False Negative

In the context of binary classification, a false negative (FN) occurs when a test incorrectly indicates the absence of a condition when it is actually present. Mathematically, it is defined as FN = actual positives - true positives. This metric is critical in evaluating the performance of diagnostic tests, particularly in healthcare, where failing to detect a disease can have dire consequences. The false negative rate (FNR) is calculated as FNR = FN / (FN + TP), and it is essential to minimize this rate to ensure that patients receive appropriate care. False negatives can arise from various factors, including limitations in the diagnostic test, sample size, and the underlying characteristics of the disease. In machine learning, algorithms can be tuned to reduce false negatives, often at the expense of increasing false positives, necessitating a careful balance in model evaluation.