STEPS Dataset Summaries
James Oguta
May 2025
- 1 Load the dataset
- 2 Summarize the dataset
- 3 Display the missing observations by variable
- 4 Summarize the systolic blood pressure of patients
- 5 Generate summary statistics for the systolic blood pressure
- 6 Generate a histogram of the systolic blood pressure
- 7 Generate a histogram of the systolic blood pressure by age group
- 8 Generate a bar plot of the systolic blood pressure by age group
- 9 Summarise systolic BP for patients with hypertension
- 10 Generate a histogram of the systolic blood pressure for patients with hypertension
- 11 Plot a bar graph of the systolic blood pressure for patients with hypertension by age group
- 12 Generate a histogram of the systolic blood pressure for patients on hypertension treatment
- 13 Plot a bar graph of the systolic blood pressure for patients on hypertension treatment by age group
- 14 Generate a histogram of the systolic blood pressure for patients with diabetes
- 15 Plot a bar graph of the systolic blood pressure for patients with diabetes by age group
- 16 Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension
- 17 Plot a bar graph of the systolic blood pressure for patients with diabetes and hypertension by age group
- 18 Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension treatment
- 19 Plot a bar graph of the systolic blood pressure for patients with diabetes and hypertension treatment by age group
- 20 End of the R Markdown document
- 21 Save the R Markdown document
- 22 Save the R Markdown document as a PDF
- 23 Save the R Markdown document as a Word document
knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)
library(rmarkdown)
library(kableExtra)
library(ggplot2)
library(dplyr)##
## Attaching package: 'dplyr'## The following object is masked from 'package:kableExtra':
##
## group_rows## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union#Clear the environment
1 Load the dataset
# Load the steps_subset dataset
steps_subset <- read_csv("/Users/jamesoguta/Documents/James Oguta/My PhD Folder-2023-2025/Trainings/KenyaCVDModel/steps_subset.csv")
# Display the first few rows of the dataset
head(steps_subset)## # A tibble: 6 × 19
## id psu stratum wealth age age_group county sex region smk systolic
## <dbl> <dbl> <dbl> <chr> <dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
## 1 1001 32 1 4 Four… 39 35-39 19 Women Coast No 125.
## 2 1003 32 1 2 Seco… 35 35-39 19 Men Coast Yes 132.
## 3 1008 32 1 3 Midd… 60 60-64 19 Men Coast No 213.
## 4 1011 32 1 2 Seco… 18 15-19 19 Men Coast No 114
## 5 1013 32 1 4 Four… 51 50-54 19 Women Coast No 175.
## 6 1016 32 1 5 Rich… 47 45-49 19 Women Coast No 115
## # ℹ 8 more variables: htn <dbl>, htn_treatment <dbl>, diastolic <dbl>,
## # diabetes <dbl>, diabetes_treatment <dbl>, chol <dbl>, alcohol <dbl>,
## # weights <dbl>2 Summarize the dataset
## id psu stratum wealth
## Min. : 1001 Min. : 1.00 Min. :1.000 Length:4500
## 1st Qu.: 51074 1st Qu.: 51.75 1st Qu.:1.000 Class :character
## Median :103013 Median :103.00 Median :1.000 Mode :character
## Mean :101783 Mean :102.00 Mean :1.488
## 3rd Qu.:153026 3rd Qu.:152.00 3rd Qu.:2.000
## Max. :200123 Max. :200.00 Max. :2.000
##
## age age_group county sex
## Min. :16.0 Length:4500 Min. : 1.00 Length:4500
## 1st Qu.:27.0 Class :character 1st Qu.:12.00 Class :character
## Median :35.0 Mode :character Median :23.00 Mode :character
## Mean :37.5 Mean :23.43
## 3rd Qu.:46.0 3rd Qu.:35.00
## Max. :70.0 Max. :47.00
##
## region smk systolic htn
## Length:4500 Length:4500 Min. : 70.67 Min. :0.0000
## Class :character Class :character 1st Qu.:114.33 1st Qu.:1.0000
## Mode :character Mode :character Median :123.67 Median :1.0000
## Mean :127.12 Mean :0.8963
## 3rd Qu.:135.00 3rd Qu.:1.0000
## Max. :263.67 Max. :1.0000
## NA's :63 NA's :3063
## htn_treatment diastolic diabetes diabetes_treatment
## Min. :0.000 Min. : 48.33 Min. :0.0000 Min. :0.000
## 1st Qu.:0.000 1st Qu.: 74.33 1st Qu.:0.0000 1st Qu.:0.000
## Median :0.000 Median : 81.67 Median :0.0000 Median :1.000
## Mean :0.244 Mean : 82.44 Mean :0.0356 Mean :0.514
## 3rd Qu.:0.000 3rd Qu.: 89.33 3rd Qu.:0.0000 3rd Qu.:1.000
## Max. :1.000 Max. :151.67 Max. :1.0000 Max. :1.000
## NA's :4017 NA's :59 NA's :319 NA's :4428
## chol alcohol weights
## Min. : 2.000 Min. :1.000 Min. : 105.8
## 1st Qu.: 2.830 1st Qu.:1.000 1st Qu.: 1130.1
## Median : 3.550 Median :1.000 Median : 2631.9
## Mean : 3.714 Mean :1.208 Mean : 3839.8
## 3rd Qu.: 4.300 3rd Qu.:1.000 3rd Qu.: 4969.9
## Max. :10.300 Max. :2.000 Max. :55389.3
## NA's :331 NA's :1## spc_tbl_ [4,500 × 19] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ id : num [1:4500] 1001 1003 1008 1011 1013 ...
