Virtual Medical Coaching is developing a new generation of adaptive teaching and learning modules for medical imaging and radiation sciences.
These modules are designed for education across radiography, diagnostic imaging, radiation therapy, nuclear medicine, radiation safety, and related areas of radiologic sciences education.
The aim is simple: help students understand what they know, help educators see where support is needed, and make formative assessment more useful than a final score.
Many online learning systems still treat assessment as a fixed quiz. A student answers a question, receives a mark, and moves on.
That approach can show whether a student answered correctly, but it does not always show whether they are developing mastery, guessing, repeating the same misunderstanding, or struggling because an earlier prerequisite concept was missed.
Virtual Medical Coaching’s adaptive modules are being built to give a more detailed view of learning. Each response can contribute to a live picture of the student’s progress across defined learning strands.
These strands may include anatomy recognition, image quality, positioning, exposure and technique, radiation protection, clinical decision making, image critique, patient safety, and confidence calibration.
Bayesian Knowledge Tracing, or BKT, is used to estimate a student’s mastery of a specific concept after each question.
In practice, this means every answer updates the system’s view of what the student is likely to understand. A correct answer can increase the mastery estimate for that strand. An incorrect answer can signal that the student may need more support, more practice or a different explanation.
This is particularly useful in medical imaging and radiation sciences because a single score can hide important variation.
A student may understand anatomy but struggle with positioning. Another may know the theory of radiation protection but apply it poorly in a clinical decision. Another may answer correctly but show low confidence, suggesting they need reassurance and repetition.
BKT helps make those differences visible.
Learning changes over time. A student may improve after feedback, lose confidence after a difficult session, or show inconsistent performance across different cases.
Hidden Markov Models, or HMMs, can support session-to-session progression tracking by helping the platform interpret changes in learning state over time.
This means the system can look beyond one question or one assessment attempt. It can help identify whether a student appears to be consolidating knowledge, progressing toward mastery, remaining uncertain, or showing signs of regression.
For teaching teams, this can be more useful than a simple pass or fail result. It gives a clearer view of how students are developing across the module.
Some learning problems occur because a student is trying to answer an advanced question without the required foundation.
Knowledge Space Theory, or KST, helps define prerequisite relationships between concepts.
For example, a student may need to recognise key anatomy before making a positioning decision. They may need to understand exposure principles before interpreting image quality. They may need to understand dose and shielding before making a radiation safety judgement.
KST allows the platform to structure learning pathways more intelligently. When a student struggles with a higher-level task, the system can consider whether a prerequisite concept needs to be revisited.
This supports guided progression rather than simply giving every student the same next question.
Large question banks are only useful if the questions are properly structured.
Item Response Theory, or IRT, helps support calibrated question banks by considering the difficulty and performance characteristics of individual questions.
Not every question should carry the same educational weight. A simple recall item should not be treated the same as a complex clinical judgement question. A well-calibrated item bank can help create fairer, more meaningful assessments across different ability levels.
For medical imaging, radiation therapy, nuclear medicine, and radiation safety education, this matters because students need to develop both knowledge and applied decision-making.
IRT helps support question banks that can grow over time while remaining educationally useful.
The student dashboard is designed to give learners clear insight into their own progress.
Instead of only showing a final mark, the system can show where the student is secure, where they are developing, and where they may need targeted revision.
Students can see performance across learning strands, confidence patterns, image critique decisions, and areas where further practice may be useful.
This supports self-directed learning. It also helps students understand that learning is not just about getting an answer right. It is about building reliable mastery across the knowledge and decision-making skills needed for safe clinical practice.
Educators need more than individual marks. They need to know where the cohort is struggling, which concepts need revisiting, and which students may need support before a practical assessment or clinical placement.
Virtual Medical Coaching’s teaching analytics are being designed to show both individual student progress and cohort-level signals.
A lecturer may be able to see that a cohort is generally progressing well in anatomy recognition but is showing difficulty with image critique. Another cohort may be secure in exposure and technique but less confident in radiation protection decisions.
The platform can also highlight confidence calibration, including students who are confidently incorrect. This is important because high confidence in an incorrect answer may require a different teaching response than low confidence or uncertainty.
Virtual Medical Coaching’s adaptive modules are not limited to radiography.
They are being designed for the wider field of medical imaging and radiation sciences, including diagnostic imaging, radiography, radiologic sciences, medical radiation science, radiation therapy, radiotherapy, nuclear medicine, and radiation safety education.
This broader approach matters because terminology differs across countries.
In some regions, students train as diagnostic radiographers. In others, they may be called radiologic technologists, medical imaging technologists, medical radiation technologists or medical radiation practitioners.
The educational need is similar: students must connect anatomy, physics, image formation, positioning, technique, radiation protection, clinical reasoning, and patient care.
The purpose of adaptive learning is not to replace the lecturer.
The purpose is to give educators better information and give students better feedback.
When teaching teams can see where students are progressing and where they are struggling, they can use classroom, lab, and simulation time more effectively.
Adaptive analytics can help lecturers decide whether to revisit a concept, provide worked examples, focus on a difficult learning strand, or support individual students who are at risk of falling behind.
Medical imaging and radiation sciences education requires more than memorisation.
Students need to make decisions, interpret images, understand risk, apply physics, manage technique, and reflect on quality. They also need to build confidence without becoming overconfident.
Virtual Medical Coaching’s adaptive teaching and learning modules are being developed to support that process.
By combining BKT for immediate per-question mastery, HMM for session-to-session progression, KST for prerequisite rules, and IRT for calibrated question banks, the platform can provide a more meaningful picture of learning.
For students, that means clearer feedback.
For educators, that means better insight.
For universities, that means stronger visibility across individual and cohort performance.
Adaptive learning uses student responses to adjust feedback, learning pathways, and mastery estimates. In medical imaging and radiation sciences, this can help track understanding across anatomy, image quality, positioning, exposure, radiation protection, and clinical decision-making.
No. The modules are being designed for the broader field of medical imaging and radiation sciences, including radiography, diagnostic imaging, radiologic sciences, radiation therapy, radiotherapy, nuclear medicine, and radiation safety education.
BKT updates a student’s estimated mastery after each question. This gives students and educators a clearer view of which learning strands are secure and which need more support.
HMM helps interpret how a student’s learning state changes between sessions. This supports longer-term progression tracking rather than relying only on a single assessment result.
KST helps define prerequisite rules. If a student struggles with an advanced task, the system can identify whether a foundational concept may need to be revisited.
IRT helps calibrate question difficulty. This allows large question banks to support more meaningful assessments across different student ability levels.
Students can see detailed individual analytics, including areas of strength, developing areas, confidence patterns, and suggested areas for review.
Teaching teams can see individual student analytics and cohort analytics, helping them identify common learning gaps, confidence issues, and areas that may need further teaching support.
Virtual Medical Coaching’s adaptive modules are being built to make formative assessment more useful for students and educators.
By combining learning science with detailed analytics, the platform can help medical imaging and radiation sciences programmes support progress earlier, more precisely and with clearer evidence.
Every question becomes more than a mark.
It becomes part of a live picture of student learning.