Headache disorders are very common, often disabling, costly and associated with overuse of analgesics [1], [2], [3], [4]. Neck pain and its associated disorders also cause a significant health burden in the general population and are experienced by people of all ages [5], [6], [7]. Noninvasive physical management is often prescribed for headache and neck pain. Systematic reviews, however, indicate that the evidence of its efficacy is limited, as most studies have small sample sizes and short follow-ups [8], [9], 10,11,12. A further problem is that attention is usually concentrated on either headache or neck pain, overlooking the fact that they are frequently associated [13], [14].

For some time, we have applied a simple educational and physical program to decrease muscle tension in the head and neck/shoulder area. In our clinical experience, this approach has reduced the frequency and intensity of headache and neck/shoulder pain and the amount of drug intake in a considerable number of patients. In a controlled, non-randomized trial to evaluate the effectiveness of this program administered to a large cohort of public servants, we found that 6 months following treatment, the monthly frequency of headache and neck/shoulder pain was reduced by about 40% in the intervention group (IG) compared to controls [15]. These results were stable at a 12-month follow-up [16].

We have now performed a cluster-randomized controlled trial to evaluate the effectiveness of our program in a much larger cohort of public servants after 6 and 12 months of follow-up. As our program included exercises and visual feedback measures in the workplace, individual randomization was not feasible due to the high level of interference and contamination between subjects working in the same environment. In this paper, we report the results in terms of the primary objective of the study, i.e., to evaluate the effectiveness of the program in reducing the frequency of head and neck/shoulder pain after 6 months.

The protocol for this cluster-randomized trial and supporting CONSORT checklist are available as supporting information; see Checklist S1 and Protocol S1.

Figure 1 shows the trial profile. Out of 11,780 eligible workers in 444 departments, 2895 (25%) within 271 departments gave informed consent for participation. However, 534 (37%) workers randomized to IG and 448 (31%) workers randomized to the control group did not complete the baseline diary for month 1. Using information collected in the informed consent form, the group of workers who did not fill out the baseline diary showed a higher prevalence among males (18% vs. 14%) and an higher prevalence among people with a low education level (23% vs. 15%) with respect to workers who filled out the baseline diary. Thus, it was possible to collect the baseline diaries on the remaining 1913 workers within 236 departments (119 departments and 923 workers in the IG, 117 departments and 990 workers in the control group). Overall, the proportion of subjects who filled out the diary directly via the web site was comparable between the two groups (67.7% of IG and 69.8% of controls). At month 7 of the study, six months after randomization, 32 workers (14 IG, 18 control group) did not fill out the follow-up diary. Table 1 summarizes the department and worker characteristics of the analyzed population (909 in the IG, 972 in the control group). The median numbers of workers per department were four and five, respectively, in the intervention and the control group. Although the randomization procedure was cluster-based, the groups were quite similar on demographic and baseline characteristics. The analyzed population was predominantly female, with a median age of 47 years at enrollment. Almost two-thirds of workers were diagnosed as having TTH, and M was diagnosed in 1099 workers (58%); overall, 1471 (78%) workers received a diagnosis of MP.

The headache responder rate was significantly higher in the IG (RR = 1.58, 95% CI 1.28 to 1.92) (Table 2). The ICC for the headache responder rate was 0.039 (95% CI 0.012 to 0.120). Additionally, the probability of achieving a ≥50% decrease of neck/shoulder pain days among symptomatic subjects was greater in the IG (RR = 1.53, 95% CI 1.27 to 1.82). The ICC for the neck/shoulder pain responder rate was 0.029 (95% CI 0.007 to 0.110). When considering the combined outcome (headache and/or neck/shoulder pain) the responder rate was significantly higher in the IG (RR = 1.82, 95% CI 1.52 to 2.15). The ICC for the headache and/or neck/shoulder pain responder rate was 0.044 (95% CI 0.016 to 0.112). An effect was found also in the reduction of drug consumption in the IG (RR = 1.45, 95% CI 1.05 to 1.97). The ICC for the drug consumption responder rate was 0.081 (95% CI 0.030 to 0.199).

