Package {nhscancerwaits}

Type:	Package
Title:	NHS Cancer Waiting-Time Analysis, Benchmarking and Multilevel Modelling
Version:	1.0.2
Description:	Provides tools for importing, harmonising, cleaning, analysing, benchmarking and visualising National Health Service (NHS) England Cancer Waiting Times data. The package supports national performance monitoring, provider-level benchmarking and cancer pathway comparisons through key performance indicator summaries, provider filtering, clustering analyses, mixed-effects regression models, variance decomposition, intraclass correlation coefficient estimation, adjusted provider performance estimation and sensitivity analyses. Functions are included for exploratory analysis, publication-ready visualisations and spreadsheet exports, supporting reproducible health services research, cancer services evaluation, quality improvement and assessment of waiting-time performance across healthcare organisations. Mixed-effects modelling functionality is based on Bates et al. (2015) <doi:10.18637/jss.v067.i01>. Multilevel modelling concepts and variance decomposition follow Gelman and Hill (2007, ISBN:9780521686891). Cancer Waiting Times definitions and reporting standards follow NHS England https://www.england.nhs.uk/statistics/statistical-work-areas/cancer-waiting-times/.
License:	MIT + file LICENSE
Encoding:	UTF-8
Language:	en-GB
RoxygenNote:	7.3.3
Depends:	R (≥ 4.2.0)
Imports:	dplyr, tidyr, readr, readxl, stringr, lubridate, rlang, ggplot2, scales, lme4, broom.mixed, performance, cluster, stats, writexl
Suggests:	testthat (≥ 3.0.0), knitr, rmarkdown, quarto, covr
VignetteBuilder:	knitr
Config/testthat/edition:	3
URL:	https://github.com/zerish12/nhscancerwaits
BugReports:	https://github.com/zerish12/nhscancerwaits/issues
NeedsCompilation:	no
Packaged:	2026-06-12 13:55:47 UTC; muhammadzahirkhan
Author:	Muhammad Zahir Khan [aut, cre]
Maintainer:	Muhammad Zahir Khan <zahirstat007@gmail.com>
Repository:	CRAN
Date/Publication:	2026-06-19 12:00:14 UTC

Calculate Intraclass Correlation Coefficient

Description

Calculates the intraclass correlation coefficient from a fitted mixed-effects model.

Usage

calculate_icc(model)

Arguments

Value

A data frame with provider variance, residual variance, total variance and ICC.

Calculate Provider Clustering Silhouette Score

Description

Calculates the average silhouette score for provider clusters.

Usage

calculate_silhouette_score(clustered_data)

Arguments

Value

Average silhouette score.

Check Mixed-Model Performance Diagnostics

Description

Returns standard model diagnostics using the performance package.

Usage

check_cwt_model(model)

Arguments

Value

A model diagnostic object.

Clean NHS Cancer Waiting-Time Data

Description

Standardises column names, provider fields, reporting dates, performance values and activity denominators.

Usage

clean_cwt_data(data)

Arguments

Value

A cleaned data frame.

Cluster Providers by Performance and Activity

Description

Groups providers into performance clusters using provider-level summaries.

Usage

cluster_providers(
  data,
  provider_var = "provider_code",
  performance_var = "performance_percent",
  activity_var = "total_treated",
  k = 3
)

Arguments

Value

A data frame containing provider summaries and cluster labels.

Export Analysis Tables to Excel

Description

Exports one or more analysis tables to an Excel workbook.

Usage

export_excel_tables(tables, path = "nhscancerwaits_outputs.xlsx")

Arguments

Value

The output file path, invisibly.

Export Provider Rankings to Excel

Description

Exports adjusted provider effects or provider ranking tables to Excel.

Usage

export_provider_rankings(provider_rankings, path = "provider_rankings.xlsx")

Arguments

Value

The output file path, invisibly.

Extract Fixed Effects from Mixed Model

Description

Extract Fixed Effects from Mixed Model

Usage

extract_model_effects(model)

Arguments

Value

A data frame of fixed-effect estimates.

Extract Adjusted Provider Effects

Description

Extracts provider-specific random effects from a fitted mixed-effects model.

Usage

extract_provider_effects(model, provider_name = "provider_code")

Arguments

Value

A data frame of adjusted provider effects.

Filter Providers for Reliable Analysis

Description

Keeps providers with sufficient activity, repeated observations and stable performance values.

Usage

filter_providers(
  data,
  provider_var = "provider_code",
  activity_var = "total_treated",
  performance_var = "performance_percent",
  min_mean_activity = 20,
  min_observations = 5,
  max_cv = 0.5
)

Arguments

Value

A filtered data frame.

Fit Mixed-Effects Model for Cancer Waiting-Time Performance

Description

Fits a random-intercept mixed-effects model with provider as the grouping variable.

