def test_multiple_matches(self):
text = "\n".join([
"HPI: 50 yo m with hx of dm2, presents with chest pain",
"Assessment: Plan:",
"50 yo m with hx of dm2, presents with chest pain",
"chest pain:",
"- PCI today",
"- DAPT, statin, bb",
])
# A delimiter matching the regex (:) is found inside the marker
marker_dict = {
"hpi": ["history of present illness"],
"assessment": ["assessment and plan"],
"assessment: plan": ["assessment and plan"],
}
section_finder = note_section_lib.SectionFinder(marker_dict)
self.assertListEqual(section_finder.find_sections(text), [
note_section_lib.Section(
char_start=0,
char_end=54,
section_types=["history of present illness"]),
note_section_lib.Section(char_start=54,
char_end=163,
section_types=["assessment and plan"]),
])
def test_extract_ap_sections(self):
section_markers = {
"hpi": ["history of present illness"],
"a&p": ["assessment and plan"],
}
note = data_lib.Note(
note_id=1,
text="hpi:\n 50yof with hx of dm2.\na&p:\n # dm2:\n-RISS",
subject_id=0,
category="PHYSICIAN")
expected = [note_section_lib.Section(28, 46, ["assessment and plan"])]
self.assertEqual(
list(data_lib.extract_ap_sections(note.text, section_markers)),
expected)
# multi section
note = data_lib.Note(
note_id=1,
text="hpi:\n 50yof with hx of dm2.\na&p: DM2\na&p:\n # dm2:\n-RISS",
subject_id=0,
category="PHYSICIAN")
expected = [
note_section_lib.Section(28, 37, ["assessment and plan"]),
note_section_lib.Section(37, 55, ["assessment and plan"]),
]
self.assertEqual(
list(data_lib.extract_ap_sections(note.text, section_markers)),
expected)
def test_multiple_section_types(self):
text = "\n".join([
"HPI: 50 yo m with hx of dm2, presents with chest pain",
"past medical and surgical history:",
"-DM2 on insulin",
"-s/p CABG 1999",
"A&P:",
"50 yo m with hx of dm2, presents with chest pain",
"chest pain:",
"- PCI today",
"- DAPT, statin, bb",
])
self.assertListEqual(self.section_finder.find_sections(text), [
note_section_lib.Section(
char_start=0,
char_end=54,
section_types=["history of present illness"]),
note_section_lib.Section(char_start=54,
char_end=120,
section_types=[
"past medical history",
"past surgical history"
]),
note_section_lib.Section(char_start=120,
char_end=216,
section_types=["assessment and plan"]),
])
def test_process_rating_labels(self):
rating_labels = [
ap_parsing_lib.LabeledCharSpan(
span_type=ap_parsing_lib.LabeledSpanType.PROBLEM_TITLE,
start_char=0,
end_char=50), # before
ap_parsing_lib.LabeledCharSpan(
span_type=ap_parsing_lib.LabeledSpanType.PROBLEM_TITLE,
start_char=45,
end_char=65), # partially contained
ap_parsing_lib.LabeledCharSpan(
span_type=ap_parsing_lib.LabeledSpanType.PROBLEM_TITLE,
start_char=50,
end_char=150), # exactly matches section
ap_parsing_lib.LabeledCharSpan(
span_type=ap_parsing_lib.LabeledSpanType.PROBLEM_TITLE,
start_char=100,
end_char=105), # contained
ap_parsing_lib.LabeledCharSpan(
span_type=ap_parsing_lib.LabeledSpanType.PROBLEM_TITLE,
start_char=150,
end_char=155), # after
]
expected = [
ap_parsing_lib.LabeledCharSpan(
span_type=ap_parsing_lib.LabeledSpanType.PROBLEM_TITLE,
start_char=0,
end_char=100),
ap_parsing_lib.LabeledCharSpan(
span_type=ap_parsing_lib.LabeledSpanType.PROBLEM_TITLE,
start_char=50,
end_char=55)
]
self.assertEqual(
data_lib.process_rating_labels(
rating_labels, note_section_lib.Section(50, 150, [])),
expected)