knitr::opts_chunk$set(echo=FALSE)
library(dslabs)
library(ggplot2)
How do mean radius and mean texture measurements differ between benign and malignant breast tumors, and which of the two variables shows a clearer distinction between the tumor classes?
The data set used in this analysis is the Breast Cancer Wisconsin Diagnostic data set (brca), which is commonly used for medical classification tasks.
The data set contains 569 observations and 31 variables. Each observation represents measurements taken from a digitized image of a breast mass.
The variables describe characteristics of cell nuclei, such as size, texture, and shape.
B = Benign (non-cancerous) M = Malignant (cancerous)
Understanding this outcome is important because early detection of malignant tumors can significantly improve treatment outcomes and survival rates.
The original data set is stored as a list containing:
x: numeric feature matrix (measurements)
y: classification labels
To make the data set suitable for analysis, it was converted into a structured data frame:
data(brca)
breast_cancer <- as.data.frame(brca$x)
breast_cancer$Class <- as.factor(brca$y)
class(breast_cancer)
## [1] "data.frame"
names(breast_cancer)
## [1] "radius_mean" "texture_mean" "perimeter_mean"
## [4] "area_mean" "smoothness_mean" "compactness_mean"
## [7] "concavity_mean" "concave_pts_mean" "symmetry_mean"
## [10] "fractal_dim_mean" "radius_se" "texture_se"
## [13] "perimeter_se" "area_se" "smoothness_se"
## [16] "compactness_se" "concavity_se" "concave_pts_se"
## [19] "symmetry_se" "fractal_dim_se" "radius_worst"
## [22] "texture_worst" "perimeter_worst" "area_worst"
## [25] "smoothness_worst" "compactness_worst" "concavity_worst"
## [28] "concave_pts_worst" "symmetry_worst" "fractal_dim_worst"
## [31] "Class"
summary(breast_cancer)
## radius_mean texture_mean perimeter_mean area_mean
## Min. : 6.981 Min. : 9.71 Min. : 43.79 Min. : 143.5
## 1st Qu.:11.700 1st Qu.:16.17 1st Qu.: 75.17 1st Qu.: 420.3
## Median :13.370 Median :18.84 Median : 86.24 Median : 551.1
## Mean :14.127 Mean :19.29 Mean : 91.97 Mean : 654.9
## 3rd Qu.:15.780 3rd Qu.:21.80 3rd Qu.:104.10 3rd Qu.: 782.7
## Max. :28.110 Max. :39.28 Max. :188.50 Max. :2501.0
## smoothness_mean compactness_mean concavity_mean concave_pts_mean
## Min. :0.05263 Min. :0.01938 Min. :0.00000 Min. :0.00000
## 1st Qu.:0.08637 1st Qu.:0.06492 1st Qu.:0.02956 1st Qu.:0.02031
## Median :0.09587 Median :0.09263 Median :0.06154 Median :0.03350
## Mean :0.09636 Mean :0.10434 Mean :0.08880 Mean :0.04892
## 3rd Qu.:0.10530 3rd Qu.:0.13040 3rd Qu.:0.13070 3rd Qu.:0.07400
## Max. :0.16340 Max. :0.34540 Max. :0.42680 Max. :0.20120
## symmetry_mean fractal_dim_mean radius_se texture_se
## Min. :0.1060 Min. :0.04996 Min. :0.1115 Min. :0.3602
## 1st Qu.:0.1619 1st Qu.:0.05770 1st Qu.:0.2324 1st Qu.:0.8339
## Median :0.1792 Median :0.06154 Median :0.3242 Median :1.1080
## Mean :0.1812 Mean :0.06280 Mean :0.4052 Mean :1.2169
## 3rd Qu.:0.1957 3rd Qu.:0.06612 3rd Qu.:0.4789 3rd Qu.:1.4740
## Max. :0.3040 Max. :0.09744 Max. :2.8730 Max. :4.8850
## perimeter_se area_se smoothness_se compactness_se
## Min. : 0.757 Min. : 6.802 Min. :0.001713 Min. :0.002252
## 1st Qu.: 1.606 1st Qu.: 17.850 1st Qu.:0.005169 1st Qu.:0.013080
## Median : 2.287 Median : 24.530 Median :0.006380 Median :0.020450
## Mean : 2.866 Mean : 40.337 Mean :0.007041 Mean :0.025478
## 3rd Qu.: 3.357 3rd Qu.: 45.190 3rd Qu.:0.008146 3rd Qu.:0.032450
## Max. :21.980 Max. :542.200 Max. :0.031130 Max. :0.135400
## concavity_se concave_pts_se symmetry_se fractal_dim_se
## Min. :0.00000 Min. :0.000000 Min. :0.007882 Min. :0.0008948
## 1st Qu.:0.01509 1st Qu.:0.007638 1st Qu.:0.015160 1st Qu.:0.0022480
## Median :0.02589 Median :0.010930 Median :0.018730 Median :0.0031870
## Mean :0.03189 Mean :0.011796 Mean :0.020542 Mean :0.0037949
## 3rd Qu.:0.04205 3rd Qu.:0.014710 3rd Qu.:0.023480 3rd Qu.:0.0045580
## Max. :0.39600 Max. :0.052790 Max. :0.078950 Max. :0.0298400
## radius_worst texture_worst perimeter_worst area_worst
## Min. : 7.93 Min. :12.02 Min. : 50.41 Min. : 185.2
## 1st Qu.:13.01 1st Qu.:21.08 1st Qu.: 84.11 1st Qu.: 515.3
## Median :14.97 Median :25.41 Median : 97.66 Median : 686.5
## Mean :16.27 Mean :25.68 Mean :107.26 Mean : 880.6
## 3rd Qu.:18.79 3rd Qu.:29.72 3rd Qu.:125.40 3rd Qu.:1084.0
## Max. :36.04 Max. :49.54 Max. :251.20 Max. :4254.0
## smoothness_worst compactness_worst concavity_worst concave_pts_worst
## Min. :0.07117 Min. :0.02729 Min. :0.0000 Min. :0.00000
## 1st Qu.:0.11660 1st Qu.:0.14720 1st Qu.:0.1145 1st Qu.:0.06493
## Median :0.13130 Median :0.21190 Median :0.2267 Median :0.09993
## Mean :0.13237 Mean :0.25427 Mean :0.2722 Mean :0.11461
## 3rd Qu.:0.14600 3rd Qu.:0.33910 3rd Qu.:0.3829 3rd Qu.:0.16140
## Max. :0.22260 Max. :1.05800 Max. :1.2520 Max. :0.29100
## symmetry_worst fractal_dim_worst Class
## Min. :0.1565 Min. :0.05504 B:357
## 1st Qu.:0.2504 1st Qu.:0.07146 M:212
## Median :0.2822 Median :0.08004
## Mean :0.2901 Mean :0.08395
## 3rd Qu.:0.3179 3rd Qu.:0.09208
## Max. :0.6638 Max. :0.20750
str(breast_cancer)
