Skin cancer remains one of the most common cancers in the United Kingdom, and melanoma incidence has been rising for decades. Most patients first present to their general practitioner, whose task is to decide which suspicious lesions need urgent referral to a specialist and which can be safely monitored. That judgement is difficult: benign moles vastly outnumber malignant ones, and distinguishing between them by eye is a skill that varies considerably between clinicians. AI tools trained on tens of thousands of dermoscopic images have shown impressive accuracy in research settings, and several systems are now being trialled in NHS practices as decision-support aids that sit alongside, rather than replace, clinical judgement.

Yet technical performance is only part of the story. If patients distrust the technology, or if certain design choices put them off, even the most accurate algorithm will struggle to achieve its potential. This is the gap the new study set out to address. Rather than simply asking people whether they like the idea of AI, the researchers used a discrete choice experiment, an economic method that presents respondents with a series of hypothetical scenarios in which the attributes of a diagnostic service are varied systematically. By analysing the choices people make across many paired options, the method can quantify how much each attribute matters and how people trade one feature off against another.

The survey was designed to capture the dimensions most likely to shape real-world acceptance. Respondents considered factors such as where the assessment takes place, whether the AI acts as a first reader before a clinician reviews the image or as a second opinion after the doctor has made a judgement, the accuracy of the technology, the speed of the referral decision, and the degree of human oversight involved. Participants were recruited from across the UK to reflect a broad population sample, and their responses were modelled statistically to estimate the relative weight each attribute carried in shaping preferences.

The headline result is one that developers and health planners will welcome: on balance, people are receptive to AI being used to help detect skin cancer in general practice. The technology is not viewed as an unwelcome intrusion but as a potentially useful partner in a diagnostic process that many recognise as imperfect. Importantly, the strength and direction of that acceptance depended on how the system was deployed. Preferences were not uniform across all configurations of an AI-enabled service, which suggests that implementation choices, not just algorithm accuracy, will determine public trust.

One of the clearest signals in the data concerned the role of the clinician. Respondents placed substantial value on scenarios in which a human doctor remains central to the diagnostic pathway, with the AI serving as an aid rather than an autonomous decision-maker. This aligns with a recurring theme in the wider literature on medical AI: people generally support algorithms that support clinicians, but are far more hesitant about systems that appear to bypass human expertise altogether. For skin cancer detection, where a missed melanoma can be fatal, that desire for oversight is perhaps unsurprising.

Accuracy itself also mattered. Respondents preferred services in which the AI, or the combined human-AI process, was described as more reliable in distinguishing harmless lesions from those needing urgent attention. Trade-off analysis allowed the researchers to express these preferences quantitatively, revealing how much additional waiting time, for example, people would accept in exchange for a measurable gain in diagnostic accuracy. Such estimates are valuable because they convert abstract attitudes into concrete quantities that health service designers can weigh against cost and capacity constraints.

The study also found that preferences varied across different groups of respondents. Familiarity with AI, previous experience of skin checks, and demographic factors all influenced how people weighed the attributes of an AI-supported service. This heterogeneity matters for policy. A one-size-fits-all rollout of AI tools could encounter pockets of resistance, whereas a deployment strategy that communicates clearly what the technology does, who oversees it, and how errors are handled is more likely to build broad acceptance. The authors suggest that transparency about the assistive role of these systems should be a central feature of any NHS implementation.

The timing of this research is significant. Health systems around the world are under pressure from rising demand and workforce shortages, and diagnostic backlogs have become a persistent concern. AI triage tools for skin lesions promise to speed up the pathway, potentially allowing low-risk cases to be managed in primary care while ensuring that high-risk lesions reach specialists quickly. Early trials of such tools in the UK have reported encouraging results, but large-scale adoption will depend as much on public confidence as on clinical evidence. By quantifying what patients actually want from these services, this study provides an evidence base for designing AI deployments that people are willing to use.

The broader lesson extends well beyond dermatology. As algorithms enter ever more areas of medicine, from radiology to pathology to general practice triage, understanding the public’s terms of engagement becomes an essential part of responsible innovation. This UK-wide experiment demonstrates that acceptance is conditional, nuanced and measurable. People appear ready to embrace AI that makes skin cancer detection faster and more accurate, provided that clinicians stay firmly in the loop and that the promises made on behalf of the technology are honest ones. In that sense, the study offers not just a snapshot of current attitudes but a practical roadmap for introducing AI into primary care in a way that earns, rather than assumes, public trust.

