Recent estimates for Germany indicate that the five-year prevalence of cancer patients is approximately 1.33 million [1]. Improved treatment and early detection regimes have contributed to an increased survival of cancer patients – at least in the well-developed countries. As survival has improved for most cancer types, the impact of disease and treatment on patient’s quality of life (QoL) becomes more important in clinical practice as well as in health care research and clinical research [2]. During the last decades several questionnaires to assess QoL have been developed. In oncology one of the most frequently used questionnaires to measure health-related quality of life is the Quality of Life Questionnaire Core module with 30 items provided by the European Organization for Research and Treatment of Cancer (EORTC QLQ-C30). The QLQ-C30 is a multi-dimensional assessment tool as it includes a range of items covering physical, emotional und social health issues – issues being relevant to cancer patients irrespective of diagnosis. It can be used for detection of early and long-term consequences of the cancer disease itself and its treatment. Further, the QLQ-C30 can be used for individual patient management as well as for evaluation of undesired treatment effects on the group level. There is sufficient evidence to support its reliability and validity [3,4].

Although asking patients about their QoL is clinically intuitive, simple and easy to conduct, a number of methodological problems are to be discussed. In particular, the question which values in a continuum of possible values between 0 and 100 indicate ‘a good quality of life’ is very challenging [2,5]. Osoba et al. raised the question of clinical importance of differences and defined differences of 10 points or more as clinically relevant [6] – both for differences within and between persons and groups, respectively. Another problem is that “baseline values” in cancer patients are collected after the persons have been diagnosed with cancer. At this time cancer patients may be already psychologically affected by the cancer diagnosis and may suffer from symptoms – both biases baseline values. Therefore, using reference data from the general population of corresponding age and sex is an important alternative to assess the baseline QoL of individual patients [5,7].

The EORTC QLQ-C30 has been translated into more than 60 languages. It is said to be applicable across a range of cultural settings [8]. However, Hjermstadt emphasizes the importance of national reference data [9] as quality of life measured with the EORTC QLQ-C30 was found to vary by age and sex. Furthermore, QoL seems to be influenced by the cultural context and/or the degree of morbidity in the general population [5,10,11]. Therefore, national reference data can help researchers and clinicians to interpret their patients’ self-assessed QoL.

The most recent reference / normative data for the EORTC QLQ-C30 was published for samples of the Swedish [7] and the Dutch population [12]. In 2001, Schwarz and Hinz published reference data for Germany based on a sample of 2,028 persons [13]. However, these data were collected by means of face-to-face interviews in Leipzig, Eastern Germany, nine years after the reunification. At that time marked social and health differences were found between Western and Eastern Germany, e.g. the proportion of unemployed persons in Eastern Germany was nearly twice as high as in Western Germany and the proportion of persons at-risk-for-poverty was 7% higher in Eastern than in Western Germany. Further, life expectancy differed by 2 years for women and 3 years for men and morbidity patterns showed relevant differences. Today social differences between the “old” and the “new” federal states are still to be found – even though to a lesser extent [14,15]. Thus, it can be questioned whether the Schwarz and Hinz data still reflect the situation in Germany today. As new data are warranted, we aimed to assess up-to-date normative data for the EORTC QLQ-C30 in a random sample of the population in Luebeck, Northern Germany, aged 16 years and older with our survey “33 questions for Luebeck”.

Our survey aimed to assess up-to-date normative data for the EORTC QLQ-C30 in a random sample of a population in Luebeck, Northern Germany, with a minimum age of 16 years. Four important findings emerge from our study: First of all, although we contacted a random sample of the “apparently healthy” population, study participation was remarkably high with 47% of eligible persons filling out the questionnaire. Participation behavior followed the expected pattern with women compared to men being more likely to participate and younger as well as the oldest persons compared to middle-aged persons being less likely to respond. Second, a high level of self-reported morbidity was found in our random sample of the population. Especially the prevalence of a “lifetime diagnosis” of mental diseases was high. Third of all, QoL differences between men and women and younger and older persons, respectively, were as expected – that is, men scored slightly higher on the function scales, women reported a slightly higher level of symptomatology/problems and younger persons scored higher on the function scales and lower on the symptom scales/items than the elderly. And finally, if differences of ten points or more were considered as clinically relevant as suggested by Osoba and colleagues [6], relevantly higher levels of fatigue, pain and insomnia were found when our data was compared to (age-adjusted) Schwarz and Hinz data published in 2001 [13].