## $ psu : num [1:4500] 32 32 32 32 32 32 32 32 32 32 ...
## $ stratum : num [1:4500] 1 1 1 1 1 1 1 1 1 1 ...
## $ wealth : chr [1:4500] "4 Fourth" "2 Second" "3 Middle" "2 Second" ...
## $ age : num [1:4500] 39 35 60 18 51 47 38 45 41 48 ...
## $ age_group : chr [1:4500] "35-39" "35-39" "60-64" "15-19" ...
## $ county : num [1:4500] 19 19 19 19 19 19 19 19 19 19 ...
## $ sex : chr [1:4500] "Women" "Men" "Men" "Men" ...
## $ region : chr [1:4500] "Coast" "Coast" "Coast" "Coast" ...
## $ smk : chr [1:4500] "No" "Yes" "No" "No" ...
## $ systolic : num [1:4500] 125 132 213 114 175 ...
## $ htn : num [1:4500] NA NA 1 NA 1 NA 1 NA 1 NA ...
## $ htn_treatment : num [1:4500] NA NA NA NA NA NA NA NA 0 NA ...
## $ diastolic : num [1:4500] 85 81.3 94.7 69.3 101.3 ...
## $ diabetes : num [1:4500] 0 0 0 0 0 0 0 0 0 1 ...
## $ diabetes_treatment: num [1:4500] NA NA NA NA NA NA NA NA NA 1 ...
## $ chol : num [1:4500] 3.68 4.49 3.79 2.59 3.31 4.14 3.72 3.72 4.49 4.26 ...
## $ alcohol : num [1:4500] 1 1 1 1 1 1 1 1 1 1 ...
## $ weights : num [1:4500] 4027 5714 3973 9097 3578 ...
## - attr(*, "spec")=
## .. cols(
## .. id = col_double(),
## .. psu = col_double(),
## .. stratum = col_double(),
## .. wealth = col_character(),
## .. age = col_double(),
## .. age_group = col_character(),
## .. county = col_double(),
## .. sex = col_character(),
## .. region = col_character(),
## .. smk = col_character(),
## .. systolic = col_double(),
## .. htn = col_double(),
## .. htn_treatment = col_double(),
## .. diastolic = col_double(),
## .. diabetes = col_double(),
## .. diabetes_treatment = col_double(),
## .. chol = col_double(),
## .. alcohol = col_double(),
## .. weights = col_double()
## .. )
## - attr(*, "problems")=<externalptr>## [1] 4500 19## [1] "id" "psu" "stratum"
## [4] "wealth" "age" "age_group"
## [7] "county" "sex" "region"
## [10] "smk" "systolic" "htn"
## [13] "htn_treatment" "diastolic" "diabetes"
## [16] "diabetes_treatment" "chol" "alcohol"
## [19] "weights"## # A tibble: 4,500 × 19
## id psu stratum wealth age age_group county sex region smk systolic
## <dbl> <dbl> <dbl> <chr> <dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
## 1 1001 32 1 4 Fou… 39 35-39 19 Women Coast No 125.
## 2 1003 32 1 2 Sec… 35 35-39 19 Men Coast Yes 132.
## 3 1008 32 1 3 Mid… 60 60-64 19 Men Coast No 213.
## 4 1011 32 1 2 Sec… 18 15-19 19 Men Coast No 114
## 5 1013 32 1 4 Fou… 51 50-54 19 Women Coast No 175.
## 6 1016 32 1 5 Ric… 47 45-49 19 Women Coast No 115
## 7 1018 32 1 3 Mid… 38 35-39 19 Men Coast No 131.
## 8 1023 32 1 4 Fou… 45 45-49 19 Men Coast No 137
## 9 1026 32 1 1 Poo… 41 40-44 19 Women Coast No 219.
## 10 1028 32 1 2 Sec… 48 45-49 19 Men Coast Yes 115.
## # ℹ 4,490 more rows
## # ℹ 8 more variables: htn <dbl>, htn_treatment <dbl>, diastolic <dbl>,
## # diabetes <dbl>, diabetes_treatment <dbl>, chol <dbl>, alcohol <dbl>,
## # weights <dbl>## [1] 19## [1] 12285## [1] 4500## [1] 19## # A tibble: 6 × 19
## id psu stratum wealth age age_group county sex region smk systolic
## <dbl> <dbl> <dbl> <chr> <dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
## 1 1001 32 1 4 Four… 39 35-39 19 Women Coast No 125.
## 2 1003 32 1 2 Seco… 35 35-39 19 Men Coast Yes 132.
## 3 1008 32 1 3 Midd… 60 60-64 19 Men Coast No 213.
## 4 1011 32 1 2 Seco… 18 15-19 19 Men Coast No 114
## 5 1013 32 1 4 Four… 51 50-54 19 Women Coast No 175.
## 6 1016 32 1 5 Rich… 47 45-49 19 Women Coast No 115
## # ℹ 8 more variables: htn <dbl>, htn_treatment <dbl>, diastolic <dbl>,
## # diabetes <dbl>, diabetes_treatment <dbl>, chol <dbl>, alcohol <dbl>,
## # weights <dbl>## # A tibble: 6 × 19
## id psu stratum wealth age age_group county sex region smk systolic
## <dbl> <dbl> <dbl> <chr> <dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
## 1 200097 200 2 5 Ric… 27 25-29 4 Men Weste… No 120
## 2 200102 200 2 3 Mid… 46 45-49 4 Men Weste… No 175.
## 3 200106 200 2 4 Fou… 23 20-24 4 Men Weste… No 125
## 4 200115 200 2 5 Ric… 61 60-64 4 Men Weste… No 133.
## 5 200119 200 2 5 Ric… 27 25-29 4 Women Weste… No 118.
## 6 200123 200 2 4 Fou… 47 45-49 4 Women Weste… No 135.
## # ℹ 8 more variables: htn <dbl>, htn_treatment <dbl>, diastolic <dbl>,
## # diabetes <dbl>, diabetes_treatment <dbl>, chol <dbl>, alcohol <dbl>,
## # weights <dbl>3 Display the missing observations by variable
# Display the missing observations by variable
missing_values <- sapply(steps_subset, function(x) sum(is.na(x)))
missing_values <- data.frame(variable = names(missing_values), missing = missing_values)
missing_values <- missing_values[missing_values$missing > 0, ]
# Display the missing values
missing_values## variable missing
## age_group age_group 1
## smk smk 3
## systolic systolic 63
## htn htn 3063
## htn_treatment htn_treatment 4017
## diastolic diastolic 59
## diabetes diabetes 319
## diabetes_treatment diabetes_treatment 4428
## chol chol 331
## alcohol alcohol 1# Display the missing values as a table
missing_values_table <- kable(missing_values, format = "html", caption = "Missing Values by Variable") %>%
kable_styling("striped", full_width = F)
# Display the table
missing_values_table| variable | missing | |
|---|---|---|
| age_group | age_group | 1 |
| smk | smk | 3 |
| systolic | systolic | 63 |
| htn | htn | 3063 |
| htn_treatment | htn_treatment | 4017 |
| diastolic | diastolic | 59 |
| diabetes | diabetes | 319 |
| diabetes_treatment | diabetes_treatment | 4428 |
| chol | chol | 331 |
| alcohol | alcohol | 1 |
4 Summarize the systolic blood pressure of patients
# Summarize the systolic blood pressure of all patients
systolic_bp <- steps_subset %>%
group_by(systolic) %>%
summarise(count = n()) %>%
arrange(desc(count))
# Display the summary of systolic blood pressure
systolic_bp## # A tibble: 352 × 2
## systolic count
## <dbl> <int>
## 1 NA 63
## 2 124 60
## 3 123 52
## 4 118. 51
## 5 125 51
## 6 117. 48
## 7 115. 47
## 8 120. 47
## 9 117. 46
## 10 119. 45
## # ℹ 342 more rows5 Generate summary statistics for the systolic blood pressure
# Generate summary statistics for the systolic blood pressure
systolic_bp_summary <- steps_subset %>%
summarise(mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary statistics for the systolic blood pressure
