Clinical Trial Telemetry Aggregation and Summary Statistics Script Generator

Role: Lead Research Informatics Engineer specializing in reproducible biostatistical reporting scripts.

Context

• Study identifier: {{trial_phase_name}}
• Raw data format: {{telemetry_data_schema}}
• Key endpoint: {{primary_endpoint_metric}}
• Comparison grouping: {{cohort_grouping_factor}}
• Significance threshold: {{statistical_significance_cutoff}}
• Export file format: {{export_file_format}}

Task

Generate a complete, fully documented R statistical script that ingests experimental trial telemetry, validates data integrity, computes baseline demographic and endpoint statistical aggregations across study arms, conducts significance tests, and exports publication-ready summary tables.

Method

1. Load raw study logs matching {{telemetry_data_schema}} using tidyverse and data.table conventions.
2. Filter observation records applicable strictly to {{trial_phase_name}} while stripping incomplete patient runs.
3. Compute central tendency metrics (mean, median, standard deviation, IQR) for {{primary_endpoint_metric}}.
4. Stratify statistical summaries across cohorts defined by {{cohort_grouping_factor}}.
5. Execute two-tailed hypothesis testing evaluating cohort separation against {{statistical_significance_cutoff}}.
6. Construct formatted output tables adhering to clinical summary standards (including sample size, effect sizes, and p-values).
7. Write the finalized summary datasets to disk matching {{export_file_format}} specifications.

Constraints

• Code MUST be written in modern R (v4.2+) utilizing tidyverse packages (dplyr, tidyr, readr).
• MUST NOT modify or overwrite raw primary telemetry source files.
• MUST explicitly set random seeds for any resampling or non-parametric statistical methods used.
• Output table column headers must be sanitized for human-readable scientific publication.

Output format

Provide the generated deliverable in these designated sections:

1. Pipeline Metadata (bulleted list of required R packages, environment assumptions, and input paths).
2. Complete R Analysis Script (single executable R script structured with explicit headers, transformation functions, and export routines).
3. Sample Output Table Preview (ASCII or Markdown representation of the resulting summary report).

Self-review

• Ensure the statistical tests applied are appropriate for the data types implied in {{primary_endpoint_metric}}.
• Verify all 6 variables are referenced within the R script parameters or data load blocks.
• Confirm reproducible seed management and file output paths are implemented without syntax errors.