Predicting the risk and timing of major mood disorder in offspring of bipolar parents: exploring the utility of a neural network approach.
Ontology highlight
ABSTRACT: Background
Bipolar disorder onset peaks over early adulthood and confirmed family history is a robust risk factor. However, penetrance within families varies and most children of bipolar parents will not develop the illness. Individualized risk prediction would be helpful for identifying those young people most at risk and to inform targeted intervention. Using prospectively collected data from the Canadian Flourish High-risk Offspring cohort study available in routine practice, we explored the use of a neural network, known as the Partial Logistic Artificial Neural Network (PLANN) to predict the time to diagnosis of major mood disorders in 1, 3 and 5-year intervals.Results
Overall, for predictive performance, PLANN outperformed the more traditional discrete survival model for 3-year and 5-year predictions. PLANN was better able to discriminate or rank individuals based on their risk of developing a major mood disorder, better able to predict the probability of developing a major mood disorder and better able to identify individuals who would be diagnosed in future time intervals. The average AUC achieved by PLANN for 5-year prediction was 0.74, which indicates good discrimination.Conclusions
This evaluation of PLANN is a useful step in the investigation of using neural networks as tools in the prediction of mood disorders in at-risk individuals and the potential that neural networks have in this field. Future research is needed to replicate these findings in a separate high-risk offspring sample.
SUBMITTER: Cooper A
PROVIDER: S-EPMC8245610 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:OBJECTIVES:There is limited information on the specificity of associations between parental bipolar disorder (BPD) and major depressive disorder (MDD) and the risk of psychopathology in offspring. The chief aim of the present study was to investigate the association between mood disorder subtypes in the two parents and mental disorders in the offspring. METHODS:A total of 376 offspring (aged 6.0-17.9 years; mean=11.5years) of 72 patients with BPD (139 offspring), 56 patients with MDD (110 offspring), and 66 controls (127 offspring) participated in a family study conducted in two university hospital centers in Switzerland. Probands, offspring, and biological co-parents were interviewed by psychologists blind to proband diagnoses, using a semi-structured diagnostic interview. RESULTS:Rates of mood and anxiety disorders were elevated among offspring of BPD probands (34.5% any mood; 42.5% any anxiety) and MDD probands (25.5% any mood; 44.6% any anxiety) as compared to those of controls (12.6% any mood; 22.8% any anxiety). Moreover, recurrent MDD was more frequent among offspring of BPD probands (7.9%) than those of controls (1.6%). Parental concordance for bipolar spectrum disorders was associated with a further elevation in the rates of mood disorders in offspring (64.3% both parents versus 27.2% one parent). CONCLUSIONS:? These findings provide unique information on the broad manifestations of parental mood disorders in their offspring. The earlier onset and increased risk of recurrent MDD in the offspring of parents with BPD compared to those of controls suggests that the episodicity characterizing BPD may emerge in childhood and adolescence.
| S-EPMC7041416 | biostudies-literature
Project description:BackgroundFamily history is a significant risk factor for bipolar disorders (BD), but the magnitude of risk varies considerably between individuals within and across families. Accurate risk estimation may increase motivation to reduce modifiable risk exposures and identify individuals appropriate for monitoring over the peak risk period. Our objective was to develop and independently replicate an individual risk calculator for bipolar spectrum disorders among the offspring of BD parents using data collected in routine clinical practice.MethodsData from the longitudinal Canadian High-Risk Offspring cohort study collected from 1996 to 2020 informed the development of a 5 and 10-year risk calculator using parametric time-to-event models with a cure fraction and a generalized gamma distribution. The calculator was then externally validated using data from the Lausanne-Geneva High-Risk Offspring cohort study collected from 1996 to 2020. A time-varying C-index by age in years was used to estimate the probability that the model correctly classified risk. Bias corrected estimates and 95% confidence limits were derived using a jackknife resampling approach.FindingsThe primary outcome was age of onset of a major mood disorder. The risk calculator was most accurate at classifying risk in mid to late adolescence in the Canadian cohort (n = 285), and a similar pattern was replicated in the Swiss cohort (n = 128). Specifically, the time-varying C-index indicated that there was approximately a 70% chance that the model would correctly predict which of two 15-year-olds would be more likely to develop the outcome in the future. External validation within a smaller Swiss cohort showed mixed results.InterpretationFindings suggest that this model may be a useful clinical tool in routine practice for improved individualized risk estimation of bipolar spectrum disorders among the adolescent offspring of a BD parent; however, risk estimation in younger high-risk offspring is less accurate, perhaps reflecting the evolving nature of psychopathology in early childhood. Based on external validation with a Swiss cohort, the risk calculator may not be as predictive in more heterogenous high-risk populations.FundingThe Canadian High-Risk Study has been funded by consecutive operating grants from the Canadian Institutes for Health Research, currently CIHR PJT Grant 152796 he Lausanne-Geneva high-risk study was and is supported by five grants from the Swiss National Foundation (#3200-040,677, #32003B-105,969, #32003B-118,326, #3200-049,746 and #3200-061,974), three grants from the Swiss National Foundation for the National Centres of Competence in Research project "The Synaptic Bases of Mental Diseases" (#125,759, #158,776, and #51NF40 - 185,897), and a grant from GlaxoSmithKline Clinical Genetics.