systolic_bp_summary## # A tibble: 1 × 5
## mean median sd min max
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 127. 124. 19.9 70.7 264.# Display the summary statistics for the systolic blood pressure as a table
systolic_bp_summary_table <- kable(systolic_bp_summary, format = "html", caption = "Summary Statistics for Systolic Blood Pressure-All Patients") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_summary_table| mean | median | sd | min | max |
|---|---|---|---|---|
| 127.1154 | 123.6667 | 19.89775 | 70.66667 | 263.6667 |
6 Generate a histogram of the systolic blood pressure
# Generate a histogram of the systolic blood pressure
histogram <- ggplot(steps_subset, aes(x = systolic)) +
geom_histogram(binwidth = 5, fill = "blue", color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure-All Patients",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal()
# Display the histogram
histogram
# Generate a boxplot of the systolic blood pressure
# Generate a boxplot of the systolic blood pressure
boxplot <- ggplot(steps_subset, aes(x = "", y = systolic)) +
geom_boxplot(fill = "blue", color = "black", alpha = 0.7) +
labs(title = "Boxplot of Systolic Blood Pressure-All Patients",
x = "",
y = "Systolic Blood Pressure") +
theme_minimal()
# Display the boxplot
boxplot
# Summarise systolic BP by age group
# Summarise systolic BP by age group -include number of patients
systolic_bp_age_group <- steps_subset %>%
group_by(age_group) %>%
summarise(count = n(),
mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure by age group
systolic_bp_age_group## # A tibble: 12 × 7
## age_group count mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 15-19 217 119. 119 13.0 92.3 167.
## 2 20-24 593 121. 119 12.9 85.3 175
## 3 25-29 688 122. 120. 14.7 80.3 196.
## 4 30-34 666 122. 121 14.4 81.7 200.
## 5 35-39 588 125. 124 16.8 70.7 214
## 6 40-44 459 127. 124 17.8 81.7 219.
## 7 45-49 334 133. 128. 24.2 83 258.
## 8 50-54 285 135. 131. 23.0 83.7 234.
## 9 55-59 256 137. 134. 25.1 86.3 249.
## 10 60-64 226 141. 137 26.9 95.7 264.
## 11 65-69 187 147. 144. 26.3 89.3 229.
## 12 <NA> 1 139 139 NA 139 139# Export the table to a CSV file
write.csv(systolic_bp_age_group, "Steps_sbp_age_all_pts.csv", row.names = FALSE)
# Display the summary of systolic blood pressure by age group as a table
systolic_bp_age_group_table <- kable(systolic_bp_age_group, format = "html", caption = "Summary of Systolic Blood Pressure by Age Group-All patients") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_age_group_table| age_group | count | mean | median | sd | min | max |
|---|---|---|---|---|---|---|
| 15-19 | 217 | 119.1312 | 119.0000 | 12.96394 | 92.33333 | 167.3333 |
| 20-24 | 593 | 120.8713 | 119.0000 | 12.92174 | 85.33333 | 175.0000 |
| 25-29 | 688 | 121.6706 | 119.6667 | 14.65747 | 80.33333 | 196.3333 |
| 30-34 | 666 | 122.2111 | 121.0000 | 14.43230 | 81.66667 | 199.6667 |
| 35-39 | 588 | 124.8330 | 124.0000 | 16.82695 | 70.66667 | 214.0000 |
| 40-44 | 459 | 127.4081 | 124.0000 | 17.78734 | 81.66667 | 218.6667 |
| 45-49 | 334 | 132.9939 | 127.5000 | 24.19028 | 83.00000 | 258.3333 |
| 50-54 | 285 | 134.6450 | 131.3333 | 23.01394 | 83.66667 | 234.3333 |
| 55-59 | 256 | 137.4196 | 134.3333 | 25.14245 | 86.33333 | 249.3333 |
| 60-64 | 226 | 141.3007 | 137.0000 | 26.85366 | 95.66667 | 263.6667 |
| 65-69 | 187 | 146.9604 | 144.3333 | 26.34179 | 89.33333 | 229.3333 |
| NA | 1 | 139.0000 | 139.0000 | NA | 139.00000 | 139.0000 |
7 Generate a histogram of the systolic blood pressure by age group
# Generate a histogram of the systolic blood pressure by age group
histogram_age_group <- ggplot(steps_subset, aes(x = systolic, fill = age_group)) +
geom_histogram(binwidth = 5, color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure by Age Group",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal() +
facet_wrap(~ age_group)
# Display the histogram
histogram_age_group
8 Generate a bar plot of the systolic blood pressure by age group
# Generate a bar plot of the systolic blood pressure by age group
bar_plot_age_group <- ggplot(systolic_bp_age_group, aes(x = age_group, y = mean)) +
geom_bar(stat = "identity", fill = "blue", color = "black", alpha = 0.7) +
labs(title = "Bar Plot of Systolic Blood Pressure by Age Group-All Patients",
x = "Age Group",
y = "Mean Systolic Blood Pressure") +
theme_minimal()
# Display the bar plot
bar_plot_age_group
9 Summarise systolic BP for patients with hypertension
# Generate summary statistics for systolic BP for all patients with hypertension
systolic_bp_hypertension <- steps_subset %>%
filter(htn == 1) %>%
summarise(mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with hypertension
systolic_bp_hypertension## # A tibble: 1 × 5
## mean median sd min max
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 149. 144. 20.8 107 264.# Display the summary of systolic blood pressure for patients with hypertension as a table
systolic_bp_hypertension_table <- kable(systolic_bp_hypertension, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Hypertension") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_hypertension_table| mean | median | sd | min | max |
|---|---|---|---|---|
| 148.9481 | 144.3333 | 20.8193 | 107 | 263.6667 |
10 Generate a histogram of the systolic blood pressure for patients with hypertension
# Generate a histogram of the systolic blood pressure for patients with hypertension
histogram_hypertension <- ggplot(steps_subset %>% filter(htn == 1), aes(x = systolic)) +
geom_histogram(binwidth = 5, fill = "red", color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Hypertension",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal()
# Display the histogram
histogram_hypertension
# Generate a boxplot of the systolic blood pressure for patients with
hypertension
# Generate a boxplot of the systolic blood pressure for patients with hypertension
boxplot_hypertension <- ggplot(steps_subset %>% filter(htn == 1), aes(x = "", y = systolic)) +
geom_boxplot(fill = "red", color = "black", alpha = 0.7) +
labs(title = "Boxplot of Systolic Blood Pressure for Patients with Hypertension",
x = "",
y = "Systolic Blood Pressure") +
theme_minimal()
