The following steps should be taken into consideration when planning the use of Adaptive Learning Platforms (ALP) on AMR/AMS:

1. Define Granular AMR/AMS Learning Objectives and Competencies: Clearly identify the specific AMR/AMS knowledge, skills, and competencies that the ALP will target. Break down complex topics into smaller, measurable learning objects or concepts.
2. Platform Selection or Development: Choose a suitable existing Adaptive Learning Platform (e.g., Smart Sparrow, CogBooks, Area9 Lyceum, Knewton, Realizeit, or others mentioned in general educational technology literature) that allows for the desired level of adaptivity and content integration, or plan for custom development if resources permit. (Samulski et al., 2016, used Smart Sparrow for cytopathology modules; Putra et al., 2022, used CogBooks for veterinary dermatology).
3. Content Creation and Curation for Adaptivity: Develop or curate a rich repository of diverse AMR/AMS learning resources in various formats (e.g., text, short videos, interactive simulations, case studies, image banks, audio clips, links to guidelines). Content needs to be modular and tagged appropriately to allow the system to select and present it dynamically.
4. Authoring Adaptive Rules, Pathways, and Logic: This is a critical step. Define the rules, algorithms, and decision trees that will govern how the platform adapts to the learner. This includes setting up prerequisite relationships between learning objects, defining mastery thresholds for concepts, determining how learner performance on embedded assessments will trigger different content pathways (e.g., remedial loops, advanced topics, alternative explanations), and specifying the nature of adaptive feedback. (Samulski et al., 2016, describe the process of creating adaptive tutorials with branching logic).
5. Integration of Formative Assessments: Embed frequent, varied formative assessment activities (e.g., multiple-choice questions, open-ended questions, problem-solving tasks, virtual patient interactions) throughout the learning experience. These assessments provide the data that fuels the adaptation engine.
6. User Interface (UI) and User Experience (UX) Design: Ensure the platform has an intuitive and engaging interface that clearly presents the personalized learning path and makes it easy for learners to navigate and interact with the adaptive content.
7. Pilot Testing and Iterative Refinement: Conduct thorough pilot testing with representatives of the target AMR/AMS learners to evaluate the platform’s usability, the effectiveness of the adaptive logic, learner engagement, and the achievement of learning objectives. Use feedback and performance data to iteratively refine the content, adaptive pathways, and platform configuration.

Facilitator’s role (Instructional Designer/Content Expert/Platform Manager/Learning Analyst): This role is heavily concentrated in the upfront design and development phases: defining learning architectures, authoring adaptive rules and pathways, creating or curating granular, high-quality AMR/AMS content, and configuring the platform. During course delivery, the facilitator monitors overall learner progress at a cohort level using platform analytics, identifies common points of difficulty that might indicate a need to refine pathways or content, updates content based on new AMR/AMS evidence, and may provide high-level support for complex issues that the platform’s automated feedback cannot resolve. Direct, individualized tutoring is less frequent as the platform is designed to handle much of the personalized guidance.

Participant’s role (Learner): Actively engage with the Adaptive Learning Platform, diligently complete learning activities and embedded assessments. The learner’s performance, responses, and interactions directly influence the personalization of their learning path. Learners must be comfortable with a technology-driven, often self-paced, learning experience and be proactive in utilizing the adaptive features to their benefit.

Methods

• Platform-Generated Learning Analytics: ALPs provide rich data on individual learning paths, time spent on specific learning objects or topics, performance on all embedded assessments, identified areas of difficulty or misconception, rates of progress, and levels of mastery achieved for specific AMR/AMS competencies.
• Pre- and Post-Intervention Knowledge/Skill Tests: Use validated instruments or custom-developed tests to measure overall gains in AMR/AMS knowledge, improvements in clinical reasoning or decision-making skills, or changes in attitudes/confidence before and after engaging with the ALP. (Fontaine et al., 2019, in their meta-analysis found AEEs can improve knowledge and skills; Putra et al., 2022, demonstrated higher post-test scores in an adaptive learning group).
• Performance on Embedded Summative Assessments: Evaluation of performance on specific quizzes, simulations, or problem-solving tasks designed to assess mastery of key AMR/AMS learning objectives within the platform.
• Learner Satisfaction and Engagement Surveys: Collect feedback from users on their experience with the platform, including its usability, the perceived effectiveness and relevance of the personalized learning path, engagement levels, and overall satisfaction. (Yakin and Linden, 2021, and Putra et al., 2022, assessed student perceptions and engagement).
• Learning Efficiency Analysis: Where appropriate, compare the time taken by learners to achieve mastery of AMR/AMS concepts using the ALP versus traditional or non-adaptive e-learning approaches. (Fontaine et al., 2019, suggest AEEs may be more efficient).

Tools

Adaptive Learning Platform’s built-in analytics dashboards and reporting functionalities. Standardized or custom-designed AMR/AMS knowledge tests and clinical reasoning assessments. Validated user experience (UX) and satisfaction questionnaires . Possibly eye-tracking or detailed interaction log analysis for deeper research into learning behaviors within the adaptive environment.