Studies of potential genetic effects on risk for suicide are based on investigations of twins and of adoptees and their families. Twin studies have shown that concordance for suicide is significantly more frequent in monozygotic than in dizygotic twins [1-3], suggesting genetic contributions to suicide. However, drawing this conclusion from twin studies assumes that the common environmental influences in utero and due to living in the same families, as well as the total genetic variance are identical in mono- and dizygotic pairs [4]. Moreover, genetic influences may be additive (i.e. due to different genetic variants) typically being expressed in parents and their offspring or non-additive (i.e. dominance effects by genetic variants or by interactions among genes), expressed among full siblings [4]. An example of a non-additive effect was found in an earlier adoptions study; analysing incidence and case-fatality of infectious disease in adoptees and their siblings there appeared to be a strong non-additive genetic influence on risk of fatal outcome [5]. In twin studies common environmental influences cannot be distinguished from non-additive genetic influences [4]. Unfortunately, there are extremely limited data on suicide risk in twins reared apart compared to those reared together, which might provide information on the contribution of both common environmental effects and genetic effects [3].

A large Swedish study investigated familial clustering of suicide risk in, among others, full- and half-siblings, parents and their offspring and also in spouses and adopted children [6]. This confirmed that there is a genetic influence contributing to the familial clustering of suicide risk. Further, based on higher risk among full siblings compared to parents and their offspring pairs and higher risk in maternal half siblings than in paternal half-siblings, they concluded that shared environment contributes to the familial risk of suicide. However, a stronger correlation between full siblings than between parents and their offspring could be due to either shared environment or to non-additive genetic effects [4]. Also, the stronger correlation in maternal half-siblings than in paternal half-sibling could be caused by either shared environment before as well after birth or it could be due to non-paternity for a proportion of those registered as paternal half-siblings. These alternative explanations could neither be proved nor disproved in the adopted children in the Swedish study.

Investigation of adoptees and their biological and adoptive parents and siblings provide powerful means of investigating genetic and familial environmental influences on risk of diseases. This has shown, for example, that premature death in adults, especially due to infection and vascular causes, has a strong genetic background [7,8]. We chose this approach for the present study.

An earlier adoption study of suicide, based on the Danish Adoption Register, demonstrated that suicide risk was significantly increased in the biological parents and siblings of adoptees who died by suicide compared to the biological parents and siblings of adoptees who did not die by suicide [9]. This study was, however, limited to adoptees from the Copenhagen area (with just 57 adoptee suicides). Moreover, it did not distinguish between parents and siblings of the adoptees, and the analysis did not take into account clustering in families. The Swedish Multi-Generational register has been used to identify large groups of adoptees, born between 1946 and 1986, and their parents. This showed a two-fold increased risk of suicide in adoptees whose biological parents had died by suicide [10]. When adopted by relatives in the biologically-related family, the adoptee is brought up in a family environment that is not clearly separated from their genetic background. Investigations of non-familial adoptions, as in the Danish Adoption Register, enable better separation of genetic and familial environmental effect. Restricting analyses to siblings would also enable better assessment of non-additive genetic effects and reduce the potentially confounding influences from generational changes.

Severe psychiatric disorders necessitating psychiatric hospital admission are strongly associated with risk of suicide [11-13]. Schulsinger and colleagues found evidence of genetic influence among people dying by suicide who did not have a history of psychiatric hospitalization as well as among those with such a history [9]. They discussed whether this suggests a pathogenic factor contributing to suicide independent of psychiatric disease, or whether suicide reflects an acute and severe psychiatric illness manifesting as suicide. A large Danish study strongly suggested that familial history of psychiatric illness increases suicide risk only through increasing the risk of developing a mental disorder. It also showed that family suicide history significantly increases suicide risk independently of familial history of psychiatric illness [14].

Using the national Danish Adoption Register and Danish Health Registers, we have estimated risk of suicide in biological full siblings and half-siblings and in adoptive siblings of adoptees. We compared the risk in siblings of adoptees who had died by suicide with the risk in siblings of surviving adoptees. The analyses include examination of risk according to history of psychiatric treatment. Our hypothesis was that our findings for suicide would provide evidence that genetically-transmitted risk (i.e. observed in biologically-related siblings) and familial environmentally-determined risk (i.e. observed in adoptive siblings) are present, and that these would occur irrespective of whether or not there was a history of psychiatric treatment.

