in SWEDD patients, respect to both PD and HC. Mixed model analyses revealed a statistically significant association between anxiety and ICBs in the SWEDD patients who did not take any DRT. Findings suggest the independence between anxiety and DRT in ICBs development, and provide new evidence for the motivational opponency theoretical framework.
Collapse
Affiliation(s)
- Elisa Di Rosa
- Department of General Psychology, University of Padua, Padua, Italy; School of Psychology, Keele University, Staffordshire, UK.
| | - Daniela Mapelli
- Department of General Psychology, University of Padua, Padua, Italy
| | - Lucia Ronconi
- Department of General Psychology, University of Padua, Padua, Italy
| | - Eleonora Macchia
- Department of General Psychology, University of Padua, Padua, Italy
| | - Claudio Gentili
- Department of General Psychology, University of Padua, Padua, Italy; Padua Neuroscience Centre, University of Padua, Padua, Italy; Centro di Ateneo dei Servizi Clinici Universitari Psicologici, University of Padua, Padua, Italy
| | - Patrizia Bisiacchi
- Department of General Psychology, University of Padua, Padua, Italy; Padua Neuroscience Centre, University of Padua, Padua, Italy
| | - Nicky Edelstyn
- School of Psychology, Keele University, Staffordshire, UK
| |
Collapse
|
7
|
Kirsch DE, Lippard ET. Early life stress and substance use disorders: The critical role of adolescent substance use. Pharmacol Biochem Behav 2022; 215:173360. [PMID: 35219756 PMCID: PMC8983562 DOI: 10.1016/j.pbb.2022.173360] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/05/2021] [Revised: 12/06/2021] [Accepted: 02/20/2022] [Indexed: 12/12/2022]
Abstract
Early life stress (ELS) is a well-established risk factor for many psychiatric and medical disorders, including substance use disorders (SUDs). The relationship between ELS and SUDs is complex and there are likely multiple pathways from ELS to adverse substance use outcomes. The association between ELS and substance use emerges in adolescence. Adolescence is a critical period in development during which substance exposure markedly increases risk for SUDs. Therefore, this review focuses on the literature supporting the hypothesis that ELS increases risk for the development of SUDs through its influence on adolescent substance use. We discuss studies substantiating the role of ELS in adolescent substance use and explore how internalizing and externalizing psychopathology may be antecedents of substance use in adolescence. We examine clinical work suggesting ELS sculpts the Hypothalamic-Pituitary-Adrenal (HPA) Axis and developing brain-particularly subcortical brain regions that underlie stress response, mesocorticolimbic brain systems associated with reward sensitivity, and prefrontal regions that underlie executive control-in a way that increases risk for adolescent substance use and SUDs. We further explore how substance use during adolescence alters structure and function of these same systems, and how brain changes following ELS and adolescent substance use may independently, additively, or interactively contribute to risk for addiction. We conclude by discussing how the current literature can inform interventions aimed at reducing risk for SUDs in individuals with a history of ELS.
Collapse
|