MedDataSets

Author

Sergio Uribe

UPDATED

November 2, 2024

Anorexia Data on Weight Change

Treat: A factor indicating the treatment group (with 3 possible levels).
Prewt: A numeric value representing the weight of the patient before treatment (in pounds).
Postwt: A numeric value representing the weight of the patient after treatment (in pounds).

Pre-existing Conditions in Children

condition: A factor indicating the pre-existing condition of the children (with 8 possible levels).

Cardiovascular Problems for Two Types of Diabetes Medicines

The Child Health and Development Studies

case: An integer indicating the case number.
bwt: An integer representing the birth weight of the infant (in grams).
gestation: An integer indicating the gestation period (in weeks).
parity: An integer representing the number of previous births.
age: An integer indicating the age of the mother (in years).
height: An integer indicating the height of the mother (in cm).
weight: An integer indicating the weight of the mother (in kg).
smoke: An integer indicating whether the mother smoked during pregnancy (1 = yes, 0 = no).

Rows: 1,236
Columns: 8
$ case      <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1…
$ bwt       <int> 120, 113, 128, 123, 108, 136, 138, 132, 120, 143, 140, 144, …
$ gestation <int> 284, 282, 279, NA, 282, 286, 244, 245, 289, 299, 351, 282, 2…
$ parity    <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
$ age       <int> 27, 33, 28, 36, 23, 25, 33, 23, 25, 30, 27, 32, 23, 36, 30, …
$ height    <int> 62, 64, 64, 69, 67, 62, 62, 65, 62, 66, 68, 64, 63, 61, 63, …
$ weight    <int> 100, 135, 115, 190, 125, 93, 178, 140, 125, 136, 120, 124, 1…
$ smoke     <int> 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, …

Characteristic	exp(Beta)	95% CI¹	p-value
gestation	1.56	1.47, 1.65	<0.001
parity	0.04	0.00, 0.33	0.003
age	0.99	0.84, 1.17	>0.9
height	3.17	2.12, 4.74	<0.001
weight	1.05	1.00, 1.10	0.047
smoke	0.00	0.00, 0.00	<0.001
¹ CI = Confidence Interval

Presence of Bacteria after Drug Treatments

y: A factor indicating the presence (1) or absence (0) of bacteria.
ap: A factor indicating the result of an antibiotic susceptibility test (yes/no).
hilo: A factor indicating a high or low bacterial load (high/low).
week: An integer representing the week of treatment.
ID: A factor representing the unique identifier for each patient (with 50 possible levels).
trt: A factor indicating the treatment group (with 3 possible levels).

Rows: 220
Columns: 6
$ y    <fct> y, y, y, y, y, y, n, y, y, y, y, y, y, y, y, y, y, y, y, y, y, y,…
$ ap   <fct> p, p, p, p, a, a, a, a, a, a, a, a, a, p, p, p, p, p, p, p, p, p,…
$ hilo <fct> hi, hi, hi, hi, hi, hi, hi, hi, lo, lo, lo, lo, lo, lo, lo, lo, l…
$ week <int> 0, 2, 4, 11, 0, 2, 6, 11, 0, 2, 4, 6, 11, 0, 2, 4, 6, 11, 0, 2, 4…
$ ID   <fct> X01, X01, X01, X01, X02, X02, X02, X02, X03, X03, X03, X03, X03, …
$ trt  <fct> placebo, placebo, placebo, placebo, drug+, drug+, drug+, drug+, d…

Pfizer-BioNTech COVID-19 Vaccine Efficacy in Adolescents

group: A factor indicating the group (e.g., vaccinated vs. unvaccinated).
outcome: A factor indicating the outcome (e.g., infection status).

