pyhealth.tasks.temple_university_EEG_tasks#

pyhealth.tasks.temple_university_EEG_tasks.EEG_isAbnormal_fn(record)[source]#

Processes a single patient for the abnormal EEG detection task on TUAB.

Abnormal EEG detection aims at determining whether a EEG is abnormal.

Parameters:

record –

a singleton list of one subject from the TUABDataset. The (single) record is a dictionary with the following keys:

load_from_path, patient_id, visit_id, signal_file, label_file, save_to_path

Returns:

a list of samples, each sample is a dict with patient_id, visit_id, record_id,

and epoch_path (the path to the saved epoch {“signal”: signal, “label”: label} as key.

Return type:

samples

Note that we define the task as a binary classification task.

Examples

>>> from pyhealth.datasets import TUABDataset
>>> isabnormal = TUABDataset(
...         root="/srv/local/data/TUH/tuh_eeg_abnormal/v3.0.0/edf/", download=True,
...     )
>>> from pyhealth.tasks import EEG_isabnormal_fn
>>> EEG_abnormal_ds = isabnormal.set_task(EEG_isAbnormal_fn)
>>> EEG_abnormal_ds.samples[0]
{
    'patient_id': 'aaaaamye',
    'visit_id': 's001',
    'record_id': '1',
    'epoch_path': '/home/zhenlin4/.cache/pyhealth/datasets/832afe6e6e8a5c9ea5505b47e7af8125/10-1/1/0.pkl',
    'label': 1
}
pyhealth.tasks.temple_university_EEG_tasks.EEG_events_fn(record)[source]#

Processes a single patient for the EEG events task on TUEV.

This task aims at annotating of EEG segments as one of six classes: (1) spike and sharp wave (SPSW), (2) generalized periodic epileptiform discharges (GPED), (3) periodic lateralized epileptiform discharges (PLED), (4) eye movement (EYEM), (5) artifact (ARTF) and (6) background (BCKG).

Parameters:

record –

a singleton list of one subject from the TUEVDataset. The (single) record is a dictionary with the following keys:

load_from_path, patient_id, visit_id, signal_file, label_file, save_to_path

Returns:

a list of samples, each sample is a dict with patient_id, visit_id, record_id, label, offending_channel,

and epoch_path (the path to the saved epoch {“signal”: signal, “label”: label} as key.

Return type:

samples

Note that we define the task as a multiclass classification task.

Examples

>>> from pyhealth.datasets import TUEVDataset
>>> EEGevents = TUEVDataset(
...         root="/srv/local/data/TUH/tuh_eeg_events/v2.0.0/edf/", download=True,
...     )
>>> from pyhealth.tasks import EEG_events_fn
>>> EEG_events_ds = EEGevents.set_task(EEG_events_fn)
>>> EEG_events_ds.samples[0]
{
    'patient_id': '0_00002265',
    'visit_id': '00000001',
    'record_id': 0,
    'epoch_path': '/Users/liyanjing/.cache/pyhealth/datasets/d8f3cb92cc444d481444d3414fb5240c/0_00002265_00000001_0.pkl',
    'label': 6,
    'offending_channel': array([4.])
}
pyhealth.tasks.temple_university_EEG_tasks.BuildEvents(signals, times, EventData)[source]#
pyhealth.tasks.temple_university_EEG_tasks.convert_signals(signals, Rawdata)[source]#
pyhealth.tasks.temple_university_EEG_tasks.readEDF(fileName)[source]#