Cross-sectional studies (surveys) are easy to realize at comparably low costs. But several problems are inherent in this study type: One problem of cross-sectional studies is their “snapshot” character, that is, surveys are often conducted only at one time point or period. Another problem is associated with the mode of recruitment and the resulting representativeness of the respondents. With regard to representativeness random samples are to be preferred in contrast to -for example- volunteers answering to advertisements. However, random samples hold the danger of low response rates as there is no relationship (of whatever nature) between potential participants and researchers resulting – depending on the number of potential participants – in small subgroups. In our survey we contacted 10,000 potential participants – that is 5.5% of the total population living in Luebeck aged 16 years or older [16]. The sample was representative with regard to age, sex and urban district. The latter had no influence on study participation while younger persons and men were less likely to respond. This participation pattern was also found in the study of Derogar et al. [7] and of van de Poll-Franse et al. [12]. Nevertheless, study participation in our study was very high allowing subgroup analyses. The high participation rate might be due to the context. In the year 2012, Luebeck was the City of Science (“Stadt der Wissenschaft” [17]) – a title that is awarded by the Donors’ Association for German Science (“Stifterverband für die Deutsche Wissenschaft” [18]). In the context of the “City of Science” several events, awareness campaigns and public campaigns were conducted with the aim of bringing science, researchers and the public together. This and the wish to contribute to a good reputation of the city may have prompted a high motivation to participate.

Current data regarding the health status or morbidity of the Luebeck population is not available in detail, therefore, we compare our data to the German DEGS-sample (Studie zur Gesundheit Erwachsener in Deutschland (DEGS) [German Health Interview and Examination Survey for Adults]: data collection: 11/2008 -01/2012; 8,152 participants, Germany-wide recruitment, 180 study centres [19]) and to the GEDA-2010-sample (Gesundheit in Deutschland aktuell (GEDA) [German Health Update]: GEDA complements DEGS; data collection: 09/2009 -07/2010, telephone interview with 22,050 participants, Germany-wide recruitment [20]).

Regarding the diseases of affluence our data corresponds well to the DEGS- and GEDA-2010 data. Hypertension, arthritis and hyperlipidemia were the three diseases most often reported in our study. In the GEDA-sample the single most prevalent health condition was hypertension (32% in women, 31% in men; lifetime prevalence) followed by hyperlipidemia (women: 28%; men: 31%) and arthritis (women: 27%, men: 18% [20]). A diabetes diagnosis was reported by 9.5% of our participants which is a little higher than the percentage of GEDA-participants (women: 9%, men: 8% [20]) and DEGS-participants with known diabetes (7.2%; taking diabetes medication or reporting a medical diagnosis of diabetes). If self-reported levels of blood glucose and/or HbA1c were taken into account an additional 0.7-2.1% of DEGS-participants (depending whether either glucose or HbA1c or both were considered) were classified as having diabetes [19].

Approximately 8% of women and men in our sample had survived a tumor disease which equals the lifetime prevalence for any malignant disease in the female GEDA-2009-sample (8.4%) while GEDA-men reported a lifetime prevalence of 5.3% [21]. On the one hand, the difference in lifetime prevalence of any cancer might be due to the slightly differing age structure between our and the GEDA-2009-sample (proportion of study participants aged >= 50 years: 53.9% of men in our sample, 43.1% in the GEDA-sample), with our sample being older. On the other hand, it might be due to the fact that the federal state of Schleswig-Holstein is one of the states in Germany with highest incidences for prostate cancer, malignant melanoma, basal and squamous cell carcinoma [22]. Not only prostate cancer, but also non-melanoma skin cancer has a high five-year relative survival rate which might have contributed to the higher lifetime prevalence of any malignant tumor disease in our cohort.