The discrete choice experiment approach used in this study has a long pedigree in health services research, having been employed to elicit preferences for everything from screening programmes to vaccination schedules. Its strength lies in forcing respondents to make realistic trade-offs rather than simply endorsing or rejecting a technology in the abstract. When people are asked directly whether they support medical AI, many express generic enthusiasm or generic unease; when asked to choose between two concrete service designs, their underlying priorities become visible. This is particularly valuable for technologies at an early stage of deployment, where public attitudes are still forming and where policy decisions made now could lock in patterns of trust or distrust for years to come.

The context for this work is a diagnostic pathway under genuine strain. Melanoma, while accounting for a minority of skin cancer cases, is responsible for the large majority of skin cancer deaths, and its incidence in the UK has increased substantially over recent decades, partly attributed to historical trends in overseas sun exposure and an ageing population. At the same time, urgent suspected cancer referrals have grown faster than dermatology capacity in many parts of the country, creating waiting times that clinicians and patient groups have repeatedly flagged as concerning. Tools that can safely reduce the number of benign lesions progressing along the urgent pathway could free specialist time for those who need it most, which is precisely the promise that has attracted NHS innovation funding to this area.

It is worth noting how the regulatory landscape is evolving in parallel. Software intended to inform clinical decisions about suspected cancer falls within the scope of medical device regulation, and the United Kingdom has been developing its own post-Brexit framework for approving and monitoring such tools. Real-world evaluation is a central expectation of that framework, and studies of patient acceptability complement the technical validation studies that dominate the field. A system may pass accuracy benchmarks in retrospective image datasets yet still fail in practice if the public declines to engage with the service in which it is embedded. Evidence on preferences therefore feeds directly into implementation guidance and commissioning decisions.

The finding that prior familiarity with AI shapes preferences echoes a consistent pattern in the behavioural literature: experience tends to moderate both utopian and dystopian expectations. People who have encountered algorithmic tools in everyday life, whether in navigation apps or online services, often report more calibrated views of what such systems can and cannot do. In the clinical setting, this suggests that early, well-communicated deployments could themselves build the familiarity that supports later acceptance, whereas a poorly explained first encounter could colour attitudes across an entire community.

There are, of course, limits to what any stated-preference study can establish. Hypothetical scenarios do not carry the emotional weight of a real diagnosis, and respondents may behave differently when a genuine lesion of their own is at stake. Discrete choice experiments also require researchers to select which attributes to vary, and unmeasured concerns, such as data privacy or the fear of being deprioritised by an algorithm, may not be fully captured. Longitudinal follow-up of actual deployments, capturing both uptake and outcomes, will be needed to confirm that the preferences measured here translate into behaviour. Nevertheless, by quantifying the conditions of acceptance before widespread rollout, this study offers health planners a rare opportunity to design AI-enabled services around public expectations rather than retrofitting trust after the fact.

Subject of Research: Public preferences for AI-assisted skin cancer detection in UK primary care, measured using a nationwide discrete choice experiment.

Article Title: Preferences for the use of Artificial Intelligence (AI) technologies to help detect skin cancer in primary care settings: a UK-wide discrete choice experiment (DCE)

Article References: Jones, O. T., Walter, F. M., Matin, R. N., Calanzani, N., Emery, J., van der Schaar, M., & Morris, S. (2026). Preferences for the use of Artificial Intelligence (AI) technologies to help detect skin cancer in primary care settings: a UK-wide discrete choice experiment (DCE). British Journal of Cancer. https://doi.org/10.1038/s41416-026-03611-x

Image Credits: AI Generated

DOI: 10.1038/s41416-026-03611-x

Keywords: artificial intelligence, skin cancer, melanoma, primary care, general practice, discrete choice experiment, patient preferences, clinical decision support, dermatology, NHS, diagnostic accuracy, public attitudes

The research team recruited 301 caregivers of unvaccinated adolescent girls through hospitals and community health service centers in Jiangsu and Zhejiang provinces, two economically developed eastern coastal regions of China. The median age of the caregivers surveyed was 41 years, with an interquartile range of 38 to 44, meaning the respondents were overwhelmingly mothers and fathers in the prime of their decision-making years for family health matters. Each participant completed two separate discrete choice experiments: one presenting hypothetical vaccine profiles varying in attributes such as cancer protection, side-effect risk and cost, and another presenting alternative vaccination service delivery arrangements varying in who recommends the vaccine, where it is administered, how appointments are made, and what incentives are offered.

