Identifying cardiac abnormalities in multi-lead ECGs using hybrid neural network with fulcrum based data re-balancing

A system for identifying cardiac abnormalities in multi-lead electrocardiograms (ECGs), the system comprising:

• a memory storing instructions;
• one or more Input/Output (I/O) interfaces;
• and
• one or more hardware processors coupled to the memory via the one or more I/O interfaces, wherein the one or more hardware processors are configured by the instructions to:
• receive a training data set comprising a plurality of ECG recordings with multilabel-multiclass cardiac abnormalities, wherein each of the plurality of ECGs are sampled at varying frequencies;
• down sample the plurality of ECG recordings with a single frequency pre-identified statistically;
• prune the down sampled plurality of ECG recordings to generate a pruned training dataset by eliminating one or more ECG recordings that fail to capture information related to at least one cardiac abnormality among a set of cardiac abnormalities identified as a set scoring classes;
• slice each ECG recording in the pruned training data set to generate a windowed dataset of overlapping windows, and each ECG recording is segmented into predefined seconds window with a predefined percentage overlap, wherein the slicing reduces discrepancy between length of varied ECG recordings and the predefined percentage overlap enables to maintain all parts of the predefined seconds window into focus;
• apply a fulcrum-based data rebalancing technique on the windowed dataset to generate a rebalanced training dataset for the multiclass-multilabel cardiac abnormalities, and the fulcrum-based data rebalancing enables modifying existing balance in data being skewed in nature to maintain natural balance of the data and controls re-sample volume while supporting the lowly represented classes,
• wherein the fulcrum-based data rebalancing technique reduces bias introduced in a Deep Learning model (DL) model contributing to accuracy of a Hybrid Neural Network (HNN) architecture thereby improving multi-class classification or prediction of cardiac abnormality,
• wherein the fulcrum-based data rebalancing technique identifies most represented classes, treats rest of the classes as minority, augments rest of the classes to match the majority class, and the fulcrum-based data re-balancing technique maintains volume of dataset after rebalancing under control, wherein the fulcrum-based data rebalancing technique comprising:
• deriving a fulcrum point (Nfulcrum) of the windowed dataset from class frequency of each window in the windowed dataset based on one or more class labels from among the set of scoring classes assigned to each window, wherein one or more classes from among the set of scoring classes with class frequency above the fulcrum point are identified as majority classes, wherein classes with class frequency below the fulcrum point are identified as minority classes;
• and
• performing a random sampling on the windowed dataset that is identified under minority classes to reach the fulcrum point, wherein random sampling provides a representation at least equal to the fulcrum point to the minority classes, wherein the majority classes are excluded from the random sampling;
• and
• train the HNN architecture based DL model using the rebalanced training dataset to classify input ECG signal.

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:

• receiving, a training data set comprising a plurality of ECG recordings with multilabel-multiclass cardiac abnormalities, wherein each of the plurality of ECGs are sampled at varying frequencies;
• down sampling, via the one or more hardware processors, the plurality of ECG recordings with a single frequency pre-identified statistically;
• pruning, via the one or more hardware processors, the down sampled plurality of ECG recordings to generate a pruned training dataset by eliminating one or more ECG recordings that fail to capture information related to at least one cardiac abnormality among a set of cardiac abnormalities identified as a set scoring classes;
• slicing, via the one or more hardware processors, each ECG recording in the pruned training data set to generate a windowed dataset of overlapping windows, and each ECG recording is segmented into predefined seconds window with a predefined percentage overlap, wherein the slicing reduces discrepancy between length of varied ECG recordings and the predefined percentage overlap enables to maintain all parts of the predefined seconds window into focus;
• applying, via the one or more hardware processors, a fulcrum-based data rebalancing technique on the windowed dataset to generate a rebalanced training dataset for the multiclass-multilabel cardiac abnormalities, and the fulcrum-based data rebalancing enables modifying existing balance in data being skewed in nature to maintain natural balance of the data and controls re-sample volume while supporting the lowly represented classes,
• wherein the fulcrum-based data rebalancing technique reduces bias introduced in a Deep Learning model (DL) model contributing to accuracy of a Hybrid Neural Network (HNN) architecture thereby improving multi-class classification or prediction of cardiac abnormality,
• wherein the fulcrum-based data rebalancing technique identifies most represented classes, treats rest of the classes as minority, augments rest of the classes to match the majority class, and the fulcrum-based data re-balancing technique maintains volume of dataset after rebalancing under control, wherein the fulcrum-based data rebalancing technique comprising:
• deriving a fulcrum point (Nfulcrum) of the windowed dataset from class frequency of each window in the windowed dataset based on one or more class labels from among the set of scoring classes assigned to each window, wherein one or more classes from among the set of scoring classes with class frequency above the fulcrum point are identified as majority classes, wherein classes with class frequency below the fulcrum point are identified as minority classes;
• and
• performing a random sampling on the windowed dataset that is identified under minority classes to reach the fulcrum point, wherein random sampling provides a representation at least equal to the fulcrum point to the minority classes, wherein the majority classes are excluded from the random sampling;
• and
• training, via the one or more hardware processors, the HNN architecture based DL model using the rebalanced training dataset to classify input ECG signals.