A graphic description of the variations in symptom frequencies is reported in the appendix S2. The frequency of the outcomes in the analyzed population, as well as the mean differences for each group and their absolute between-group differences, both crude and adjusted, are summarized in Table 3. For all these end-points associated with headache and neck/shoulder pain, the IG subjects achieved meaningful and statistically significant improvements by the end of the follow-up compared to controls. Mean intervention effects (days per month, 95% CI) when comparing the change from baseline at month 7 were headache frequency −1.72 (−2.40 to −1.04) and frequency of neck/shoulder pain −2.51 (−3.56 to −1.47). Moreover, the headache or neck/shoulder pain index significantly decreased in the IG. For drug consumption, the reduction of frequency in the IG was statistically significant considering the overall group of workers, but not among workers with ≥4 days/month of drug consumption. Similar results were obtained using the Huber/White/Sandwich estimator to account for clustering: headache frequency −1.78 (95% CI, −2.45 to −1.11); frequency of neck/shoulder pain −2.82 (95% CI, −3.82 to −1.82); frequency of headache and/or neck/shoulder pain −3.00 (95% CI, −3.97 to −2.04) frequency of analgesic drugs consumption −0.42 (95% CI, −0.88 to 0.04).

Figure 2 reports the effects of treatment on the frequency of headache, neck/shoulder pain and the combined outcome (headache and/or neck/shoulder pain) by subgroups. Reduction of headache frequency seemed to be more evident in workers with a diagnosis of M and/or TTH associated with MP. For neck/shoulder pain a higher reduction of frequency was found in workers with a diagnosis of MP not associated with headache.

The self-reported compliance in the IG group was: 23% low (if exercises were performed fewer than once a week), 54% medium (if exercises were performed once or twice a week), 22% high (if they were performed three or more days a week [19%] or exactly as indicated [3%]).

In the IG, the reduction of the monthly frequency of days with pain was greater among workers with a medium or high level of compliance compared with those with a lower compliance. For headache pain, mean change of frequency from baseline was −1.33 (−2.26 to −0.39) for low compliance, −2.59 (−3.21 to −1.98) for medium compliance, and −3.31 (−4.25 to −2.36) for high compliance. For neck/shoulder pain, mean change of frequency from baseline was −0.95 (−2.40 to 0.50) for low compliance, −3.46 (−4.43 to −2.49) for medium compliance, −4.67 (−6.14 to −3.20) for high compliance. Adjusted mean differences when comparing high vs. low compliance were headache frequency −1.68 (−2.77 to −0.59) and frequency of neck/shoulder pain −3.52 (−5.20 to −1.83). Adjusted mean differences when comparing medium vs. low compliance were headache frequency −0.92 (−1.84 to 0.00) and frequency of neck/shoulder pain −2.18 (−3.60 to −0.77).

For all outcomes analyzed, there were no substantial differences between crude and adjusted estimates of intervention effects (Tables 2 and 3).

The sensitivity analyses performed on the whole randomized population demonstrate that the efficacy of the intervention on headache and neck/shoulder pain persists also in the worst scenario (Table 4).

In this cluster-randomized controlled trial, we have demonstrated the effectiveness of our educational and physical program in reducing headache and neck/shoulder pain in a large working community. Among these workers, the proportion of those with at least 4 days/month with pain achieving a ≥50% reduction of days with headache (main outcome of the study) or neck/shoulder pain was increased by at least 1.5 times in the IG compared to controls. Overall, the benefit of the intervention was consistent for all examined end-points associated with headache and neck/shoulder pain, although it was slightly less pronounced for the reduction of drug consumption. An absolute mean reduction of about 2 days/month of pain was observed in the IG subjects compared to controls. The benefit of the intervention was significantly related to the level of compliance.