Discrete choice experiments rest on a foundational principle of behavioral economics: people rarely judge a health intervention on a single attribute. Instead, they mentally trade off competing characteristics, accepting a higher out-of-pocket price in exchange for better protection, or tolerating a small risk of side effects if the expected benefit is large. By randomly varying attribute levels across repeated choice sets and analyzing responses with mixed logit models, researchers can estimate the relative weight each attribute carries in the decision and, critically, predict how uptake would shift under realistic policy scenarios. This approach moves beyond simple opinion surveys, which often overstate willingness to act, because respondents must make consequential trade-offs with every choice.

When it came to the vaccine itself, two attributes towered over all others. Protection against cervical cancer carried a relative importance of 25.2 percent, while the risk of severe side effects accounted for 21.3 percent of the decision weight. Protection against genital warts followed closely at 20.3 percent, an intriguing result because it suggests Chinese caregivers value a benefit that extends beyond cancer prevention to broader sexual health. Cost contributed 11.9 percent and place of manufacture 11.6 percent, with all five attributes showing statistically significant effects at the p less than 0.05 threshold. Notably, the country where a vaccine is manufactured, an attribute that has generated considerable public discussion in China amid the introduction of domestic HPV vaccines, mattered less than every clinical attribute, indicating that perceived efficacy and safety dominate the calculus.

The service delivery experiment revealed an equally instructive hierarchy. Who recommends the vaccine was by far the most influential factor, carrying a relative importance of 35.3 percent, more than any single vaccine attribute. Incentives ranked second at 19.5 percent, followed by vaccination location at 17.5 percent, message framing at 13.1 percent and appointment methods at 12.4 percent, all statistically significant. In practical terms, a recommendation from a doctor carried far more weight than a generic reminder message, and the promise of an incentive meaningfully shifted preferences, particularly when framed in altruistic terms. The dominance of professional recommendation underscores a persistent truth in immunization research: trusted clinical messengers remain the single most reliable bridge between vaccine availability and vaccine uptake.

The policy simulations embedded in the study translate these preference weights into concrete projections. Predicted vaccine uptake increased by 40.8 percent when protection against both cervical cancer and genital warts was raised to the 90 percent level, a figure that speaks directly to the growing portfolio of nine-valent HPV vaccines capable of preventing a wider spectrum of HPV-related disease. Even more striking, projected service uptake rose by 54.5 percent when three elements were combined: a doctor’s recommendation, school-based vaccination, and altruistic incentives that appeal to protecting others in the community rather than personal gain. This synergy effect is central to the paper’s conclusion, because no single intervention in isolation produced a comparable improvement.

The emphasis on altruistic framing aligns with a growing body of behavioral science showing that messages highlighting collective benefit can outperform self-interested appeals, particularly in cultural contexts that prize family and community obligation. In China, where HPV vaccination programs for adolescents are still expanding and coverage among the target 9 to 14 age group lags behind WHO elimination targets, such culturally resonant framing may prove decisive. The authors argue that integrating evidence-based vaccine education, culturally sensitive delivery models, and well-designed incentive structures could accelerate progress toward the World Health Organization’s 90-70-90 strategy, which calls for fully vaccinating 90 percent of girls by age 15 in every country by 2030.

Methodologically, the study strengthens a literature that has often relied on smaller samples or simpler survey designs. The dual-experiment architecture allowed the researchers to separate questions about the product itself from questions about how the product reaches families, a distinction that matters for policy because ministries of health control service delivery while vaccine attributes are fixed by manufacturers and regulators. Model fit was assessed using standard information criteria, and the mixed logit specification captured preference heterogeneity across respondents, acknowledging that a single average preference may mask meaningful variation between urban and rural families, between income groups, and between caregivers with different levels of health literacy. The study received ethical approval from Nanjing Medical University and was funded by the National Natural Science Foundation of China and institutional career development grants.

The limitations are worth noting. The sample was drawn from two relatively affluent eastern provinces, so preference weights may differ in less developed regions where cost sensitivity could be higher and access to physician recommendations scarcer. Discrete choice experiments measure stated preferences rather than revealed behavior, and the gap between what people say in a survey and what they do at a clinic is well documented. Still, the internal consistency of the findings, with the most clinically meaningful attributes and the most trusted messengers emerging as dominant drivers, provides a credible roadmap for program designers.

