The research, led by Mehrdad Askarian of Shiraz University of Medical Sciences together with colleagues at Amirkabir University of Technology, the University of Saskatchewan, and Shiraz University of Medical Sciences, presents a safety-first machine learning framework for what the authors call precision public health. Instead of treating an entire population as a single audience, the framework sorts individuals into distinct psychometric profiles, each of which calls for a different communication strategy. The goal is to route people toward messages they can actually use, and away from messages that might backfire.

The study draws on a cross-sectional survey of 457 Iranian adults, of which 404 records made it into the de-identified machine learning dataset after processing. From demographic and geographic information, the framework maps each person onto one of three operational segments: Accepting, Ambivalent, and Resistant. These labels are not arbitrary. They were constructed from fixed boundaries on Likert-scale responses to theory-grounded composites built on two established models of health behavior: the Health Belief Model, which explains protective behavior through perceived susceptibility, severity, benefits, and barriers, and the Confidence, Complacency, and Convenience model, known as the 3C model, which is one of the most widely used frameworks for understanding vaccine hesitancy worldwide.

The classification engine itself is deliberately conventional. The researchers evaluated a logistic regression model using nested stratified cross-validation, a rigorous scheme in which the data is repeatedly split so that the model is tested on samples it has never seen, with an inner loop used for tuning. The results are strikingly modest, and the authors are refreshingly candid about that. The base classifier achieved an accuracy of 0.446, with a 95 percent confidence interval of 0.401 to 0.493, a balanced accuracy of 0.447, and a macro-F1 score of 0.419. For context, simply guessing the most common class every time would yield an accuracy of 0.438. In other words, the model barely outperformed a coin weighted toward the majority.

That near-baseline performance is not a failure of the study; it is the point around which the entire design pivots. The authors argue that in high-stakes health communication, a wrong prediction is not merely a statistical error but a potential harm. If a genuinely resistant person is misclassified as accepting and receives a pushy pro-vaccination message, the result could be reactance and entrenchment. If an ambivalent person is pushed too hard, they might slide toward refusal. The framework therefore treats misclassification asymmetrically, prioritizing the avoidance of what it calls critical errors over raw coverage.

The centerpiece of this safety philosophy is a mechanism the authors call the Safety Valve. Rather than forcing the classifier to commit to a prediction for every individual, the system computes a confidence threshold for each fold of the cross-validation procedure, with a mean threshold of 0.406, a standard deviation of 0.038, and a range spanning 0.36 to 0.45. When the model’s confidence in a prediction falls below this threshold, the case is not assigned to any segment at all. Instead, it is deferred to a human path the authors label Dialogue/Review, where communication is handled through conversation and professional judgment rather than automated targeting. In the reported evaluation, the Safety Valve deferred 16.8 percent of cases to this route.

The effect on harm was measurable, if modest. Observed critical errors, the mistakes most likely to cause communication damage, fell from 15.25 percent without the valve to 11.86 percent with it. The authors report that this reduction was not statistically significant, with a McNemar test yielding a p-value of 0.50, and they are careful not to overclaim. But the design logic is clear: the system trades some autonomous coverage for a lower rate of potentially harmful misrouting, and it explicitly flags the cases where the data is too ambiguous to justify automated action. This is a notable departure from the prevailing culture in applied machine learning, where models are typically optimized to predict everything and confidence calibration is an afterthought.

To make the model interpretable, the team applied SHAP analysis, or SHapley Additive exPlanations, a technique from game theory that assigns each input feature a contribution to individual predictions. The analysis identified the largest grouped predictors as healthcare professional status, education, employment, marital status, and province of residence. The authors stress that these are statistical correlates, not causal determinants. Knowing that a person works in healthcare or holds a certain educational level does not explain why they hesitate; it only signals where they tend to fall in the observed distribution. This distinction matters for anyone hoping to translate the framework into policy, because targeting based on correlates can entrench stereotypes if it is mistaken for causal understanding.

