CINC2018

class torch_ecg.databases.CINC2018(db_dir: str | bytes | PathLike | None = None, working_dir: str | bytes | PathLike | None = None, verbose: int = 1, **kwargs: Any)[source]

Bases: PhysioNetDataBase, PSGDataBaseMixin

You Snooze You Win - The PhysioNet Computing in Cardiology Challenge 2018

ABOUT

  1. includes 1,985 subjects, partitioned into balanced training (n = 994), and test sets (n = 989)

  2. signals include

    electrocardiogram (ECG), electroencephalography (EEG), electrooculography (EOG), electromyography (EMG), electrocardiology (EKG), oxygen saturation (SaO2), etc.

  3. frequency of all signal channels is 200 Hz

  4. units of signals:

    mV for ECG, EEG, EOG, EMG, EKG percentage for SaO2

  5. six sleep stages were annotated in 30 second contiguous intervals:

    wakefulness, stage 1, stage 2, stage 3, rapid eye movement (REM), undefined

  6. annotated arousals were classified as either of the following:

    spontaneous arousals, respiratory effort related arousals (RERA), bruxisms, hypoventilations, hypopneas, apneas (central, obstructive and mixed), vocalizations, snores, periodic leg movements, Cheyne-Stokes breathing, partial airway obstructions

  7. Webpage of the database on PhysioNet [1].

Usage

  1. sleep stage

  2. sleep apnea

References

Citation

10.22489/CinC.2018.049 10.13026/6phb-r450

Parameters:

  • db_dir (path-like, optional) – Storage path of the database. If not specified, data will be fetched from Physionet.

  • working_dir (path-like, optional) – Working directory, to store intermediate files and log files.

  • verbose (int, default 1) – Level of logging verbosity.

  • kwargs (dict, optional) – Auxilliary key word arguments.

property database_info: DataBaseInfo

The DataBaseInfo object of the database.

get_available_signals(rec: str | int) → List[str][source]

Get the available signals of the record.

Parameters:

rec (str or int) – Record name or index of the record in all_records.

Returns:

signals – Names of available signal of the record.

Return type:

List[str]

get_fs(rec: str | int) → int[source]

Get the sampling frequency of the record.

Parameters:

rec (str or int) – Record name or index of the record in all_records.

Returns:

fs – Sampling frequency of the record.

Return type:

int

get_siglen(rec: str | int) → int[source]

Get the length of the signal of the record.

Parameters:

rec (str or int) – Record name or index of the record in all_records.

Returns:

siglen – Length of the signal of the record.

Return type:

int

get_subject_id(rec: str) → int[source]

Attach a unique subject ID for the record.

Parameters:

rec (str or int) – Record name or index of the record in all_records.

Returns:

Subject ID associated with the record.

Return type:

int

load_ann(rec: str | int, sampfrom: int | None = None, sampto: int | None = None, keep_original: bool = False) → Dict[str, Dict[str, List[List[int]]]][source]

Load sleep stage and arousal annotations of the record.

Parameters:

  • rec (str or int) – Record name or index of the record in all_records.

  • sampfrom (int, optional) – Start index of the corresponding PSG data.

  • sampto (int, optional) – End index of the corresponding PSG data.

  • keep_original (bool, default False) – If True, indices will keep the same with the annotation file, otherwise subtract sampfrom if specified.

Returns:

A dictionary with keys “sleep_stages” and “arousals”, each of which is a dictionary with keys of sleep stages and arousals, and values of lists of lists of start and end indices of the sleep stages and arousals.

Return type:

dict

load_arousals_ann(rec: str | int, sampfrom: int | None = None, sampto: int | None = None, keep_original: bool = False) → Dict[str, List[List[int]]][source]

Load arousal annotations of the record.

Parameters:

  • rec (str or int) – Record name or index of the record in all_records.

  • sampfrom (int, optional) – Start index of the corresponding PSG data.

  • sampto (int, optional) – End index of the corresponding PSG data.

  • keep_original (bool, default False) – If True, indices will keep the same with the annotation file, otherwise subtract sampfrom if specified.

Returns:

A dictionary with keys of arousals and values of lists of lists of start and end indices of the arousals.

Return type:

dict

load_data(rec: str | int, sampfrom: int | None = None, sampto: int | None = None, data_format: str = 'channel_first', units: str | None = 'mV', fs: Real | None = None, return_fs: bool = False) → ndarray | Tuple[ndarray, Real][source]

Load ECG data of the record.

Parameters:

  • rec (str or int) – Record name or index of the record in all_records.

  • leads (str or int or Sequence[str] or Sequence[int], optional) – The leads of the ECG data to load. None or “all” for all leads.

  • sampfrom (int, optional) – Start index of the data to be loaded.

  • sampto (int, optional) – End index of the data to be loaded.

