← Back to portfolio

R · DECISION TREES · HEALTHCARE ANALYTICS

Cardiotocography Classification

A graduate healthcare-analytics project using interpretable tree-based methods to classify fetal health patterns.

Recreated cardiotocography classification dashboard
Portfolio visualization recreated with sample or illustrative data to demonstrate the project’s analytical approach.

OBJECTIVE

Evaluate whether cardiotocography measurements could be organized into useful classification rules for distinguishing fetal health categories.

APPROACH

Explored the CTG variables, prepared the data in R, and compared conditional inference trees with recursive partitioning using ctree and rpart. Reviewed tree structure, splits, and classification behavior.

ANALYTICAL VALUE

Showed how interpretable models can convert complex clinical measurements into decision paths that are easier to explain than black-box predictions.

SKILLS SHOWN

Exploratory analysis, decision trees, healthcare data, classification, model interpretation, and comparative modeling.

TOOLS

RctreerpartHealthcare Data
Visualization note: The visual above is a portfolio reconstruction based on the project methods and deliverables. It is provided to demonstrate the analysis without reproducing restricted course or organizational materials.