For global cervical cancer elimination efforts, the message from Nanjing is ultimately optimistic. Caregivers in this study were not immutable vaccine skeptics; they were rational decision-makers whose choices responded predictably to information, access and incentives. When vaccines offer broad protection, when doctors speak clearly and consistently in their favor, when clinics come to schools so that a vaccination does not require a parent to lose a day of work, and when public health campaigns appeal to the shared goal of a cancer-free generation, uptake responds. As China continues to scale its national immunization infrastructure and domestic vaccine supply, the study’s evidence-based playbook offers a template not only for China but for the many middle- and low-income countries now designing adolescent HPV vaccination programs from the ground up.

Beyond the headline findings, the study’s design details illuminate how preference research can inform immunization policy in practice. Because the two experiments were analyzed separately, the authors could quantify trade-offs within each domain without conflating how caregivers judge a vaccine’s clinical profile with how they judge the system that delivers it. This separation matters for implementation: regulators and manufacturers determine efficacy and safety profiles, while local health authorities control who delivers recommendations, where clinics operate, and which incentives are offered, so the service-side results point to actions that are immediately actionable by program managers.

The prominence of recommendation sources, at more than a third of the decision weight in the service experiment, echoes a consistent theme in vaccination research across countries: the credibility of the messenger often outweighs the content of the message. That incentives still contributed nearly a fifth of the weight suggests they are best understood as complements to, rather than substitutes for, clinical endorsement. Similarly, the moderate weight given to appointment methods implies that reducing logistical friction helps, but only at the margin once trust and access are established.

For readers interpreting the uptake projections, the combined-scenario gains should be viewed as upper-bound estimates grounded in stated choices. Nevertheless, the direction of the effects, with clinical benefit, professional endorsement, school delivery and altruistic framing all pulling in the same direction, offers a coherent, testable framework that future implementation studies in China and comparable settings can evaluate in real-world rollout.

Subject of Research: Caregiver preferences for HPV vaccination services and incentives for adolescent girls in China

Article Title: HPV vaccination services and incentives preferences of Chinese daughters’ caregivers: a discrete choice experiment

Article References: Fang, H., Li, Y., Yang, S., Li, M., Huang, B., Chow, E. P. F., Ong, J. J., Wu, D., & Zhang, Y. (2026). HPV vaccination services and incentives preferences of Chinese daughters’ caregivers: a discrete choice experiment. BMC Health Services Research. https://doi.org/10.1186/s12913-026-15397-y

Image Credits: AI Generated

DOI: 10.1186/s12913-026-15397-y

Keywords: HPV, vaccination, discrete choice experiment, parental preferences, cervical cancer, adolescent health, China, vaccine incentives, school-based vaccination, mixed logit model, health services research, services

The study, led by Balázs Kertesz of the Doctoral School of Business and Management at the University of Debrecen, together with Klára Bíró of the Institute of Health Economics and Management and Péter Balogh of the Institute of Methodology and Business Digitalization, was designed to fill a stubborn evidence gap. Hungary’s public system has faced well-documented underfunding, leading to long waiting lists and constrained access to specialists. Those frictions have become the engine of private-sector growth, as households increasingly pay directly for consultations, diagnostics and elective procedures. Yet until now, policymakers have had little rigorous information about which attributes of private services actually matter to the general adult population, rather than to existing private clinic customers. Understanding those preferences matters for anyone planning service networks, setting prices, or designing policies aimed at narrowing regional inequalities in access.

Methodologically, the researchers deployed a two-stage approach that is considered state of the art in stated-preference research. Before constructing the main choice experiment, they conducted a best-worst scaling (BWS) exercise to identify which candidate attributes of private healthcare were most relevant to respondents. BWS asks participants to repeatedly identify the best and worst options in small sets of attributes, producing a ranking of relative importance that is less vulnerable to the scale distortions of simple rating scales. From this preparatory work, five attributes survived into the final experimental design: the cost of the service, the distance to the provider, the availability of appointments, the reputation of the provider, and the type of clinic or provider.

The main survey then confronted each of the 1,014 respondents with a series of realistic decision scenarios. In each of eight choice situations, participants saw three hypothetical private healthcare offers described by varying combinations of the five attributes, alongside a fourth option: to decline all of them and remain in public healthcare. This opt-out alternative is methodologically crucial. Because Hungarian adults can always default to the public system, a well-designed experiment must allow them to express that preference rather than forcing them to choose among private options they might reject in real life. Including a no-choice option anchors the experiment in the genuine decision architecture of Hungary’s dual system and prevents the overstatement of demand that plagues forced-choice designs.

