Databricks Certified Machine Learning - Associate
Get started today
Ultimate access to all questions.
A health organization is developing a classification model to identify patients with a specific infection. Their primary goal is to maximize the detection of actual cases. Which classification metric is most appropriate for evaluating the model's performance in this scenario? Choose the ONE best answer.
A health organization is developing a classification model to identify patients with a specific infection. Their primary goal is to maximize the detection of actual cases. Which classification metric is most appropriate for evaluating the model's performance in this scenario? Choose the ONE best answer.
Explanation:
Recall, also known as sensitivity, is the metric that measures the proportion of actual positive cases correctly identified by the model. In healthcare settings, maximizing recall is crucial to minimize false negatives, ensuring that as many patients with the infection as possible are identified, even if it means accepting more false positives. This approach is vital when the cost of missing an actual positive case is high. Other metrics like accuracy, precision, RMSE, and AUC-ROC do not specifically focus on maximizing the identification of positive cases as recall does.