Visualization
This library provides a visualization tool that aggregates the data to provide two interactive dashboards and a summary table describing various statistical properties of your biological data.
Input
It expects a Data object containing the following OMOP format tables:
Measurement
The function can be used on raw data or on the transformed data returned by the bioclean function .
from eds_scikit.io import HiveData
from eds_scikit.biology import plot_biology_summary
db_name = "cse_xxxxxxx_xxxxxxx"
tables = ["measurement", "concept", "concept_relationship", "visit_occurrence", "care_site"]
data = HiveData(db_name, tables_to_load=tables)
plot_biology_summary(data)
Output
plot_biology_summary() creates a folder for each concepts-set. For instance, let us see what you will find in the folder Glucose_Blood_Quantitative`.
Summary table
A statistical summary table as below:
| LOINC_concept_code | AnaBio_concept_code | LOINC_concept_name | AnaBio_concept_name | unit_source_value | count | mean | std | min | 25% | 50% | 75% | max | MAD | max_threshold | min_threshold | care_site_short_name | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 395136991232 | 14749-6 | A0141 | Glucose [Moles/Volume] Serum/Plasma - Numerique | Glucose_Serum/Plasma_mmol/L | mmol/l | 691358.0 | 6.63218 | 6.55476 | 0.0 | 4.9 | 5.69 | 7.16 | 4500.0 | 1.4652 | 11.5508 | 0.0 | ALL |
| 704374636544 | 14749-6 | F2406 | Glucose [Moles/Volume] Serum/Plasma - Numerique | Glucose Fibromax_Serum/Plasma_mmol/L | mmol/l | 108.0 | 6.761852 | 3.534022 | 2.0 | 4.99 | 5.8 | 7.09 | 29.37 | 1.4504 | 11.6016 | 0.0 | ALL |
| 824633720832 | 14749-6 | A7339 | Glucose [Moles/Volume] Serum/Plasma - Numerique | Glucose h?_Serum/Plasma_mmol/L | mmol/l | 600.0 | 5.690167 | 2.524383 | 0.7 | 4.5 | 5.1 | 6.1 | 24.2 | 1.036 | 9.244 | 0.956 | ALL |
| 893353197568 | 14749-6 | B9553 | Glucose [Moles/Volume] Serum/Plasma - Numerique | Glucose_Plasma_mmol/L | mmol/l | 26635.0 | 6.731067 | 3.334219 | 1.3 | 4.8 | 5.6 | 7.4 | 66.4 | 1.48 | 11.52 | 0.0 | ALL |
| 1082331758592 | 2345-7 | E7312 | Glucose SerPl-mCnc | Glucose_Serum/Plasma_mg/dL | mg/dl | 119144.0 | 117.097998 | 242.990109 | 3.6 | 84.6 | 99.0 | 124.2 | 81045.0 | 24.124 | 195.496 | 2.504 | ALL |
| 1511828488192 | 14749-6 | A8424 | Glucose [Moles/Volume] Serum/Plasma - Numerique | Glucose_Plasma FNA_mmol/L | mmol/l | 103334.0 | 6.667987 | 3.790141 | 0.1 | 4.8 | 5.6 | 7.3 | 160.9 | 1.48 | 11.52 | 0.0 | ALL |
| 8589934592 | 14749-6 | A0141 | Glucose [Moles/Volume] Serum/Plasma - Numerique | Glucose_Serum/Plasma_mmol/L | mmol/l | 83756.0 | 6.650058 | 3.138156 | 0.01 | 5.05 | 5.78 | 7.17 | 93.35 | None | None | None | CARE SITE 10 |
| 34359738368 | 2345-7 | E7312 | Glucose SerPl-mCnc | Glucose_Serum/Plasma_mg/dL | mg/dl | 8.0 | 109.325 | 46.192261 | 72.0 | 72.0 | 95.4 | 106.0 | 216.0 | None | None | None | CARE SITE 2 |
| 103079215104 | 14749-6 | A0141 | Glucose [Moles/Volume] Serum/Plasma - Numerique | Glucose_Serum/Plasma_mmol/L | mmol/l | 99030.0 | 6.725521 | 3.319078 | 0.2 | 5.0 | 5.8 | 7.3 | 89.9 | None | None | None | CARE SITE 11 |
| 154618822656 | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
Volumetry dashboard
An interactive dashboard describing the volumety properties over time.
An example is available here.
Distribution dashboard
An interactive dashboard describing the distribution properties.
An example is available here.