Explanation of the most commonly used terms in medical AI research. Updated weekly.

Artificial intelligence involves creating computer systems capable of performing tasks that typically require human intelligence. These tasks include learning, reasoning, problem-solving, perception, and language understanding. In healthcare, AI can support various applications, from diagnostic processes to personalized medicine and patient care management.

Deep learning is a more complex subset of machine learning that uses neural networks with many layers to process data in sophisticated ways. This technology is behind many advances in medical imaging and diagnostics.

Machine learning is a subset of AI focusing on algorithms that learn from data patterns and make decisions with minimal human intervention. It's used extensively in healthcare for predictive analytics, disease diagnosis, and treatment recommendations.

Internal Validation is a process within a study to assess the accuracy of a predictive model or algorithm using the data on which it was developed.

External Validation is the evaluation of a predictive model or algorithm's performance on a completely independent dataset, not used during the model's development.

Neural network is a computer model inspired by the human brain that learns to recognize patterns and solve problems.

Convolutional neural network is a specialized type designed specifically for handling images, learning visual patterns directly from pixels with minimal preprocessing.


Sensitivity measures a test's ability to correctly identify those with a condition (true positives).

Specificity measures its ability to correctly identify those without the condition (true negatives).