Rheumatoid arthritis (RA) is thought to develop through “multiple hits”,[1] with genetic and environmental risk factors,[2] followed by antibodies such as rheumatoid factor (RF) and anti-citrullinated protein antibodies (ACPA),[3–5] that accumulate during an “at-risk” pre-clinical phase. This pre-clinical phase lasts 3–5 years before culminating in clinical disease and can be described in five phases.[6–9] Asymptomatic phases (A-C) depend on whether individuals have genetic (Phase A) or environmental (Phase B) risk factors, or systemic autoimmunity associated with RA (Phase C). In Phase D, people first develop symptoms such as joint pain but do not have clinical arthritis. In Phase E individuals are described as having unclassified arthritis and in Phase F, RA. Increasingly, it is thought these pre-clinical phases offer a window of opportunity for potential preventive treatment.[10]

Several randomized controlled trials (RCTs) are currently exploring early intervention with traditional and biologic disease-modifying anti-rheumatic drugs (DMARDs) to prevent RA in people at increased risk for developing the disease (i.e., Phase C[11,12]) and transition from arthralgias to RA (i.e. Phase D[13–16]). This ongoing research in pre-clinical RA assumes that asymptomatic people, predicted to be at high-risk of RA (i.e. Phase C), would be willing to accept the risks and inconvenience of a treatment trying to prevent a disease that they may not subsequently develop. To date, only one small study has elicited preferences of people at-risk of developing RA for hypothetical preventive treatments, finding that preventive treatment would have to offer a high reduction in the risk of developing RA with low-risk of serious side effects.[17] Though informative, the small sample size limits the number of features that can be included, limiting the ability to predict uptake of individual treatments or explore subgroups with different preferences. Further studies with larger sample sizes, in different countries, are still needed to explore preferences and heterogeneity of prefrences of at-risk individuals for preventive treatment, and how these may affect uptake.

As uptake of treatment is critical for the success of preventive treatment, the aim of this study was to (1) understand preferences and trade-offs of asymptomatic, at-risk populations for features of preventive treatments, and (2) predict uptake of preventive treatments currently under study.

A web-based discrete choice experiment (DCE) survey was administered to a sample of self-reported first-degree relatives (FDRs) of RA patients from the USA. FDRs represent individuals at an elevated risk of RA.[18,19] DCEs, developed in market research, assume any product, including health care interventions, can be described by characteristics (attributes) and that value of products depends on the levels of these characteristics.[20] An RA-related treatment attribute might be how treatment is taken, and levels could be oral, injection or infusion.[21] DCEs are useful where products or services do not exist (i.e. before launch). DCEs are underpinned by random utility theory. When choosing between options, individuals are assumed to assign a perceived utility (or attractiveness) to each alternative which depends on characteristics of both the alternative and the individual, and choose the one with the highest perceived utility. Random utility theory acknowledges that the utility people assign to an alternative cannot be measured (and must be treated as a random variable) meaning it is not possible to predict with certainty which alternative people will choose. Instead, random utility theory attempts to predict the probability that alternative A will be preferred to alternative B, and that this choice is proportional to the degree to which alternative A is valued more (has a higher utility) than alternative B.[22]

FDRs were recruited through Amazon’s Mechanical Turk (MTurk) platform. FDR status was determined in two-stages. Respondents self-reported whether they or an FDR (i.e. parent, sibling, adult child) had one or more of a list of chronic conditions lincluding RA. The list included clinical lycanthropy, an extremely rare condition, to screen out individuals who reported all conditions. Those who did not report RA but had an FDR with RA were invited to take the full survey. The survey included a series of questions about whether their FDR had physician-confirmed RA, and was/is taking a drug to treat RA (e.g. methotrexate or a biologic drug); those indicating yes to both questions were invited to take the survey. Each respondent received approximately $2 for completing the survey. As with a previous DCE of similar length, we excluded those who completed the entire survey in less than three minutes.[21] Ethical approval was granted by the University of British Columbia behavioural ethics board (H15-01948).

