We investigated common genetic and environmental influences on social isolation and mental health symptoms from childhood to young adulthood using a nationally-representative UK sample. We found that shared genetic risk largely explained the longitudinal overlap between social isolation and mental health symptoms, but the magnitude of this effect varied across disorders and timepoints. Genetically-influenced transdiagnostic risk can account for the longitudinal co-occurrence of social isolation with depression symptoms and psychotic-like experiences, but not for conduct problems. Through a longitudinal genetically sensitive approach, we emphasise moving away from a view that aetiology is static and highlight that social isolation is developmentally intertwined with the experience of poor mental health.

Social experiences are not independent of a person’s characteristics, such as personality or psychopathology. Our hypothesis for a heritable component of social isolation arises from the genetic influences shared with these heritable characteristics. Consistent with previous research on other social behaviours [17, 18], we showed that social isolation was around 50% heritable across childhood. Although social isolation is an environmental experience, the genetic basis likely reflects other heritable characteristics that predispose children to negative interactions with others [19]. Genetic factors contribute to how young people create social connections: individuals self-select and modify their environment or evoke reactions (active and evocative gene-environment correlations, respectively) that can lead to solitary behaviour. This is consistent with other childhood social exposures such as bullying victimisation and other forms of childhood adversity [29]. Children with phenotypic expressions of a genetic liability to mental health symptoms can increase the risk of rejection from people around them.

We found differences in the pattern of genetic and environmental influences on social isolation across development. Genetic factors were prominent early in childhood and contributed to the continuation of social isolation across time. Rather than a specific time period where environmental experiences are most important for social inclusion, unique environmental experiences contributed to developmental changes that were specific to each age. We show evidence for a dynamic aetiology of childhood social isolation, whereby genetic and environmental influences show distinct patterns over time. This pattern is widely reported for childhood internalising, externalising, and withdrawn behaviour [24]. It is possible that the genetic contribution to the stability of social isolation is a reflection of heritable mental health symptoms showing the same developmental pattern.

Our findings suggest that social isolation can be conceptualised as an intertwined component of poor mental health. Rather than a risk factor or an outcome of poor mental health, social isolation could be a marker of functional impairment that occurs alongside mental health symptoms. One comparable example of this type of comorbidity is sleep disturbances. Mental health symptoms are longitudinally and bidirectionally associated with sleep disturbances across childhood and adolescence, and research suggests this is due to underlying risk factors that occur sequentially, in parallel, and interact with each other [30]. Sleep disturbances are distinct from mental health problems, but they typically go hand-in-hand phenotypically and genetically [30]. They are often treated as a peripheral or secondary symptom for mental health disorders. Sleep disturbances can both act as an indicator that a person is having difficulties, as well as subsequently worsen symptoms for people with these disorders. Social isolation and mental health symptoms are interconnected in a similar way to sleep disturbances. Inquiring about social isolation can provide an avenue to identify young people that not only are at risk for mental health symptoms but are already experiencing difficulties that have not yet been recognised.

Our findings support this notion in two ways. First, we found similar patterns of association regardless of the longitudinal direction of effect. For depression symptoms and psychotic experiences, the contribution of genetic and environmental influences was consistent irrespective of whether social isolation was assessed before or after mental health symptoms. This suggests similar mechanisms underlying longitudinal associations, regardless of temporal precedence. Conceptualising social isolation solely as a risk factor could underestimate the complexity of the links to poor mental health. We must note that these findings are based on associations rather than testing causal effects. Qualitative studies have also reported a lack of social connections as integral for people with lived experience of depression, anxiety, and psychosis [31, 32]. A lack of supportive relationships could act as a general indicator or social symptom for mental health problems in young people [11, 13]. Second, genetic factors contributed to over 80% of the association between social isolation and depression symptoms and psychotic experiences. Therefore, previous longitudinal findings could be confounded by common genetic influence. Genetic confounding is well-documented in psychiatric research [33] and has been demonstrated for other childhood environmental exposures [29]. This is one explanation for the mixed findings in the existing literature on the direction of the association between social isolation and mental health symptoms [7], as this association is substantially confounded by shared genetic liabilities across mental health disorders and social behaviours in young people [22]. Genetic overlap suggests intricate interplay between social isolation and mental health symptoms. Our findings emphasise that we cannot assume social isolation is associated with later poor mental health (and vice versa) entirely through an environmental pathway. Instead, social experiences could be considered integral to the phenotypic profile of some psychiatric disorders.

