Many cancer patients express interest in acupuncture for nausea [1]-[2] but it is not known if acupuncture is more effective for emesis (nausea and vomiting) than standard care during radiotherapy. Approximately 60% of patients irradiated over abdominal and/or pelvic fields experienced emesis during radiotherapy [1], [3]–[4]. Antiemetics are effective, especially serotonin-receptor antagonists combined with corticosteroids [5]. However, some patients at risk for nausea do not receive potent antiemetics, do not respond satisfactorily [1], [3], [5], or experience side-effects [5]. In a previous study we found that of 145 nauseous patients irradiated over a variety of regions, one third asked for more treatment against nausea while 40% rejected antiemetics [1].

Between two and 31% of patients undergoing cancer treatment use acupuncture for various kinds of symptoms [2]. In chemotherapy-induced nausea, acupuncture and acupressure reduced nausea more than antiemetics, but those studies did not include any sham treated control groups [6]–[11]. In a study of 80 chemotherapy patients, penetrating acupuncture did not reduce nausea more than telescopic non-penetrating sham needles [12]. In our study of radiotherapy-induced nausea, 70% of patients randomized to penetrating acupuncture and 62% of patients treated with telescopic sham needles experienced nausea during the radiotherapy period [13]. Apparently there was a lack of effects that could be related to the specific characteristics of verum (genuine) acupuncture; i.e. stimulation of skin penetrating needles in traditional acupuncture points resulting in a “deqi” sensation. However, as many as 95% of patients in both groups considered the treatment to be effective, and 89% were interested in receiving the treatments in the future [13]. In the light of the apparent conflict between lack of specific effects from verum acupuncture and large subjectively experienced positive effects it seems interesting to evaluate if acupuncture has antiemetic effects related to nonspecific mechanisms.

The aims of the study were to compare nausea and vomiting experienced by a cohort treated with verum or sham acupuncture with that experienced by a cohort receiving standard care during radiotherapy, and to evaluate if expectations of nausea and of acupuncture effects were related to the actual occurrence of nausea.

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

We found lower occurrence of nausea and vomiting in patients treated with penetrating “deqi”-creating acupuncture or sham acupuncture compared to patients who had received standard care. Almost all patients in the acupuncture cohort highly expected antiemetic effects from the treatment. Patients who expected nausea had increased risk for nausea compared to patients who expected low risk for nausea.

There are many, not sham-controlled studies, reporting emesis-reducing effects of acupuncture compared to standard care in chemotherapy-induced nausea [14]. Our results indicate that nonspecific factors such as the extra care or the high expectations of positive treatment effects, not the specific characteristics of verum acupuncture, reduced emesis. Alternatively, the findings could result from flaws in our non-randomized design. Since the patients were not randomized to standard care, we investigated if an imbalance of confounding factors possibly contributing to emesis may have explained the higher prevalence of emesis in the standard care group, according to the hierarchical step model [18]. The higher risk for nausea in the standard care cohort was valid also after adjusting for possible confounding factors for emesis and after omitting patients taking serotonin-receptor antagonists and corticosteroids, indicating that our findings are valid. We have not identified any previous study of the effect of verum or sham acupuncture compared to standard care on radiotherapy-induced emesis (Pubmed, http://www.ncbi.nlm.nih.gov/ pubmed/accessed 10/11/10, using the combined search terms acupuncture, radiotherapy, nausea and vomiting). A Cochrane review of acupuncture for chemotherapy-induced nausea included eleven studies [14]. Only two sham-controlled studies were reported, one positive (n = 104) [19] and one negative (n = 80) [12], except for a pilot study including only 10 patients [20]. As concerns conditions in general, there exist positive sham controlled studies, but there are also indications that the effect of acupuncture may not be related to the specific characters of verum acupuncture. In line with our results, Haake and co-workers [21] found substantial improvement of back pain in 48% of 387 patients treated by verum acupuncture, in 44% of 387 patients treated with sham and in 27% of 388 patients receiving standard care. In other studies sham acupuncture reduced musculoskeletal arm pain significantly more than verum acupuncture [22].

The verum and the sham group received extra care compared to the standard care group, which may have reduced emesis: patient-therapist communication, the knowledge that continuous contact with one single therapist would continue during the whole radiotherapy period, the tactile stimulation from the therapists' hands, the extra time for rest and relaxation and the extra attention to the patient's symptoms through the daily emesis questions all are important elements of this extra care. The verum and sham performing therapists in our study might have had a supportive attitude. Arving and co-workers [23] found that chemotherapy patients who received supportive conversations reported higher quality of life and less nausea than did patients receiving standard care. Börjeson and co-workers [24] also found that chemotherapy patients who received extra care comprising information and relaxation training increased their well-being compared to patients receiving antiemetics only, despite the fact that the extra-care group received a less optimal antiemetic treatment.

