The aim of our study was to identify factors that could be addressed by specific interventions in a health care setting to further improve QoL in transgender individuals.

A total of 154 transgender individuals (82 TW, 72 TM) were included in this study. All participants were part of an observational multicenter study in Germany to assess the effects of medical interventions on psychological and metabolic outcomes of transition-related health care. This study reports on data that had been collected between November 2013 and July 2015 at four different centers: the Department of Endocrinology of the Max Planck Institute of Psychiatry, Munich in conjunction with the “Hormon- und Stoffwechselzentrum München”, Munich, the Gynaecological Department of the University hospital of Erlangen, the Interdisciplinary Transgender Health Care Center with the Institute for Sex Research and Forensic Psychiatry, Hamburg. All patients were diagnosed with gender dysphoria (DSM-5, 302.85) or Transsexualism (ICD-10, F64.0) and were treated according to the 7^th version of the Standards of Care (SoC 7) published by the World Professional Association for Transgender Health [24],although there are some national peculiarities due to health insurance´s reimbursement policies. Every eligible subject was asked for participation during a routine visit at the corresponding center. Individuals treated at the Interdisciplinary Transgender Health Care Center associated with the Institute for Sex Research in Hamburg were included right after referral for SHT, while participants from other centers were included before and after initiation of SHT.

The study was approved by the local ethics committees of the Ludwig Maximilian University of Munich, the Friedrich-Alexander University Erlangen-Nürnberg and the regional physician chambers (Landesärztekammern) of Bavaria and Hamburg. The study was conducted in accordance with the ethical standards laid down in the 1964 Declaration of Helsinki. All participants gave written informed consent. This study is registered at clinicaltrials.gov (identifier: NCT02185274).

The following variables were acquired by a self-administered questionnaire and verified with the data available in the individuals clinical records: Age, sex, age of onset (early vs. late onset), educational level (not having graduated, low, intermediate or high education and holding a university degree), employment status, self-estimation of the financial situation (good, average, bad), relationship status (single vs. in a relationship), the current use of SHT and having undergone one or more TRS. Participants being classified as having undergone any genital surgery had per our definition undergone orchiectomy, penectomy and vaginoplasty if they were transitioning from a male to a female physical appearance and ovariectomy, hysterectomy with or without phalloplasty if they were transitioning from a female to a male physical appearance. Additionally, we report on the frequency of performed mastectomies and breast augmentation surgeries. Participants were further asked to report if they had suffered from any kind of pain that had lasted for more than 5 consecutive days in the last 3 months (chronic pain). In this case, they were further asked to fill out the German pain questionnaire (GPQ) version 1. They also completed a self-constructed questionnaire rating potential side effects of hormonal therapy such as flushing, sweating, acne etc. with a rating from 0 (not at all) to 4 (severe).

Statistical analysis was performed using PASW Statistics (formerly SPSS) Version 22.0 for Windows. Sample characteristics were compared using χ2 tests and Fisher's exact test for categorical variables and the Mann-Whitney U test for ordinal and nominal variables. Univariate correlation analyses were performed using Pearson's or Spearman correlation coefficient as appropriate. Separate multivariate regression analyses were used to identify independent contributors for QoL in both sexes. Severely skewed variables were log-transformed before further analysis. A two-sided P value of < 0.05 was considered statistically significant.

General characteristics are reported in Table 1. TM and TW did only differ in terms of mean age at study inclusion (32.4 ±11.2 years vs. 42.2 ±12.4: p = 0.001). There was in particular no difference in medical treatment characteristics and socioeconomic variables such as relationship status or financial situation.

Results of the different questionnaire instruments are reported in Table 2. TM and TW did not significantly differ in QoL according to the age-adjusted SF-36 global score or the different subscales. There were also no significant differences in the STAI-X total score or the BDI-II. We did not observe any difference in sleep quality assessed by the PSQI. TW reported on significantly less practical support (p = 0.02), social integration (p = 0.01) and satisfaction (p = 0.022) than TM in the SSS. They also reported on more “physical reactions and physical–sexual discomfort” according to the FBeK (p = 0.039).

