Help for package DIVINE

Type:

Package

Title:

Curated Datasets and Tools for Epidemiological Data Analysis

Version:

0.1.0

Maintainer:

Natàlia Pallarès <npallares@igtp.cat>

Description:

Curated datasets and intuitive data management functions to streamline epidemiological data workflows. It is designed to support researchers in quickly accessing clean, structured data and applying essential cleaning, summarizing, visualization, and export operations with minimal effort. Whether you're preparing a cohort for analysis or creating reports, 'DIVINE' makes the process more efficient, transparent, and reproducible.

License:

GPL (≥ 3)

Encoding:

UTF-8

RoxygenNote:

7.3.3

URL:

https://bruigtp.github.io/DIVINE/

BugReports:

https://github.com/bruigtp/DIVINE/issues

Suggests:

knitr, rmarkdown

VignetteBuilder:

knitr

Depends:

R (≥ 4.1)

LazyData:

true

Imports:

dplyr, fmsb, ggplot2, gtsummary, haven, openxlsx, plotly, purrr, rlang, scales, stringr, tibble, tidyselect

NeedsCompilation:

Packaged:

2025-11-06 13:23:26 UTC; jcarmezim

Author:

Natàlia Pallarès [aut, cre], João Carmezim [aut], Pau Satorra [aut], Lucia Blanc [aut], Cristian Tebé [aut]

Repository:

CRAN

Date/Publication:

2025-11-11 10:00:21 UTC

DIVINE's table on laboratory data

Description

Information on laboratory data of patients included in the DIVINE cohort. Data was collected at hospital admission.

Usage

data(analytics)

Format

A data frame with 5813 rows and 9 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
analytics_available:: Is there an analytic available for this patient?
total_leukocytes:: Total leukocytes (mil/mm³)
hemoglobin:: Hemoglobin (g/dl)
total_lymphocytes:: Total lymphocytes (mil/mm³)
d_dimer:: D-dimer (µg/L)
c_reactive_protein:: C-reactive protein (mg/L)

References

Pallarès, N., Tebé, C., Abelenda-Alonso, G., Rombauts, A., Oriol, I., Simonetti, A. F., Rodríguez-Molinero, A., Izquierdo, E., Díaz-Brito, V., Molist, G., Gómez Melis, G., Carratalà, J., Videla, S., & MetroSud and Divine study groups (2023). Characteristics and Outcomes by Ceiling of Care of Subjects Hospitalized with COVID-19 During Four Waves of the Pandemic in a Metropolitan Area: A Multicenter Cohort Study. Infectious diseases and therapy, 12(1), 273–289. https://doi.org/10.1007/s40121-022-00705-w

DIVINE's table on information about comorbidities

Description

Information about comorbidities of patients included in the DIVINE cohort. Data was collected at hospital admission.

Usage

data(comorbidities)

