15 Important AI Definitions Every Clinician Needs to Know

Diving into the world of AI in medicine can often feel like navigating a maze of technical jargon. But as AI becomes increasingly incorporated into various aspects of healthcare, it’s crucial to understand the lingo so you can make informed decisions when using it. 

Our curated glossary of AI definitions is designed to empower you to navigate through this complex landscape with confidence, and provide a practical level of everyday understanding that’s essential in today’s healthcare environment.

How many of these terms are you familiar with?

AI (artificial intelligence)

This is the simulation of human intelligence by machines that are programmed to think and perform tasks like humans. It encompasses a broad range of technologies and techniques that enable machines to sense, comprehend, act, and learn from experience. The primary aim of AI is to create systems that are able to perform tasks that normally require human intelligence, for example, recognizing speech, making decisions, interpreting visual input and understanding language. Over the years AI evolved to include various subfields, ranging from machine learning and deep learning to robotics and natural language processing, all of which have use cases within healthcare.


This is a step-by-step process for solving a problem. Think of it as a recipe, where each step is clearly laid out to achieve a desired outcome. In the context of artificial intelligence, algorithms drive the logic behind software applications. This enables them to process data, make decisions, and produce results in a consistent manner.

Bias (in AI)

This refers to systematic errors in predictions due to underlying factors in the training data. For example, if the training data contains built-in prejudices or is not representative of the broader population or scenario, the AI model’s output can perpetuate or magnify these biases.


These AI systems are engineered to mimic conversations with human users. In the healthcare sector, AI-driven chatbots could serve important roles such as arranging appointments, providing symptom assessments, and offering medication reminders.


This is a type of task where the goal is to predict which category or class an input belongs to.

Confusion matrix

This is a table used to evaluate the performance of a classification model. For example, a classification problem with possible outcomes of  “positive” and “negative” will have a confusion matrix that looks like this:

Predicted value

Actual value
PositiveTrue positiveFalse negative
NegativeFalse positiveTrue negative
  • True positive: The number of times the model correctly predicted “positive”
  • True negative: The number of times the model correctly predicted “negative”
  • False positive: The number of times the model incorrectly predicted “positive”
  • False negative: The number of times the model incorrectly predicted “negative”

Here are three potential uses of a confusion matrix in medicine:

  1. Disease Detection: AI models might be trained to detect the presence or absence of a disease based on medical images, lab results, or other diagnostic data. The confusion matrix can help determine how often the model correctly identifies patients with the disease (True Positives) versus misdiagnosing healthy individuals as having the disease (False Positives), and so on. For example, this JAMA study used a confusion matrix to help evaluate the ability of AI to distinguish Kawasaki Disease from other causes of fever in children brought to a paediatric emergency department.
  2. Treatment Recommendation: AI might be used to recommend whether a patient should receive a certain treatment or not. In such cases, a confusion matrix can be used to understand how often the AI’s recommendations align with expert opinions or outcomes.
  3. Predictive Modelling: AI can be used to predict patient outcomes, such as whether a patient will be readmitted to a hospital within 30 days. The confusion matrix can show how accurate these predictions are.
Deep learning

This is a subset of machine learning, inspired by the human brain’s structure and function, specifically, neural networks. It involves algorithms known as artificial neural networks, which can process enormous amounts of data and automatically extract patterns and features from it. These networks are ‘deep’ because they consist of multiple layers of interconnected nodes, allowing them to make sophisticated decisions. 

This paper from the Journal of the American College of Cardiology discusses an example of deep learning in medicine: they found that deep learning may make it possible to automate echocardiogram analysis and predict disease on a large scale.


This refers to an AI model’s capacity to apply its learning from one set of data to new, unfamiliar data. In essence, it measures how well a model can predict or make decisions in real-world scenarios that it wasn’t specifically taught to handle.

Large language models

Often abbreviated as LLMs, these are advanced algorithms designed to process, generate, and understand human language on a vast scale. They’re trained on large amounts of text from diverse sources, enabling them to generate coherent sentences, answer questions, and even produce content resembling human-written prose. Examples of large language models include ChatGPT, Claude, and Gemini. Learn the key things clinicians need to know when using large language models here.

Machine learning

This refers to a computer system using algorithms to learn and improve from experience. The algorithms analyse data to recognize patterns, and use those to make choices and/or predictions. The more data system processes, the more accurate its outputs become, which can allow it to tackle complex tasks that used to require human judgement.

Natural language processing (NLP)

This is a subfield of AI that focuses on the interaction between computers and humans through natural language. This technology is a key component of large language models like ChatGPT.

Neural network

This is a type of machine learning model inspired by the human brain, composed of interconnected nodes or ‘neurons’.


This refers to giving an AI system a specific instruction or question. Prompts can be as short or long as you need them to be. But keep in mind that the more specific your prompts are, the more likely it is that the AI’s output will be what you’re looking for. For help with creating prompts that contain the required level of detail, try this prompting course and the accompanying prompting tool.

Reinforcement learning

A type of machine learning where an AI learns how to behave in an environment by performing actions and receiving rewards and/or punishments. This paper in Nature shows how reinforcement learning was used to train an AI to detect skin cancer. 

Supervised learning

With this type of machine learning, an AI learns from a dataset where each example is paired with the correct output.

Training data

This refers to the data used to teach an AI model.

You’re off to a good start!

Knowing these 15 essential AI definitions equips you to better understand and navigate the exciting possibilities that AI brings to healthcare. The journey into AI in healthcare is just beginning, and your newfound knowledge is a vital step towards embracing and influencing this technological revolution.


Educational Resources


Want to become a pro at prompting, and consistently get usable results? Be sure to check out Medmastery’s AI prompting course. Learn techniques to apply to the plethora of AI resources in constant development.

Sheralyn Guilleminot LITFL Author

BSc.Pharm (University of Manitoba), Pharmacist and Medical Writer

BA MA (Oxon) MBChB (Edin) FACEM FFSEM. Emergency physician, Sir Charles Gairdner Hospital.  Passion for rugby; medical history; medical education; and asynchronous learning #FOAMed evangelist. Co-founder and CTO of Life in the Fast lane | Eponyms | Books | Twitter |

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.