Perceived social support may affect QoL by different mechanisms such as reducing experienced stress, increasing personal resources or by supporting active coping strategies [33]. In our cohort, TW had lower scores for the social support questionnaire subdomains “practical support”, “social integration” and “satisfaction”, indicating a general lower perceived social support in comparison to TM. It has been shown before that TW have lower scores in perceived social support scales compared with natal women [34]. However, in the general population perceived social support is usually reported to be higher for women than for men [35]. This discrepancy could possibly be explained by the high degree of discrimination in various domains of live and less social support and acceptance by family members in TW in comparison to TM. It has been demonstrated before that the inverse relationship between perceived stigmatization and psychological well-being is mediated by social support [36]. All three social support domains were significantly correlated with QoL in TW, while this was only true for the domain “social burden” in TM. It has been demonstrated before hat social support can be an independent predictor of QoL in TW [37], as well as in TM [38]. It has also been shown that social support seems to be more important for general and psychosocial well-being in women than in men [39].

The subdomain "social integration" was a significant positive contributor to the SF-36 global score in TW but not in TM. The domain social integration gives information on the availability of friends and/or persons sharing similar interests to conduct joint activities. Peer groups have been considered a significant source of social support, providing access to new coping strategies, sharing similar experiences or strengthening the feeling of belonging to a group that may subsequently improve emotional well-being and QoL [40]. The relationship of the “social integration” score with QoL was independent of depressive symptoms according to the BDI-score, but was no longer significant after adjustment for the STAIX score, indicating a mediating effect of anxiety traits. It has been shown before that social support is strongly negatively correlated with the perception of anxiety symptoms in TW [37].

In TM the only domain of social support influencing QoL was “social burden”, which correlated inversely with the subdomain "social role functioning" of the SF-36. This association was still significant in the fully adjusted model for this subdomain. The "social burden" score refers to the perceived feeling of e.g. being criticized or rejected by others.

The rate of reported poor sleep in our sample was unexpectedly high with around 80% of TM and TW having a PSQI global score equal to or above 5, which indicates poor sleep quality. Strine and colleagues did show that experienced sleep quality has a huge impact on various aspects of general well-being and is a significant predictor of QoL in the general population [41]. This is of importance, because sleep quality as well as sleep duration has moreover been shown to be a predictor of morbidity [42] and mortality [43] in several studies. A recent epidemiological study from Germany reported the prevalence of poor sleep according to the PSQI to be 62.5% for women and 37.5% for men [44] and it is a common finding that more women report poor sleep than men [41]. However, we did not observe any sex-dependent differences in our sample. Thus, the ratio between female and male subjects regarding problems with sleeping seems to be disrupted because TW and TM reported high levels of poor sleep.

The causes for poor sleep did not seem to be solely explained by the degree of chronic pain or mood disturbances which are commonly known to influence sleep quality [45]. We can only speculate on the effect of SHT in this context. The finding that neither mean PSQI scores nor the number of those classified as good or poor sleepers did differ between those with and those without SHT (data not shown), speaks against a significant role of sex hormones in this context. However, we have to acknowledge that the sample size of treatment-naïve patients was rather small. In general, sex hormones are known to affect sleep [46] and our group has shown that SHT in TW can affect sleep architecture [47]. The mostly studied population with regard to the effects of sex steroids on sleep are hypogonadal or postmenopausal women. In these patients, estrogen replacement therapy generally improves sleep e.g. by decreasing sleep latency and nightly wakefulness [46, 48]. Apart from sex steroids affecting sleep architecture on a central level, a mechanistically more simple explanation in this context has been the beneficial effects of estradiol on flushing and night sweats. Although all our patients were regarded by their treating physicians as being on adequate SHT and therefore should not suffer from hypogonadal symptoms, we also had a look on reported flushing and sweating in our cohort. Interestingly, sweating at night and flushing was more common in TM than in TW. This was also associated with poorer sleep in TM but not TW. Therefore we might speculate that the observed high prevalence of poor sleep may actually be driven by different mechanisms in both sexes.

Testosterone can as well effect sleep. In natal men, low testosterone levels may lead to poor sleep, which improves after replacement therapy. The role of testosterone in natal women is not fully understood. It has been shown repeatedly that women with polycystic ovarian syndrome (PCOS) and hyperandrogenism suffer from impaired sleep, possibly being related to sleep-disordered breathing or a high BMI [49]. According to self-report and the medical files, only one transwoman was diagnosed with OSAS. However, we do so far not systematically screen for this condition in our patients, though it is a known side effects of testosterone replacement therapy in hypogonadal men.

Lastly, progesterone is also known to have effects on sleep by inducing sleep onset in both sexes [50]. It remains speculative though if a progesterone “deficit” in TM contributes to the observed sleep disturbances.