Rows: 2,260
Columns: 2
$ group   <fct> vaccine, vaccine, vaccine, vaccine, vaccine, vaccine, vaccine,…
$ outcome <fct> no COVID-19, no COVID-19, no COVID-19, no COVID-19, no COVID-1…

Risk Factors Associated with Low Infant Birth Weight

low: An integer indicating whether the infant’s birth weight is low (1) or not (0).
age: An integer representing the age of the mother (in years).
lwt: An integer indicating the mother’s weight at last menstrual period (in pounds).
race: An integer indicating the race of the mother (coded as 1, 2, or 3).
smoke: An integer indicating whether the mother smoked during pregnancy (1 for yes, 0 for no).
ptl: An integer indicating the number of premature labors.
ht: An integer indicating whether the mother had a history of hypertension (1 for yes, 0 for no).
ui: An integer indicating whether the mother had a history of uterine irritability (1 for yes, 0 for no).
ftv: An integer indicating the number of physician visits during the first trimester.
bwt: An integer representing the infant’s birth weight (in grams).

Rows: 189
Columns: 10
$ low   <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
$ age   <int> 19, 33, 20, 21, 18, 21, 22, 17, 29, 26, 19, 19, 22, 30, 18, 18, …
$ lwt   <int> 182, 155, 105, 108, 107, 124, 118, 103, 123, 113, 95, 150, 95, 1…
$ race  <int> 2, 3, 1, 1, 1, 3, 1, 3, 1, 1, 3, 3, 3, 3, 1, 1, 2, 1, 3, 1, 3, 1…
$ smoke <int> 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0…
$ ptl   <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0…
$ ht    <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0…
$ ui    <int> 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1…
$ ftv   <int> 0, 3, 1, 2, 0, 0, 1, 1, 1, 0, 0, 1, 0, 2, 0, 0, 0, 3, 0, 1, 2, 3…
$ bwt   <int> 2523, 2551, 2557, 2594, 2600, 2622, 2637, 2637, 2663, 2665, 2722…

Characteristic	exp(Beta)	95% CI¹	p-value
age	1.0	0.98, 1.01	0.4
lwt	1.00	1.00, 1.00	0.064
race	1.08	1.00, 1.16	0.045
smoke	1.18	1.02, 1.35	0.024
ptl	1.12	0.98, 1.29	0.089
ht	1.45	1.11, 1.89	0.007
ui	1.17	0.97, 1.40	0.10
ftv	1.01	0.95, 1.07	0.8
¹ CI = Confidence Interval

Weekly Notified Dengue Cases in Sri Lanka

Cases: Number of dengue cases reported during the week (integer).
Year: Year of the reported cases (integer).
Week: Week of the year (integer).
TEM: Average temperature (numeric).
TMAX: Maximum temperature recorded (numeric).
Tm: Minimum temperature recorded (numeric).
SLP: Sea level pressure (character).
H: Humidity levels (numeric).
PP: Precipitation levels (numeric).
VV: Wind velocity (numeric).
V: Another wind variable (numeric).
VM: Yet another wind variable (numeric).

Rows: 279
Columns: 12
$ Cases <int> 44, 39, 57, 53, 29, 45, 47, 34, 28, 26, 27, 25, 28, 23, 20, 31, …
$ Year  <int> 2009, 2009, 2009, 2009, 2009, 2009, 2009, 2009, 2009, 2009, 2009…
$ Week  <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 1…
$ TEM   <dbl> 27.3000, 26.4000, 27.1400, 26.8000, 26.7750, 26.8500, 26.2400, 2…
$ TMAX  <dbl> 32.7000, 29.7667, 32.0200, 31.0000, 30.0750, 30.5500, 30.9200, 3…
$ Tm    <dbl> 23.6000, 23.9000, 23.5200, 23.3500, 23.6000, 23.0000, 22.1800, 2…
$ SLP   <chr> "1010.7", "1010.7", "1012.58", "1009.9", "1010.1", "1012.05", "1…
$ H     <dbl> 68.0000, 78.6667, 67.0000, 68.0000, 78.0000, 72.5000, 65.2000, 6…
$ PP    <dbl> 0.0000, 0.0000, 0.0000, 0.0000, 17.2100, 0.0000, 0.0000, 0.0000,…
$ VV    <dbl> 13.0000, 18.3333, 20.0000, 20.0000, 18.9750, 20.0000, 20.0000, 1…
$ V     <dbl> 11.1000, 5.8333, 6.1200, 7.1500, 3.2000, 5.5500, 4.7200, 4.5750,…
$ VM    <dbl> 20.6000, 9.2000, 10.4600, 11.1000, 6.8250, 10.3000, 9.2800, 8.37…

