Project Overview
Our team analyzed a dataset containing information about lung cancer patients across several European countries. Each record represented an individual patient and included variables such as age, gender, smoking history, diagnosis date, treatment type, BMI, cholesterol level, asthma status, country, and survival outcome.
Using Microsoft Excel, we cleaned and filtered the data, created pivot tables, and developed four visualizations to answer questions about patient health and treatment outcomes. The final findings were presented through assertion-evidence slides designed to communicate each result clearly.
Tools and Methods
- Microsoft Excel
- Data cleaning and filtering
- Pivot tables
- Histograms
- Time-series charts
- Scatter plots and trendlines
- Bar charts
- Assertion-evidence presentation design
Cholesterol Levels Among Lung Cancer Patients
Research Question
Are there identifiable trends in cholesterol levels among lung cancer patients in Europe?
Method
We isolated the cholesterol data and grouped patient values into six intervals ranging from 150 to 300. Each interval covered a range of 25 units. We then created a histogram to visualize how cholesterol levels were distributed across the dataset.
Key Finding
The visualization helped identify the most common cholesterol ranges among the patients and showed whether the distribution was concentrated or widely dispersed.
Asthma Trends Over Time
Research Question
How did the number of lung cancer patients with asthma change between 2014 and 2024?
Method
We filtered the dataset to include only patients who had asthma and grouped the remaining records by year. A time-series chart was then created to examine changes throughout the decade.
Key Finding
Most years showed a relatively stable number of lung cancer patients with asthma. The unusually low values at the beginning and end of the period may reflect incomplete reporting rather than meaningful changes in patient patterns.
BMI and Age Among Non-Smoking Women
Research Question
Is there a relationship between BMI and age among non-smoking women between the ages of 20 and 40 who were diagnosed with lung cancer?
Method
The dataset was filtered to include:
- Female patients
- Non-smokers
- Patients between 20 and 40 years old
We created a scatter plot using age and BMI and added a linear trendline with an R² value to measure the strength of the relationship.
Key Finding
The analysis showed a weak negative linear relationship between BMI and age. This indicates that age explained very little of the variation in BMI within this patient group.
Treatment Type and Survival
Research Question
Does the type of treatment received affect a lung cancer patient’s likelihood of survival?
Method
We used the treatment and survival variables to create a pivot table. Survival rates were calculated for each treatment category and presented in a bar chart for comparison.
Key Finding
The visualization allowed us to compare survival outcomes across treatments such as chemotherapy, radiation, and surgery. Differences were observed among the treatment categories, although additional variables would need to be considered before concluding that treatment type alone caused the differences.
Project Takeaways
This project strengthened our ability to:
- Clean and organize a large healthcare dataset
- Select appropriate charts for different analytical questions
- Use Excel pivot tables and filtering tools
- Interpret relationships and trends without overstating conclusions
- Present technical findings in a clear visual format