The heatmap on the left shows the starting knowledge for 420 learners. It shows how they answered the first time they saw the question. Amplifire is adaptive in two dimensions. It serves up a question, asks a learner to choose the most accurate answer, and asks for their level of confidence regarding the answer. They can signal they are certain, uncertain, or just don’t know.
Our heatmaps use the following colors:
You can think of the heatmap as a visual proxy for the pattern of neurons that represent information in the minds of clinicians. Furthermore, think of confidence as the precursor to the decision making that leads to behavior. When you are confident, you act. When you are confident yet wrong, a mistake becomes far more likely.
The Amplifire algorithm is based in the cognitive psychology of learning and memory and adapts to each learner. If a learner is confident and correct on a question, they never see it again. If they are confident and wrong, the system will show them concise explanations and ask them the question again later in the module. Everyone gets to confident and correct along their own unique path.
The algorithm does not allow a learner to escape until all confidently held misinformation and uncertainty are eliminated. The heatmap on the right represents a state of mastery. Is it permanent? Sadly, no.
CHM is made up of neurons that are connected in a strong pattern, and this pattern will return. Regression is a topic we consider elsewhere, but suffice to say that our analysis of over a million learners in Amplifire indicates that about 75% CHM is permanently eliminated but 25% CHM returns within a month. Amplifire refreshers are designed to reduce regression over time. CHM can be tamed, but the brain’s architecture and processes mean that a 100% instantaneous fix does not appear possible.
Despite this reality, 100% confident and correct across all topics is indeed possible, as we regularly see that state in our refresher heatmaps. Like most things, it just takes some work to get there.