Week 1 – Why Biostatistics Matters in Clinical Practice

Contents Covered: Role of biostatistics in evidence-based medicine, Data types: categorical, continuous, ordinal, time-to-event, Data scales: nominal, ordinal, interval, ratio, Sample vs population, Types of study: cross-sectional, case-control, cohort, RCT, systematic review

Clinical Application: Recognizing data types in charts, lab reports, How understanding data supports diagnostic reasoning

Week 2 – Getting Started with R and Clinical Data

Contents Covered: What is R and RStudio? Opening CSV/excel files using readr, Understanding rows, columns, and variable types, Exploring data: head(), str(), summary()

Clinical Application: Load and explore a dataset of patient demographics and vitals, Identify variable types (numeric vs categorical)

Week 3 – Describing Clinical Data

Contents Covered: Central tendency: mean, median, mode, Spread: range, interquartile range (IQR), standard deviation, Identifying outliers, Data visualization: histograms, bar charts, box plots

Clinical Application: Understand distribution of Blood Pressure, BMI, Blood glucose etc.

Week 4 – Descriptive Statistics and Visualization in R

Contents Covered: dplyr functions: filter(), select(), summarise(), Counting categories with count(), table(), Visualizing with ggplot2: bar charts, box plots, histograms, Saving images with ggsave()

Clinical Application: Create boxplots of CRP by ward, Bar chart of discharge outcomes by diagnosis

Week 5 – Understanding Probability and Distributions

Contents Covered: Normal distribution vs skewed data, Probability, False positives and false negatives

Clinical Application: Why most lab values (e.g., D-dimer, ALT) are skewed, How test thresholds impact patient outcome

Week 6 – Exploring Probability and Distributions in R

Contents Covered: Simulating normal and skewed data with rnorm() and rexp(), Plotting distributions using ggplot2, Exploring mean vs median with skew, Simple probability using pnorm(), qnorm()

Clinical Application: Visualize simulated CRP or D-dimer data, Model test result probabilities

Week 7 – Confidence Intervals and p-values

Contents Covered: What is a confidence interval?, What a p-value means (and does not), Statistical vs clinical significance, Common misinterpretations

Clinical Application: Reading results from a published trial, How to interpret: “p = 0.04, CI = [2.1, 5.3]”

Week 8 – Comparing Groups in R (t-test and CI)

Contents Covered: Using t.test() to compare means, Reading p-values and confidence intervals from R, Grouping with group_by(), Writing brief summaries: “There was a significant difference…”

Clinical Application:Compare blood pressure by medication type, Interpret difference in pain scores/ length of antibiotic treatment in two groups

Week 9 – Common Statistical Tests in Medicine

Contents Covered:When to use:t-tests (2 groups), Chi-square tests (categorical association), One-way ANOVA (3+ groups), Pearson correlation (r-values), Strengths and limitations of each test

Clinical Application: Association between smoking and COPD, Correlation between BMI and BP

Week 10 – Running Medical Statistical Tests in R

Contents Covered: Chi-square test with chisq.test(), One-way ANOVA with aov(), Correlation analysis with cor.test(), Creating and reading contingency tables with table(), Visualizing with ggplot2 and geom_smooth()

Clinical Application: Test association between smoking and COPD, Run correlation between cholesterol and weight

Week 11 – Making Sense of Medical Literature

Contents Covered: Diagnostic accuracy: sensitivity, specificity, PPV, NPV, Understanding ROC curves and AUC (simple introduction), Interpreting graphs in publications: forest plots, Kaplan-Meier curves, Recap of key biostatistical messages from the course

Clinical Application: Interpreting procalcitonin test data, How to critically appraise figures and tables in medical literature

Week 12 – Prediction Models and Final Practice in R

Contents Covered: Introduction to logistic regression with glm(), Creating binary outcomes (e.g., readmitted vs not), Using model output to interpret variable importance, (Optional) Simple ROC curve with pROC::roc(), Recap of key R skills from the course

Clinical Application: Build a basic model to predict 30-day readmission, Present results with summary table and plot