# Display the boxplot
boxplot_hypertension
# Summarise systolic BP for patients with hypertension by age group-include number of patients
systolic_bp_hypertension <- steps_subset %>%
filter(htn == 1) %>%
group_by(age_group) %>%
summarise(count = n(),
mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with hypertension
systolic_bp_hypertension## # A tibble: 11 × 7
## age_group count mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 15-19 34 137. 133. 12.8 114. 167.
## 2 20-24 88 139. 139. 12.0 108. 175
## 3 25-29 109 143. 141 16.8 116. 196.
## 4 30-34 118 140. 138. 15.9 116. 200.
## 5 35-39 159 143. 141. 16.3 111. 214
## 6 40-44 137 146. 142 17.7 117. 219.
## 7 45-49 139 152. 146. 25.0 111. 258.
## 8 50-54 132 152. 146 20.5 121. 234.
## 9 55-59 125 156. 150. 21.8 120. 249.
## 10 60-64 124 158. 154 24.2 120. 264.
## 11 65-69 123 160. 156 21.5 107 229.# Export the table to a CSV file
write.csv(systolic_bp_hypertension, "Steps_sbp_age_hypertension.csv", row.names = FALSE)
# Display the summary of systolic blood pressure for patients with hypertension as a table
systolic_bp_hypertension_table <- kable(systolic_bp_hypertension, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Hypertension") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_hypertension_table| age_group | count | mean | median | sd | min | max |
|---|---|---|---|---|---|---|
| 15-19 | 34 | 136.7353 | 133.1667 | 12.79409 | 114.3333 | 167.3333 |
| 20-24 | 88 | 139.4713 | 139.3333 | 11.97840 | 108.3333 | 175.0000 |
| 25-29 | 109 | 143.1223 | 141.0000 | 16.78916 | 115.6667 | 196.3333 |
| 30-34 | 118 | 140.4548 | 137.6667 | 15.88537 | 115.6667 | 199.6667 |
| 35-39 | 159 | 143.0764 | 140.6667 | 16.27772 | 111.3333 | 214.0000 |
| 40-44 | 137 | 145.9611 | 142.0000 | 17.69162 | 117.3333 | 218.6667 |
| 45-49 | 139 | 152.1087 | 146.1667 | 25.02392 | 111.3333 | 258.3333 |
| 50-54 | 132 | 151.9389 | 146.0000 | 20.51457 | 121.3333 | 234.3333 |
| 55-59 | 125 | 155.8627 | 150.3333 | 21.82683 | 120.3333 | 249.3333 |
| 60-64 | 124 | 158.3442 | 154.0000 | 24.20506 | 119.6667 | 263.6667 |
| 65-69 | 123 | 160.0054 | 156.0000 | 21.50549 | 107.0000 | 229.3333 |
11 Plot a bar graph of the systolic blood pressure for patients with hypertension by age group
# Plot a bar graph of the systolic blood pressure for patients with hypertension by age group
bar_plot_hypertension <- ggplot(systolic_bp_hypertension, aes(x = age_group, y = mean)) +
geom_bar(stat = "identity", fill = "red", color = "black", alpha = 0.7) +
labs(title = "Bar Plot of Systolic Blood Pressure for Patients with Hypertension by Age Group",
x = "Age Group",
y = "Mean Systolic Blood Pressure") +
theme_minimal()
# Display the bar plot
bar_plot_hypertension
# Generate a histogram of the systolic blood pressure for patients with
hypertension by age group
# Generate a histogram of the systolic blood pressure for patients with hypertension by age group
histogram_hypertension_age_group <- ggplot(steps_subset %>% filter(htn == 1), aes(x = systolic, fill = age_group)) +
geom_histogram(binwidth = 5, color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Hypertension by Age Group",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal() +
facet_wrap(~ age_group)
# Display the histogram
histogram_hypertension_age_group
11.0.1 Generate summary statistics for systolic BP for patients on hypertension treatment
# Generate summary statistics for systolic BP for patients on hypertension treatment
systolic_bp_treatment <- steps_subset %>%
filter(htn == 1 & htn_treatment == 1) %>%
summarise(mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients on hypertension treatment
systolic_bp_treatment## # A tibble: 1 × 5
## mean median sd min max
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 148. 142. 27.0 107 258.# Display the summary of systolic blood pressure for patients on hypertension treatment as a table
systolic_bp_treatment_table <- kable(systolic_bp_treatment, format = "html", caption = "Summary of Systolic Blood Pressure for Patients on Hypertension Treatment") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_treatment_table| mean | median | sd | min | max |
|---|---|---|---|---|
| 148.4195 | 142.1667 | 26.97177 | 107 | 258.3333 |
12 Generate a histogram of the systolic blood pressure for patients on hypertension treatment
# Generate a histogram of the systolic blood pressure for patients on hypertension treatment
histogram_treatment <- ggplot(steps_subset %>% filter(htn == 1 & htn_treatment == 1), aes(x = systolic)) +
geom_histogram(binwidth = 5, fill = "green", color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients on Hypertension Treatment",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal()
# Display the histogram
histogram_treatment
# Generate a boxplot of the systolic blood pressure for patients on
hypertension treatment
# Generate a boxplot of the systolic blood pressure for patients on hypertension treatment
boxplot_treatment <- ggplot(steps_subset %>% filter(htn == 1 & htn_treatment == 1), aes(x = "", y = systolic)) +
geom_boxplot(fill = "green", color = "black", alpha = 0.7) +
labs(title = "Boxplot of Systolic Blood Pressure for Patients on Hypertension Treatment",
x = "",
y = "Systolic Blood Pressure") +
theme_minimal()
# Display the boxplot
boxplot_treatment
# Summarise systolic BP for patients on hypertension treatment by age
group
# Summarise systolic BP for patients on hypertension treatment by age group
systolic_bp_treatment <- steps_subset %>%
filter(htn == 1 & htn_treatment == 1) %>%
group_by(age_group) %>%
summarise(count = n(),
mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients on hypertension treatment