San Francisco COVID-19 Hospital Capacity

Rows: 4,514
Columns: 5
$ hospital <chr> "All SF Acute Hospitals", "All SF Acute Hospitals", "All SF A…
$ date     <date> 2020-07-22, 2021-07-18, 2020-07-22, 2021-07-18, 2021-07-18, …
$ bed_type <chr> "Intensive Care Surge", "Intensive Care Surge", "Acute Care S…
$ status   <chr> "Available", "Available", "Available", "Available", "Availabl…
$ count    <int> 309, 298, 406, 487, 247, 123, 15, 148, 0, 31, 1098, 0, 905, 7…

hospital: The name of the hospital (character).
date: The date of the reported data (Date).
bed_type: The type of bed (character), such as ICU, general, etc.
status: The status of the beds (character), indicating if they are occupied, available, etc.
count: The number of beds reported (integer).

Malaria Vaccine Trial

Rows: 20
Columns: 2
$ treatment <fct> vaccine, vaccine, vaccine, vaccine, vaccine, vaccine, vaccin…
$ outcome   <fct> infection, infection, infection, infection, infection, no in…

treatment: A factor indicating the type of treatment administered (e.g., vaccine or placebo).
outcome: A factor indicating the outcome of the treatment (e.g., success or failure).


    Pearson's Chi-squared test with Yates' continuity correction

data:  table(malaria_tbl_df$outcome, malaria_tbl_df$treatment)
X-squared = 4.6561, df = 1, p-value = 0.03094

Sinusitis and Antibiotic Experiment

group: A factor indicating the treatment group (e.g., antibiotic vs. placebo).
self_reported_improvement: A factor indicating the participants’ self-reported improvement (e.g., yes or no).

Rows: 166
Columns: 2
$ group                     <fct> treatment, treatment, treatment, treatment, …
$ self_reported_improvement <fct> yes, yes, yes, yes, yes, yes, yes, yes, yes,…


    Pearson's Chi-squared test with Yates' continuity correction

data:  table(sinusitis_tbl_df$self_reported_improvement, sinusitis_tbl_df$group)
X-squared = 0.048463, df = 1, p-value = 0.8258

The Effect of Vitamin C on Tooth Growth in Guinea Pigs

Rows: 60
Columns: 3
$ len  <dbl> 4.2, 11.5, 7.3, 5.8, 6.4, 10.0, 11.2, 11.2, 5.2, 7.0, 16.5, 16.5,…
$ supp <fct> VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, V…
$ dose <dbl> 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1.0, 1.0, 1.0, …

len: Tooth length (numeric).
supp: Type of supplement: either “VC” (Vitamin C) or “OJ” (Orange Juice) (factor).
dose: Dose of Vitamin C administered in milligrams per day (numeric).