| S-EPMC8382986 | biostudies-literature
Project description:Bipolar disorder (BD) is a devastating disorder with a strong genetic component. While the frontolimbic profile of individuals suffering from BD is relatively well-established, there is still disagreement over the neuroanatomical features of unaffected BD offspring.Brain volumetric measures were obtained for 82 children and adolescents including 18 unaffected BD offspring (10.50 ± 3.37 years), 19 BD offspring suffering from psychiatric disorders (12.87 ± 3.28 years) and 45 healthy controls (HC-10.50 ± 3.37 years). Clinical diagnoses were established according to the Diagnostic and Statistical Manual of Mental Disorders (DSM-IV) criteria. Cortical reconstruction and volumetric segmentation were performed with the Freesurfer image analysis suite. Profile analyses compared frontolimbic volumes across groups. Age, gender, testing site, ethnicity and intracranial volume were entered as covariates.The right amygdala was significantly larger in unaffected BD offspring compared to BD offspring with psychiatric disorders and HC. Volumes of striatal, hippocampal, cingulate, and temporal regions were comparable across groups.The size of the amygdala may be a marker of disease susceptibility in offspring of BD parents. Longitudinal studies are needed to examine rates of conversion to BD as related to specific pre-morbid brain abnormalities.
| S-EPMC4254042 | biostudies-literature
Project description:OBJECTIVE:To examine structural differences in selected anterior limbic brain regions between at-risk children of parents with bipolar I disorder and children with healthy parents. We hypothesized that at-risk (AR) children would exhibit abnormalities in brain regions that are involved in mood regulation. METHOD:Children (8-12 years old) of parents with bipolar I disorder (AR children, n = 21) and of parents without any DSM-IV Axis I disorder (healthy controls, n = 24) were evaluated using diagnostic assessments and brain magnetic resonance imaging. Morphometric analyses were used to examine group differences in the prefrontal cortical, thalamic, striatal, and amygdalar volumes. RESULTS:Nine (43%) of the AR children met DSM-IV-TR criteria for a nonbipolar mood disorder at the time of assessment. AR and healthy control children did not demonstrate statistically significant differences across regions of interest (Wilks lambda =.86, F4,39 = 1.64, p = .18; effect size, f = 0.19). Post hoc analyses of covariance showed the largest relative effect size was contributed by the prefrontal cortex (f = 0.26). CONCLUSIONS:Eight- to 12-year-old children with a familial risk for mania do not exhibit any statistically significant volumetric differences in the prefrontal cortex, thalamus, striatum, or amygdala as compared with age-matched children of parents without any psychopathology. Longitudinal studies examining whether structural changes over time may be associated with vulnerability for developing subsequent bipolar disorder are needed to clarify the underlying pathophysiology of this disorder.
| S-EPMC3381335 | biostudies-literature
Project description:BackgroundBasic symptoms, defined as subjectively perceived disturbances in thought, perception and other essential mental processes, have been established as a predictor of psychotic disorders. However, the relationship between basic symptoms and family history of a transdiagnostic range of severe mental illness, including major depressive disorder, bipolar disorder and schizophrenia, has not been examined.AimsWe sought to test whether non-severe mood disorders and severe mood and psychotic disorders in parents is associated with increased basic symptoms in their biological offspring.MethodWe measured basic symptoms using the Schizophrenia Proneness Instrument - Child and Youth Version in 332 youth aged 8-26 years, including 93 offspring of control parents, 92 offspring of a parent with non-severe mood disorders, and 147 offspring of a parent with severe mood and psychotic disorders. We tested the relationships between parent mental illness and offspring basic symptoms in mixed-effects linear regression models.ResultsOffspring of a parent with severe mood and psychotic disorders (B = 0.69, 95% CI 0.22-1.16, P = 0.004) or illness with psychotic features (B = 0.68, 95% CI 0.09-1.27, P = 0.023) had significantly higher basic symptom scores than control offspring. Offspring of a parent with non-severe mood disorders reported intermediate levels of basic symptoms, that did not significantly differ from control offspring.ConclusionsBasic symptoms during childhood are a marker of familial risk of psychopathology that is related to severity and is not specific to psychotic illness.Declaration of interestNone.