systolic_bp_treatment## # A tibble: 11 × 7
## age_group count mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 15-19 4 129. 124. 17.2 114. 153.
## 2 20-24 2 118 118 13.7 108. 128.
## 3 25-29 1 128. 128. NA 128. 128.
## 4 30-34 3 138. 133. 13.0 129. 153
## 5 35-39 9 142. 135. 23.0 120. 192.
## 6 40-44 10 146. 138. 19.7 126. 181.
## 7 45-49 20 148. 137 38.9 111. 258.
## 8 50-54 11 151. 142. 24.3 121. 208.
## 9 55-59 18 159. 152 30.1 130. 249.
## 10 60-64 18 148. 146. 21.8 120. 186
## 11 65-69 22 152. 148 23.6 107 192.# Export the table to a CSV file
write.csv(systolic_bp_treatment, "Steps_sbp_age_hypertension_treatment.csv", row.names = FALSE)
# Display the summary of systolic blood pressure for patients on hypertension treatment as a table
systolic_bp_treatment_table <- kable(systolic_bp_treatment, format = "html", caption = "Summary of Systolic Blood Pressure for Patients on Hypertension Treatment") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_treatment_table| age_group | count | mean | median | sd | min | max |
|---|---|---|---|---|---|---|
| 15-19 | 4 | 128.6667 | 123.5000 | 17.24121 | 114.3333 | 153.3333 |
| 20-24 | 2 | 118.0000 | 118.0000 | 13.67073 | 108.3333 | 127.6667 |
| 25-29 | 1 | 128.3333 | 128.3333 | NA | 128.3333 | 128.3333 |
| 30-34 | 3 | 138.1111 | 132.6667 | 13.04834 | 128.6667 | 153.0000 |
| 35-39 | 9 | 142.4583 | 134.8333 | 23.04236 | 120.3333 | 191.6667 |
| 40-44 | 10 | 145.7000 | 138.3333 | 19.66287 | 126.3333 | 180.6667 |
| 45-49 | 20 | 147.6140 | 137.0000 | 38.86384 | 111.3333 | 258.3333 |
| 50-54 | 11 | 150.5455 | 142.3333 | 24.25021 | 121.3333 | 207.6667 |
| 55-59 | 18 | 158.8519 | 152.0000 | 30.06990 | 130.3333 | 249.3333 |
| 60-64 | 18 | 147.7778 | 146.1667 | 21.75142 | 119.6667 | 186.0000 |
| 65-69 | 22 | 152.1212 | 148.0000 | 23.64431 | 107.0000 | 191.6667 |
13 Plot a bar graph of the systolic blood pressure for patients on hypertension treatment by age group
# Plot a bar graph of the systolic blood pressure for patients on hypertension treatment by age group
bar_plot_treatment <- ggplot(systolic_bp_treatment, aes(x = age_group, y = mean)) +
geom_bar(stat = "identity", fill = "green", color = "black", alpha = 0.7) +
labs(title = "Bar Plot of Systolic Blood Pressure for Patients on Hypertension Treatment by Age Group",
x = "Age Group",
y = "Mean Systolic Blood Pressure") +
theme_minimal()
# Display the bar plot
bar_plot_treatment
# Generate a histogram of the systolic blood pressure for patients on
hypertension treatment by age group
# Generate a histogram of the systolic blood pressure for patients on hypertension treatment by age group
histogram_treatment_age_group <- ggplot(steps_subset %>% filter(htn == 1 & htn_treatment == 1), aes(x = systolic, fill = age_group)) +
geom_histogram(binwidth = 5, color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients on Hypertension Treatment by Age Group",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal() +
facet_wrap(~ age_group)
# Display the histogram
histogram_treatment_age_group
# Generate a summary of the systolic blood pressure for diabetes
patients
# Generate summary statistics for systolic BP for all patients with diabetes
systolic_bp_diabetes <- steps_subset %>%
filter(diabetes == 1) %>%
summarise(mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with diabetes
systolic_bp_diabetes## # A tibble: 1 × 5
## mean median sd min max
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 140. 134. 26.7 91.3 249.# Display the summary of systolic blood pressure for patients with diabetes as a table
systolic_bp_diabetes_table <- kable(systolic_bp_diabetes, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Diabetes") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_diabetes_table| mean | median | sd | min | max |
|---|---|---|---|---|
| 140.0685 | 133.6667 | 26.6901 | 91.33333 | 249.3333 |
14 Generate a histogram of the systolic blood pressure for patients with diabetes
# Generate a histogram of the systolic blood pressure for patients with diabetes
histogram_diabetes <- ggplot(steps_subset %>% filter(diabetes == 1), aes(x = systolic)) +
geom_histogram(binwidth = 5, fill = "purple", color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Diabetes",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal()
# Display the histogram
histogram_diabetes
# Generate a boxplot of the systolic blood pressure for patients with
diabetes
# Generate a boxplot of the systolic blood pressure for patients with diabetes
boxplot_diabetes <- ggplot(steps_subset %>% filter(diabetes == 1), aes(x = "", y = systolic)) +
geom_boxplot(fill = "purple", color = "black", alpha = 0.7) +
labs(title = "Boxplot of Systolic Blood Pressure for Patients with Diabetes",
x = "",
y = "Systolic Blood Pressure") +
theme_minimal()
