CapnoBase

• Home

CapnoBase is a collaborative research project that provides user friendly research tools and an online database of respiratory signals obtained from capnography and spirometry.
The database contains annotated respiratory signals such as inhaled and exhaled carbon-dioxide (CO2) also known as capnogram, respiratory flow, and pressure. The database also includes a benchmark dataset.
Before the creation of CapnoBase, there was no benchmark dataset publically available for respiratory signal analysis. Ideally, a benchmark dataset is required to objectively assess and compare algorithm performance.

 

 

CapnoBase contains both capnography and spirometry signals. We have divided the data into three types of datasets:

In-Vivo dataset

The in-vivo dataset contains capnography signals that were recorded during real clinical cases. Any information that could possibly identify the source of the data has been removed.

Simulation dataset

The simulation dataset was produced with a computer model that simulates the behavior of the human cardio-respiratory system.
Producing artificial capnography signals is useful when signals that are otherwise hard to obtain are required, or when the condition or change in state of the patient must to be precisely known.

Benchmark dataset

The CapnoBase benchmark dataset contains 44 scenarios that were recorded in the same manner as the in-vivo dataset. The scenarios contain very typical capnography and spirometry signals or patient conditions that may arise during anesthesia.
The benchmark dataset is used by researchers to test and compare algorithms. This dataset should not be used to train or tune an algorithm as it may bias the performance results.

CapnoBase provides software tools to annotate and evaluate respiratory signals. For more information, see the Download and Tutorial sections.