Format

A data frame with 5813 rows and 37 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
sociofunctional:: A factor with levels ⁠Lives with a spouse of similar age⁠, ⁠Lives with a spouse with some degree of dependency⁠, ⁠Lives with a non-family caregiver⁠, ⁠Lives with family. The caregiver is not their spouse⁠, ⁠Lives with family without physical dependency⁠, ⁠Lives alone and has no children or they are far away⁠, ⁠Lives alone and has nearby children⁠. Sociofunctional status
frailty:: A factor with levels No, PCC and MACA. Is the patient a chronic complex patient (PCC) or a patient with advanced chronic disease (MACA)?
barthel_score:: Punctuation in the Barthel scale used to measure performance in activities of daily living
weight:: Weight (kg)
height:: Height (cm)
body_mass_index:: Body mass index computed as \frac{\mbox{weight (kg)}}{\mbox{height (m)}^2}
dm:: A factor with levels No and Yes. Diabetes mellitus Type 2
type_dm:: A factor with levels ⁠With target organ involvement⁠ and ⁠Without complications⁠. For patients with diabetes mellitus type 2, type of disease
chronic_lung_disease:: A factor with levels No and Yes. Chronic lung disease (including COPD, asthma and obstructive sleep apnea, among others)
chronic_kidney_disease:: A factor with levels No and Yes. Severe chronic kidney disease
mild_kidney_disease:: A factor with levels No and Yes. Mild kidney disease
renal_therapy:: A factor with levels No and Yes. Is the patient currently receiving renal replacement therapy?
heart_disease:: A factor with levels No and Yes. Heart failure
coronary_disease:: A factor with levels No and Yes. Coronary heart disease
myocardial_infarction:: A factor with levels No and Yes. Has the patient ever had a heart attack?
hematologic_neo:: A factor with levels No and Yes. Haematological neoplasia
hematologic_neo_type:: A factor with levels Leukemia, Lymphoma and Myeloma. For patients with Haematological neoplasia, type of disease.
non_metastatic_neo:: A factor with levels No and Yes. Non-Metastatic Neoplasia
metastatic_neo:: A factor with levels No and Yes. Metastatic Neoplasia
stroke_tia:: A factor with levels No and Yes. Has the patient ever had a stroke or a transient ischemic attack?
peripheral_vasculopathy:: A factor with levels No and Yes. Peripheral artery disease
dementia:: A factor with levels No and Yes. Dementia
mild_liver_disease:: A factor with levels No and Yes. Mild liver disease
severe_liver_disease:: A factor with levels No and Yes. Severe liver disease
connective_tissue_disease:: A factor with levels No and Yes. Connective tissue disease
peptic_ulcer:: A factor with levels No and Yes. Peptic ulcer
hemiplegia:: A factor with levels No and Yes. Hemiplegia
hiv:: A factor with levels No and Yes. Human immunodeficiency virus
charlson_index:: Value of the Charlson Comorbidity Index. This index predicts the ten-year mortality for a patient given the information of their comorbid conditions
hypertension:: A factor with levels No and Yes. Hypertension
dyslipidemia:: A factor with levels No and Yes. Dyslipidemia
depression:: A factor with levels No and Yes. Depression
ceiling:: A factor with levels ⁠Oxygen mask⁠ (non-rebreather oxygen mask), ⁠HFNC or NIMV⁠ (high-flow nasal cannula or non-invasive mechanical ventilation) and ⁠IMV and ICU admission⁠ (invasive mechanical ventilation and acces to intensive care unit). Therapeutic ceiling of care assigned to the patient
ceiling_dico:: A factor with the dichotomization of the variable ceiling in two levels No (⁠IMV and ICU admission⁠) and Yes (⁠Oxygen mask⁠ and ⁠HFNC or NIMV⁠)

References

DIVINE's table on complications data

Description

Information on complications data of patients included in the DIVINE cohort. Data was collected during hospitalization.

Usage

data(complications)

Format

A data frame with 5813 rows and 9 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
comp:: A factor with levels No and Yes. Did the patient experiment a complication while hospitalised?
kidney_failure:: A factor with levels No and Yes. Did the patient experiment kidney failure during hospital admission?
mental_status_change:: A factor with levels No and Yes. Did the patient experiment a change in its mental status during hospital admission?
nosocomial_infection:: A factor with levels No and Yes. Did the patient experiment a nosocomial infection during hospital admission?
comp_cardiac:: A factor with levels No and Yes. Did the patient experiment a cardiac complication during hospital admission? Cardiac complications included heart failure and acute coronary event.
comp_respiratory:: A factor with levels No and Yes. Did the patient experiment a respiratory complication during hospital admission? Respiratory complications included acute respiratory failure, venous thromboembolism, and pneumonia.

References

DIVINE's table on treatments previous to hospital admission

Description

Information on previous treatments for patients included in the DIVINE cohort. Data was collected at hospital admission.

Usage

data(concomitant_medication)

Format

A data frame with 5813 rows and 11 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
statins_pre:: A factor with levels No and Yes. Previous treatment with statins
cortis_pre:: A factor with levels No and Yes. Previous treatment with corticosteroids
acei_pre:: A factor with levels No and Yes. Previous treatment with angiotensin-converting enzyme (ACE) inhibitors
ara2_pre:: A factor with levels No and Yes. Previous treatment with angiotensin II receptor antagonists (ARA-II)
cortis_systemic_pre:: A factor with levels No and Yes. Routine treatment with systemic corticosteroids
cortis_inhaled_pre:: A factor with levels No and Yes. Routine treatment with inhaled corticosteroids
anticoagulants_pre:: A factor with levels No and Yes. Previous treatment with anticoagulants
immunosuppre_pre:: A factor with levels No and Yes. Previous treatment with immunosuppressants

References

Data Overview Function

Description

This function provides a comprehensive overview of a data frame, including its dimensions, variable types, missing values count and a preview of the first few rows.

