Introduction to Machine Learning in Pharmaceutical Sciences

Shree Sai Prakashan is writing a full set of B.Pharm titles to this new NEP 2020 syllabus. Get notified the moment the book for this subject is released, or pre-book sets for your college.

Unit 1 · Foundations of Machine Learning 6 hrs

Definition and scope of Artificial Intelligence, Machine Learning and Data Science; types of learning (supervised, unsupervised, reinforcement); features and labels, training and testing data; model building and prediction; train–test split, overfitting and underfitting; the bias–variance trade-off; and the basic ML workflow.

Unit 2 · Regression Models in Healthcare 6 hrs

Predictive modelling for continuous outcomes — linear and multiple linear regression, model coefficients and their interpretation, residuals and goodness-of-fit; performance metrics (MSE, RMSE, R²); and implementation on pharmaceutical data (dose–response relationships, drug-dissolution rates, PK-parameter estimation) using Python libraries such as scikit-learn.

Unit 3 · Classification Models in Clinical Applications 6 hrs

Logistic regression, probability output and threshold selection; the confusion matrix and metrics (accuracy, sensitivity, specificity, precision, recall); ROC curve and AUC; k-nearest neighbours; and clinical examples such as adverse-drug-reaction and disease-risk prediction.

Unit 4 · Tree-Based Models & Ensemble Learning 6 hrs

Decision trees (structure, splitting criteria, decision paths and feature importance); random forests and the ensemble concept; advantages and limitations of tree-based models; and applications such as ADR risk stratification, patient classification and treatment-outcome prediction.

Unit 5 · Unsupervised Learning & Case Studies 6 hrs

The concept of unsupervised learning; clustering and K-means, choosing the number of clusters and interpreting cluster outputs; and a mini-case study integrating regression, classification or clustering on healthcare datasets for patient segmentation and drug grouping.