Analysis of Cardiovascular Disease Risk Factors
Andreina Arias
2026-04-01
#Load Libraries
library(tidyverse)## Warning: package 'ggplot2' was built under R version 4.5.1## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 4.0.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(caret)## Loading required package: lattice
##
## Attaching package: 'caret'
##
## The following object is masked from 'package:purrr':
##
## liftlibrary(corrplot)## corrplot 0.95 loadedlibrary(rpart)
library(rpart.plot)
library(randomForest)## randomForest 4.7-1.2
## Type rfNews() to see new features/changes/bug fixes.
##
## Attaching package: 'randomForest'
##
## The following object is masked from 'package:dplyr':
##
## combine
##
## The following object is masked from 'package:ggplot2':
##
## marginlibrary(pROC)## Type 'citation("pROC")' for a citation.
##
## Attaching package: 'pROC'
##
## The following objects are masked from 'package:stats':
##
## cov, smooth, varLoaded data from https://www.kaggle.com/datasets/redwankarimsony/heart-disease-data
df<-read.csv("https://raw.githubusercontent.com/Andreina-A/Data698/refs/heads/main/heart_disease_uci.csv")#view structure
str(df)## 'data.frame': 920 obs. of 16 variables:
## $ id : int 1 2 3 4 5 6 7 8 9 10 ...
## $ age : int 63 67 67 37 41 56 62 57 63 53 ...
## $ sex : chr "Male" "Male" "Male" "Male" ...
## $ dataset : chr "Cleveland" "Cleveland" "Cleveland" "Cleveland" ...
## $ cp : chr "typical angina" "asymptomatic" "asymptomatic" "non-anginal" ...
## $ trestbps: int 145 160 120 130 130 120 140 120 130 140 ...
## $ chol : int 233 286 229 250 204 236 268 354 254 203 ...
## $ fbs : logi TRUE FALSE FALSE FALSE FALSE FALSE ...
## $ restecg : chr "lv hypertrophy" "lv hypertrophy" "lv hypertrophy" "normal" ...
## $ thalch : int 150 108 129 187 172 178 160 163 147 155 ...
## $ exang : logi FALSE TRUE TRUE FALSE FALSE FALSE ...
## $ oldpeak : num 2.3 1.5 2.6 3.5 1.4 0.8 3.6 0.6 1.4 3.1 ...
## $ slope : chr "downsloping" "flat" "flat" "downsloping" ...
## $ ca : int 0 3 2 0 0 0 2 0 1 0 ...
## $ thal : chr "fixed defect" "normal" "reversable defect" "normal" ...
## $ num : int 0 2 1 0 0 0 3 0 2 1 ...Columns: id (Unique id for each patient) age (Age of the patient in years) origin (place of study) sex (Male/Female) cp chest pain type ([typical angina, atypical angina, non-anginal, asymptomatic]) trestbps resting blood pressure (resting blood pressure (in mm Hg on admission to the hospital)) chol (serum cholesterol in mg/dl) fbs (if fasting blood sugar > 120 mg/dl) restecg (resting electrocardiographic results) – Values: [normal, stt abnormality, lv hypertrophy] thalach: maximum heart rate achieved exang: exercise-induced angina (True/ False) oldpeak: ST depression induced by exercise relative to rest slope: the slope of the peak exercise ST segment ca: number of major vessels (0-3) colored by fluoroscopy thal: [normal; fixed defect; reversible defect] num: the predicted attribute 0: No heart disease (absence of disease).The exact meaning of values 1 through 4 can depend on the specific dataset, but they generally indicate the extent or severity of the disease 1: Mild heart disease, 2: Moderate heart disease, 3: Severe heart disease, and 4: Very severe heart disease.
License: Data files © Original Authors
Citation Request: The authors of the databases have requested that any publications resulting from the use of the data include the names of the principal investigator responsible for the data collection at each institution. They would be:
Hungarian Institute of Cardiology. Budapest: Andras Janosi, M.D. University Hospital, Zurich, Switzerland: William Steinbrunn, M.D. University Hospital, Basel, Switzerland: Matthias Pfisterer, M.D. V.A. Medical Center, Long Beach and Cleveland Clinic Foundation:Robert Detrano, M.D., Ph.D.
