Install and supported files

Install

pip install git+https://github.com/Kernel236/fastEIT.git

Python 3.10 to 3.12. For development (tests, linting) and to build this site:

git clone https://github.com/Kernel236/fastEIT.git
cd fastEIT
pip install -e ".[dev,docs]"
mkdocs serve        # the site at http://127.0.0.1:8000/fastEIT/

Supported files

The analysis starts from reconstructed images (32x32 pixels per frame):

File	Read as	Analysed
Dräger PulmoVista 500 .bin	ReconstructedFrameData (images and ventilator signals)	yes
Timpel .csv, .txt, .asc export	ReconstructedFrameData	yes
Dräger .eit	RawImpedanceData (208 raw measurements per frame)	no: needs a reconstruction first
Dräger .asc export	ContinuousSignalData (signals only)	no: no images

load_data(path) recognises the vendor and the format by itself. Large .bin and .eit files are not read into memory at once: the images and measurements are read from disk when they are used.

The four steps

from fasteit.export import recording_tables, write_csv
from fasteit.features import tidal_features
from fasteit.models import RecordingContext
from fasteit.parsers.loader import load_data
from fasteit.preprocessing import preprocess

raw = load_data("recording.bin")                                   # 1. read the file
recording = preprocess(raw, context=RecordingContext(patient_id="P01", label="T0"))  # 2. breaths
features = tidal_features(recording)                               # 3. clinical indices
write_csv(recording_tables(features), "results/")                  # 4. tables for R and SPSS

Each step returns an object that keeps the one before it, with a log of what was done. A PEEP trial adds one step (segment_peep_trial) between 2 and 3. The user guide goes through the steps: analyse a recording (both protocols), cut a recording, review figures and export for R and SPSS. How each layer works is under "How it works" (data model).

Research use only - not a medical device.