Self

Lung Cancer Similarity Estimator (2015 - 2025)

A rough profile-based estimator using lung cancer patient attributes. It is a learning project and not medical advice.

Workflow

Load and parse lung_cancer_dataset.csv with risk-factor columns.
Convert user inputs into a weighted similarity score (smoking, exposure, symptoms, demographics).
Calibrate score against the dataset to compute percentile and a rough chance band.
Return an estimate, confidence label, and plain-language interpretation.

Disclaimer: This tool is for educational demo purposes only and is not a diagnosis.

Important caveat: this is a demo estimator, not a medical model. The site's dataset (https://www.kaggle.com/datasets/zkskhurram/lung-cancer-clinical-dataset-20152025/data) is patient-only, so it is not a true population probability model.

Dataset

Default dataset path: lung_cancer_dataset.csv

Or upload a CSV

Dataset not loaded yet.

Estimate My Similarity Profile

Fill what you know. Leave the rest at defaults.

Age

Gender

Smoking Status

Cigarettes / Day

Years Smoking

Air Pollution Exposure

Secondhand Smoke

Family History

Chronic Lung Disease

Asbestos Exposure i

Radon Exposure i

Coughing Blood

Load your dataset to begin.

Back to Projects