Usage

data_overview(data, preview_rows = 6)

Arguments

data

A data frame. The dataset for which you want an overview.

preview_rows

Integer. The number of rows to display in the preview. Default is 6.

Details

The function is useful for quickly inspecting the structure of a data frame and identifying any missing values or general characteristics of the data. It also allows users to customize how many rows they want to preview from the dataset.

Value

A list containing the following components:

dimensions

A vector of two elements: the number of rows and columns in the data.

variable_types

A named vector with the class of each variable (column) in the data.

missing_values

A named vector with the count of missing values (NA) for each variable.

preview

A data frame showing the first preview_rows rows of the dataset.

Examples

# Example usage with a simple data frame
data <- data.frame(
  Age = c(25, 30, NA, 22, 35),
  Height = c(175, 160, 180, NA, 165),
  Gender = c("Male", "Female", "Female", "Male", "Male")
)
overview <- data_overview(data, preview_rows = 4)
print(overview)

# Example usage with the default preview size (6 rows)
overview_default <- data_overview(data)
print(overview_default)

DIVINE's demographic table

Description

Demographic data of patients included in the DIVINE cohort. Data was collected at hospital admission.

Usage

data(demographic)

Format

A data frame with 5813 rows and 8 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
sex:: A factor with levels Male and Female. Sex at birth
age:: Age at hospital admission
smoker:: A factor with levels Ex-smoker, No and Yes. Smoking status
alcohol:: A factor with levels No and Yes. Consumption of alcohol
residence_center:: A factor with levels No and Yes. Is the patient currently living in a long-term facility?

References

DIVINE's table on closure data

Description

Information on closure data of patients included in the DIVINE cohort. Data was collected at the end of hospitalization.

Usage

data(end_followup)

Format

A data frame with 5813 rows and 8 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
clinical_stability_days:: Days from hospital admission to clinical stability
exitus_days:: Days from hospital admission to exitus
discharge_days:: Days from hospital admission to discharge
discharge:: A factor with levels No and Yes. Was the patient discharge from the hospital?
exitus:: A factor with levels No and Yes. Did the patient die during hospital admission?

References

Export Data to Various Formats

Description

Export a dataframe or tibble to multiple file formats. If format is NULL (default), the format will be inferred from the file extension of path. If format is provided and the extension in path does not match, the function will update the path to use the extension that corresponds to format and warn the user.

Usage

export_data(data = NULL, path = NULL, format = NULL)

Arguments

data

A dataframe or tibble to export.

path

A character string specifying the file path for the exported file.

format

Optional character string specifying the export format. Supported formats: "xlsx", "csv", "rds", "txt", "sav", "dta", "sas7bdat" (alias "xpt"). If NULL (default), the function infers the format from the path extension.

Details

Supported formats and their functionality are provided via the package dependencies:

xlsx: Uses openxlsx for Excel exports.
csv: Base R functionality.
rds: Base R functionality.
txt: Base R functionality with tab-separated values.
sav: Uses haven for SPSS exports.
dta: Uses haven for Stata exports.
sas7bdat: Uses haven for SAS exports.

Value

This function does not return a value. It writes the data to the specified file path and displays a success message upon completion.

Examples

## Not run: 
df <- data.frame(Name = c("Alice", "Bob"), Age = c(25, 30))

# Infer format from path extension (no format argument)
export_data(df, path = "example.xlsx")
export_data(df, path = "example.csv")

# Explicit format (function will ensure path extension matches)
export_data(df, format = "csv", path = "example")         # adds .csv
export_data(df, format = "rds", path = "example.rds")

## End(Not run)

DIVINE's table on icu data

Description

Information on ICU data of patients included in the DIVINE cohort. Data was collected during hospitalization.

Usage

data(icu)

Format

A data frame with 5813 rows and 12 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
icu:: A factor with levels No and Yes. Was the patient admitted to the ICU?
icu_enter_days:: Days from hospital admission to ICU admission.
icu_exit_days:: Days from hospital admission to ICU discharge.
vent_mec:: A factor with levels No and Yes. Did the patient received invasive mechanical ventilation?
vent_mec_start_days:: Days from hospital admission to start of invasive mechanical ventilation.
vent_mec_end_days:: Days from hospital admission to end of invasive mechanical ventilation.
vent_mec_no_inv:: A factor with levels No and Yes. Did the patient received non-invasive mechanical ventilation?
vent_mec_no_inv_start_days:: Days from hospital admission to start of non-invasive mechanical ventilation.
vent_mec_no_inv_end_days:: Days from hospital admission to end of non-invasive mechanical ventilation.