The study’s limitations are as instructive as its results. The sample was enriched with healthcare professionals and highly educated respondents, a consequence of recruitment channels that the authors acknowledge openly. This means the segment distribution and the model’s decision boundaries reflect a population that is not representative of Iranian adults at large, let alone other countries. The authors state plainly that the findings are not directly generalizable without recalibration and external validation, and that scalability, effectiveness, and feasibility all require field testing. No scalability claim is made. The framework is offered as a descriptive blueprint, a proof of concept for how risk-stratified health communication could be structured, rather than a deployable system.

Even in that modest form, the study lands at a moment when the questions it raises are urgent. Vaccine confidence has become one of the most politically and psychologically charged issues in global health, and blunt messaging campaigns have repeatedly shown their limits. The idea that an algorithm should be built to defer, to hand uncertain cases to human dialogue rather than push automated messages, inverts the usual logic of predictive systems. Whether safety valves like this one can be validated at scale, and whether segmenting populations by trust profile can be done ethically and without stigmatizing the Resistant segment, are questions the authors themselves place on the future agenda. What the study demonstrates now is that precision public health can be designed with harm prevention as its first objective, and that admitting uncertainty may be the most valuable prediction a health algorithm can make.

Subject of Research: A safety-first machine learning framework for segmenting vaccine hesitancy among Iranian adults into tailored public health communication profiles

Article Title: A safety-first machine learning framework for precision public health: segmenting vaccine hesitancy among Iranian adults

Article References: Askarian, M., Bayati, S., Rajabi, H., Askarian, A., Hatam, N., & Ayareh, N. (2026). A safety-first machine learning framework for precision public health: segmenting vaccine hesitancy among Iranian adults. BMC Public Health. https://doi.org/10.1186/s12889-026-29763-2

Image Credits: AI Generated

DOI: 10.1186/s12889-026-29763-2

Keywords: vaccine hesitancy, machine learning, precision public health, psychological reactance, explainable AI, health communication, logistic regression, SHAP, Health Belief Model, 3C model, Iran, psychometrics

The problem the researchers set out to address is well documented. Globally, digital technologies have become a core element of primary teacher training, with organizations such as ISTE and UNESCO pushing for classroom technology competence, and with curricula like Australia’s demanding that students develop algorithmic thinking and problem-solving skills embedded in authentic contexts. Yet studies of initial teacher education consistently reveal that programs emphasize technological knowledge while neglecting technological pedagogical knowledge, the crucial understanding of how to teach with and about technology. Without that, pre-service teachers tend to fall back on generic strategies, reproducing commercial step-by-step coding activities without conceptual understanding, or relying on loosely connected, activity-based lessons that look engaging but lack instructional coherence.

The research team, led by Peter Curtis, Michael D. Carey and Natalie McMaster of the University of the Sunshine Coast, together with David A. Martin of Edith Cowan University, points to striking evidence of this gap. In a frequently cited study by Bower and Falkner, when pre-service teachers were asked to list pedagogical strategies for developing students’ computational thinking, most simply equated computational thinking with using technology, and only one explicitly mentioned coding. Even more telling, the candidates reported high confidence in their abilities, a phenomenon the researchers describe as a third order of ignorance: being unaware of one’s own lack of pedagogical knowledge. Systematic reviews of computational thinking in teacher education reach similar conclusions, finding that translating confidence with digital tools into meaningful classroom practice remains a persistent challenge.

The 3C Model, whose three Cs stand for Context, Capabilities and Computational focus, emerged from an earlier qualitative study by Martin, Curtis and Redmond that examined how primary school students learned coding and computational thinking through the framework. That study used a triangulated design combining semi-structured focus-group interviews, analyzed through Clarke and Braun’s thematic analysis with NVivo software, and an insider researcher’s systematic observations and reflective field notes analyzed through Schön’s framework of reflection-in-action and reflection-on-action. The findings showed that the model enhanced student engagement and supported curriculum learning outcomes, and subsequent work by Wang and Kale highlighted its potential as a developmentally appropriate approach for building foundational computational thinking skills in pre-service teachers.

