The basis for sickness absence is reduced work capacity due to illness. From being completely healthy and able to work the individual is affected by any form of sickness leading to loss of work capacity, which can be acute (e.g. stomach flu), episodic (e.g. migraine) or chronic (e.g. onset of diabetes). The individual must then decide how he or she will act in relation to the illness or loss of work capacity. Sickness absence (SA) is not the only option in this situation; as people can sometimes also choose sickness presence, i.e. – going to work despite feeling unhealthy. Sickness absence and sickness presence (SP) may be said to be mutually exclusive courses of action in case of sickness entailing loss of work capacity.

Two perspectives of SP are predominant in the literature and research [1]. The North American perspective is focused on productivity loss at work related to illness [2], while the Scandinavian and European literature defines SP as attending work despite illness which would have motivated sickness absence, i.e. a person goes to work despite the feeling that he/she should have stayed at home because of his/her subjectively poor health condition [3], [4]. This study is based on latter definition.

Ill health appears not unexpected as the strongest determinant of SP [5]. In cross-sectional studies there is a strong correlation between SP and various health problems. For example, a higher proportion of people with back and neck pain as well as extreme fatigue can be found in groups with high SP [6]. Cross-sectional studies have shown associations between both individual and work-related conditions and frequency of SP as income [6], sick pay [7], job insecurity [8], ease of replaceability [5], [9], sick leave policy [10], presenteeism cultures [11], [12], [13], adjustment latitudes [14], downsizing [15], stress and high job demands [16], [17] and low social support [16].

To answer the question if SP is a risk factor for future illness and sick leave longitudinal studies are needed and some such studies have been made in recent years - mostly in Europe. There are at least six such studies.

As regards the risk of future ill health self-rated health (SRH) is often used as the main outcome measures but a number of more specific outcomes that vary between studies have also been used. One Swedish study found that SP at baseline was an independent risk factor for poorer health both at 18 months and at 36 months follow-up, even when a number of potential confounders at baseline were controlled for [18]. The result was the same in the two different materials: female-dominated work in the public sector and male-dominated employment in the private sector, suggesting that the results had relatively high validity. Similar results emerged from another Swedish prospective cohort study of working people between 25 and 50 years [19]. The most obvious negative effect of SP was related to later physical complaints and to work ability, but a dose-response effect was found for a number of other more specific problems. A longitudinal three wave study from Netherland showed that high demands with subsequent SP was a risk behavior for burn-out [19].

As regards the risk that SP may increase the risk for future SA there are a few studies. A Swedish study showed that high SP (more than 5 times) during the previous year was a risk factor for future SA (more than 30 days) after two and three years also after controlling for a number of health-related lifestyle, demographic and work-related variables at baseline [18]. In a large Danish study based on a random sample (n  = 12,000), researchers found that people who had gone to work more than 6 times when they were ill the year before baseline had a 74 percent higher risk of SA longer than 2 months after controlling for confounders and health at baseline [20].

Conclusions on SP and ill health have also been drawn from other types of studies. In a study of the well-known Whitehall cohort [21], two groups of employees with poor health due to heart disease were compared. In one group, the participants had continued to work as usual (the SP group) while people in the second group had a SA period after the disease. In follow-up analysis after three years, with control for known risk factors for cardiovascular disease the researcher found that the risk of heart attacks had doubled in the SP group compared with the second group who had had low or moderate SA. In a prospective study of SP and cardiovascular disease in the same cohort, however, the authors found no evidence for SP acting as trigger [22].

The cited studies have generated hypotheses about the mechanism connecting SP and illness and diseases. Stress and hard physical work during illness could thus possibly trigger a more serious medical event, such as myocardial infarction [21], [23], [24], although the relevance of triggering for non-manual work has been challenged [22]. A second possibility is that lack of necessary rest and recuperation could prolong the course of some diseases, and possibly lead to increased risk of sequelae. Furthermore, working while ill might contribute to cumulative psychological burden with long-term pathophysiological consequences for the development of disease, consistent with allostatic load hypothesis [25]. An additional hypothesis is that SP, instead of being causal agent, is a marker of a lifestyle in which symptoms are ignored and medical care is not sought when needed [26].

Research on presenteeism and SP has recently been reviewed by Johns (2010) [27]and earlier by Schultz & Edington (2007) [2]. The research field has grown rapidly during the last decade and forms a new research area in its own, but it also has high relevance for the understanding and interpretation of SA research. The purpose of his study was to investigate whether SP can predict suboptimal SRH and self-reported SA two years later and to identify which aspects of health are most prone to be influenced by SP.

