Skip to content

edsnlp.pipelines.qualifiers.history.history

History

Bases: Qualifier

Implements an history detection algorithm.

The components looks for terms indicating history in the text.

PARAMETER DESCRIPTION
nlp

spaCy nlp pipeline to use for matching.

TYPE: Language

history

List of terms indicating medical history reference.

TYPE: Optional[List[str]]

termination

List of syntagme termination terms.

TYPE: Optional[List[str]]

use_sections

Whether to use section pipeline to detect medical history section.

TYPE: bool

attr

spaCy's attribute to use: a string with the value "TEXT" or "NORM", or a dict with the key 'term_attr' we can also add a key for each regex.

TYPE: str

on_ents_only

Whether to look for matches around detected entities only. Useful for faster inference in downstream tasks.

TYPE: bool

regex

A dictionnary of regex patterns.

TYPE: Optional[Dict[str, Union[List[str], str]]]

explain

Whether to keep track of cues for each entity.

TYPE: bool

Source code in edsnlp/pipelines/qualifiers/history/history.py 
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
class History(Qualifier):
    """
    Implements an history detection algorithm.

    The components looks for terms indicating history in the text.

    Parameters
    ----------
    nlp : Language
        spaCy nlp pipeline to use for matching.
    history : Optional[List[str]]
        List of terms indicating medical history reference.
    termination : Optional[List[str]]
        List of syntagme termination terms.
    use_sections : bool
        Whether to use section pipeline to detect medical history section.
    attr : str
        spaCy's attribute to use:
        a string with the value "TEXT" or "NORM", or a dict with the key 'term_attr'
        we can also add a key for each regex.
    on_ents_only : bool
        Whether to look for matches around detected entities only.
        Useful for faster inference in downstream tasks.
    regex : Optional[Dict[str, Union[List[str], str]]]
        A dictionnary of regex patterns.
    explain : bool
        Whether to keep track of cues for each entity.
    """

    defaults = dict(
        history=history,
        termination=termination,
    )

    def __init__(
        self,
        nlp: Language,
        attr: str,
        history: Optional[List[str]],
        termination: Optional[List[str]],
        use_sections: bool,
        explain: bool,
        on_ents_only: bool,
    ):

        terms = self.get_defaults(
            history=history,
            termination=termination,
        )

        super().__init__(
            nlp=nlp,
            attr=attr,
            on_ents_only=on_ents_only,
            explain=explain,
            **terms,
        )

        self.set_extensions()

        self.sections = use_sections and (
            "eds.sections" in nlp.pipe_names or "sections" in nlp.pipe_names
        )
        if use_sections and not self.sections:
            logger.warning(
                "You have requested that the pipeline use annotations "
                "provided by the `section` pipeline, but it was not set. "
                "Skipping that step."
            )

    @staticmethod
    def set_extensions() -> None:

        if not Token.has_extension("history"):
            Token.set_extension("history", default=False)

        if not Token.has_extension("antecedents"):
            Token.set_extension(
                "antecedents",
                getter=deprecated_getter_factory("antecedents", "history"),
            )

        if not Token.has_extension("antecedent"):
            Token.set_extension(
                "antecedent",
                getter=deprecated_getter_factory("antecedent", "history"),
            )

        if not Token.has_extension("history_"):
            Token.set_extension(
                "history_",
                getter=lambda token: "ATCD" if token._.history else "CURRENT",
            )

        if not Token.has_extension("antecedents_"):
            Token.set_extension(
                "antecedents_",
                getter=deprecated_getter_factory("antecedents_", "history_"),
            )

        if not Token.has_extension("antecedent_"):
            Token.set_extension(
                "antecedent_",
                getter=deprecated_getter_factory("antecedent_", "history_"),
            )

        if not Span.has_extension("history"):
            Span.set_extension("history", default=False)

        if not Span.has_extension("antecedents"):
            Span.set_extension(
                "antecedents",
                getter=deprecated_getter_factory("antecedents", "history"),
            )

