1 ivdtools Package Overview

ivdtools is an R statistical toolkit for in vitro diagnostic (IVD) reagent evaluation. It provides reproducible workflows for data checking, statistical analysis, result summarization, and visualization. The package covers method comparison, ROC analysis, qualitative agreement, precision, linearity, interference, dilution and spike recovery, C5/C95, measurement uncertainty, commutability, reference-material bias, reference intervals, stability, quality control, curve fitting, analytical sensitivity, outlier and normality assessment, and sample-size calculation. Statistical results should be interpreted together with the pre-specified study protocol, applicable standards, laboratory requirements, and clinical or analytical allowable limits.

1.1 Functional Modules

Module	Main entry points	Key features
Method comparison	`mcr()`	Descriptive statistics, correlation, regression, Bland–Altman, bias, and outliers
Commutability	`commutability()`	EP14, EP30, and IFCC commutability assessment
ROC	`roc()`	ROC curves, cutoffs, multivariate logistic regression, and prediction
Qualitative analysis	`raw_to_table()`, `counts_to_table()`	Four-fold tables, diagnostic accuracy metrics, Kappa agreement, and McNemar test
Precision	`precision()`	Variance components, confidence intervals, outliers, normality, and Sadler precision profiles
Linearity	`linearity()`, `linearity_*()`	Study design, HIGH/LOW preparation, linear/polynomial analysis, weights, ADL, and intervals
Interference	`interference_*()`	Replicate planning, paired studies, dose response, and patient-sample comparison
Dilution and spike recovery	`dilution_recovery()`, `spike_recovery()`, `hook_effect()`	Dilution recovery, spike recovery, and high-dose hook effect
C5/C95	`c5_c95()`	C5/C95 estimation for qualitative reagents from continuous measurements
Measurement uncertainty	`uncertainty_*()`	Type A/B, IQC, bias, homogeneity, stability, combination, and propagation
Reference-material bias	`reference_bias()`	Bias, measurement-mean uncertainty, and intervals combining reference-material uncertainty
Reference intervals	`reference_interval()`	EP28 nonparametric, biweight, type 6, parametric, and Huber intervals
Bottle/lot ANOVA	`bottle_anova()`	One-way or nested ANOVA, Tukey HSD, and compact letter display
Stability	`stability_bias()`, `stability_regression()`	Bias, stability regression, time to exceed a limit, stability plans, MKT, and Arrhenius models
Quality control	`qc_chart()`, `youden_plot()`	Levey–Jennings charts, Westgard rules, and Youden plots
Calibration and response curves	`fit_equation()`	Weighted and constrained fitting, and model comparison for linear, exponential, 4PLC, 5PLC, and other response equations; not method-comparison linearity assessment
Analytical sensitivity	`sensitivity_lob()` / `sensitivity_lod()` / `sensitivity_loq()`	Establishment and verification of LoB, LoD, and LoQ
Outliers and distributions	`outliers_test()`, `normal_test()`	Grubbs, ESD, Dixon, IQR, and multiple normality tests
Sample size	`sample_size_*()`	Bland–Altman agreement, single-proportion confidence intervals, and one-arm target-value tests

1.2 Design Features

1.2.1 Standalone Workflows

Standalone interfaces complete one task at a time, as in the following examples:

Code

normal_test(dat, col = "candidate")
reference_interval(dat, col = "candidate")

1.2.2 Progressive Workflows

Modules such as method comparison, ROC, qualitative analysis, and precision organize the analysis process with S3 objects:

%%{init: {"theme":"base","themeVariables":{"primaryColor":"#EAF2FB","primaryBorderColor":"#2780E3","primaryTextColor":"#212529","lineColor":"#6C757D","secondaryColor":"#EAF7E6","tertiaryColor":"#FFF4E8","fontSize":"13px"},"flowchart":{"nodeSpacing":18,"rankSpacing":24,"padding":6}}}%%

flowchart LR
    A["Raw data"] --> B["Constructor<br/>create analysis object"]
    B --> C["Analysis methods<br/>accumulate results"]
    C --> D["Updated object"]
    D --> E["summary()"]
    D --> F["plot()"]
    D --> G["predict()<br/>supported modules"]

    classDef input fill:#EAF2FB,stroke:#2780E3,color:#212529
    classDef process fill:#EAF7E6,stroke:#3FB618,color:#212529
    classDef output fill:#F4EEFB,stroke:#9954BB,color:#212529
    class A input
    class B,C process
    class D,E,F,G output

Progressive interfaces must be reassigned:

Code

obj <- analysis_method(obj)

If you call only analysis_method(obj) without obj <-, the new results will not accumulate in the original object.

1.3 Quick Start

The following code is for demonstrating the analysis process only.

1.3.1 Method Comparison

Code

library(ivdtools)

mc <- mcr(
  ivd_mcr_example,
  id = "sid",
  candidate = "test",
  reference = "ref"
)
mc <- describe(mc)
mc <- correlation(mc, method = "pearson")
mc <- regression(mc, method = "deming")
mc <- bland_altman(mc, type = "difference")

summary(mc)
plot(mc, type = "regression")
plot(mc, type = "bland_altman")

1.3.2 ROC

Code

ro <- roc(
  ivd_roc_example,
  cols = c("x1", "x2"),
  reference = "ref",
  positive = 1
)
ro <- describe(ro)
ro <- auc(ro)
ro <- cutoff(ro)
ro <- mlr(ro, cols = c("x1", "x2"), name = "combined")

summary(ro)
plot(ro, curves = "all", cutpoint = "Youden")

1.3.3 Qualitative Agreement

Code

qa <- raw_to_table(
  ivd_qualitative_example,
  candidate = "new",
  reference = "gold",
  id = "id",
  positive = "positive"
)
qa <- describe(qa)
qa <- diagnostics(qa)
qa <- kappa(qa)
qa <- mcnemar(qa)

summary(qa)

1.3.4 Bottle-to-Bottle Difference

Code

ba <- bottle_anova(
  ivd_bottle_example,
  value ~ bottle
)
print(ba)

posthoc <- tukey(ba)
print(posthoc)

1.4 Dependencies

ivdtools primarily depends on ggplot2, ggrepel, VCA, VFP, minpack.lm, nloptr, nls2, nortest, rlang, and ppwdeming.