stem_generator: Generate disease stems

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

Description

Generate disease stems on the basis of combination frequency (if no outcome_positions is passed) or the proportion of records associated with an outcome event (if outcome_positions is passed).

Usage

stem_generator(
  poscolumn,
  max_combos = 3,
  all_diseases,
  outcome_positions = 0,
  min_freq = 0,
  tots,
  use_outcome = FALSE
)

Arguments

poscolumn	Vector of numbers which describe position of 1s in a comorbid string, generated using .get_locales().
max_combos	Number of maximum combinations to attempt.
all_diseases	List of positions associated with each disease, generated using .get_disease_counts().
outcome_positions	Numeric vector where each number 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	Total number of records included to allow calculation of disease frequency.
use_outcome	Logical if to use outcome variable for stem generation.

Value

A dataframe with the main_stem for each pattern up to a maximum set in max_combos.

Examples

positions = list(c(1,2,3,4), c(3), c(3), c(2,3))
disease_counts = list(c(1), c(1,4), c(1,2,3,4), c(1))

# generate stems on basis of frequency
stem_generator(poscolumn = positions,
max_combos = 2,
all_diseases = disease_counts,
outcome_positions = 0, tots=4)

# generate stems on basis of outcome
stem_generator(poscolumn = positions,
 max_combos = 2,
 all_diseases = disease_counts,
 outcome_positions = c(2,3,4), tots = 4)

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