References

Replace Missing Values

Description

Replace missing values (NA) in a data.frame with a specified value or method (such as mean, median, mode, constant, or custom function), applying imputation column-wise.

Usage

impute_missing(
  data,
  method = list(dplyr::where(is.numeric) ~ "mean", dplyr::where(is.character) ~ "mode",
    dplyr::where(is.factor) ~ "mode"),
  filter_by = NULL,
  drop_all_na = FALSE,
  verbose = TRUE
)

Arguments

data

A data frame. The dataset in which missing values should be imputed.

method

A list of one-sided formulas of the form ⁠<selector> ~ <value>⁠. Supported ⁠<value>⁠ options are:

"mean": replace with the column mean (numeric columns only).
"median": replace with the column median (numeric columns only).
"mode": replace with the most frequent value (works for numeric, character, or factor).
A numeric constant: replace with that constant (numeric columns).
A character constant: replace with that value (character/factor columns).
A function: a function ⁠function(col)⁠ that receives the column and returns a single value to be used as replacement for NA.

The default is list(dplyr::where(is.numeric) ~ "mean",dplyr::where(is.character) ~ "mode",dplyr::where(is.factor) ~ "mode").

filter_by

Character vector of column names. If provided, only rows that have all specified columns non-NA are kept (applied before imputation).

drop_all_na

Logical; if TRUE, rows where all columns are NA are removed before imputation.

verbose

Logical; if TRUE (default) print a concise final summary of what was imputed. Set to FALSE to suppress messages.

Details

You can remove rows that are entirely NA before imputation using drop_all_na, or filter rows based on specific variables using filter_by.

The method argument uses tidyselect helpers. For example, where(is.numeric()) ~ "median" imputes all numeric columns by their medians.
"mode" works for numeric, character and factor columns.
When imputing factors with a character constant, the constant is added as a new level if needed.
When passing a custom function, it should return at least one value; if multiple values are returned, only the first is used (with a warning).

Value

A tibble with missing values replaced according to the provided specifications.

Examples

# Impute all numeric columns by their means:
impute_missing(icu)

# Impute numeric columns by median:
impute_missing(
  icu,
  method = list(where(is.numeric) ~ "median")
)

# Keep only rows where both "vent_mec_no_inv" and "vent_mec" are non-missing:
impute_missing(
  icu,
  filter_by = c("vent_mec_no_inv", "vent_mec")
)

DIVINE's table on antibiotics received during hospitalization

Description

Information on antibiotics received for patients included in the DIVINE cohort. Data was collected during hospitalization.

Usage

data(inhosp_antibiotics)

Format

A data frame with 5813 rows and 17 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
any_antibiotic:: A factor with levels No and Yes. Did the patient receive treatment with antibiotics during hospital admission?
amoxicillin:: A factor with levels No and Yes. Treatment with amoxicillin
amoxicillin_clavulanic_acid:: A factor with levels No and Yes. Treatment with amoxicillin and clavulanic acid
azithromycin:: A factor with levels No and Yes. Treatment with azithromycin
ceftriaxone:: A factor with levels No and Yes. Treatment with ceftriaxone
ciprofloxacin:: A factor with levels No and Yes. Treatment with ciprofloxacin
cotrimoxazole:: A factor with levels No and Yes. Treatment with cotrimoxazole
levofloxacin:: A factor with levels No and Yes. Treatment with levofloxacin
linezolid:: A factor with levels No and Yes. Treatment with linezolid
meropenem:: A factor with levels No and Yes. Treatment with meropenem
piperacillin:: A factor with levels No and Yes. Treatment with piperacillin
piperacillin_tazobactam:: A factor with levels No and Yes. Treatment with piperacillin+tazobactam
teicoplanin:: A factor with levels No and Yes. Treatment with teicoplanin
other_antibiotic:: A factor with levels No and Yes. Treatment with another antibiotic

References

DIVINE's table on antivirals received during hospitalization

Description

Information on antivirals for patients included in the DIVINE cohort. Data was collected during hospitalization.