#check for missing values
colSums(is.na(df))## id age sex dataset cp trestbps chol fbs
## 0 0 0 0 0 59 30 90
## restecg thalch exang oldpeak slope ca thal num
## 0 55 55 62 0 611 0 0Seven columns have missing data, I used a simple imputation where the the median will be used of the numeric values and mode will be used for the categorical values.
for(col in names(df)){
if(is.numeric(df[[col]])){
df[[col]][is.na(df[[col]])]<-median(df[[col]], na.rm=TRUE)
}else{
mode_val<-names(sort(table(df[[col]]),decreasing=TRUE))[1]
df[[col]][is.na(df[[col]])]<-mode_val
}
}#check for missing values again
colSums(is.na(df))## id age sex dataset cp trestbps chol fbs
## 0 0 0 0 0 0 0 0
## restecg thalch exang oldpeak slope ca thal num
## 0 0 0 0 0 0 0 0I converted the target variable “num” into a binary variable, instead of using all heart stages I will set no heart disease at 0 and all other stages into just 1 where it indicatess heart disease.
#coverted target column into binary
df$num <- ifelse(df$num == 0, 0, 1)
df$num <- as.factor(df$num)
#converted categorical columns to factors
df$sex <- as.factor(df$sex)
df$cp <- as.factor(df$cp)
df$fbs <- as.factor(df$fbs)
df$restecg <- as.factor(df$restecg)
df$exang <- as.factor(df$exang)
df$slope <- as.factor(df$slope)#Train/Test split
set.seed(21)
trainIndex<- createDataPartition(df$num, p = 0.8, list = FALSE)
train_df <- df[trainIndex, ]
test_df <- df[-trainIndex, ]Correlation Analysis
numeric_data<-df|>
select(where(is.numeric))
cor_matrix<-cor(numeric_data)
corrplot(cor_matrix, method="color", type="upper", tl.cex=0.8)
Logistic Regression Model
log_model<-glm(num~., data=train_df,family = "binomial")
log_probs<-predict(log_model, test_df,type="response")
log_pred<-ifelse(log_probs>0.5,1,0)|>
as.factor()Decision Tree Model
DT_model<-rpart(num~., data=train_df,method = "class")
rpart.plot(DT_model)
DT_pred<- predict(DT_model, test_df, type="class")
DT_probs<-predict(DT_model, test_df, type = "prob")[,2]Random Forest model
rf_model<-randomForest(num~., data=train_df,ntree =100)
rf_pred<- predict(rf_model, test_df)
rf_probs<-predict(rf_model, test_df, type="prob")[,2]Evaluation
#Evaulation Function
evaluate_model <- function(true, pred, probs) {
cm <- confusionMatrix(pred, true, positive = "1")
accuracy <- unname(cm$overall["Accuracy"])
precision <- unname(cm$byClass["Precision"])
recall <- unname(cm$byClass["Recall"])
f1 <- unname(cm$byClass["F1"])
true_numeric <- as.numeric(true) - 1
roc_obj <- roc(true_numeric, probs)
roc_auc <- as.numeric(auc(roc_obj))
return(c(
Accuracy = accuracy,
Precision = precision,
Recall = recall,
F1_Score = f1,
ROC_AUC = roc_auc
))
}#Evaluation models
log_results<-evaluate_model(test_df$num, log_pred,log_probs)## Setting levels: control = 0, case = 1## Setting direction: controls < casesDT_results<-evaluate_model(test_df$num, DT_pred,DT_probs)## Setting levels: control = 0, case = 1
## Setting direction: controls < casesrf_results<-evaluate_model(test_df$num, rf_pred,rf_probs)## Setting levels: control = 0, case = 1
## Setting direction: controls < cases#Result
results<-rbind(
Logistic_Regression = log_results,
Decision_Tree = DT_results,
Random_Forest = rf_results
)
print(results)## Accuracy Precision Recall F1_Score ROC_AUC
## Logistic_Regression 0.7978142 0.8200000 0.8118812 0.8159204 0.9054576
## Decision_Tree 0.8743169 0.8900000 0.8811881 0.8855721 0.9018957
## Random_Forest 0.8579235 0.8865979 0.8514851 0.8686869 0.9437938plot(roc(test_df$num, DT_probs), col="blue")## Setting levels: control = 0, case = 1## Setting direction: controls < casesplot(roc(test_df$num, rf_probs), col="red", add=TRUE)## Setting levels: control = 0, case = 1
## Setting direction: controls < casesplot(roc(test_df$num, log_probs), col= "green", add= TRUE)## Setting levels: control = 0, case = 1
## Setting direction: controls < caseslegend("bottomright", legend=c("Decision Tree", "Random Forest", "Logistic Regression"),
col=c("blue","red", "green"), lwd=2)