Explainable Machine learning terms in Public Health for beginners скачать в хорошем качестве

Explainable Machine learning terms in Public Health for beginners

In this video, I walk through a hands-on machine learning practice session focused on applied epidemiology and public health use cases. We build and evaluate multiple classification models including Logistic Regression, Decision Trees, and Random Forests, covering the full ML workflow: data preparation, feature engineering, train–test splitting, model training, evaluation with confusion matrix, precision, recall, and accuracy, and model interpretation. I also explain feature importance vs logistic regression coefficients, why scaling is critical for some models and unnecessary for tree-based models, and how to use pipelines correctly to avoid data leakage. Along the way, we debug real ML errors and discuss what these metrics actually mean in healthcare and disease prediction contexts. This video is ideal for: • Beginners transitioning from theory to practice • Public health professionals learning ML • Anyone interested in explainable machine learning Time stamps 00:00 Introduction 01:12 Why machine learning matter 03:57 Overview of interpretable models 05:09 Understanding Ground Truth and Predictions 08:39 Confusion Matrix 16:05 What accuracy tells us 17:45 Precision 23:59 Recall Sensitivity in Public Health 27:33 Interpreting Logistic regression coefficients 37:01 Model comparison for Public Health Decision Making 39:21 Outro