Usage

data(inhosp_antivirals)

Format

A data frame with 5813 rows and 10 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
any_antiviral:: A factor with levels No and Yes. Did the patient receive treatment with antivirals during hospital admission?
hydroxychloroquine:: A factor with levels No and Yes. Treatment with hydroxychloroquine
interferon_b:: A factor with levels No and Yes. Treatment with interferon beta
kaletra_ritonavir_lopinavir:: A factor with levels No and Yes. Treatment with kaletra/ritonavir-lopinavir
remdesivir:: A factor with levels No and Yes. Treatment with remdesivir
tocilizumab:: A factor with levels No and Yes. Treatment with tocilizumab
other_antiviral:: A factor with levels No and Yes. Treatment with another antiviral

References

DIVINE's table on other treatments received during hospitalization.

Description

Information on other treatments for patients included in the DIVINE cohort. Data was collected during hospitalization.

Usage

data(inhosp_other_treatments)

Format

A data frame with 5813 rows and 6 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
corticosteroids:: A factor with levels No and Yes. Treatment with corticosteroids
lmwh:: A factor with levels No and Yes. Treatment with low-molecular-weight heparin (LMWH)
oral_anticoagulants:: A factor with levels No and Yes. Treatment with oral anticoagulants

References

Multi-Dataset Join Utility

Description

This function performs a sequential join of multiple datasets by a specified key column.

Usage

multi_join(
  datasets,
  key = c("record_id", "covid_wave", "center"),
  join_type = "left"
)

Arguments

datasets

A list of data frames to be joined.

key

A character string representing the key column to join by. Defaults to "record_id".

join_type

A character string specifying the type of join. Options are "left", "right", "inner", or "full".

Value

A single data frame containing the joined datasets.

Examples

multi_join(
  list(analytics, comorbidities),
  join_type = "left"
)

multi_join(
  list(analytics, comorbidities),
  key = c("record_id", "covid_wave", "center"),
  join_type = "left"
)

multi_plot: Flexible Static or Interactive Plotting of Variables

Description

Generate a variety of plots—histogram, density, boxplot, barplot, violin, scatter, heatmap, or spider (radar)—either as static ggplot2 objects or interactive Plotly widgets.

Usage

multi_plot(
  data,
  x_var = NULL,
  y_var = NULL,
  plot_type = NULL,
  interactive = FALSE,
  fill_color = "steelblue",
  color = "black",
  bin_width = NULL,
  group = NULL,
  facet_var = NULL,
  z_var = NULL,
  radar_color = "steelblue",
  radar_vlabels = NULL,
  radar_vlcex = 1,
  radar_ref_lev = "Yes",
  title = NULL,
  x_lab = NULL,
  y_lab = NULL,
  legend_position = "right",
  axis_text_angle = 0,
  axis_text_size = 12,
  title_size = 14,
  theme_custom = ggplot2::theme_minimal()
)

Arguments

data

A data frame or tibble containing your data.

x_var

Character; name of the variable for x‑axis (required for all plot types except spider).

y_var

Character; name of the variable for y‑axis (required for boxplot, violin, scatter, and heatmap).

plot_type

Character; one of "histogram", "density", "boxplot", "barplot", "violin", "scatter", "heatmap", or "spider".

interactive

Logical; if TRUE, returns a Plotly interactive plot (not available for spider/radar charts). Default: FALSE.

fill_color

Character; fill color for non‑grouped geoms (default "steelblue").

color

Character; outline/line color (default "black").

bin_width

Numeric; bin width for histograms. If NULL, computed automatically.

group

Character; name of grouping variable (optional).

facet_var

Character; name of variable to facet by (optional).

z_var

Character vector; names of numeric variables for spider plot (only for "spider").

radar_color

Character or vector; border/fill color for spider chart (only for "spider").

radar_vlabels

Character or vector; names of the variables for spider chart (only for "spider").

radar_vlcex

Numeric; font size for variable labels in the spider chart (only for "spider").

radar_ref_lev

Character; reference level for factors included in the spider chart (only for "spider").

title

Character; plot title (optional).

x_lab

Character; x‑axis label (defaults to x_var).

y_lab

Character; y‑axis label (defaults to y_var or "Count").

legend_position

Character; one of "right","left","top","bottom","none" (default "right").

axis_text_angle

Numeric; rotation angle (degrees) for x‑axis tick labels (default 0).

axis_text_size

Numeric; size of axis text in pts (default 12).

title_size

Numeric; size of plot title text in pts (default 14).

theme_custom

A ggplot2 theme object (default theme_minimal()).

