Methodology minute: a machine learning primer for infection prevention and control.

Area of Science:

• Informatics
• Public Health
• Epidemiology

Background:

• Machine learning and predictive modeling are increasingly utilized in infection prevention and control.
• Infection preventionists require a foundational understanding of model creation and evaluation to make informed decisions.
• Assessing model performance and utility is crucial for effective infection control programs.

Purpose of the Study:

• To introduce infection preventionists to supervised learning, a prevalent machine learning method.
• To provide a foundational understanding of supervised learning for practical application in infection control.
• To equip infection preventionists with the knowledge to evaluate machine learning models.

Main Methods:

• This primer focuses on supervised learning, a key machine learning technique.
• Explanation of core concepts related to supervised learning model development.
• Discussion on methods for evaluating the performance and applicability of predictive models.

Main Results:

• Supervised learning is identified as the most common machine learning method in infection prevention.
• The primer aims to demystify the creation and evaluation of these models.
• Understanding these methods enables better decision-making regarding model implementation.

Conclusions:

• Infection preventionists need to understand machine learning, particularly supervised learning.
• This knowledge is essential for assessing the value and performance of predictive models.
• Effective use of machine learning can enhance infection prevention and control strategies.