  • data_format (str, default "channel_first") – Format of the ECG data, “channel_last” (alias “lead_last”), or “channel_first” (alias “lead_first”), or “flat” (alias “plain”) which is valid only when leads is a single lead

  • units (str or None, default "mV") – Units of the output signal, can also be “μV” (aliases “uV”, “muV”). None for digital data, without digital-to-physical conversion.

  • fs (numbers.Real, optional) – Sampling frequency of the output signal. If not None, the loaded data will be resampled to this frequency, otherwise, the original sampling frequency will be used.

  • return_fs (bool, default False) – Whether to return the sampling frequency of the output signal.

Returns:

  • data (numpy.ndarray) – The ECG data loaded from the record, with given units and data_format.

  • data_fs (numbers.Real, optional) – Sampling frequency of the output signal. Returned if return_fs is True.

load_ecg_data(rec: str | int, sampfrom: int | None = None, sampto: int | None = None, data_format: str = 'channel_first', units: str | None = 'mV', fs: Real | None = None, return_fs: bool = False) → ndarray | Tuple[ndarray, Real][source]

Load ECG data of the record.

Parameters:

  • rec (str or int) – Record name or index of the record in all_records.

  • leads (str or int or Sequence[str] or Sequence[int], optional) – The leads of the ECG data to load. None or “all” for all leads.

  • sampfrom (int, optional) – Start index of the data to be loaded.

  • sampto (int, optional) – End index of the data to be loaded.

  • data_format (str, default "channel_first") – Format of the ECG data, “channel_last” (alias “lead_last”), or “channel_first” (alias “lead_first”), or “flat” (alias “plain”) which is valid only when leads is a single lead

  • units (str or None, default "mV") – Units of the output signal, can also be “μV” (aliases “uV”, “muV”). None for digital data, without digital-to-physical conversion.

  • fs (numbers.Real, optional) – Sampling frequency of the output signal. If not None, the loaded data will be resampled to this frequency, otherwise, the original sampling frequency will be used.

  • return_fs (bool, default False) – Whether to return the sampling frequency of the output signal.

Returns:

  • data (numpy.ndarray) – The ECG data loaded from the record, with given units and data_format.

  • data_fs (numbers.Real, optional) – Sampling frequency of the output signal. Returned if return_fs is True.

load_psg_data(rec: str | int, channel: str | Sequence[str] | None = None, sampfrom: int | None = None, sampto: int | None = None, data_format: str = 'channel_first', physical: bool = True, fs: Real | None = None, return_fs: bool = False) → ndarray | Tuple[ndarray, Real][source]

Load PSG data of the record.

Parameters:

  • rec (str or int) – Record name or index of the record in all_records.

  • channel (str, optional) – Nname of the channel of PSG data. If is None, all channels will be returned.

  • sampfrom (int, optional) – Start index of the data to be loaded.

  • sampto (int, optional) – End index of the data to be loaded.

  • data_format (str, default "channel_first".) – Format of the ECG data, “channel_last” (alias “lead_last”), or “channel_first” (alias “lead_first”), or “flat” (alias “plain”) which is valid only when only one channel is passed.

  • physical (bool, default True) – If True, the data will be converted to physical units, otherwise, the data will be in digital units.

  • fs (numbers.Real, optional) – Sampling frequency of the output signal. If not None, the loaded data will be resampled to this frequency, otherwise, the original sampling frequency will be used.

  • return_fs (bool, default False) – Whether to return the sampling frequency of the output signal.

Returns:

  • data (numpy.ndarray) – PSG data corr. to the given channel of the record.

  • data_fs (numbers.Real, optional) – Sampling frequency of the output signal.

load_sleep_stages_ann(rec: str | int, sampfrom: int | None = None, sampto: int | None = None, keep_original: bool = False) → Dict[str, List[List[int]]][source]

Load sleep stage annotations of the record.

Parameters:

  • rec (str or int) – Record name or index of the record in all_records.

  • sampfrom (int, optional) – Start index of the corresponding PSG data.

  • sampto (int, optional) – End index of the corresponding PSG data.

  • keep_original (bool, default False) – If True, indices will keep the same with the annotation file, otherwise subtract sampfrom if specified.

Returns:

A dictionary with keys of sleep stages and values of lists of lists of start and end indices of the sleep stages.

Return type:

dict

plot() → None[source]

NOT implemented yet.

plot_ann(rec: str | int) → tuple[source]

Plot the sleep stage and arousal annotations of the record.

Parameters:

rec (str or int) – Record name or index of the record in all_records.

Returns:

  • fig (matplotlib.figure.Figure) – The figure object.

  • ax (matplotlib.axes.Axes) – The axes object.

TODO

Plot arousals events.

set_subset(subset: str | None) → None[source]

Set the subset of the database to use.