fastEIT

Python library for electrical impedance tomography (EIT) recordings of the Dräger PulmoVista 500 and of Timpel: it reads the files, prepares each breath and computes the clinical indices of tidal recordings and PEEP trials, as tables ready for a database or R.

Research use only

fastEIT is for research. It is not a medical device and has not been validated for clinical decisions.

From a file to the clinical indices

Each layer returns one object that holds the object of the layer before it:

Dräger .bin, Timpel .csv / .txt / .asc
 └─ load_data() ───────────► ReconstructedFrameData   layer 1: the file as it is (32x32 images)
     └─ preprocess() ──────► EITRecording             layer 2: the measured breaths
          ├─ tidal_features() ───────► TidalFeatures       layer 3: indices
          └─ segment_peep_trial() ───► PeepTrial           layer 2b: PEEP steps
               └─ peep_trial_features() ► PeepTrialFeatures  layer 3: indices
                    └─ recording_tables() ► tables, CSV        layer 4: export

The pipeline starts from reconstructed images. A Dräger .eit file holds the raw measurements (RawImpedanceData, 208 transimpedances per frame) and needs a reconstruction first; a Dräger .asc export holds signals only (ContinuousSignalData) and has no images (parsers).

Layer	What it does	How it works
1. Parsers	Dräger .bin, .eit, .asc and Timpel files to data containers	Parsers
2. Preprocessing	cardiac filter, breaths with quality flags, exclusions, lung mask, regions; auxiliary signals in cmH2O, L/s, mL; PEEP, plateau, driving pressure and tidal volume of each breath	Preprocessing
2b. Segmentation	PEEP steps from the pressure or placed by hand, breaths analysed, driving pressure and tidal volume of each step	Segmentation
3. Clinical indices	EELI, TIV, share by region, GI, centre of ventilation, compliance, Costa collapse and overdistension, changes between steps, recruitment-to-inflation ratio	Clinical indices
4. Export	one row per recording, breath and PEEP step, keyed by patient, recording and phase; a whole study at once; CSV for R, SPSS and Excel	Export

Every method states its source (paper and DOI, or the evidence notebook) and the reimplemented steps are checked against eitprocessing.

Start with the user guide: install and supported files, then analyse a recording, cut a recording, check it with the review figures and export the tables. The pages under "How it works" describe each layer and its choices; every function is in the API reference.