| S-EPMC6582212 | biostudies-literature
Project description:BACKGROUND:Altered reward circuitry function is observed in individuals with bipolar disorder (BD) and their unaffected offspring (OBP). While OBP are at elevated risk for BD, modifiable risk factors that may exacerbate neural vulnerabilities in OBP remain under-characterized. As sleep loss is strongly linked to mania in BD, this study tested associations between sleep duration, reward circuitry function, and mood dysregulation in OBP. METHODS:Two groups of youth unaffected with BD (9-17yr) completed a number-guessing fMRI reward paradigm: 25 OBP and 21 age-sex-IQ-matched offspring of control parents with non-BD psychopathology (OCP), to differentiate risk for BD from risk for psychopathology more broadly. Regressions tested effects of group status, self-reported past-week sleep duration, and their interaction on neural activity and bilateral ventral striatum (VS) functional connectivity to win>control. Correlations with parent-reported mood dysregulation were assessed. RESULTS:Group effects were observed for right posterior insula activity (OCP>OBP) and VS-left posterior insula connectivity (OBP>OCP). Group?sleep duration interactions were observed for left dorsal anterior-mid-cingulate (daMCC) activity and VS-left anterior insula/ventrolateral prefrontal cortex (VLPFC) connectivity. Specifically, sleep duration and daMCC activity were positively related in OBP, but negatively related in OCP and sleep duration and VS-left anterior insula/VLPFC connectivity were negatively related in OBP, but positively in OCP. Additionally, increased VS-left posterior insula connectivity and VS-left anterior insula/VLPFC connectivity were associated with greater mood dysregulation in OBP only. LIMITATIONS:Cross-sectional design and small sample size. CONCLUSIONS:Altered reward-related VS-insula connectivity could represent a neural pathway underpinning mood dysregulation in OBP, and may be modulated by shortened sleep duration.
| S-EPMC5129838 | biostudies-literature
Project description:ObjectivesStudies in children of patients affected with bipolar disorder (BD; bipolar offspring) are at high risk to develop mood disorders. Our aim is to investigate how environmental factors such as childhood trauma and family functioning relate to the development of mood disorders in offspring at familial risk for BD.DesignThe current study is part of a longitudinal prospective cohort study among offspring of parents with BD.MethodsThe current study is part of the Dutch Bipolar Offspring Study, an ongoing prospective cohort study among adolescent offspring of a parent with BD. Bipolar offspring were psychiatrically evaluated at baseline and at 1-, 5-, and 12-year follow-up. Complete follow-up data over de 12-year follow-up were available for 102 offspring. Childhood trauma was measured with the Childhood Trauma Questionnaire (CTQ) and filled out by the offspring. Family functioning was reported by the mother with the 130-item Questionnaire for Family Problems (QFP).ResultsEmotional maltreatment was significantly associated (HR = 1.82, CI 1.18-2.82, p = .007) with mood disorder onset in bipolar offspring. No association was found with the family functioning total score (HR = 1.04, CI 0.94-15, p = .085) nor its subscales.ConclusionsThe current study suggests that emotional maltreatment is associated with mood disorder development in bipolar offspring. Remarkably, the association of offspring-reported emotional maltreatment and mood disorder onset was not reflected in parent-reported family functioning (e.g., support and communication, openness or involvement). Possible explanations are discussed and warrant further study.Practitioner pointsOffspring of bipolar patients are at increased risk of developing mood disorders across the life-time. Emotional trauma contributes to the likelihood of developing mood disorders in bipolar offspring. In the daily treatment of bipolar patients having children, attention should be given to parental style and difficulties. Further research using multiple informant methods on childhood trauma an family functioning is needed to further disentangle the effects of these variables on the onset of psychopathology in bipolar offspring.
