Durations

This section shows how to use the duration functionality of Episuite. The main class of this module is the Durations, that represents any kind of duration between events. One example is representing the length of stay (also known as LoS) for patients in ICU units.

Note

In the example below, we will use a sample dataset that comes embedded in Episuite with real data from the SARS-CoV-2 outbreak in south of Brazil. This dataset can be accessed using the admissions_sample() function from the data module.

See also

Module episuite.durations

Documentation of the episuite.durations module.

Module episuite.data

Documentation of the episuite.data module.

import episuite
from matplotlib import pyplot as plt

from episuite.durations import Durations
from episuite import data

Load the sample data

First we need to load a sample dataset.

sample_data = data.admissions_sample()

sample_data.head()

	DATE_START	DATE_END	OUTCOME
0	2020-06-17	2020-08-03	RECOVERY
1	2020-06-11	2020-06-21	DEATH
2	2020-07-12	2020-08-02	DEATH
3	2020-06-25	2020-07-31	DEATH
4	2020-07-24	2020-08-16	DEATH

sample_data.shape

(4538, 3)

# Here we are filtering only outcomes that were RECOVERY or DEATH.
sample_data = sample_data[sample_data["OUTCOME"].isin(["RECOVERY", "DEATH"])]

Build the durations object

Here we are going to build the durations object. Please note that this class requires you to specify the start and end date column names. By default, it will assume that the columns are named DATE_START and DATE_END.

adm = Durations(sample_data)

Data visualization

The durations have a plot object that you can use to make visualizations of the duration distribution.

fig = plt.figure(figsize=(7, 4))
adm.plot.histogram()
plt.xlim(0, 80)
plt.show()

fig = plt.figure(figsize=(7, 3))
adm.plot.histogram(hue="OUTCOME")
plt.xlim(0, 80)
plt.show()

fig = plt.figure(figsize=(7, 4))
adm.plot.density(hue="OUTCOME")
plt.xlim(0, 80)
plt.show()

<Figure size 504x288 with 0 Axes>

This plot shows the average distribution per day. In this case we are computing 100 bootstrap samples to compute the default confidence interval (CI 95%).

fig = plt.figure(figsize=(10, 5))
adm.plot.timeplot(n_boot=100)
plt.show()

fig = plt.figure(figsize=(10, 5))
adm.plot.timeplot(n_boot=100, hue="OUTCOME")
plt.show()

Getting Started ICU - Admissions