Usage

fit_cwt_mixed_model(
  data,
  performance_var = "performance_percent",
  month_var = "month_index",
  pathway_var = "cancer_type",
  provider_var = "provider_code"
)

Arguments

Value

A fitted lmerMod model object.

Load NHS Cancer Waiting-Time CSV Files

Description

Reads one or more NHS Cancer Waiting-Time CSV files and combines them into a single data frame.

Usage

load_cwt_data(files)

Arguments

Value

A data frame containing combined cancer waiting-time records.

Load NHS Cancer Waiting-Time Excel Files

Description

Reads one or more NHS Cancer Waiting-Time Excel files and combines them into a single data frame.

Usage

load_cwt_excel(files, sheet = 1, .name_repair = "unique")

Arguments

Value

A combined tibble with a source_file column.

Reshape Monthly Provider Performance to Wide Format

Description

Creates a provider-by-month performance table.

Usage

pivot_provider_months(
  data,
  provider_var = "provider_code",
  month_var = "reporting_date",
  performance_var = "performance_percent"
)

Arguments

Value

A wide provider-by-month table.

Plot national 62-day Cancer Waiting-Time performance

Description

Creates a publication-ready line plot showing national 62-day Cancer Waiting-Time performance over reporting months.

Usage

plot_national_performance(
  national_trend,
  date_col = "reporting_date",
  performance_col = "national_performance",
  standard = 85,
  save = FALSE,
  output_prefix = "National_Performance_Figure",
  output_dir = ".",
  width = 11,
  height = 6,
  dpi = 600
)

Arguments

Value

A ggplot object.

Examples

## Not run: 
plot_national_performance(national_trend)

plot_national_performance(
  national_trend,
  save = TRUE,
  output_dir = "figures",
  output_prefix = "National_Performance_Figure"
)

## End(Not run)

Plot National Cancer Waiting-Time Trends

Description

Creates a monthly performance trend plot.

Usage

plot_national_trends(
  data,
  month_var = "reporting_date",
  performance_var = "performance_percent",
  group_var = "standard"
)

Arguments

Value

A ggplot object.

Plot Adjusted Pathway Performance

Description

Creates a horizontal plot of adjusted predicted performance by cancer pathway.

Usage

plot_pathway_predictions(
  pathway_predictions,
  pathway_var = "cancer_type",
  prediction_var = "predicted_performance"
)

Arguments

Value

A ggplot object.

Plot Provider Clusters

Description

Creates a scatter plot of provider clusters.

Usage

plot_provider_clusters(clustered_data)

Arguments

Value

A ggplot object.

Plot Adjusted Provider Effects

Description

Creates a ranked plot of adjusted provider effects.

Usage

plot_provider_effects(
  provider_effects,
  provider_var = "provider_code",
  effect_var = "adjusted_effect"
)

Arguments

Value

A ggplot object.

Predict Adjusted Performance by Cancer Pathway

Description

Generates adjusted predicted performance for each cancer pathway from a fitted mixed-effects model.

Usage

predict_pathway_performance(
  model,
  data,
  pathway_var = "cancer_type",
  month_var = "month_index",
  provider_var = "provider_code"
)

Arguments

Value

A data frame with adjusted predicted pathway performance.

Run Sensitivity Analyses

Description

Runs mixed-effects models across alternative provider-filtering thresholds. If a cohort is too small or a model fails, the function returns a row with status information rather than stopping.

Usage

run_sensitivity_analysis(
  data,
  cohorts = data.frame(cohort = c("Main cohort", "No outlier removal",
    "Stricter cohort"), min_mean_activity = c(20, 20, 30), min_observations = c(5, 5, 5),
    max_cv = c(0.5, 0.75, 0.5)),
  provider_var = "provider_code",
  activity_var = "total_treated",
  performance_var = "performance_percent",
  month_var = "month_index",
  pathway_var = "cancer_type",
  min_providers = 3,
  min_rows = 20
)

Arguments

Value

A data frame summarising model results across cohorts.

Summarise Cancer Waiting-Time KPIs

Description

Calculates summary statistics for cancer waiting-time performance.

Usage

summarise_kpis(
  data,
  group_var = "standard",
  performance_var = "performance_percent"
)

Arguments

Value

A summary data frame.

Summarise Cancer Pathway Performance

Description

Summarise Cancer Pathway Performance

Usage

summarise_pathways(
  data,
  pathway_var = "cancer_type",
  performance_var = "performance_percent"
)

Arguments

Value

Pathway-level summary table.

Summarise Provider Performance

Description

Summarise Provider Performance

Usage

summarise_providers(
  data,
  provider_var = "provider_code",
  performance_var = "performance_percent",
  activity_var = "total_treated"
)

Arguments

Value

Provider-level summary table.