Classification Models Lab
Introduction to Machine Learning in Pharmaceutical Sciences (BP301T) · Semester 3 · Unit 3: Classification Models in Clinical Applications
Calculate confusion-matrix metrics and explore probability-threshold, ROC/AUC, and classification trade-offs in a simulated teaching context.
What this unit covers
Logistic regression, probability outputs, threshold choice, a confusion matrix, accuracy, sensitivity, specificity, precision, recall, ROC/AUC, and k-nearest-neighbor concepts help learners reason about categorical teaching outputs. No browser result is a clinical classifier.
Apply it
Change a fictional screening threshold and explain the sensitivity–specificity trade-off, confusion-matrix entries, and no-clinical-use boundary.
How this lab works
A fictional classification table makes sensitivity, specificity, precision, and threshold trade-offs visible.
Data used
Fictional or browser-generated teaching inputs; no patient, proprietary manufacturing, or clinical-record data.
Limits
Educational simulation only. Outputs are not clinical advice, patient-specific predictions, release specifications, regulatory decisions, or professional competency evidence.