Both verum acupuncture and sham-acupuncture like tactile stimulation have been seen to activate the limbic system [15]; did the low dose of sensory stimulation at the non-acupuncture point reduce emesis? Kaptchuk and co-workers [25] implied that the patient-therapist meeting was more important than the needle stimulation. Of 87 patients who received sham acupuncture from an emphatic committed therapist 62% reported adequate symptom relief of irritable bowel symptoms, compared to 44% of 88 patients receiving sham acupuncture from a non-communicating therapist and 28% of 87 patients on waiting list. The verum and sham treated patients in our study received extra time for rest and relaxation and slightly more body-contact than the standard care patients, which may have reduced distress. Psychological distress has been seen as a predictor for emesis [26] and studies indicate that relaxation [27] as well as body-contact (tactile stimulation, massage) [28] may reduce nausea in cancer patients.

Since almost all patients in the acupuncture cohort expected positive antiemetic effects of the treatment, the positive expectation may be another factor that reduced emesis. Expectations are known to influence intervention outcomes in general [29]. Indeed, Pariente and co-workers [30] found with the use of positron emission tomography (PET) that when individuals were informed that the blunt sham needle they were treated with was ineffective, no activity in the pain modulating areas in the mid-brain was seen. When a credible telescopic sham needle was used that the individuals believed was effective, a large pain-modulating activity was seen. Likewise, Linde and co-workers [31] found that acupuncture and sham treated patients with headache, chronic low back pain or osteoarthritis who had high expectations on pain-reduction reported better effects than patients with low expectations. In our study there were no differences in the occurrence of nausea between the patients who believed in the antiemetic effects of treatment and those who had a lesser belief in the antiemetic effects of treatment. Either expectations about the treatment effect were not important for nausea, or the category scale used was not sufficiently sensitive, thus resulting in a “roof effect”. The patients' trust in the antiemetic effect of verum or sham acupuncture decreased if nausea occurred and increased if nausea did not occur. This finding is in concordance with results from experiments indicating that the placebo response is a short-time effect; for example if a noxious stimulation is performed after taking a placebo pill, the study subject no longer believes in the effect of the placebo pill [29]. In our study, patients who expected nausea apparently had an increased risk for nausea, in concordance with findings regarding chemotherapy-induced nausea [32]. Thus, patients are either capable of judging their own risk for nausea or the negative expectations per se produce nausea. This finding implies that health care professionals might well consider asking the patients about their expectations about experiencing nausea and might consider the information to decide on appropriate antiemetic treatment.

Since nausea was prevalent in the standard care group and nausea may be associated with a reduced quality of life [1], [33] treatment using verum or sham acupuncture may be valuable and cost-effective since positive effects do occur. A crude calculation of the cost for providing the median number of 11 verum or sham sessions lasting 30 minutes each results in a mean cost per patient of $69 USD. Two patients (median) were treated at the same time, meaning that one patient consumed three therapist hours*. In comparison, the approximate costs of the recommended dose [6] of 8 mg of a serotonin-receptor antagonists once per day during the radiotherapy period is $98 USD**.

Emesis was measured using a well-established method [17]. The standard care cohort rated emesis only once, covering the preceding week. Some patients in the standard care cohort may, by forgetfulness, have underreported emesis, compared to the acupuncture cohort, who rated emesis daily. The acupuncture cohort was compared with a reference group, not to a third randomized arm. That design requires for a thorough investigation of potential imbalance of confounding factors between groups, as discussed above, but the design may have the benefit of avoiding the impact of the data collection per se on reported emesis. Repeated measurement of emesis per se may reduce (through the so called Hawthorne effect) or increase emesis experience [34]. Young and co-workers found that emesis questions per se increased self-reported occurrence of nausea [34]. To pay extra attention to emesis through daily data collection, without performing any extra emesis-reducing treatment in this frail patient cohort, was therefore evaluated as being unethical. We presented a cross sectional comparison at the time when the mean radiotherapy dose was the same in the acupuncture and the standard care cohorts. If we instead had observed another week of the radiotherapy period, it would not have changed the conclusions of this study; the weekly proportion of patients experiencing nausea was lower in the acupuncture cohort all radiotherapy weeks (varied 22 to 44% as described previously [13]) compared to the standard care cohort. The patients who were treated by verum or sham experienced close to 50% lower occurrence of emesis compared to the patients receiving standard care. If the extra care caused the emesis reduction, this indicates that as long as the best available antiemetic treatment is offered, patients who believe that acupuncture has beneficial effects may be satisfied with treatment with verum acupuncture or non-penetrating needles, either of which produces a moment of relaxation and attention from the therapist. A next obvious step is to further study what components in the acupuncture procedures are of importance for this dramatically positive but as yet not fully understood effect, in an effort to make possible the use of those components to further increase quality of care.

* A public hospital employing a physiotherapist for three hours spends $68 USD (408 SEK to provide the mean salary value for that service according to Swedish Association of Registered Physiotherapists 2007, www.valuta.se, date 080404). Costs for needles may be approximately $0.72 USD (24 needles consumed during 12 sessions, at six US cents according to prices at www.acuprime.com, date 101109).

** Consuming one tablet at a cost of 16.25 SEK (www.fass.se) during the mean value of 36 radiotherapy days in treatment costs $98 USD (based on cost in Sweden of 850 SEK www.valuta.se, date 101109).