Conduct problems had a distinct aetiological structure which contributed differently to associations with social isolation. Shared environmental factors substantially influenced associations with social isolation, rather than shared genetic influences as for the other mental health symptoms examined here. Children growing up in a violent community or family could be more likely to develop conduct problems and be isolated from their peers [34]. Conduct problems may differentiate from depression and psychotic-like experiences as these atypical behaviours actively shape and maintain social interactions [35]. We show that when conduct problems led to later social isolation, genetic effects contributed 30%, but when this direction was reversed, the genetic effect disappeared. This is consistent with evocative rGE: adolescents who are predisposed to developing conduct problems may evoke negative responses from their peer group. Genetic risk could shape young people’s cognitive and affective functioning which inhibits building and maintaining of social relationships [35]. Conduct disorder is highly heterogeneous in its symptomatology and variation in genetic architecture across aggressive and non-aggressive symptoms could explain the lack of genetic overlap [36].

This research has limitations. First, we used different instruments to assess the same constructs over time which could influence model estimates. Particularly for social isolation, variance could be misattributed due to differences in measurement. However, developmental measures must be appropriate for each age and we used clinically relevant measures of mental health symptoms rather than a single child behaviour scale typically used in longitudinal studies. Second, we used only twin-based methods to estimate additive genetic effects which could overestimate genetic effects if the equal environments assumption does not hold (MZ twins treated more similarly compared to DZ twins), when non-additive effects such as gene-gene or gene-environment interactions are being captured. Future research should aim to triangulate DNA-based and twin designs, or move towards a full shift in family-based genomic research which can provide more accurate findings on the developmental aetiology of psychopathology [37]. Third, the six-year age gap between assessments would not have captured dynamic processes between social isolation and mental health. Fourth, our findings on social isolation in a twin sample may not generalise to singletons. As all participants share a sibling of the same age and sex, levels of isolation may be underestimated. However, twins could become isolated from their peers despite, and perhaps because of, closeness with their cotwin. For example, children may withdraw or not seek active socialisation with peers outside the dyad in favour of the company of their cotwin. Fifth, it is unclear how our findings would differ for clinical populations of people with depression, conduct disorder, or psychosis. Therefore, heritability estimates presented here will differ from other samples of different ages, measures, and clinical sampling, but provide insight into developmental processes of these disorders beyond a clinical setting. Sixth, measures of social isolation used in this study were not specifically designed to assess isolation which could limit interpretability. Items were instead selected from the CBCL, an instrument designed to screen for a wide range of emotional and behavioural problems. The selected items broadly capture a reduction in social contact through social withdrawal or peer rejection. Age 18 isolation was operationalised as a lack of social support, as this reflects the extent to which an individual is embedded within a social network. Seventh, experiences of isolation can include feelings of loneliness which could confound the association with mental health problems. However, social isolation takes into consideration an individual’s material social surroundings, rather than focusing on subjective expectations of social connection that can vary from person to person. Identifying structural factors that contribute to a lack of social connectedness shifts away from individual perceptions and identifies areas that are targetable through policy and intervention. Eighth, twin modelling estimates are reliant on a multitude of model specification decisions. Genetic and environmental estimates can vary depending on how many traits are included in the model, how reporter estimates are combined, and which effects are freely estimated. Caution is warranted in interpreting model estimates as true values and replication is needed in other twin cohorts.

Our findings have key implications for clinicians, educational professionals, and future research. First, social isolation can act as an indicator to help identify underlying mental health symptoms in young people. Given the stigma and difficulty to recognise mental health symptoms, assessing social isolation provides an additional way for children to communicate their difficulties. For example, when children report they are consistently by themselves or do not play with any other children at school, this could signal to clinicians other co-occurring difficulties within which social isolation is embedded. The substantial genetic overlap we found does not suggest that being isolated is determined by genes, nor that mental health symptoms will always lead to isolation (or vice versa), nor that either cannot be addressed through interventions. Rather, we provide evidence that integrative assessment of social experiences such as isolation may be a helpful add-on to assessments of mental health symptoms, and that any social support interventions for mental health symptoms should be put into practice as early as possible in development. Second, nuanced interdisciplinary research that integrates genetic, social, and developmental approaches into study designs is fundamental to understanding behaviour. Identifying dynamic processes between reciprocal social interactions and psychopathology whilst accounting for genetic confounding is warranted. We demonstrate the value in modelling genetically sensitive longitudinal associations between social isolation and mental health symptoms, that capture both trait overlap and specificity.