# Display the boxplot
boxplot_diabetes
# Summarise systolic BP for patients with diabetes by age group
# Summarise systolic BP for patients with diabetes by age group
systolic_bp_diabetes <- steps_subset %>%
filter(diabetes == 1) %>%
group_by(age_group) %>%
summarise(count = n(),
mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with diabetes
systolic_bp_diabetes## # A tibble: 12 × 7
## age_group count mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 15-19 1 117. 117. NA 117. 117.
## 2 20-24 3 119. 119. 16.0 108 131.
## 3 25-29 10 124. 123. 11.5 110. 151.
## 4 30-34 9 113. 112. 10.1 99 129.
## 5 35-39 13 120. 124. 12.3 91.3 135
## 6 40-44 19 134. 128. 20.1 105. 178.
## 7 45-49 17 142. 132 25.2 115. 211
## 8 50-54 20 150. 145. 25.7 112 209
## 9 55-59 20 157. 153. 35.1 97 249.
## 10 60-64 17 139. 133 25.4 115 219.
## 11 65-69 19 156. 155. 21.5 124. 204
## 12 <NA> 1 139 139 NA 139 139# Export the table to a CSV file
write.csv(systolic_bp_diabetes, "Steps_sbp_age_diabetes.csv", row.names = FALSE)
# Display the summary of systolic blood pressure for patients with diabetes as a table
systolic_bp_diabetes_table <- kable(systolic_bp_diabetes, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Diabetes") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_diabetes_table| age_group | count | mean | median | sd | min | max |
|---|---|---|---|---|---|---|
| 15-19 | 1 | 116.6667 | 116.6667 | NA | 116.66667 | 116.6667 |
| 20-24 | 3 | 119.3333 | 119.3333 | 16.02775 | 108.00000 | 130.6667 |
| 25-29 | 10 | 124.5000 | 122.6667 | 11.46250 | 110.33333 | 151.3333 |
| 30-34 | 9 | 112.9630 | 112.3333 | 10.11111 | 99.00000 | 128.6667 |
| 35-39 | 13 | 120.0513 | 123.6667 | 12.30390 | 91.33333 | 135.0000 |
| 40-44 | 19 | 133.8246 | 128.3333 | 20.13791 | 105.33333 | 178.3333 |
| 45-49 | 17 | 142.1961 | 132.0000 | 25.23722 | 114.66667 | 211.0000 |
| 50-54 | 20 | 150.3833 | 145.1667 | 25.65704 | 112.00000 | 209.0000 |
| 55-59 | 20 | 156.9825 | 152.6667 | 35.14493 | 97.00000 | 249.3333 |
| 60-64 | 17 | 138.5417 | 133.0000 | 25.38879 | 115.00000 | 218.6667 |
| 65-69 | 19 | 156.1228 | 154.6667 | 21.53757 | 123.66667 | 204.0000 |
| NA | 1 | 139.0000 | 139.0000 | NA | 139.00000 | 139.0000 |
15 Plot a bar graph of the systolic blood pressure for patients with diabetes by age group
# Plot a bar graph of the systolic blood pressure for patients with diabetes by age group
bar_plot_diabetes <- ggplot(systolic_bp_diabetes, aes(x = age_group, y = mean)) +
geom_bar(stat = "identity", fill = "purple", color = "black", alpha = 0.7) +
labs(title = "Bar Plot of Systolic Blood Pressure for Patients with Diabetes by Age Group",
x = "Age Group",
y = "Mean Systolic Blood Pressure") +
theme_minimal()
# Display the bar plot
bar_plot_diabetes
# Generate a histogram of the systolic blood pressure for patients with
diabetes by age group
# Generate a histogram of the systolic blood pressure for patients with diabetes by age group
histogram_diabetes_age_group <- ggplot(steps_subset %>% filter(diabetes == 1), aes(x = systolic, fill = age_group)) +
geom_histogram(binwidth = 5, color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Diabetes by Age Group",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal() +
facet_wrap(~ age_group)
# Display the histogram
histogram_diabetes_age_group
# Generate a summary of the systolic blood pressure for diabetes
patients with hypertension
# Generate summary statistics for systolic BP for all patients with diabetes and hypertension
systolic_bp_diabetes_hypertension <- steps_subset %>%
filter(diabetes == 1 & htn == 1) %>%
summarise(mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with diabetes and hypertension
systolic_bp_diabetes_hypertension## # A tibble: 1 × 5
## mean median sd min max
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 155. 150. 25.3 121. 249.# Display the summary of systolic blood pressure for patients with diabetes and hypertension as a table
systolic_bp_diabetes_hypertension_table <- kable(systolic_bp_diabetes_hypertension, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Diabetes and Hypertension") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_diabetes_hypertension_table| mean | median | sd | min | max |
|---|---|---|---|---|
| 155.3049 | 150.3333 | 25.32885 | 120.6667 | 249.3333 |
16 Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension
# Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension
histogram_diabetes_hypertension <- ggplot(steps_subset %>% filter(diabetes == 1 & htn == 1), aes(x = systolic)) +
geom_histogram(binwidth = 5, fill = "orange", color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Diabetes and Hypertension",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal()
# Display the histogram
histogram_diabetes_hypertension
# Generate a boxplot of the systolic blood pressure for patients with
diabetes and hypertension
# Generate a boxplot of the systolic blood pressure for patients with diabetes and hypertension
boxplot_diabetes_hypertension <- ggplot(steps_subset %>% filter(diabetes == 1 & htn == 1), aes(x = "", y = systolic)) +
geom_boxplot(fill = "orange", color = "black", alpha = 0.7) +
labs(title = "Boxplot of Systolic Blood Pressure for Patients with Diabetes and Hypertension",
x = "",
y = "Systolic Blood Pressure") +
theme_minimal()
# Display the boxplot
boxplot_diabetes_hypertension
# Summarise systolic BP for patients with diabetes and hypertension by
age group
# Summarise systolic BP for patients with diabetes and hypertension by age group
systolic_bp_diabetes_hypertension <- steps_subset %>%
filter(diabetes == 1 & htn == 1) %>%
group_by(age_group) %>%
summarise(count = n(),
mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with diabetes and hypertension