--- title: "MedDataSets" author: "Sergio Uribe" date-modified: last-modified language: title-block-published: "CREATED" title-block-modified: "UPDATED" format: html: toc: true toc-expand: 3 code-fold: true code-tools: true editor: visual execute: echo: false cache: true warning: false message: false --- ```{r} pacman::p_load(MedDataSets, gtsummary, stargazer, tidyverse, ggstats, sjPlot, janitor) ``` ```{r} theme_set(theme_minimal()) ``` # **Anorexia Data on Weight Change** **Treat** : A factor indicating the treatment group (with 3 possible levels). **Prewt** : A numeric value representing the weight of the patient before treatment (in pounds). **Postwt** : A numeric value representing the weight of the patient after treatment (in pounds). ```{r} # Change on weigth anorexia_df |> pivot_longer(Prewt:Postwt, names_to = "Stage", values_to = "Weight") |> # the plot ggplot(aes( x = Treat, y = Weight, color = Stage, fill = Stage )) + geom_violin(width = 1, alpha = 0.2, position = position_dodge(width = 0.9)) + geom_boxplot( width = 0.3, alpha = 0.4, position = position_dodge(width = 0.9), outlier.shape = NA ) + geom_jitter( size = 1.5, alpha = 0.6, position = position_dodge(width = 0.9) ) ``` # **Pre-existing Conditions in Children** **condition** : A factor indicating the pre-existing condition of the children (with 8 possible levels). ```{r} antibiotics_tbl_df |> ggplot(aes(x = fct_rev(fct_infreq(condition)))) + geom_bar() + labs(x = "Condition", y = "Count") + coord_flip() ``` # **Cardiovascular Problems for Two Types of Diabetes Medicines** ```{r} avandia_tbl_df |> ggplot(aes(x = treatment, fill = cardiovascular_problems)) + geom_bar(position = "fill") + scale_y_continuous(labels = scales::percent) ``` # **The Child Health and Development Studies** **case** : An integer indicating the case number. **bwt** : An integer representing the birth weight of the infant (in grams). **gestation** : An integer indicating the gestation period (in weeks). **parity** : An integer representing the number of previous births. **age** : An integer indicating the age of the mother (in years). **height** : An integer indicating the height of the mother (in cm). **weight** : An integer indicating the weight of the mother (in kg). **smoke** : An integer indicating whether the mother smoked during pregnancy (1 = yes, 0 = no). ```{r} glimpse(babies_tbl_df) ``` ```{r} crawling <- glm(bwt ~ gestation + parity + age + height + weight + smoke, data = babies_tbl_df) ``` ```{r} crawling |> gtsummary::tbl_regression(exponentiate = T) ``` ```{r} plot_model(crawling, type = "est", # Plot type for coefficients transform = "exp", # Transform coefficients to odds ratios show.values = TRUE, # Show odds ratio values on the plot value.offset = .3, # Offset for value labels title = "Odds Ratios for Birth Weight Model") + theme_minimal() ``` ```{r} ggstats::ggcoef_model(crawling, exponentiate = TRUE, significance = NULL, colour = NULL) ``` ```{r} ggcoef_table(crawling, exponentiate = TRUE) ``` ```{r} rm(crawling) ``` # **Presence of Bacteria after Drug Treatments** **y** : A factor indicating the presence (1) or absence (0) of bacteria. **ap** : A factor indicating the result of an antibiotic susceptibility test (yes/no). **hilo** : A factor indicating a high or low bacterial load (high/low). **week** : An integer representing the week of treatment. **ID** : A factor representing the unique identifier for each patient (with 50 possible levels). **trt** : A factor indicating the treatment group (with 3 possible levels). ```{r} glimpse(bacteria_df) ``` ```{r} bacteria_df |> group_by(week, trt, y) %>% summarise(count = n(), .groups = "drop") |> # the plot ggplot(aes(x = week, y = count, color = as.factor(y), group = interaction(trt, y))) + geom_line() + facet_wrap(~ trt) + # Create separate panels for each treatment group labs(title = "Count of Presence (Y) by Week and Treatment Group", x = "Week", y = "Count", color = "Presence (Y)") + theme_minimal() + theme(axis.text.x = element_text(angle = 45, hjust = 1)) ``` # **Pfizer-BioNTech COVID-19 Vaccine Efficacy in Adolescents** **group** : A factor indicating the group (e.g., vaccinated vs. unvaccinated). **outcome** : A factor indicating the outcome (e.g., infection status). ```{r} glimpse(biontech_teens_tbl_df) ``` ```{r} biontech_teens_tbl_df |> ggplot(aes(x = group, fill = outcome)) + geom_bar(position = "fill") + # Stacks the bars to show proportions scale_y_continuous(labels = scales::percent) + labs(title = "Proportion of Outcomes by Group", x = "Group", y = "Percentage", fill = "Outcome") + theme_minimal() ``` # **Risk