Table 2 shows the occurrence of suicide in biological and adoptive siblings of adoptees who died by suicide before the age of 60 years or survived to age 60 years. Table 3 presents associations between suicide in adoptees and rate of suicide in siblings. In full siblings a statistically significant excess rate of suicides was found among siblings of adoptees dying by suicide before age 60 years versus siblings of adoptees surviving to age 60 years. The excess rate in maternal half siblings was not statistically significant. In adoptive siblings the rate ratio could not be estimated as no one died by suicide among those having an adoptive sibling who died by suicide (confer the 0 cell in Table 2), suggesting no increase in risk of suicide given suicide in the adoptee. We found no statistically significant difference in effect on male and female biological siblings (p>0.12) and no statistically significant difference in effect on biological siblings under or above age 30 years (p>0.82).

Adjustment for psychiatric illness of the siblings attenuated the associations, but they remained significant for biological full siblings. When the comparison was restricted to adoptees without a psychiatric admission, together with adjustment for psychiatric admission in the siblings, the elevated rate of suicide in full biological siblings was increased to 13.9, but with a very wide confidence interval. The non-significantly elevated rate of suicide in maternal half siblings remained.

In the robustness analyses of siblings of adoptees dying by suicide before 2006 versus those surviving to 2006, the rate ratios found were 8.66 (1.53 - 48.9) in full siblings, 1.49 (0.47 - 4.74) in paternal half siblings, 2.73 (1.12 - 6.65) in maternal half siblings, and 0.93 (0.12 - 7.16) in adoptive siblings.

This adoption study of genetic and familial environmental influences on suicide has provided clear evidence of genetic transmission of suicide risk. Depending on the time period for observing suicides in the adoptees, this risk in full biological siblings of adoptees who had died by suicide was elevated five and eight times compared to the risk in biological full siblings of adoptees not dying by suicide. We found no evidence of environmental influence of adoptive families, since there was no correlation between adoptee outcome and risk in their adoptive siblings. These results corroborate the findings of earlier twin and adoptive family studies [3,9,10]. The increased risk for biological full siblings found in our study is higher than in the Swedish study of biological parents and adoptees [10]. This could be due to several factors, for example, non-additive genetic effects and confounding from generational changes in environmental factors when studying parents and children instead of siblings. The findings from our study and that of Tidemalm et al. differed in terms of the influence of the shared environment on suicide risk [6]. This could be due to lack of statistical power in our study, or it could be due to the fact that non-additive genetic influences and non-paternity biased the estimate of the influence of shared environment in the Swedish study. Though the study included as many adoptive siblings as biological full siblings, from the analyses where adoptive siblings were followed up until 2006, which was the only period where the risk in adoptive siblings of adoptees who had died by suicide compared to the risk in adoptive siblings of adoptees not dying by suicide could be estimated, the estimated rate ratio was 0.93 (0.12 - 7.16). It is evident from the wide confidence interval that our study lacked power to exclude there being an influence from shared environment. Our results confirmed that the elevated risk of suicide in biological siblings of adoptees is largely independent of a family history of psychiatric disorder leading to hospital admissions.

In contrast to earlier studies we did not include parents, but instead focused on siblings, and divided them into full, paternal half and maternal half siblings. The results suggested that maternal transmission of suicide risk may be greater than paternal transmission, as also found in the general Nordic populations [6,18]. However, non-paternity might have influenced this finding by reducing the strength of the associations on the fathers’ side as compared to the mothers’ side. According to Kety and colleagues [19], the accuracy of identification of biological fathers of adoptees is probably greater than is usually the case since the law requires putative fathers to acknowledge paternity and to contribute to the costs of care of their children. Stronger associations between risks in adoptees and their maternal half-siblings than between adoptees and their paternal half-siblings could also come about by pre-adoptive (most likely prenatal) influences of the maternal environment. This may contribute to the associations between adoptees and full siblings, but the differences in associations with the full siblings and with the maternal half-siblings indicate that genetic contributions are more important than the maternal environment equally shared by the two types of siblings.

Although the genetic associations appeared independent of psychiatric admissions, the mechanisms involved in genetic transmission of risk of suicide may imply undiagnosed psychiatric conditions or psychological pathways under genetic control. Likely candidates include transmission of personality traits associated with suicide such as aggression and impulsivity [20]. There is reasonable evidence that suicide risk is increased in the presence of reduced levels of 5-hydroxyindoleacetic acid [21-23], which is also known to be associated with aggression [22]. This may be a mediator of genetic transmission, given the known association of increased risk of suicide in individuals with certain polymorphisms of genes influencing the serotonergic transmission system [24].

Genetic influences make a major contribution to risk of suicide, which may occur independent of known psychiatric disorder. This is important because it not only increases our understanding of influences on risk of suicide, but also has implications for provision of advice to families with a history of suicide, including possible preventive initiatives. Also, future studies should, where possible, include control for all psychiatric disorders, not just those identified by history of psychiatric admission.