6 Specific adverse events

6.1 Setup

import sys
import os
# Add the python-package directory to Python path for demo001 access
sys.path.insert(0, os.path.join(os.path.dirname(os.getcwd()), 'python-package'))

import polars as pl
import rtflite as rtf

# Import demo001 package functions
from demo001 import find_project_root, load_adam_dataset
from demo001.safety import create_ae_by_soc_table

polars.config.Config

# Load data using demo001 utility functions
project_root = find_project_root()
adsl = load_adam_dataset("adsl", project_root)
adae = load_adam_dataset("adae", project_root)
treatments = ["Placebo", "Xanomeline Low Dose", "Xanomeline High Dose"]

6.2 Step 1: Load and Explore Data

We start by examining the adverse events data structure and understanding the MedDRA hierarchy.

# Display key variables in ADAE dataset
adae_vars = adae.select(["USUBJID", "TRTA", "AEBODSYS", "AEDECOD", "AESEV", "AESER"])
# Key ADAE variables
adae_vars

shape: (1_191, 6)

USUBJID	TRTA	AEBODSYS	AEDECOD	AESEV	AESER
str	str	str	str	str	str
"01-701-1015"	"Placebo"	"GENERAL DISORDERS AND ADMINIST…	"APPLICATION SITE ERYTHEMA"	"MILD"	"N"
"01-701-1015"	"Placebo"	"GENERAL DISORDERS AND ADMINIST…	"APPLICATION SITE PRURITUS"	"MILD"	"N"
"01-701-1015"	"Placebo"	"GASTROINTESTINAL DISORDERS"	"DIARRHOEA"	"MILD"	"N"
…	…	…	…	…	…
"01-718-1427"	"Xanomeline High Dose"	"METABOLISM AND NUTRITION DISOR…	"DECREASED APPETITE"	"MODERATE"	"N"
"01-718-1427"	"Xanomeline High Dose"	"GASTROINTESTINAL DISORDERS"	"NAUSEA"	"MODERATE"	"N"

# Examine the MedDRA hierarchy structure
# System Organ Classes (SOCs) in the data
soc_summary = adae.group_by("AEBODSYS").agg(
    n_participants=pl.col("USUBJID").n_unique(),
    n_events=pl.len()
).sort("n_participants", descending=True)
soc_summary

shape: (23, 3)

AEBODSYS	n_participants	n_events
str	u32	u32
"GENERAL DISORDERS AND ADMINIST…	108	292
"SKIN AND SUBCUTANEOUS TISSUE D…	105	276
"NERVOUS SYSTEM DISORDERS"	59	101
…	…	…
"SOCIAL CIRCUMSTANCES"	1	1
"HEPATOBILIARY DISORDERS"	1	1

6.3 Step 2: Prepare Analysis Population

Following regulatory standards, we focus on the safety analysis population.

# Define safety population
adsl_safety = adsl.filter(pl.col("SAFFL") == "Y").select(["USUBJID", "TRT01A"])
# Safety population size
adsl_safety.height

# Get safety population counts by treatment
pop_counts = adsl_safety.group_by("TRT01A").agg(N=pl.len()).sort("TRT01A")
# Safety population by treatment
pop_counts

shape: (3, 2)

TRT01A	N
str	u32
"Placebo"	86
"Xanomeline High Dose"	84
"Xanomeline Low Dose"	84

# Filter adverse events to safety population
adae_safety = adae.join(adsl_safety, on="USUBJID", how="inner")
# AE records in safety population
adae_safety.height

6.4 Step 3: Data Preparation and Standardization

We standardize the adverse event terms and prepare the hierarchical data structure.

# Create hierarchical AE table using demo001 safety functions
df_ae_specific = create_ae_by_soc_table(adae_safety, pop_counts, treatments)

# Display the table structure
df_ae_specific.shape
df_ae_specific

shape: (267, 4)

System Organ Class / Preferred Term	Placebo	Xanomeline Low Dose	Xanomeline High Dose
str	str	str	str
"Participants in population"	"86"	"84"	"84"
""	""	""	""
"Cardiac Disorders"	""	""	""
…	…	…	…
" Orthostatic Hypotension"	"1"	"0"	"0"
" Wound Haemorrhage"	"0"	"0"	"1"

6.5 Step 4: Create Regulatory-Compliant RTF Output

We format the table following regulatory submission standards with proper hierarchy and formatting.

# Create comprehensive RTF document
doc_ae_specific = rtf.RTFDocument(
    df=df_ae_specific,
    rtf_title=rtf.RTFTitle(
        text=[
            "Adverse Events by System Organ Class and Preferred Term",
            "(Safety Analysis Set)"
        ]
    ),
    rtf_column_header=rtf.RTFColumnHeader(
        text=[
            "System Organ Class\\line   Preferred Term",
            f"Placebo\\line (N={pop_counts.filter(pl.col('TRT01A') == 'Placebo')['N'][0]})",
            f"Xanomeline Low Dose\\line (N={pop_counts.filter(pl.col('TRT01A') == 'Xanomeline Low Dose')['N'][0]})",
            f"Xanomeline High Dose\\line (N={pop_counts.filter(pl.col('TRT01A') == 'Xanomeline High Dose')['N'][0]})"
        ],
        col_rel_width=[4, 1.5, 1.5, 1.5],
        text_justification=["l", "c", "c", "c"],
        text_format="b",  # Bold headers
        border_bottom="single"
    ),
    rtf_body=rtf.RTFBody(
        col_rel_width=[4, 1.5, 1.5, 1.5],
        text_justification=["l", "c", "c", "c"],
        # Apply bold formatting to SOC headers (rows without indentation)
        text_font_style=lambda df, i, j: "b" if j == 0 and not str(df[i, j]).startswith("  ") and str(df[i, j]) != "" else ""
    ),
    rtf_footnote=rtf.RTFFootnote(
        text=[
            "MedDRA version 25.0.",
            "Each participant is counted once within each preferred term and system organ class.",
            "Participants with multiple events in the same preferred term are counted only once for that term."
        ]
    ),
    rtf_source=rtf.RTFSource(
        text=["Source: ADAE Analysis Dataset (Data cutoff: 01JAN2023)"]
    )
)

# Generate RTF file
doc_ae_specific.write_rtf(project_root / "output" / "tlf_ae_specific.rtf")
# RTF file created: rtf/tlf_ae_specific.rtf

/home/runner/work/demo-py-esub/demo-py-esub/output/tlf_ae_specific.rtf