systolic_bp_diabetes_hypertension## # A tibble: 10 × 7
## age_group count mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 20-24 1 NaN NA NA Inf -Inf
## 2 25-29 3 135. 133. 15.0 122. 151.
## 3 30-34 1 129. 129. NA 129. 129.
## 4 35-39 2 132. 132. 1.89 131 134.
## 5 40-44 10 146. 148. 19.3 121. 178.
## 6 45-49 8 158. 155. 29.3 124. 211
## 7 50-54 16 157. 149. 23.7 133 209
## 8 55-59 16 167. 158. 28.6 138. 249.
## 9 60-64 9 149. 140. 32.4 122 219.
## 10 65-69 18 158. 156. 21.3 124. 204# Export the table to a CSV file
write.csv(systolic_bp_diabetes_hypertension, "Steps_sbp_age_diabetes_hypertension.csv", row.names = FALSE)
# Display the summary of systolic blood pressure for patients with diabetes and hypertension as a table
systolic_bp_diabetes_hypertension_table <- kable(systolic_bp_diabetes_hypertension, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Diabetes and Hypertension") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_diabetes_hypertension_table| age_group | count | mean | median | sd | min | max |
|---|---|---|---|---|---|---|
| 20-24 | 1 | NaN | NA | NA | Inf | -Inf |
| 25-29 | 3 | 135.2222 | 132.6667 | 14.997531 | 121.6667 | 151.3333 |
| 30-34 | 1 | 128.6667 | 128.6667 | NA | 128.6667 | 128.6667 |
| 35-39 | 2 | 132.3333 | 132.3333 | 1.885618 | 131.0000 | 133.6667 |
| 40-44 | 10 | 146.0667 | 148.5000 | 19.328735 | 120.6667 | 178.3333 |
| 45-49 | 8 | 157.9583 | 154.6667 | 29.261512 | 123.6667 | 211.0000 |
| 50-54 | 16 | 157.1250 | 149.1667 | 23.666471 | 133.0000 | 209.0000 |
| 55-59 | 16 | 166.8750 | 158.3333 | 28.560235 | 137.6667 | 249.3333 |
| 60-64 | 9 | 149.0417 | 139.5000 | 32.413224 | 122.0000 | 218.6667 |
| 65-69 | 18 | 157.5185 | 155.8333 | 21.259438 | 123.6667 | 204.0000 |
17 Plot a bar graph of the systolic blood pressure for patients with diabetes and hypertension by age group
# Plot a bar graph of the systolic blood pressure for patients with diabetes and hypertension by age group
bar_plot_diabetes_hypertension <- ggplot(systolic_bp_diabetes_hypertension, aes(x = age_group, y = mean)) +
geom_bar(stat = "identity", fill = "orange", color = "black", alpha = 0.7) +
labs(title = "Bar Plot of Systolic Blood Pressure for Patients with Diabetes and Hypertension by Age Group",
x = "Age Group",
y = "Mean Systolic Blood Pressure") +
theme_minimal()
# Display the bar plot
bar_plot_diabetes_hypertension
# Generate a histogram of the systolic blood pressure for patients with
diabetes and hypertension by age group
# Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension by age group
histogram_diabetes_hypertension_age_group <- ggplot(steps_subset %>% filter(diabetes == 1 & htn == 1), aes(x = systolic, fill = age_group)) +
geom_histogram(binwidth = 5, color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Diabetes and Hypertension by Age Group",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal() +
facet_wrap(~ age_group)
# Display the histogram
histogram_diabetes_hypertension_age_group
# Generate a summary of the systolic blood pressure for diabetes
patients on hypertension treatment
# Generate summary statistics for systolic BP for all patients with diabetes and hypertension treatment
systolic_bp_diabetes_hypertension_treatment <- steps_subset %>%
filter(diabetes == 1 & htn == 1 & htn_treatment == 1) %>%
summarise(mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with diabetes and hypertension treatment
systolic_bp_diabetes_hypertension_treatment## # A tibble: 1 × 5
## mean median sd min max
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 158. 151. 32.0 122 249.# Display the summary of systolic blood pressure for patients with diabetes and hypertension treatment as a table
systolic_bp_diabetes_hypertension_treatment_table <- kable(systolic_bp_diabetes_hypertension_treatment, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Diabetes and Hypertension Treatment") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_diabetes_hypertension_treatment_table| mean | median | sd | min | max |
|---|---|---|---|---|
| 158.3333 | 151.3333 | 31.96145 | 122 | 249.3333 |
18 Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension treatment
# Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension treatment
histogram_diabetes_hypertension_treatment <- ggplot(steps_subset %>% filter(diabetes == 1 & htn == 1 & htn_treatment == 1), aes(x = systolic)) +
geom_histogram(binwidth = 5, fill = "pink", color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Diabetes and Hypertension Treatment",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal()
# Display the histogram
histogram_diabetes_hypertension_treatment
# Generate a boxplot of the systolic blood pressure for patients with
diabetes and hypertension treatment
# Generate a boxplot of the systolic blood pressure for patients with diabetes and hypertension treatment
boxplot_diabetes_hypertension_treatment <- ggplot(steps_subset %>% filter(diabetes == 1 & htn == 1 & htn_treatment == 1), aes(x = "", y = systolic)) +
geom_boxplot(fill = "pink", color = "black", alpha = 0.7) +
labs(title = "Boxplot of Systolic Blood Pressure for Patients with Diabetes and Hypertension Treatment",
x = "",
y = "Systolic Blood Pressure") +
theme_minimal()
# Display the boxplot
boxplot_diabetes_hypertension_treatment
# Summarise systolic BP for patients with diabetes and hypertension
treatment by age group
# Summarise systolic BP for patients with diabetes and hypertension treatment by age group
systolic_bp_diabetes_hypertension_treatment <- steps_subset %>%
filter(diabetes == 1 & htn == 1 & htn_treatment == 1) %>%
group_by(age_group) %>%
summarise(count = n(),
mean = mean(systolic, na.rm = TRUE),
median = median(systolic, na.rm = TRUE),
sd = sd(systolic, na.rm = TRUE),
min = min(systolic, na.rm = TRUE),
max = max(systolic, na.rm = TRUE))