Factors Associated with Low Infant Birth Weight** **low** : An integer indicating whether the infant's birth weight is low (1) or not (0). **age** : An integer representing the age of the mother (in years). **lwt** : An integer indicating the mother's weight at last menstrual period (in pounds). **race** : An integer indicating the race of the mother (coded as 1, 2, or 3). **smoke** : An integer indicating whether the mother smoked during pregnancy (1 for yes, 0 for no). **ptl** : An integer indicating the number of premature labors. **ht** : An integer indicating whether the mother had a history of hypertension (1 for yes, 0 for no). **ui** : An integer indicating whether the mother had a history of uterine irritability (1 for yes, 0 for no). **ftv** : An integer indicating the number of physician visits during the first trimester. **bwt** : An integer representing the infant's birth weight (in grams). ```{r} glimpse(birthwt_df) ``` ```{r} birthwt <- glm(low ~ age + lwt + race + smoke + ptl + ht + ui + ftv, data = birthwt_df) ``` ```{r} birthwt |> gtsummary::tbl_regression(exponentiate = T) ``` ```{r} plot_model(birthwt, type = "est", # Plot type for coefficients transform = "exp", # Transform coefficients to odds ratios show.values = TRUE, # Show odds ratio values on the plot value.offset = .3, # Offset for value labels ) + theme_minimal() ``` # **Weekly Notified Dengue Cases in Sri Lanka** **Cases** : Number of dengue cases reported during the week (integer). **Year** : Year of the reported cases (integer). **Week** : Week of the year (integer). **TEM** : Average temperature (numeric). **TMAX** : Maximum temperature recorded (numeric). **Tm** : Minimum temperature recorded (numeric). **SLP** : Sea level pressure (character). **H** : Humidity levels (numeric). **PP** : Precipitation levels (numeric). **VV** : Wind velocity (numeric). **V** : Another wind variable (numeric). **VM** : Yet another wind variable (numeric). ```{r} glimpse(colmozzie_tbl_df) ``` ```{r} colmozzie_tbl_df |> mutate(date = as.Date(paste(`Year`, `Week`, 1, sep = "-"), format = "%Y-%U-%u")) |> select(date, Cases) |> ggplot(aes(x = date, y = Cases)) + geom_line() ``` # **San Francisco COVID-19 Hospital Capacity** ```{r} glimpse(covid19sf_hospital_df) ``` **hospital** : The name of the hospital (character). **date** : The date of the reported data (Date). **bed_type** : The type of bed (character), such as ICU, general, etc. **status** : The status of the beds (character), indicating if they are occupied, available, etc. **count** : The number of beds reported (integer). ```{r} covid19sf_hospital_df |> ggplot(aes(x = date, y = count, color = status)) + geom_line() + facet_grid(. ~ status ) + # Facet by bed type and hospital labs(title = "Bed Occupancy by Bed Type and Date per Hospital", x = "Date", y = "Number of Beds", color = "Status") + theme_minimal() + theme(axis.text.x = element_text(angle = 45, hjust = 1)) + scale_y_log10() ``` # **Malaria Vaccine Trial** ```{r} glimpse(malaria_tbl_df) ``` **treatment** : A factor indicating the type of treatment administered (e.g., vaccine or placebo). **outcome** : A factor indicating the outcome of the treatment (e.g., success or failure). ```{r} mosaicplot(table(malaria_tbl_df$outcome, malaria_tbl_df$treatment), shade = T) ``` ```{r} chisq.test(table(malaria_tbl_df$outcome, malaria_tbl_df$treatment)) ``` # **Sinusitis and Antibiotic Experiment** **group** : A factor indicating the treatment group (e.g., antibiotic vs. placebo). **self_reported_improvement** : A factor indicating the participants' self-reported improvement (e.g., yes or no). ```{r} glimpse(sinusitis_tbl_df) ``` ```{r} mosaicplot(table(sinusitis_tbl_df$self_reported_improvement, sinusitis_tbl_df$group), shade = T) ``` ```{r} chisq.test(table(sinusitis_tbl_df$self_reported_improvement, sinusitis_tbl_df$group)) ``` # **The Effect of Vitamin C on Tooth Growth in Guinea Pigs** ```{r} glimpse(ToothGrowth_df) ``` **len** : Tooth length (numeric). **supp** : Type of supplement: either "VC" (Vitamin C) or "OJ" (Orange Juice) (factor). **dose** : Dose of Vitamin C administered in milligrams per day (numeric). ```{r} ToothGrowth_df |> ggplot(aes(x = dose, y = len, color = supp, group = supp)) + geom_line() + # Line to show changes in len by dose for each supplement geom_point() + # Points to show actual data points labs(title = "Changes in Tooth Length by Supplement Type and Dose", x = "Dose (mg/day)", y = "Tooth Length", color = "Supplement Type") + theme_minimal() + scale_color_manual(values = c("VC" = "blue", "OJ" = "orange")) ```