Skip to content

edsteva.probes.biology.completeness_predictors.per_measurement

compute_completeness_predictor_per_measurement

compute_completeness_predictor_per_measurement(
    self,
    data: Data,
    start_date: datetime,
    end_date: datetime,
    care_site_levels: Union[bool, str, List[str]],
    stay_types: Union[bool, str, Dict[str, str]],
    care_site_ids: List[int],
    care_site_short_names: List[str],
    care_site_specialties: Union[bool, List[str]],
    measurement_concept_codes: Union[bool, List[str]],
    care_sites_sets: Union[str, Dict[str, str]],
    specialties_sets: Union[str, Dict[str, str]],
    concepts_sets: Union[str, Dict[str, str]],
    length_of_stays: List[float],
    source_terminologies: Dict[str, str],
    mapping: List[Tuple[str, str, str]],
    age_ranges: List[int],
    gender_source_values: Union[bool, str, Dict[str, str]],
    condition_types: Union[bool, str, Dict[str, str]],
    diag_types: Union[bool, str, Dict[str, str]],
    provenance_sources: Union[bool, str, Dict[str, str]],
    stay_sources: Union[bool, str, Dict[str, str]],
    drg_sources: Union[bool, str, Dict[str, str]],
    **kwargs
)

Script to be used by compute()

The per_measurement algorithm computes \(c_(t)\) the availability of biological measurements:

\[ c(t) = \frac{n_{biology}(t)}{n_{max}} \]

Where \(n_{biology}(t)\) is the number of biological measurements, \(t\) is the month and \(n_{max} = \max_{t}(n_{biology}(t))\).

Source code in edsteva/probes/biology/completeness_predictors/per_measurement.py
 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
def compute_completeness_predictor_per_measurement(
    self,
    data: Data,
    start_date: datetime,
    end_date: datetime,
    care_site_levels: Union[bool, str, List[str]],
    stay_types: Union[bool, str, Dict[str, str]],
    care_site_ids: List[int],
    care_site_short_names: List[str],
    care_site_specialties: Union[bool, List[str]],
    measurement_concept_codes: Union[bool, List[str]],
    care_sites_sets: Union[str, Dict[str, str]],
    specialties_sets: Union[str, Dict[str, str]],
    concepts_sets: Union[str, Dict[str, str]],
    length_of_stays: List[float],
    source_terminologies: Dict[str, str],
    mapping: List[Tuple[str, str, str]],
    age_ranges: List[int],
    gender_source_values: Union[bool, str, Dict[str, str]],
    condition_types: Union[bool, str, Dict[str, str]],
    diag_types: Union[bool, str, Dict[str, str]],
    provenance_sources: Union[bool, str, Dict[str, str]],
    stay_sources: Union[bool, str, Dict[str, str]],
    drg_sources: Union[bool, str, Dict[str, str]],
    **kwargs
):
    r"""Script to be used by [``compute()``][edsteva.probes.base.BaseProbe.compute]

    The ``per_measurement`` algorithm computes $c_(t)$ the availability of biological measurements:

    $$
    c(t) = \frac{n_{biology}(t)}{n_{max}}
    $$

    Where $n_{biology}(t)$ is the number of biological measurements, $t$ is the month and $n_{max} = \max_{t}(n_{biology}(t))$.
    """
    self._metrics = ["c", "n_measurement"]
    check_tables(
        data=data,
        required_tables=[
            "visit_occurrence",
            "care_site",
            "fact_relationship",
            "measurement",
            "concept",
            "concept_relationship",
        ],
    )
    care_site_relationship = prepare_care_site_relationship(
        data=data,
    )
    self.care_site_relationship = care_site_relationship
    standard_terminologies = self._standard_terminologies
    biology_relationship = prepare_biology_relationship(
        data=data,
        standard_terminologies=standard_terminologies,
        source_terminologies=source_terminologies,
        mapping=mapping,
    )

    self.biology_relationship = biology_relationship
    root_terminology = mapping[0][0]

    person = (
        prepare_person(data, gender_source_values)
        if (age_ranges or gender_source_values)
        else None
    )
    cost = prepare_cost(data, drg_sources) if drg_sources else None

    measurement = prepare_measurement(
        data=data,
        biology_relationship=biology_relationship,
        measurement_concept_codes=measurement_concept_codes,
        concepts_sets=concepts_sets,
        start_date=start_date,
        end_date=end_date,
        root_terminology=root_terminology,
        standard_terminologies=standard_terminologies,
        per_visit=False,
    )

    visit_occurrence = prepare_visit_occurrence(
        data=data,
        start_date=None,
        end_date=None,
        stay_types=stay_types,
        length_of_stays=length_of_stays,
        provenance_sources=provenance_sources,
        stay_sources=stay_sources,
        cost=cost,
        person=person,
        age_ranges=age_ranges,
    ).drop(columns=["visit_occurrence_source_value", "date"])
    if condition_types:
        conditions = prepare_condition_occurrence(
            data,
            extra_data=None,
            visit_occurrence=None,
            source_systems="ORBIS",
            diag_types=diag_types,
            condition_types=condition_types,
            start_date=start_date,
            end_date=end_date,
        )[["visit_occurrence_id", "condition_type", "diag_type"]].drop_duplicates()
        visit_occurrence = visit_occurrence.merge(conditions, on="visit_occurrence_id")

    care_site = prepare_care_site(
        data=data,
        care_site_ids=care_site_ids,
        care_site_short_names=care_site_short_names,
        care_site_specialties=care_site_specialties,
        care_sites_sets=care_sites_sets,
        specialties_sets=specialties_sets,
        care_site_relationship=care_site_relationship,
    )

    hospital_measurement = get_hospital_measurements(
        measurement=measurement,
        visit_occurrence=visit_occurrence,
        care_site=care_site,
    )
    hospital_name = CARE_SITE_LEVEL_NAMES["Hospital"]
    biology_predictor_by_level = {hospital_name: hospital_measurement}

    if care_site_levels and not hospital_only(care_site_levels=care_site_levels):
        logger.info(
            "Biological measurements are only available at hospital level for now"
        )
        care_site_levels = "Hospital"

    biology_predictor = concatenate_predictor_by_level(
        predictor_by_level=biology_predictor_by_level,
        care_site_levels=care_site_levels,
    )

    return compute_completeness(self, biology_predictor)