# Display the summary of systolic blood pressure for patients with diabetes and hypertension treatment
systolic_bp_diabetes_hypertension_treatment## # A tibble: 6 × 7
## age_group count mean median sd min max
## <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 40-44 2 154. 154. 34.6 129. 178.
## 2 45-49 2 154. 154. 43.1 124. 185.
## 3 50-54 3 175. 168. 29.5 150 208.
## 4 55-59 5 177. 153. 46.6 138. 249.
## 5 60-64 3 127. 124. 6.69 122 134.
## 6 65-69 7 154. 161 18.6 124. 175# Export the table to a CSV file
write.csv(systolic_bp_diabetes_hypertension_treatment, "Steps_sbp_age_diabetes_hypertension_treatment.csv", row.names = FALSE)
# Display the summary of systolic blood pressure for patients with diabetes and hypertension treatment as a table
systolic_bp_diabetes_hypertension_treatment_table <- kable(systolic_bp_diabetes_hypertension_treatment, format = "html", caption = "Summary of Systolic Blood Pressure for Patients with Diabetes and Hypertension Treatment") %>%
kable_styling("striped", full_width = F)
# Display the table
systolic_bp_diabetes_hypertension_treatment_table| age_group | count | mean | median | sd | min | max |
|---|---|---|---|---|---|---|
| 40-44 | 2 | 153.8333 | 153.8333 | 34.64823 | 129.3333 | 178.3333 |
| 45-49 | 2 | 154.1667 | 154.1667 | 43.13351 | 123.6667 | 184.6667 |
| 50-54 | 3 | 175.3333 | 168.3333 | 29.46373 | 150.0000 | 207.6667 |
| 55-59 | 5 | 176.8667 | 152.6667 | 46.60150 | 138.3333 | 249.3333 |
| 60-64 | 3 | 126.6667 | 123.6667 | 6.69162 | 122.0000 | 134.3333 |
| 65-69 | 7 | 153.8571 | 161.0000 | 18.57603 | 123.6667 | 175.0000 |
19 Plot a bar graph of the systolic blood pressure for patients with diabetes and hypertension treatment by age group
# Plot a bar graph of the systolic blood pressure for patients with diabetes and hypertension treatment by age group
bar_plot_diabetes_hypertension_treatment <- ggplot(systolic_bp_diabetes_hypertension_treatment, aes(x = age_group, y = mean)) +
geom_bar(stat = "identity", fill = "pink", color = "black", alpha = 0.7) +
labs(title = "Bar Plot of Systolic Blood Pressure for Patients with Diabetes and Hypertension Treatment by Age Group",
x = "Age Group",
y = "Mean Systolic Blood Pressure") +
theme_minimal()
# Display the bar plot
bar_plot_diabetes_hypertension_treatment
# Generate a histogram of the systolic blood pressure for patients with
diabetes and hypertension treatment by age group
# Generate a histogram of the systolic blood pressure for patients with diabetes and hypertension treatment by age group
histogram_diabetes_hypertension_treatment_age_group <- ggplot(steps_subset %>% filter(diabetes == 1 & htn == 1 & htn_treatment == 1), aes(x = systolic, fill = age_group)) +
geom_histogram(binwidth = 5, color = "black", alpha = 0.7) +
labs(title = "Histogram of Systolic Blood Pressure for Patients with Diabetes and Hypertension Treatment by Age Group",
x = "Systolic Blood Pressure",
y = "Frequency") +
theme_minimal() +
facet_wrap(~ age_group)
# Display the histogram
histogram_diabetes_hypertension_treatment_age_group
# Create subsets of the datasets for statistical analysis- Selecting
only id, systolic BP, and age
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -All patients
steps_subset_all <- steps_subset %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_all")
# Save the dataset
write.csv(steps_subset_all, "Steps_subset_all.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients with hypertension
steps_subset_hypertension <- steps_subset %>%
filter(htn == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_hypertension")
# Save the dataset
write.csv(steps_subset_hypertension, "Steps_subset_hypertension.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients with hypertension and hypertension treatment
steps_subset_hypertension_treatment <- steps_subset %>%
filter(htn == 1 & htn_treatment == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_hypertension_treatment")
# Save the dataset
write.csv(steps_subset_hypertension_treatment, "Steps_subset_hypertension_treatment.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients with diabetes
steps_subset_diabetes <- steps_subset %>%
filter(diabetes == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_diabetes")
# Save the dataset
write.csv(steps_subset_diabetes, "Steps_subset_diabetes.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients with diabetes and hypertension
steps_subset_diabetes_hypertension <- steps_subset %>%
filter(diabetes == 1 & htn == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_diabetes_hypertension")
# Save the dataset
write.csv(steps_subset_diabetes_hypertension, "Steps_subset_diabetes_hypertension.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients with diabetes and hypertension treatment
steps_subset_diabetes_hypertension_treatment <- steps_subset %>%
filter(diabetes == 1 & htn == 1 & htn_treatment == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_diabetes_hypertension_treatment")
# Save the dataset
write.csv(steps_subset_diabetes_hypertension_treatment, "Steps_subset_diabetes_hypertension_treatment.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients in rural areas
steps_subset_rural <- steps_subset %>%
filter(stratum == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_rural")
# Save the dataset
write.csv(steps_subset_rural, "Steps_subset_rural.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients in urban areas
steps_subset_urban <- steps_subset %>%
filter(stratum == 2) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_urban")
# Save the dataset
write.csv(steps_subset_urban, "Steps_subset_urban.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients in rural areas with hypertension
steps_subset_rural_hypertension <- steps_subset %>%
filter(stratum == 1 & htn == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_rural_hypertension")
# Save the dataset
write.csv(steps_subset_rural_hypertension, "Steps_subset_rural_hypertension.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients in urban areas with hypertension
steps_subset_urban_hypertension <- steps_subset %>%
filter(stratum == 2 & htn == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_urban_hypertension")
# Save the dataset
write.csv(steps_subset_urban_hypertension, "Steps_subset_urban_hypertension.csv", row.names = FALSE)
# Create subsets of the datasets for statistical analysis- Selecting only id, systolic BP, and age -Patients in rural areas with diabetes
steps_subset_rural_diabetes <- steps_subset %>%
filter(stratum == 1 & diabetes == 1) %>%
select(id, systolic, age, age_group) %>%
mutate(dataset="steps_subset_rural_diabetes")