Of 525 initial respondents, 288 (55%) had an FDR with physician-confirmed RA currently taking a drug for RA, meeting our inclusion criteria as FDRs. No participants were excluded for completing the survey within 3 minutes (minimum time-to-complete 3.28 minutes; mean 9.11 (SD 8.29)) and none always chose Treatment A or treatment B. The ‘no treatment for now’ option was chosen 33% of the time (for 856 of the total 2592 choices made), and 10% of participants (n = 29) always chose no treatment. The sample was primarily female (60%), aged 18–39 years (66%), and most reported European (84%) ancestry (Table 3). A minority (12%) reported no medical insurance; those with private insurance mainly had employer plans (51%), 22% had Medicare/Medicaid coverage. Most (91%) indicated that they would be willing to pay out of pocket for preventive treatment for RA.

Results of this study suggest asymptomatic, at-risk individuals, may be willing to take preventative treatment to reduce their risk of RA, although they have different appetites for risk, reassurance, and convenience of treatments. Importantly, our findings suggest preventive treatments preferred by at-risk individuals will not necessarily be those offering the largest reduction in risk of RA; uptake is likely to be driven as much by how treatment is taken, opinions/preferences of health care professionals, and the risk and reversibility of side effects. Assuming that treatments currently being evaluated in RCTs all offer preventive efficacy, we predict highest uptake of convenient treatments offering low-to-moderate reductions in risk of developing RA and low risks of serious side-effects. This suggests that non-biologic DMARDs like hydroxychloroquine and potentially methotrexate are more likely to be acceptable preventive options than the biologic DMARDs being tested.

We predict higher uptake of preventive treatment (86%) than the only comparable previous estimate (38%), which was based on a baseline risk of RA of 40%.[17] This previous study did predict that uptake would increase as baseline risk increased (7% at 1 in 100 risk; 38% at 40 in 100 risk). Our higher baseline risk (60 in 100 over 5 years) of developing RA[4,32] could explain our higher predicted uptake. This baseline risk was based on 5-year estimates of the risk of developing RA in individuals with a family history of RA and the presence of autoantibodies which ranged from 58% to 69%.[4,32] These estimates correspond well with the context and time frame of the “at-risk” pre-clinical phase C, where people have evidence of systemic autoimmunity associated with RA but no arthralgia, that we sought to represent. Further research is needed to understand the relationship between baseline risk and uptake of preventive treatment. Our higher uptake could also relate to our dual-response question format. However, our prediction that 86% of participants would consider hydroxychloroquine is consistent with previous conclusions that people would ‘take moderately effective treatment if the risk of a serious adverse event was very low.’[17]

Our findings have two potentially major implications. One is greater patient/stakeholder involvement in choices of treatments to study in RCTs and the magnitude of benefit required on primary endpoints. All current RCTs of preventive treatment have reduction in the number of people developing RA as their primary endpoint. Given that safety, convenience and concordance with health care professional opinions may be more important, and people are willing to trade between attributes, a greater effect size on the primary endpoint may be needed to compensate for less convenient and/or safe treatments. Conversely, relatively safe and/or convenient treatments might only need to show relatively small reductions in risk of developing RA to be acceptable. Having information on treatment preferences prior to study design stage could help to ensure that RCTs are powered to demonstrate effect sizes important to potential recipients. More patient-oriented trials could test treatments or magnitudes of benefit fulfilling these criteria, and treatments unlikely to meet patient preferences can be identified earlier.[42] Our findings suggest the hydroxychloroquine is the preferred treatment from the consumer perspective, as well as potential for methotrexate to be explored as an earlier option (based on our assumption would reduce risk of developing RA more than hydroxychloroquine). Whilst we do not know whether these options will be less effective in reducing the risk of RA than biologic DMARDs, their relative safety and convenience may be more important for RA-free people who do not want to take excessive risks or would prefer to try safer pharmacological alongside other approaches to reduce their risk of developing RA such as changing their diet or stopping smoking. Our results provide little support for biologic-drugs as preventive options; despite assuming biologics would offer the greatest risk reduction (reducing risk of RA from 60 to 24 in 100), we predict very low uptake of abatacept and rituximab (≤6%).