The statistical engine behind the analysis was a conditional logit (CL) model, the workhorse specification for discrete choice data. Conditional logit assumes that the utility an individual derives from a given healthcare option is a linear function of its attributes plus a random error term, and that the probability of choosing any one option is proportional to its estimated utility relative to the full choice set. From the estimated coefficients, the team could compute both the relative importance of each attribute and—critically for health economics—willingness-to-pay (WTP) figures. WTP calculations translate abstract utility weights into monetary terms: they answer the question of how much more a patient would be willing to pay for, say, a provider located half as far away, or an appointment available a week sooner.

The results are unambiguous in their hierarchy. Provider distance emerged as the single most important attribute, accounting for 40.01% of the explained preference structure. Cost followed at 32.31%, and appointment availability took third place at 19.13%. Together, these three practical attributes dominated roughly nine-tenths of the preference weight in the model. Institutional reputation and provider type—the attributes often emphasized in private clinics’ own marketing, from glossy branding to physician celebrity—were far less influential. In other words, Hungarian patients are not primarily buying prestige when they enter the private market; they are buying proximity, affordability and speed. The willingness-to-pay estimates reinforce this picture, quantifying exactly how much shorter travel times and faster appointments are worth relative to each other and to price.

These findings carry a counterintuitive edge that helps explain the trajectory of Hungary’s private healthcare market. Many observers might assume that private care functions as a status good, with patients choosing flagship downtown clinics and renowned specialists. The data suggest something more mundane and, arguably, more consequential: demand behaves like a market for convenience. A private clinic that opens closer to where people live or work, prices its services within reach of median households, and offers appointments without long delays will capture preference share even if its reputation is unremarkable. Conversely, a prestigious institution located far from patients, or charging fees well beyond their comfort zone, leaves much of the market on the table—or sends it back to the public system entirely, where the no-choice option remains a real and frequently exercised alternative.

For policymakers, the study’s implications extend beyond marketing strategy into questions of equity and system design. Distance as the dominant attribute is a red flag for regional inequality: patients in smaller towns and rural areas face systematically longer travel to private providers, meaning the convenience premium of private care is distributed unevenly across the country. If accessibility, rather than quality perception, is what patients weigh most heavily, then the geography of private investment decisions will shape health access patterns for years to come. The findings can inform service-planning discussions about where new capacity should be located, how pricing structures affect uptake among lower-income groups, and how the public system’s waiting times—the very frictions that push patients private—might be reduced to rebalance the two sectors. The authors frame their results as input for exactly these policy conversations on access, affordability and regional disparities in Hungary’s mixed public-private healthcare system.

The research also exemplifies a broader methodological trend in health services research: the pairing of best-worst scaling with discrete choice experiments to build more realistic, behaviorally grounded preference models. By using BWS to prune the attribute set before the DCE, the researchers reduced cognitive burden on respondents and improved the interpretability of the final estimates. The inclusion of the public-care opt-out, the quota-representative sampling frame, and the translation of utilities into willingness-to-pay values together produce evidence that speaks directly to both economics and policy. The study received ethical approval from the Research Ethics Committee of the Faculty of Economics at the University of Debrecen and was conducted under the ethical principles of the Declaration of Helsinki, with all participants providing informed consent. Open access funding was provided by the University of Debrecen, and the authors thank Dr. Péter Czine for verifying the analytical methods. As Hungary’s private healthcare sector continues to expand against the backdrop of public-sector strain, this experiment provides a rare quantitative answer to a deceptively simple question: what makes a Hungarian adult choose to pay for care? The answer—closer, cheaper, sooner—may disappoint brand strategists, but it should energize anyone committed to making healthcare genuinely accessible.

Subject of Research: Patient preferences for private healthcare services among the Hungarian adult population, measured with a discrete choice experiment

Article Title: Understanding patient preferences for private healthcare services among the general Hungarian adult population using discrete choice experiment

Article References: Kertesz, B., Bíró, K., & Balogh, P. (2026). Understanding patient preferences for private healthcare services among the general Hungarian adult population using discrete choice experiment. Discover Social Science and Health. https://doi.org/10.1007/s44155-026-00482-8

Image Credits: AI Generated

DOI: 10.1007/s44155-026-00482-8

Keywords: discrete choice experiment, private healthcare, Hungary, patient preferences, willingness to pay, best-worst scaling, conditional logit, healthcare access, regional inequality, health policy, University of Debrecen, out-of-pocket spending