Details

Histogram: requires x_var; uses geom_histogram(). Use for continuous numeric variables only.
Density: requires x_var; uses geom_density(). It should be numeric.
Boxplot/Violin: require both x_var and y_var; automatically groups by x_var or by group if provided, with dynamic dodge width.
Barplot: requires x_var; counts occurrences. Use for categorical variables only.
Scatter: requires both x_var and y_var; uses geom_point(). Both variables must be numeric.
Heatmap: requires both x_var and y_var. Both variables must be categorical.
Spider: requires z_var (vector of variables); uses fmsb::radarchart(), static only.

Value

A ggplot object (if interactive = FALSE or plot_type = "spider") or a plotly object (if interactive = TRUE).

Examples


multi_plot(icu,
  x_var = "icu_enter_days",
  y_var = "vent_mec_start_days",
  plot_type = "scatter",
  color = "darkred",
  title = "ICU exit vs MV days"
)

multi_plot(
  comorbidities,
  x_var = "hypertension",
  y_var = "dyslipidemia",
  plot_type = "spider",
  z_var = c(
    "depression", "mild_kidney_disease", "ceiling_dico"
  ),
  radar_vlabels = stringr::str_to_sentence(
    c("hypertension", "dyslipidemia", "depression", "mild_kidney_disease", "ceiling_dico")
  ),
  radar_color = "steelblue",
  radar_ref_lev = "Yes"
)

DIVINE's table on severity scores at hospital admission

Description

Information on severity scores at hospital admission for patients included in the DIVINE cohort. Data was collected at hospital admission.

Usage

data(scores)

Format

A data frame with 5813 rows and 10 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
psi:: Pneumonia severity index (PSI) at hospital admission
group_psi:: A factor with levels 1, 2, 3, and 4. PSI group
curb65:: CURB65 score at hospital admission
group_curb65:: A factor with levels 1, 2, and 3. CURB65 group
mulbsta:: MULBSTA score at hospital admission
group_mulbsta:: A factor with levels Low-risk and High-risk. MULBSTA group
rox_index:: ROX index at hospital admission

References

Create Summary Table

Description

This function generates a summary table using the gtsummary package. It allows customization of the reported statistics for continuous variables and categorical variables. Users can optionally include p-values for group comparisons and manage the reporting of missing values.

Usage

stats_table(
  data,
  vars = NULL,
  var_labels = NULL,
  by = NULL,
  statistic_type = "mean_sd",
  pvalue = FALSE,
  test_method = NULL,
  include_na = TRUE
)

Arguments

data

A data frame containing the dataset.

vars

A character vector of variable names to include in the summary. If NULL (default), all variables are included.

var_labels

A list of labels to replace variable names in the table.

by

A character string specifying a grouping variable. If NULL (default), no grouping is applied.

statistic_type

A character string specifying the type of statistic to report for continuous variables. Options are:

"mean_sd": Mean (SD) for continuous variables.
"median_iqr": Median (Q1; Q3) for continuous variables.
"both": Both Mean (SD) and Median (Q1; Q3).

pvalue

A logical value indicating whether to include p-values in the summary. Defaults to FALSE.

test_method

Optional. Only used if pvalue = TRUE. A list specifying custom statistical tests for each variable. If NULL, gtsummary will choose default tests based on variable type.

include_na

A logical value indicating whether to include rows with missing values in the output. Defaults to TRUE.

Value

A gtsummary table object.

Examples

# Mean ± SD summary
stats_table(
  vital_signs,
  vars = c("temperature", "saturation"),
  by = "supporto2",
  statistic_type = "mean_sd"
)

# Both mean ± SD and median [Q1; Q3]
stats_table(
 vital_signs,
 statistic_type = "both",
 include_na = FALSE
)

# Add p-value with default tests
stats_table(
 vital_signs,
 vars = c("temperature", "saturation"),
 by = "supporto2",
 pvalue = TRUE
)

# Add p-value and define method
stats_table(
 vital_signs,
 vars = c("temperature", "saturation"),
 by = "supporto2",
 pvalue = TRUE,
 test_method = list(temperature ~ "t.test")
)

DIVINE's symptoms table

Description

Information on COVID-19 associated symptoms of patients included in the DIVINE cohort. Data was collected at hospital admission.

