pyDeid.process_note package

Submodules

pyDeid.process_note.PHIFinder module

class pyDeid.process_note.PHIFinder.PHIFinder(config: Config)

Bases: object

A class representing all operations to find PHI values in a given note.

Parameters:

  • custom_regexes (-) – These are named arguments that will be taken as regexes to be scrubbed from the given note. The keyword/argument name itself will be used to label the PHI in the phi_output. Note that all custom patterns will be replaced with <PHI>.

  • model (-) – The model loaded if named entity recognition (NER) is used

  • types (-) – Various PHIs we want to identify

class Config(phi_types: List[str] = <factory>, custom_regexes: List[pyDeid.phi_types.utils.CustomRegex] = <factory>, two_digit_threshold: int = 30, valid_year_low: int = 1900, valid_year_high: int = 2050, custom_dr_first_names: List[str] = <factory>, custom_dr_last_names: List[str] = <factory>, custom_patient_first_names: List[str] = <factory>, custom_patient_last_names: List[str] = <factory>, ner_model: Any = None)

Bases: object

custom_dr_first_names: List[str]
custom_dr_last_names: List[str]
custom_patient_first_names: List[str]
custom_patient_last_names: List[str]
custom_regexes: List[CustomRegex]
ner_model: Any = None
phi_types: List[str]
two_digit_threshold: int = 30
valid_year_high: int = 2050
valid_year_low: int = 1900
find_phi(row_from_mll=None) → Dict[PHI, List[str]]

Returns mutated PHI object containing PHIs of various types identified from the note

set_note(new_note: str) → None
set_phis(new_phis) → None

pyDeid.process_note.PHIHandler module

class pyDeid.process_note.PHIHandler.PHIHandler(regex_replace=True, mll_rows={})

Bases: object

Responsible for managing the current the current note and associated PHIs.

Manages relationship between find, prune and replace operations for the current note

handle_csv_row(row: Dict[str, str], errors: List[str], encounter_id_varname: str = 'genc_id', note_id_varname: str = None, note_varname: str = 'note_text') → Tuple[int, int, List[str]]

Handle the note - with find, prune, and replace

handle_string(note: str, row_from_mll: str = None) → Tuple[List[Dict[str, str]], str]
set_finder(finder)
set_note(new_note: str) → None
set_phis(new_phis) → None
set_pruner(pruner)
set_replacer(replacer=None)

pyDeid.process_note.PHIPruner module

class pyDeid.process_note.PHIPruner.PHIPruner

Bases: object

A class representing all operations required to prune the PHIs for a given note

prune_phi() → Dict[PHI, List[str]]

Returns mutated PHI object containing a reduced set of PHIs after removing paradoxes and redundencies among the PHIs that exist from the note

set_note(new_note: str) → None
set_phis(new_phis) → None

pyDeid.process_note.PHIReplacer module

class pyDeid.process_note.PHIReplacer.PHIReplacer(return_surrogates=False)

Bases: object

Handles replacement of PHI values with surrogate values.

load_phi_types(finder)
replace_phi()

Replaces PHI in the text with surrogate values, ensuring no overlapping replacements.

set_note(new_note: str) → None
set_phis(new_phis) → None

Module contents