## 'data.frame': 569 obs. of 31 variables:
## $ radius_mean : num 13.5 13.1 9.5 13 8.2 ...
## $ texture_mean : num 14.4 15.7 12.4 18.4 16.8 ...
## $ perimeter_mean : num 87.5 85.6 60.3 82.6 51.7 ...
## $ area_mean : num 566 520 274 524 202 ...
## $ smoothness_mean : num 0.0978 0.1075 0.1024 0.0898 0.086 ...
## $ compactness_mean : num 0.0813 0.127 0.0649 0.0377 0.0594 ...
## $ concavity_mean : num 0.0666 0.0457 0.0296 0.0256 0.0159 ...
## $ concave_pts_mean : num 0.04781 0.0311 0.02076 0.02923 0.00592 ...
## $ symmetry_mean : num 0.188 0.197 0.181 0.147 0.177 ...
## $ fractal_dim_mean : num 0.0577 0.0681 0.069 0.0586 0.065 ...
## $ radius_se : num 0.27 0.185 0.277 0.184 0.156 ...
## $ texture_se : num 0.789 0.748 0.977 2.342 0.957 ...
## $ perimeter_se : num 2.06 1.38 1.91 1.17 1.09 ...
## $ area_se : num 23.56 14.67 15.7 14.16 8.21 ...
## $ smoothness_se : num 0.00846 0.0041 0.00961 0.00435 0.00897 ...
## $ compactness_se : num 0.0146 0.019 0.0143 0.0049 0.0165 ...
## $ concavity_se : num 0.0239 0.017 0.0198 0.0134 0.0159 ...
## $ concave_pts_se : num 0.01315 0.00649 0.01421 0.01164 0.00592 ...
## $ symmetry_se : num 0.0198 0.0168 0.0203 0.0267 0.0257 ...
## $ fractal_dim_se : num 0.0023 0.00243 0.00297 0.00178 0.00258 ...
## $ radius_worst : num 15.11 14.5 10.23 13.3 8.96 ...
## $ texture_worst : num 19.3 20.5 15.7 22.8 22 ...
## $ perimeter_worst : num 99.7 96.1 65.1 84.5 57.3 ...
## $ area_worst : num 711 630 315 546 242 ...
## $ smoothness_worst : num 0.144 0.131 0.132 0.097 0.13 ...
## $ compactness_worst: num 0.1773 0.2776 0.1148 0.0462 0.1357 ...
## $ concavity_worst : num 0.239 0.189 0.0887 0.0483 0.0688 ...
## $ concave_pts_worst: num 0.1288 0.0728 0.0623 0.0501 0.0256 ...
## $ symmetry_worst : num 0.298 0.318 0.245 0.199 0.31 ...
## $ fractal_dim_worst: num 0.0726 0.0818 0.0777 0.0617 0.0741 ...
## $ Class : Factor w/ 2 levels "B","M": 1 1 1 1 1 1 1 1 1 1 ...
sum(is.na(breast_cancer))
## [1] 0
There were no missing data, this step ensures the data is in a format suitable for statistical analysis and visualization.
Two explanatory variables were selected:
radius_mean (average size of the cell nucleus)
texture_mean (variation in cell texture)
These variables are relevant because cancerous cells often differ in size and texture compared to normal cells.
ggplot(breast_cancer, aes(x = Class)) +
geom_bar(fill = "steelblue") +
labs(title = "Distribution of Tumor Classes",
x = "Class (B = Benign, M = Malignant)",
y = "Count")
The bar chart shows that benign (B) tumors have a count of approximately 357, while malignant (M) tumors have a count of approximately 212. Benign cases are clearly more frequent in this data set than malignant ones.This is common in medical data sets and may affect model balance.
ggplot(breast_cancer, aes(x = radius_mean)) +
geom_histogram(bins = 30, fill = "darkgreen",
color = "white") + theme_classic()+
labs(title = "Distribution of Radius Mean",
x = "Radius Mean",
y = "Frequency")
The histogram depicts the distribution of radius mean values across the data set. The distribution exhibits a right-skewed pattern, with the highest frequency of observations concentrated between radius mean values of 12 and 14, reaching a peak frequency of approximately 65 to 67.