What distinguishes the 3C Model is its explicit grounding in established learning theory. The framework is anchored in Piaget’s theory of cognitive development, specifically targeting children aged around 10 and 11 who sit near the transition from concrete operational to formal operational thinking. At this stage, learners can reason logically about tangible experiences but still rely heavily on concrete, contextualized material to support cognitive processing. The model also builds on the Concrete-Representational-Abstract instructional sequence and the Language Model, both drawn from mathematics pedagogy and rooted in Bruner’s theory of enactive, iconic and symbolic representation. The researchers are candid that TPACK, the influential framework describing the intersection of technological, pedagogical and content knowledge, tells teachers what they need to know but does not prescribe how to sequence instruction. The 3C Model fills that translational gap.

In practice, the model unfolds across a five-lesson sequence. Lesson 1, Context, introduces curriculum content through an authentic, culturally appropriate problem scenario that integrates digital technologies with other learning areas such as science, health or mathematics. Lesson 2, Capabilities, has students explore what a digital tool such as Scratch or a micro:bit can actually do, without writing any code, while the teacher elicits pre-coding language like if-then and repeat until through structured discussion. Lessons 3 and 4, the Computational focus, support a deliberate and gradual shift from student-familiar everyday language to the formal abstraction of coding and algorithmic thinking, with students acting out algorithms physically before translating their pseudocode into block-based programs. Lesson 5 invites students to create a unique artifact through project-based learning, applying their new skills to a problem of personal or community relevance.

Two design choices make the framework particularly notable for equity. First, because individual devices are not central to developing computational thinking in the early lessons, students can engage meaningfully with complex coding concepts in a largely unplugged environment, allowing schools with limited computing resources to participate fully. Second, the delayed introduction of abstract code gives teachers natural opportunities to differentiate instruction, supporting learners who need concrete representations, language support or extra scaffolding. The authors provide worked examples spanning year levels, including an upper primary unit integrating health, English, mathematics and digital technologies using Scratch, and a lower primary beach safety sequence that weaves together the Blue-Bot block-coding app, mathematics and English, alongside a marking rubric and assignment templates hosted in an open science repository for other teacher educators to adopt.

The team also reports preliminary evidence from an exploratory implementation, in which the 3C Model was embedded into coursework as pedagogical learning and assessment tasks at two Australian universities. While the authors are careful to characterize this as an informal investigation rather than a formal research study, pre-service teacher feedback suggested increased confidence and improved instructional skills in teaching coding and computational thinking. The researchers stress, however, that prerequisites matter. Programs should introduce the model only after candidates have studied TPACK and the Concrete-Representational-Abstract approach or Language Model in their technologies and mathematics coursework, since understanding the gradual release of responsibility and the principles underlying those sequences is critical to teaching coding through the model’s structure.

The implications extend beyond individual classrooms. The authors argue that embedding digital competence as a core professional expectation should be supported by incorporating frameworks like the 3C Model into accreditation and curriculum standards, and they connect the work to the United Nations Sustainable Development Goal 4 on quality education by framing it as a route to equitable access to high-quality teacher preparation. Future research, they say, should investigate the model at scale, including longitudinal exploration of pre-service teacher confidence, pedagogical shifts and student outcomes. If those studies bear out the early promise, a model that asks children to walk an algorithm before they type one may become a standard fixture of how the next generation of teachers learns to teach the language of computers.

Subject of Research: A pedagogical framework for teaching coding and computational thinking in teacher education

Article Title: Advancing digital technology teacher education through the 3C model

Article References: Advancing digital technology teacher education through the 3C model. (n.d.). https://doi.org/10.1007/s44322-026-00056-1

Image Credits: AI Generated

DOI: 10.1007/s44322-026-00056-1

Keywords: teacher education, computational thinking, coding, 3C Model, TPACK, pedagogy, pre-service teachers, digital technologies, Piaget, unplugged learning, curriculum integration, primary school