The second implication highlights the critical role of health care professionals in preventive treatment decisions. The health care professional’s opinion was among the most important attributes influencing preventive treatment decisions. To help people choose options that best reflect their preferences, we need to recognize trade-offs, value and relative importance that people place on features of treatments.[43] Decision support interventions could help health care professionals to elicit preferences of at-risk people and help them choose treatments consistent with those preferences.

Our study has a number of limitations. First, attributes and levels included in the survey influence preferences estimated from responses; including different attributes and levels would likely generate different results. However, the survey was developed in line with best-practice recommendations using focus groups of patients, their FDRs and rheumatologists[23] to identify relevant attributes and ensure that information was clear and easy to understand.[25] Further, selected attribute levels reflected treatments currently being studied. Secondly, out-of-pocket costs could influence preferences for preventive treatment, but was omitted. Cost, however, ranked last when we asked patients and FDR groups to prioritize potential attributes, and is also problematic to include as there is significant variation in the costs associated with medications according to whether someone has insurance coverage or not, and what is covered by insurance.[23] Thirdly, using MTurk limits our ability to determine whether respondents genuinely were FDRs of people with RA. The general public are known to confuse symptoms and diagnosis of RA with those of osteoarthritis. Our sample was also more likely younger and internet savvy; two-thirds were aged 18–39 years. However, we used a series of strict study entry criteria and, even after a pre-qualification survey, excluded 45% of our sample that we could not confidently classify as FDRs. Future, comparable, research with verifiable FDRs of RA patients with a confirmed diagnosis would be valuable. MTurk samples also have evidence of their validity[44,45], representativeness[46] and accurate/less biased responses.[47,48] Finally, as with any DCE, we cannot be sure that participants understood the tasks, made choices consistent with underlying theory, or that their responses reflected true preferences because test and treatment scenarios are hypothetical and we do not know their risk of disease (FDR status is a proxy for risk). The disconnect between stated (hypothetical) and revealed (actual) preferences (hypothetical bias) threatens the external validity of DCEs[49], but a recent systematic review and meta-analysis of DCEs concluded that DCEs generate reasonable predictions of health-related behaviors, particularly when predicting how someone will behave (e.g. take preventive treatment).[50] The review did caution that imperfect predictions from DCEs may lead to overestimates of demand for treatments, which supports our caution that our predictions of uptake could be overestimates.

Strengths of this study are that it is the first large sample of self-reported FDRs of people with RA, (most accurately described as Phase A (genetic risk factors for RA) as their autoimmunity status is unknown) to describe trade-offs between features of preventive treatments. However, preferences of this sample may not generalize to RA-naïve populations who have not observed the effects of RA on family member(s). A further strength is our design that allows us to predict uptake not only of preventive treatments currently under study, but other treatment options that may be available in future. Uptake estimates provide important parameters in future economic evaluations of the cost-effectiveness of preventive treatments, once results of ongoing trials are published. Future research to contrast predicted and actual uptake of preventive treatment in at-risk individuals will be valuable.

We provide preliminary predictions of uptake of preventive treatments for RA in currently RCTs. Our findings suggest people may take preventive treatment, but reduction in the risk of developing RA is one of multiple factors influence their preferences. Furthermore subgroups exist that prioritize safety, reassurance, and convenience. Decisions to take preventive treatment are complex. Only treatments that balance these preferences will be acceptable to at-risk populations, and as preferences are not predicted by socio-demographic characteristics they may need to be elicited on an individual basis. Preferences of potential recipients should also be considered when designing RCTs to prioritize studies of interventions likely to taken by potential recipients if they meet their primary endpoint.