Previous studies have assessed the efficacy of noninvasive physical management in reducing the frequencies of different types of headache and neck pain, with conflicting results [8], [9], [10], [11], [12], [25], [26], [27], [28], [29], [30]. In a Cochrane systematic review of trials aimed at quantifying the effects of non-invasive physical treatments for chronic/recurrent headaches, Bronfort et al. [9] found 10 good-quality trials, but they could not pool the results because of the high heterogeneity between the studies. The number of patients included in the trials ranged from 12 to 218, and in only three trials was the follow-up longer than 3 months. In a recent Cochrane systematic review to assess whether patient education strategies benefit adults with neck pain, Haines et al. examined 10 selected trials and concluded that no effectiveness for educational interventions for neck pain had been shown [30]. The authors emphasized that in future research, further attention to methodological quality is necessary.

Our study has several strengths. We used a pragmatic approach, with a much larger sample size and a longer follow-up than in most previous studies, and assessed clinically relevant outcomes [9], [30], [31]. Moreover, in our study, head and neck/shoulder pain were investigated jointly. A further strength of the study is the assessment of an association between the level of compliance and the magnitude of the intervention effect.

In this trial the outcomes were not evaluable for about one-third of the randomized workers who did not fill out the baseline (and end of the follow up) diary, even though they initially gave consent to participation. This major limitation was addressed with sensitivity analyses, applying two hypothetical scenarios. Even in the worst (and very unlikely) scenario, a significant, albeit reduced, benefit of the intervention on headache and neck/shoulder pain was evident; this indicates that possible attrition bias, if present, cannot explain the observed results. Another weakness of our study is that neither the subjects nor the researchers were blinded to the group allocation. However, in physical and behavioral exercise studies, double-blinding is impossible for most interventions, and effective single-blinding is also difficult to achieve in most cases [31].

The prevalence of subjects suffering from frequent pain episodes at the baseline suggests a selective participation in the trial, since subjects with more frequent episodes might have been more interested in participating than those with no or occasional pain.

Although we are not able to definitively confirm that information was recorded on a daily basis by all subjects, we think that a retrospective compilation of the diaries was unlikely because of the monitoring of the compliance by the staff and some participants. Furthermore, the method of filling out the diaries (web or paper) did not differ between intervention and control groups. Finally, even in case of a possible retrospective compilation of the diaries by a subgroup of subjects, available evidence from previous validation studies confirm a high degree of accuracy of the patient recall of headache frequency [32], [33], [34].

As previously observed [15], the improvement in the pain frequency in the control group during the study period, i.e., from October to April, could have been related to seasonal variations and to the subjects' expectations, which were reinforced by keeping a diary. Indeed, the workers of the control group were informed that they would start the program subsequently (at month 8).

Some explanations of the positive effects of the program may be suggested. In our study, management consisted of a simple, self-administered educational and exercise program performed alone at the workplace and at home. Indeed, the daily time required to perform the program is limited, and easily compatible with most occupations. Although simple, our program, in contrast to the majority of those applied in other studies, may have a positive interaction between educational and exercise components. The educational aspects consist in a clear discussion of the major aspects of the problem; in periodical instruction reinforcement, including reinforcement by the more motivated subjects of the working community; and in the application of visual feedback at the workplace and at home. These aspects probably explain also the lower rate of drop-outs compared to other trials. We found that medium-high compliance was accompanied by a greater effect; however, some efficacy was observed also in those whose compliance was low. This could be explained by the fact that the educational aspects of the program were the same for all the participants. Most subjects with a low level of compliance may have acquired the ability to maintain their craniocervical muscles at a lower contraction level during the day. Beneficial effects may have resulted partly from mechanisms involving expectation and conscious anticipation [35].

The results obtained in this study may be of high clinical relevance. Our study shows that a low-cost, low-intensity educational and physical program is effective in reducing head and neck/shoulder pain and possibly analgesic drug consumption in large working populations. This approach seems easily transferable to primary care settings. Further trials are needed to investigate if this program is also effective in a clinical setting, for highly selected patients suffering from specific headache types.