Skip to contents

ClinicoPathDescriptives: Introduction to Clinical and Pathological Descriptive Statistics

ClinicoPath Development Team

2025-06-30

Source: vignettes/clinicopath-descriptives-17-introduction-legacy.Rmd
clinicopath-descriptives-17-introduction-legacy.Rmd

Introduction

The ClinicoPathDescriptives domain provides comprehensive tools for descriptive statistics specifically designed for clinical and pathological research. This module bridges the gap between traditional statistical analysis and specialized needs of medical researchers, offering clinically meaningful output formats and interpretations.

What is ClinicoPathDescriptives?

ClinicoPathDescriptives is a specialized suite of statistical analysis tools within the ClinicoPath package that focuses on:

  • Clinical Data Summarization: Generate Table One summaries, cross-tabulations, and descriptive statistics tailored for medical research
  • Quality Assessment: Data quality checks, missing data analysis, and validation metrics
  • Agreement Analysis: Inter-rater reliability, diagnostic test agreement, and measurement concordance
  • Enhanced Reporting: Medical terminology, clinical guidelines compliance, and journal-ready outputs

Key Features

1. Table One Generation 

# Generate comprehensive Table One
library(ClinicoPath)
data(histopathology)

# Basic Table One
tableone(
  data = histopathology,
  explanatory = c("Grade", "Age", "Size"),
  dependent = "Outcome"
)

2. Advanced Cross-tabulations 

# Enhanced cross-tabulation with medical formatting
crosstable(
  data = histopathology,
  row_var = "Grade",
  col_var = "Outcome",
  add_margins = TRUE,
  statistical_test = TRUE
)

3. Agreement Analysis 

# Inter-rater agreement analysis
data(breast_agreement_data)

agreement(
  data = breast_agreement_data,
  rater1_var = "Pathologist_1_Score",
  rater2_var = "Pathologist_2_Score",
  agreement_type = "kappa"
)

4. Data Quality Assessment 

# Comprehensive data quality check
dataquality(
  data = histopathology,
  missing_threshold = 0.1,
  outlier_detection = TRUE,
  generate_report = TRUE
)

Clinical Applications

Pathology Research

  • Digital pathology validation studies
  • Biomarker concordance analysis
  • Multi-platform validation
  • Quality assurance metrics

Clinical Trials

  • Baseline characteristics tables
  • Enrollment summaries
  • Safety reporting
  • Efficacy endpoints description

Epidemiological Studies

  • Population characteristics
  • Risk factor analysis
  • Screening program evaluation
  • Public health surveillance

Integration with Clinical Workflows

ClinicoPathDescriptives is designed to integrate seamlessly with:

  1. Laboratory Information Systems (LIS)
  2. Electronic Health Records (EHR)
  3. Research Electronic Data Capture (REDCap)
  4. Clinical Data Management Systems

Available Functions

Core Descriptive Functions

Data Quality Functions

Agreement Functions

Enhanced Reporting

Getting Started

Installation and Setup 

# ClinicoPath is available through jamovi
# For R users:
# install.packages("ClinicoPath") # When available on CRAN
# Or development version:
# remotes::install_github("sbalci/ClinicoPathJamoviModule")

library(ClinicoPath)

Basic Workflow 

# 1. Load your clinical data
data(histopathology)

# 2. Check data quality
quality_check <- dataquality(histopathology)

# 3. Generate descriptive statistics
table_one <- tableone(
  data = histopathology,
  explanatory = c("Age", "Grade", "Size"),
  dependent = "Outcome"
)

# 4. Create cross-tabulations
cross_tab <- crosstable(
  data = histopathology,
  row_var = "Grade",
  col_var = "Outcome"
)

# 5. Export results
# Results are automatically formatted for clinical reporting

Best Practices

1. Data Preparation

  • Ensure consistent variable naming
  • Use appropriate data types (factors for categorical variables)
  • Handle missing data appropriately
  • Validate data entry errors

2. Variable Selection

  • Include clinically relevant variables
  • Consider regulatory requirements
  • Balance comprehensiveness with clarity
  • Group related variables logically

3. Statistical Considerations

  • Choose appropriate tests for data types
  • Consider multiple testing corrections
  • Report confidence intervals
  • Include effect sizes when relevant

4. Reporting Standards

  • Follow CONSORT guidelines for trials
  • Adhere to STROBE guidelines for observational studies
  • Use standard medical terminology
  • Include appropriate disclaimers

For more specific applications, see:

Support and Resources

Documentation

Community

  • GitHub Issues: Report bugs and request features
  • Discussion Forum: Share experiences and best practices
  • Training Materials: Workshops and tutorials

Citation

When using ClinicoPathDescriptives in your research, please cite:

Balci S (2024). ClinicoPath: Clinical and Pathological Data Analysis.
R package version X.X.X. https://github.com/sbalci/ClinicoPathJamoviModule

Conclusion

ClinicoPathDescriptives provides a comprehensive suite of tools specifically designed for clinical and pathological research. By combining statistical rigor with clinical relevance, it enables researchers to generate publication-ready results while maintaining compliance with medical research standards.

The module’s integration with jamovi makes advanced statistical analysis accessible to clinical researchers regardless of their programming background, while R users benefit from programmatic access and reproducible workflows.