The correlations between self-reported health, sickness presenteeism and sickness absence are shown in Table 1. The distribution of all independent and adjustment variables is shown in Table 2. There was a slightly higher proportion of women (56.1%), the mean age was 49 years (SD 10.3). In 2008, more than one third (35.7%) of the participants reported no SP at all during the past 12 month, while about half (51.3%) reported 1–7 days of SP. About 66% of the sample reported suboptimal sleep quality and one third of them had often had musculoskeletal pain after work. Further, in 2008, 18.2% reported suboptimal general health and in total 55% had been sickness absent (36.2% in 1 to 7 days and 18.8% >7 days). In 2010, the prevalence of self-reported suboptimal health was 20.5% and 18.7% had been absent from work more than 7 days during the last 12 months. Odds ratio of suboptimal self-rated health in 2010 was substantially increased for those who had reported more than 7 days of SP in 2008 compared to those reporting no SP (OR = 5.96; 95% CI 4.98 to 7.12) after adjustment for age, sex, and income, and OR = 1.46 (95% CI 1.15 to 1.86) in the fully adjusted model (Table 4, left). SP of 1–7 days was associated with an increased risk of suboptimal self-rated health with OR = 1.96 (95% CI 1.69 to 2.26) after adjustment for age, sex, and income and OR = 1.26 (95% CI 1.06–1.49) after adjustment for all covariates. Adjustment for self-rated health in 2008 attenuated the odds of suboptimal self-rated health in the high SP group to the largest extent with 65% (OR = 4.79; 95% CI 4.06 to 5.67) followed by sleep quality, musculoskeletal pain, life satisfaction, and physical as well as psychological work capacity. On the other hand covariates as age, education, income and smoking became non-significant after adjustments in the final model.

Another pattern was observed regarding SA. The risk of more than 7 days of SA during the last 12 months reported in 2010 was substantially increased for those who had reported 7 days or more of SP in 2008 (OR = 3.57 95% CI 2.95 to 4.33) after adjustment for age, sex, and income, and OR = 1.46 (95% CI 1.15–1.86) in the fully adjusted model (Table 4, right). However, the excess risk for those who had reported less than 7 days of SP (OR = 1.44, 95% CI 1.23 to 1.68) disappeared after full adjustment for the included confounders. The confounders which most attenuated the risk estimates for SA in 2010 were SA in 2008 followed by SRH in 2008.

Table 5 reports how adjustment for different health indicators from 2010 influenced the risk estimates for SRH and SA. Inclusion of self-rated physical and psychological work capacity did not attenuate the associations, whereas emotional exhaustion attenuated the ORs to non-significance for both outcomes.

The main results of this study were that sickness presenteeism (SP), i.e. attending work despite illness that the respondent believes (s)he should have stayed home for, predicts suboptimal SRH and sickness absence (SA) two years later, even after adjustment for multiple possible confounders at baseline. These associations seem largely to be mediated by an increased risk of emotional exhaustion at follow-up (2010) among those who had attended work despite illness. In addition, sex, low income, musculoskeletal pain, poor sleep quality, self-rated physical work capacity, suboptimal SRH, life dissatisfaction and overweight/obesity measured at baseline were significantly and independently related to suboptimal SRH and SA after two years. In accordance with previous studies in Sweden, SP predicted both future poor self-rated health [18] and SA [32], [33].

Our results are in agreement with a study which showed that physical health complaints and/or diseases have an impact on general SRH and SA. Associations between ill health and SA, and between socioeconomic status and SA, were found in the Whitehall II study which includes both men and women from 20 civil service departments in London. Furthermore, baseline health strongly predicted rates of long–term sickness absence [34]. Aronsson found that among those with high SP there was significantly higher number of persons with upper back/neck pain, fatigue, slightly depressed mood, and the levels of SA was higher among those with high SP [6]. Although we investigated the relationship between SP and ill health and SA, we found almost the same pattern in our study. Inclusion of poor health at baseline (in 2008) attenuated the odds for reporting poor health two years later with as much as 45% and 65% among those who had reported high SP. Further, SA at baseline explained 52% and 59%, respectively, of the excess risk for future SA.

Approximately 64% of the participants in the current study reported SP over a 12-month period, 51% of them for 1–7 days. It has been shown previously that educational level is another factor associated with SP [35]. Contrary to this register study, in our study the prevalence of reporting SP was higher among individuals with intermediate education than the proportion of SP in low and high educated respondents. On the other hand, education was a significant confounder when age, sex, and income were taken into account in the logistic regression model: highly educated subjects had 7% lower ORs for reporting SP than those with lower education. This significance disappeared when other confounders were including into further models. However, the total of the 64% of SP reported in our study is similar to the results in a Danish sample of 12,835 employees which showed that more than 70% reported SP at least once during a 12-month period. The same study indicated that work-related factors were slightly more predictive of SP than conservative attitudes to absence or personal circumstances [20]. We lacked assessments of personal circumstances and attitudes in the current study; however, we included several health-related factors. Some studies have previously shown that SP is correlated with sickness absence and illness [5], [9], [36]. Gustafsson and Marklund suggest that both SP and SA are strong predictors of future poor health and that SP appeared to lead to SA, whereas SA did not have any effect on future SP [19]. According to a recent a study based on the SLOSH cohort, there was a strong cross-sectional association between SA and SP even after a large number of adjustments for indicators of health and work environment, indicating that SP may be more than a behavioral alternative to SA [37]. Possible explanations for this association include an individual tendency to regard absence as an appropriate response also to minor diseases, which could be an alternative explanation for the prospective association found in the present study. We considered that SP might additionally predict SRH and SA in employed respondents. When individuals feel too ill to work, they can sometimes choose either SA or SP. In the present study we observed that SP predicts SA and suboptimal SRH two years later, also after adjustment for a large number of factors, which may suggest causality. This is in agreement with two previously published Swedish follow-up studies [18], [32]. A number of studies, however, have concluded that SA may not be the best alternative for individual health: while in some cases it may be restorative, in other it can lead to social isolation and poor personal finances [38], [39].