Regarding the mental disorders a higher degree of morbidity was found in our sample, as 14.7% of participants state to have a lifetime diagnosis of depression while only 8.1% of the DEGS-sample show symptoms of depression within the past 14 days (assessed with PHQ-9 [19]) and only 9.0% of women and 5.1% of men had a diagnosis of depression within the last 12 months in the GEDA-sample [20] (data of the GEDA-2009-sample: 8.0% of women and 4.5% of men [21]). Differences in study design (lifetime prevalence vs. prevalence with past 12 months and past 14 days, respectively) and general time trends are partly responsible for the observed differences. Not only for Germany, but also for Europe it was recently shown that the number of persons with mental disorders has been increasing during the last 25 years [22].

In conclusion, our study sample –drawn from a random sample of the population- shows a morbidity pattern that seems to reflect the frequency and the morbidity pattern in the current German population with the exception of a slightly increased prevalence of mental diseases. This level of morbidity has to be kept in mind when QoL data of “healthy” reference population are compared to QoL data of well-defined groups of patients.

The differences in EORTC QLQ-C30 scores (between men and women, young and old persons) found in our study as well as in other studies [7,12,13] underline the ability of the EORTC QLQ-C30 to detect differences in health-related QoL not only in the original target group –that is in cancer patients- but also in the general population. Nevertheless, a random sample of the general population will include healthy persons as well as diseased persons. As can be assumed, clinically relevant differences in QoL were found in our sample for ill and healthy persons (data not shown in detail).

QoL data of our German study participants stratified by sex and age groups is different from recently published QoL data of a Dutch [12] and a Swedish [7] general population sample which might be due to either cultural reasons or linguistic differences between the various translations of the EORTC QLQ-C30 as discussed by Scott and colleagues [10]. In comparison to data from The Netherlands [12] and Sweden [7] global QoL/health status in our study is clinically relevantly lower for the age groups 50-59, 60-69, and 70 years and older and also somewhat lower in the younger age groups of our study population.

Compared to the Schwarz and Hinz data published in 2001 [13] the global QoL/health status reported by our study participants is lower for all age groups except for women aged 60 to 69 years. When the age structure of our sample is used to age-adjust the Schwarz and Hinz data [13] differences for the global QoL/health status (difference of 0.2 points in women and of 1.3 points in men) and for most of the other scales and items tended to be small and not clinically relevant – with the exception of the domains fatigue (Schwarz and Hinz women: 18.9, men: 11.0), insomnia (women: 18.7, men: 13.3) and pain (women: 18.6, men: 13.5). The high level of mental diseases in our cohort corresponds well to the higher levels of fatigue, insomnia and pain in our study participants – symptoms for which co-occurrence has been shown and which were also shown to be associated with mental disorders [16,23,24]. Although the aforementioned differences between the older and the new reference data are small, we suggest to use the latest normative data as they reflect the current situation in Germany better than the data gathered in the end of the 1990s [15]. For instance, the proportion of unemployed persons in Germany today is about 6.6% with 10.3% in Eastern Germany, 5.8% in Western Germany and 6.8% in Schleswig-Holstein [25]. The proportion of persons having less than 60% of the median German equivalent income (“at-risk-of-poverty”) differed by 7% in 1990 and by 6.4% today (Germany today: 14.4%, Eastern Germany: 19.5%, Western Germany: 13.1%, Schleswig-Holstein: 13.1%) [26]. Life expectancy and morbidity pattern approximated for Eastern and Western Germany. However, data for Schleswig-Holstein (mean values, proportions) are in most cases very much alike the data for total Germany [14,15]. Therefore, we recommend the utilization of our data as normative data e.g. in the context of health care research, clinical studies or certification processes of cancer centers. Files for age adjustment of our normative data can be found in the supporting information section (see supplementary e-files; Table S1 and Table S2).

Our survey has some strengths and limitations. As discussed earlier we experienced a quite high response rate – given the recruiting method and addressing a randomly drawn sample. A total number of 174 study participants aged 16 to 19 years and 228 participants aged 80 years or older are sufficient to provide reliable estimates for groups often underrepresented in study samples. However, all our study participants were recruited in a 213,000 citizen city located in Northern Germany. Although the participants’ age and sex distribution is comparable to that in total Germany, regional differences regarding QoL scoring within Germany cannot be ruled out with certainty.

Our study participants are representative for the German general population with regard to age, sex and education. Of special interest is the high proportion of participants reporting depression which is also mirrored by high fatigue, pain and insomnia scores. The up-to-date normative data provided should be used as comparison health-related QoL data when evaluating the QoL in German cancer patients.