Taken together, insomnia in transgender people is an independent influencing factor on quality of life assessed with the SF-36. The underlying mechanisms thereon need to be elucidated with further studies that preferably investigate sleep quality in a longitudinal manner before and after initiation of SHT. Given the known impact of gonadal hormones on sleep architecture, quantity and quality, further clinical studies on the influence of these hormones on sleep seem to be promising.

It has been shown before that pain is a significant determinant of QoL in the general population [51] and may also significantly influence different subscales of the SF-36 [52]. Potential sex differences have only rarely been investigated in detail [45]. Bingefors and colleagues [53] did show that there are not only differences in the prevalence of pain but also sex differences with regard to how pain is affecting QoL. They demonstrated that headache had more impact on the physical dimensions of QoL among men; while the psychological dimensions were more affected among women [53].

We could show that chronic pain was an independent predictor for QoL in TM but not in TW, although the pain prevalence of about 20% did not differ between the sexes. In the general population, the prevalence of chronic pain is highly variable between studies and ranges from 7% [54] to 55% [55]. However, consistently almost all epidemiological studies show a higher prevalence of most pain conditions for women in comparison to men [56].

There are few studies [57] dealing with pain in transgender people aside from those investigating pain in the specific context of TRS [58]. Interestingly, our study did show that only a minority of patients in both groups did suffer from any genital related pain symptoms. Most were affected by headaches and musculoskeletal pain. These are the types of pain that are most commonly found in the general population, too [53]. In particular, headache is reported to be up to 3-times higher in women than in men followed by back pain with an OR of 1.2 [56, 59].

Alosi et al. did show that 29.8% of TW and 61.5% of TM reported any kind of pain. In these two groups headaches and musculoskeletal pain were the most common pain conditions, too. By retrospective assessment, the authors showed that initiation of SHT was associated with a higher incidence of pain in TW while the opposite was true for TM. The authors suggested that this could be a direct effect of the changed sex hormonal milieu [57] and explain for sex differences in pain reporting in the general population. However, the reason for the observed sex-dependent discrepancies in pain frequency including direct effects of sex steroids on pain perception or differences with regard to reporting behavior are still a matter of debate [60]. Controversially, Motsman and colleagues did show that TM show lower scores in bodily pain than TW [10].

Not surprisingly, our analysis showed a strong inverse correlation of depressive symptoms (BDI) and QoL. Of note, the sample comprised 10 participants with moderate (5 TW, 5 TM) and 4 participants (3 TW, 1 TM) with severe depressive symptoms. Importantly, the regression model revealed that poor sleep had a strong and independent influence on QoL in both sexes and was moreover associated with several domains of the SF-36, such as emotional role functioning and vitality. Chronic pain influenced QoL in TM only, while anxiety showed an independent influence on QoL in TW. These BDI-independent effects on the SF-36 are of great importance because insomnia, perception of pain as well as anxiety are symptoms of depression as well. The present study, however, shows, that these symptoms influence QoL assessed with the SF-36 independent of depressive symptoms.

Importantly, sleep [61] as well as pain-perception [55] are highly influenced by psychosocial stress [61]. This could be of great importance in this sample because transgender individuals seeking transition-related health care often suffer from psychosocial stress both due to being stigmatized as a sex/gender minority and due to their gender dysphoria per se [62]. As a matter of fact mental health care can improve not only sleep but as well pain perception. This has been demonstrated for cognitive behavioral therapy addressing insomnia and lower back pain [63]. Moreover, these interventions can improve QoL [64].

Taken together, psychobiological models of insomnia [53] and pain [65] may be of great importance to understand health related QoL in GD individuals. However, the interplay between psychological stressors, physical and endocrinological alterations on sleep and pain in people with GI/GD await further investigations.

The concept of QoL is highly complex and includes a variety of potentially influencing factors, which can differ depending on the population studied. Due to the low prevalence of GD the number of subjects studied so far is limited. Therefore, it is difficult to include all factors that could potentially influence QoL into our analysis. We therefore focused on variables that have been shown to have a significant impact on Qol in these subjects and on those representing psychological well-being such as the BDI and STAIX. Our model could explain for up to 65% of the variability of the SF-36 in TW, but only for 22.8% in TM. This further shows that there is still need for the identification of more relevant and potentially modifiable factors contributing to QoL in this special cohort, especially in TM.