Usage

data(symptoms)

Format

A data frame with 5813 rows and 24 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
symptoms_days:: Days from symptoms onset to hospitalization
rhinorrhea:: A factor with levels No and Yes. Rhinorrhea
anosmia:: A factor with levels No and Yes. Anosmia
ageusia:: A factor with levels No and Yes. Ageusia
arthromyalgia:: A factor with levels No and Yes. Arthromyalgia
odynophagia:: A factor with levels No and Yes. Odynophagia
fever:: A factor with levels No and Yes. Fever
cough:: A factor with levels No and Yes. Cough
dyspnea:: A factor with levels No and Yes. Dyspnoea
expectoration:: A factor with levels No and Yes. Expectoration
diarrhea:: A factor with levels No and Yes. Diarrhea
vomit:: A factor with levels No and Yes. Vomiting
nausea:: A factor with levels No and Yes. Nausea
asthenia:: A factor with levels No and Yes. Asthenia
anorexia:: A factor with levels No and Yes. Anorexia
cephal:: A factor with levels No and Yes. Headache
chest_pain:: A factor with levels No and Yes. Chest pain
abdominal_pain:: A factor with levels No and Yes. Abdominal pain
confusional_syndrome:: A factor with levels No and Yes. Confusional syndrome
shock_admission:: A factor with levels No and Yes. Shock on admission
bacterial_infection:: A factor with levels No and Yes. Bacterial infection

References

DIVINE's vaccine table

Description

Information on COVID-19 vaccines of patients included in the DIVINE cohort. Data was collected at hospital admission and it is available for waves 3 and 5 (patients were not yet vaccinated in waves 1 and 2).

Usage

data(vaccine)

Format

A data frame with 5813 rows and 6 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
vaccine:: A factor with levels No, Yes and ⁠Not applicable⁠ (for patients included in waves before vaccination started). Is the patient vaccinated for COVID-19?
complete_vaccine:: A factor with levels No, Partial, Complete and ⁠Not applicable⁠ (for patients included in waves before vaccination started). Is the patient partially vaccinated (one dose of two-dose vaccines), completely vaccinated (one dose for one-dose vaccines or two doses for two-dose vaccines) or not vaccinated at all?
immune_vaccine:: A factor with levels ⁠No immunity⁠, ⁠Partial immunity⁠, ⁠Total immunity⁠ and ⁠Not applicable⁠ (for patients included in waves before vaccination started). Defines the level of immunity of the patient: not vaccinated (⁠No immunity⁠), vaccinated with only one dose for two-dose vaccines (⁠Partial immunity⁠), vaccinated with two doses but less than 7 days have passed since the second dose (⁠Partial immunity⁠) or vaccinated with all the doses and more than 7 days have passed since the second dose (⁠Total immunity⁠)

References

DIVINE's table on vital signs

Description

Information on vital signs of patients included in the DIVINE cohort. Data was collected at hospital admission.

Usage

data(vital_signs)

Format

A data frame with 5813 rows and 13 columns

record_id:: Identifier of each record. This information does not match the real data.
covid_wave:: A factor with levels ⁠Wave 1⁠, ⁠Wave 2⁠, ⁠Wave 3⁠, and ⁠Wave 5⁠. COVID-19 wave.
center:: A factor with levels ⁠Hospital A⁠, ⁠Hospital B⁠, ⁠Hospital C⁠, ⁠Hospital D⁠, and ⁠Hospital E⁠. Center of admission
temperature:: Human body temperature (ºC)
fio2_contributed:: Fraction of inspired oxygen (%)
syst_blood_press:: Systolic blood pressure (mmHg)
diast_blood_press:: Diastolic blood pressure (mmHg)
saturation:: Oxygen saturation (%)
cardiac_freq:: Heart rate (bpm)
supporto2:: A factor with levels No and Yes. Oxygen Support
normal_radio:: A factor with levels No and Yes. Normal X-ray
pleural_effusion:: A factor with levels No and Yes. Pleural effusion
saturation_fio2:: Oxygen Saturation to FiO2 Ratio