calculate_group_frequency: Calculate group frequency for all unique combinations

In AJFOWLER/comorbidgroupr: Identify Groups of Comorbid Diseases Associated with Outcomes

Description

Generate an ordered data.frame of different disease combinations on the basis of the most frequent or most strongly associated with outcomes.

Usage

calculate_group_frequency(
  unique_combinations,
  all_diseases,
  outcome_positions,
  min_freq = 0,
  tots,
  use_outcome = FALSE
)

Arguments

unique_combinations	List of unique combinations of disease positions for a given number of combinations, generated using unique_combos.
all_diseases	List of positions associated with each disease, generated using get_disease_counts().
outcome_positions	Numeric vector where each element refers to a record that suffered a particular outcome.
min_freq	Number between 0 and 1; minimum proportion of code combinations to be included in the stem. If outcome_column is passed, min_freq is the minimum event rate per combination to be considered.
tots	Numeric, total length of comorbid_column initially profiled to calculate frequency proportions to compare against min_freq.
use_outcome	Logical if to use outcome variable for stem generation.

Value

data.frame ordered from lowest to highest proportion of those suffering outcomes (if outcome_positions entered) or number of records associated with that combination (if no outcome_positions entered).

Examples

disease_counts = list(c(1), c(1,4), c(1,2,3,4), c(1))
unique_pos = structure(c(1, 1, 1, 2, 2, 3, 2, 3, 4, 3, 4, 4), .Dim = c(6L, 2L))

calculate_group_frequency(unique_combinations = unique_pos,
all_diseases = disease_counts,
outcome_positions = 0, tots = 4)

calculate_group_frequency(unique_combinations = unique_pos,
all_diseases = disease_counts,
outcome_positions = c(0,1,1,0), tots = 4)

AJFOWLER/comorbidgroupr documentation built on May 11, 2021, 6:01 a.m.