        if not Span.has_extension("antecedent"):
            Span.set_extension(
                "antecedent",
                getter=deprecated_getter_factory("antecedent", "history"),
            )

        if not Span.has_extension("history_"):
            Span.set_extension(
                "history_",
                getter=lambda span: "ATCD" if span._.history else "CURRENT",
            )

        if not Span.has_extension("antecedents_"):
            Span.set_extension(
                "antecedents_",
                getter=deprecated_getter_factory("antecedents_", "history_"),
            )

        if not Span.has_extension("antecedent_"):
            Span.set_extension(
                "antecedent_",
                getter=deprecated_getter_factory("antecedent_", "history_"),
            )

        if not Span.has_extension("history_cues"):
            Span.set_extension("history_cues", default=[])

        if not Span.has_extension("antecedents_cues"):
            Span.set_extension(
                "antecedents_cues",
                getter=deprecated_getter_factory("antecedents_cues", "history_cues"),
            )

        if not Span.has_extension("antecedent_cues"):
            Span.set_extension(
                "antecedent_cues",
                getter=deprecated_getter_factory("antecedent_cues", "history_cues"),
            )

    def process(self, doc: Doc) -> Doc:
        """
        Finds entities related to history.

        Parameters
        ----------
        doc:
            spaCy Doc object

        Returns
        -------
        doc:
            spaCy Doc object, annotated for history
        """

        matches = self.get_matches(doc)

        terminations = get_spans(matches, "termination")
        boundaries = self._boundaries(doc, terminations)

        # Removes duplicate matches and pseudo-expressions in one statement
        matches = filter_spans(matches, label_to_remove="pseudo")

        entities = list(doc.ents) + list(doc.spans.get("discarded", []))
        ents = None

        sections = []

        if self.sections:
            sections = [
                Span(doc, section.start, section.end, label="ATCD")
                for section in doc.spans["sections"]
                if section.label_ == "antécédents"
            ]

        for start, end in boundaries:
            ents, entities = consume_spans(
                entities,
                filter=lambda s: check_inclusion(s, start, end),
                second_chance=ents,
            )

            sub_matches, matches = consume_spans(
                matches, lambda s: start <= s.start < end
            )

            sub_sections, sections = consume_spans(sections, lambda s: doc[start] in s)

            if self.on_ents_only and not ents:
                continue

            cues = get_spans(sub_matches, "history")
            cues += sub_sections

            history = bool(cues)

            if not self.on_ents_only:
                for token in doc[start:end]:
                    token._.history = history

            for ent in ents:
                ent._.history = ent._.history or history

                if self.explain:
                    ent._.history_cues += cues

                if not self.on_ents_only and ent._.history:
                    for token in ent:
                        token._.history = True

        return doc

defaults = dict(history=history, termination=termination) class-attribute

sections = use_sections and 'eds.sections' in nlp.pipe_names or 'sections' in nlp.pipe_names instance-attribute

__init__(nlp, attr, history, termination, use_sections, explain, on_ents_only)

Source code in edsnlp/pipelines/qualifiers/history/history.py 
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
def __init__(
    self,
    nlp: Language,
    attr: str,
    history: Optional[List[str]],
    termination: Optional[List[str]],
    use_sections: bool,
    explain: bool,
    on_ents_only: bool,
):

    terms = self.get_defaults(
        history=history,
        termination=termination,
    )

    super().__init__(
        nlp=nlp,
        attr=attr,
        on_ents_only=on_ents_only,
        explain=explain,
        **terms,
    )

    self.set_extensions()

    self.sections = use_sections and (
        "eds.sections" in nlp.pipe_names or "sections" in nlp.pipe_names
    )
    if use_sections and not self.sections:
        logger.warning(
            "You have requested that the pipeline use annotations "
            "provided by the `section` pipeline, but it was not set. "
            "Skipping that step."
        )

set_extensions()