The distribution gradually tapers toward the right, with values extending as far as 28, suggesting the presence of tumors with considerably larger radius measurements at the upper end of the data set.
ggplot(breast_cancer, aes(x = texture_mean)) +
geom_histogram(bins = 30, fill = "purple", color = "white") +
labs(title = "Distribution of Texture Mean",
x = "Texture Mean",
y = "Frequency")
The histogram illustrates the distribution of texture mean values across the data set. The distribution follows a relatively bell-shaped pattern, centered around values of 18 to 20, with peak frequencies reaching approximately 53 to 55. A slight right skew is observed, with values extending toward 40, indicating the presence of a small number of cases with notably higher texture mean measurements.
ggplot(breast_cancer, aes(x = Class, y = radius_mean, fill = Class)) +
geom_boxplot() +
labs(title = "Radius Mean by Tumor Class",
x = "Class",
y = "Radius Mean")
The boxplot presents a comparison of radius mean values between benign (B) and malignant (M) tumor classes. Benign tumors recorded a median radius mean of approximately 12, while malignant tumors recorded a notably higher median of approximately 17 to 18.
The boxes show minimal overlap, with the malignant group displaying a wider interquartile range, and a few outliers are visible above the benign group at approximately 17 and below at approximately 9. This clear separation suggests that radius mean is a highly effective feature in distinguishing between benign and malignant tumors.
ggplot(breast_cancer, aes(x = Class, y = texture_mean, fill = Class)) +
geom_boxplot() +
labs(title = "Texture Mean by Tumor Class",
x = "Class",
y = "Texture Mean")
The boxplot illustrates the comparison of texture mean values between benign and malignant tumor classes. Benign tumors recorded a median texture mean of approximately 18, while malignant tumors recorded a higher median of approximately 22 to 23.
Several outliers are visible in both classes, particularly in the benign group where values extend toward 30 and beyond. The considerable overlap between the interquartile ranges of both classes indicates that texture mean alone possesses limited discriminatory power in differentiating between the two tumor classifications.
Only two explanatory variables were used out of 30 available features.
The analysis is descriptive and does not establish causality.
Potential relationships between all variables were not fully explored.
The data set is simplified compared to real clinical diagnostic environments.
Based on the exploratory data analysis conducted, radius mean demonstrated a clearer distinction between the two tumor classes between benign and malignant tumors, as evidenced by the clear separation observed in the boxplot with minimal overlap between the two classes. Texture mean, while showing some differential between classes, exhibited considerable overlap, limiting its discriminatory power as a standalone feature.
The data set reflects an imbalance between tumor classes, with benign cases outnumbering malignant cases. This observation should be taken into consideration in any subsequent classification or predictive modeling.
Overall, the findings suggest that radius mean is a more reliable feature in differentiating tumor classifications, and both features should ideally be used in conjunction with additional variables to strengthen analytical outcomes.