This practical guide outlines key considerations for applying artificial intelligence (AI) and machine learning (ML) in surgical education research. AI involves studying machine intelligence to perceive and infer data, aiming to approximate human performance. ML, a subfield of AI, focuses on methods and algorithms that improve task performance through data. With growing interest in AI applications in surgery, there is a need for rigorous research methods in surgical education. Current infrastructure for data capture, storage, labeling, and analysis is insufficient for robust AI research. AI can be applied to various types of surgical education research, including quantitative, qualitative, and visual data. Multidisciplinary collaboration with statisticians and data scientists is essential for rigorous investigation. AI is particularly useful for complex data, such as images and text, which are challenging for conventional statistical analysis. The guide focuses on ML methods, which include traditional statistics like linear regression and advanced techniques like deep learning and ensemble learning. ML methods are either classification or regression problems, with supervised, unsupervised, or reinforcement learning approaches depending on the research question. Supervised learning is commonly used for tasks like predicting exam outcomes. ML tools can assist in decision-making and actions for trainees, or compare groups using such tools. ML is computationally intensive, but powerful hardware and cloud computing can help. R and Python are commonly used for ML, with open-source libraries facilitating deep learning. Automated ML tools are available but are best suited for simple problems with well-structured data. ML has limitations, including potential biases in data and lack of interpretability. It is crucial to ensure data quality and understand the research question to select appropriate methods. Evaluation metrics should be chosen based on the research question and data type. The guide emphasizes the importance of rigorous data handling, appropriate algorithm selection, and clear research questions to ensure valid and reliable results in surgical education research.This practical guide outlines key considerations for applying artificial intelligence (AI) and machine learning (ML) in surgical education research. AI involves studying machine intelligence to perceive and infer data, aiming to approximate human performance. ML, a subfield of AI, focuses on methods and algorithms that improve task performance through data. With growing interest in AI applications in surgery, there is a need for rigorous research methods in surgical education. Current infrastructure for data capture, storage, labeling, and analysis is insufficient for robust AI research. AI can be applied to various types of surgical education research, including quantitative, qualitative, and visual data. Multidisciplinary collaboration with statisticians and data scientists is essential for rigorous investigation. AI is particularly useful for complex data, such as images and text, which are challenging for conventional statistical analysis. The guide focuses on ML methods, which include traditional statistics like linear regression and advanced techniques like deep learning and ensemble learning. ML methods are either classification or regression problems, with supervised, unsupervised, or reinforcement learning approaches depending on the research question. Supervised learning is commonly used for tasks like predicting exam outcomes. ML tools can assist in decision-making and actions for trainees, or compare groups using such tools. ML is computationally intensive, but powerful hardware and cloud computing can help. R and Python are commonly used for ML, with open-source libraries facilitating deep learning. Automated ML tools are available but are best suited for simple problems with well-structured data. ML has limitations, including potential biases in data and lack of interpretability. It is crucial to ensure data quality and understand the research question to select appropriate methods. Evaluation metrics should be chosen based on the research question and data type. The guide emphasizes the importance of rigorous data handling, appropriate algorithm selection, and clear research questions to ensure valid and reliable results in surgical education research.