Source code in edsnlp/pipelines/qualifiers/history/history.py 
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
@staticmethod
def set_extensions() -> None:

    if not Token.has_extension("history"):
        Token.set_extension("history", default=False)

    if not Token.has_extension("antecedents"):
        Token.set_extension(
            "antecedents",
            getter=deprecated_getter_factory("antecedents", "history"),
        )

    if not Token.has_extension("antecedent"):
        Token.set_extension(
            "antecedent",
            getter=deprecated_getter_factory("antecedent", "history"),
        )

    if not Token.has_extension("history_"):
        Token.set_extension(
            "history_",
            getter=lambda token: "ATCD" if token._.history else "CURRENT",
        )

    if not Token.has_extension("antecedents_"):
        Token.set_extension(
            "antecedents_",
            getter=deprecated_getter_factory("antecedents_", "history_"),
        )

    if not Token.has_extension("antecedent_"):
        Token.set_extension(
            "antecedent_",
            getter=deprecated_getter_factory("antecedent_", "history_"),
        )

    if not Span.has_extension("history"):
        Span.set_extension("history", default=False)

    if not Span.has_extension("antecedents"):
        Span.set_extension(
            "antecedents",
            getter=deprecated_getter_factory("antecedents", "history"),
        )

    if not Span.has_extension("antecedent"):
        Span.set_extension(
            "antecedent",
            getter=deprecated_getter_factory("antecedent", "history"),
        )

    if not Span.has_extension("history_"):
        Span.set_extension(
            "history_",
            getter=lambda span: "ATCD" if span._.history else "CURRENT",
        )

    if not Span.has_extension("antecedents_"):
        Span.set_extension(
            "antecedents_",
            getter=deprecated_getter_factory("antecedents_", "history_"),
        )

    if not Span.has_extension("antecedent_"):
        Span.set_extension(
            "antecedent_",
            getter=deprecated_getter_factory("antecedent_", "history_"),
        )

    if not Span.has_extension("history_cues"):
        Span.set_extension("history_cues", default=[])

    if not Span.has_extension("antecedents_cues"):
        Span.set_extension(
            "antecedents_cues",
            getter=deprecated_getter_factory("antecedents_cues", "history_cues"),
        )

    if not Span.has_extension("antecedent_cues"):
        Span.set_extension(
            "antecedent_cues",
            getter=deprecated_getter_factory("antecedent_cues", "history_cues"),
        )

process(doc)

Finds entities related to history.

PARAMETER DESCRIPTION
doc

spaCy Doc object

TYPE: Doc

RETURNS DESCRIPTION
doc

spaCy Doc object, annotated for history
Source code in edsnlp/pipelines/qualifiers/history/history.py 
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
def process(self, doc: Doc) -> Doc:
    """
    Finds entities related to history.

    Parameters
    ----------
    doc:
        spaCy Doc object

    Returns
    -------
    doc:
        spaCy Doc object, annotated for history
    """

    matches = self.get_matches(doc)

    terminations = get_spans(matches, "termination")
    boundaries = self._boundaries(doc, terminations)

    # Removes duplicate matches and pseudo-expressions in one statement
    matches = filter_spans(matches, label_to_remove="pseudo")

    entities = list(doc.ents) + list(doc.spans.get("discarded", []))
    ents = None

    sections = []

    if self.sections:
        sections = [
            Span(doc, section.start, section.end, label="ATCD")
            for section in doc.spans["sections"]
            if section.label_ == "antécédents"
        ]

    for start, end in boundaries:
        ents, entities = consume_spans(
            entities,
            filter=lambda s: check_inclusion(s, start, end),
            second_chance=ents,
        )

        sub_matches, matches = consume_spans(
            matches, lambda s: start <= s.start < end
        )

        sub_sections, sections = consume_spans(sections, lambda s: doc[start] in s)

        if self.on_ents_only and not ents:
            continue

        cues = get_spans(sub_matches, "history")
        cues += sub_sections

        history = bool(cues)

        if not self.on_ents_only:
            for token in doc[start:end]:
                token._.history = history

        for ent in ents:
            ent._.history = ent._.history or history

            if self.explain:
                ent._.history_cues += cues

            if not self.on_ents_only and ent._.history:
                for token in ent:
                    token._.history = True

    return doc
Back to top