| S-EPMC7497091 | biostudies-literature
Project description:Bipolar disorder is highly heritable and typically onsets in late adolescence or early adulthood. Evidence suggests that immune activation may be a mediating pathway between genetic predisposition and onset of mood disorders. Building on a prior study of mRNA and protein levels in high-risk offspring published in this Journal, we conducted a preliminary examination of methylation profiles in candidate immune genes from a subsample of well-characterized emergent adult (mean 20 years) offspring of bipolar parents from the Canadian Flourish high-risk cohort. Models were adjusted for variable age at DNA collection, sex and antidepressant and mood stabilizer use. On cross-sectional analysis, there was evidence of higher methylation rates for BDNF-1 in high-risk offspring affected (n = 27) and unaffected (n = 23) for mood disorder compared to controls (n = 24) and higher methylation rates in affected high-risk offspring for NR3C1 compared to controls. Longitudinal analyses (25 to 34 months) provided evidence of steeper decline in methylation rates in controls (n = 24) for NR3C1 compared to affected (n = 15) and unaffected (n = 11) high-risk offspring and for BDNF-2 compared to affected high-risk. There was insufficient evidence that changes in any of the candidate gene methylation rates were associated with illness recurrence in high-risk offspring. While preliminary, findings suggest that longitudinal investigation of epigenetic markers in well-characterized high-risk individuals over the peak period of risk may be informative to understand the emergence of bipolar disorder.
| S-EPMC6682840 | biostudies-literature
Project description:OBJECTIVE:The authors sought to identify diagnostic risk factors of manic, mixed, or hypomanic episodes in the offspring of parents with bipolar disorder ("high-risk offspring"). METHOD:High-risk offspring 6-18 years old (N=391) and demographically matched offspring (N=248) of community parents without bipolar disorder were assessed longitudinally with standardized diagnostic instruments by staff blind to parental diagnoses. Follow-up assessments were completed in 91% of the offspring (mean follow-up interval, 2.5 years; mean follow-up duration, 6.8 years). RESULTS:Compared with community offspring, high-risk offspring had significantly higher rates of subthreshold mania or hypomania (13.3% compared with 1.2%), manic, mixed, or hypomanic episodes (9.2% compared with 0.8%), and major depressive episodes (32.0% compared with 14.9%). They also had higher rates of attention deficit hyperactivity disorder (30.7% compared with 18.1%), disruptive behavior disorders (27.4% compared with 15.3%), anxiety disorders (39.9% compared with 21.8%), and substance use disorders (19.9% compared with 10.1%), but not unipolar major depressive disorder (major depression with no bipolarity; 18.9% compared with 13.7%). Multivariate Cox regressions showed that in the high-risk offspring, subthreshold manic or hypomanic episodes (hazard ratio=2.29), major depressive episodes (hazard ratio=1.99), and disruptive behavior disorders (hazard ratio=2.12) were associated with subsequent manic, mixed, or hypomanic episodes. Only subthreshold manic or hypomanic episodes (hazard ratio=7.57) were associated when analyses were restricted to prospective data. CONCLUSIONS:Subthreshold manic or hypomanic episodes were a diagnostic risk factor for the development of manic, mixed, or hypomanic episodes in the offspring of parents with bipolar disorder and should be a target for clinical assessment and treatment research. Major depressive episodes and disruptive behavior disorders are also indications for close clinical monitoring of emergent bipolarity in high-risk offspring.
| S-EPMC4489996 | biostudies-literature
Project description:Sleep disturbances are a prominent feature of bipolar disorder (BP). However, it remains unclear how sleep phenotypes may evolve among at-risk youth, and their relevance to BP onset.Pittsburgh Bipolar Offspring Study (BIOS) offspring (ages 10-18) and their parents completed assessments approximately every two years pertaining to current psychopathology and offspring sleep habits. A latent transition analysis (LTA) identified latent sleep groups within offspring based on their ratings of six sleep domains using the School Sleep Habits Survey. Demographic and clinical characteristics were compared between sleep groups. Logistic regression tested links between sleep group and BP onset at the subsequent assessment.The LTA model identified latent groups of good, poor, and variable sleepers. We observed an overall trend of good sleep becoming variable, and then poor, as youth age. Offspring in the poor sleep group were more likely to have psychopathology. Adjusting for age and depression, poor sleepers had nearly twice the odds of developing BP relative to good (OR=1.99, CI=0.45-8.91) or variable (OR=2.03, CI=0.72-5.72) sleepers.Limitations include the use of proximal sleep phenotypes to predict BP onset, and a self-report measure of sleep CONCLUSIONS: We found three non-overlapping sleep phenotype groups in a large sample of offspring of bipolar probands and offspring of demographically-matched community control parents. Clinicians should consider that youth will likely experience variable and/or poor sleep as they age, and that at-risk youth with poor sleep may be at increased risk of developing MDD and BP at their next assessment.
| S-EPMC5500225 | biostudies-literature