PTB-XL Dataset, Classification Task, ResNet Models, and BiLSTM Model Implementation

docs/api/datasets.rst

@@ -238,6 +238,7 @@ Available Datasets
     datasets/pyhealth.datasets.BMDHSDataset
     datasets/pyhealth.datasets.COVID19CXRDataset
     datasets/pyhealth.datasets.ChestXray14Dataset
+    datasets/pyhealth.datasets.PTBXLDataset
     datasets/pyhealth.datasets.TUABDataset
     datasets/pyhealth.datasets.TUEVDataset
     datasets/pyhealth.datasets.ClinVarDataset

docs/api/datasets/pyhealth.datasets.PTBXLDataset.rst

@@ -0,0 +1,11 @@
+pyhealth.datasets.PTBXLDataset
+==============================
+
+PTB-XL is a publically available electrocardiography dataset. Contains 21837 samples from 18885 patients, all approximately 10 seconds in duration. For more information see `here <https://pmc.ncbi.nlm.nih.gov/articles/PMC7248071/>`_. 
+
+Kaggle: https://www.kaggle.com/datasets/physionet/ptbxl-electrocardiography-database
+
+.. autoclass:: pyhealth.datasets.PTBXLDataset
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api/models.rst

@@ -187,7 +187,11 @@ API Reference
     models/pyhealth.models.EHRMamba
     models/pyhealth.models.JambaEHR
     models/pyhealth.models.ContraWR
+    models/pyhealth.models.LambdaResNet18ECG
+    models/pyhealth.models.ResNet18ECG
+    models/pyhealth.models.SEResNet50ECG
     models/pyhealth.models.SparcNet
+    models/pyhealth.models.BiLSTMECG
     models/pyhealth.models.StageNet
     models/pyhealth.models.StageAttentionNet
     models/pyhealth.models.AdaCare

docs/api/models/pyhealth.models.BiLSTMECG.rst

@@ -0,0 +1,9 @@
+pyhealth.models.BiLSTMECG
+===================================
+
+Bidirectional LSTM for 12-lead ECG multi-label classification.
+
+.. autoclass:: pyhealth.models.BiLSTMECG
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api/models/pyhealth.models.LambdaResNet18ECG.rst

@@ -0,0 +1,24 @@
+pyhealth.models.LambdaResNet18ECG
+===================================
+
+1-D Lambda-ResNet-18 for ECG classification: Nonaka N. & Seita J., In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis. PMLR 149, 2021; lambda layer from Bello I., LambdaNetworks: Modeling Long-Range Interactions Without Attention. ICLR 2021.
+
+.. autoclass:: pyhealth.models.LambdaConv1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.LambdaBottleneck1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.LambdaResNet1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.LambdaResNet18ECG
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api/models/pyhealth.models.ResNet18ECG.rst

@@ -0,0 +1,29 @@
+pyhealth.models.ResNet18ECG
+===================================
+
+1-D ResNet-18 for ECG classification: Nonaka N. & Seita J., In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis. PMLR 149, 2021.
+
+.. autoclass:: pyhealth.models.BasicBlock1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.Bottleneck1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.ResNet1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.ECGBackboneModel
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.ResNet18ECG
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api/models/pyhealth.models.SEResNet50ECG.rst

@@ -0,0 +1,19 @@
+pyhealth.models.SEResNet50ECG
+===================================
+
+1-D SE-ResNet-50 for ECG classification: Nonaka N. & Seita J., In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis. PMLR 149, 2021; SE block from Hu J. et al., Squeeze-and-Excitation Networks. CVPR 2018.
+
+.. autoclass:: pyhealth.models.SEModule1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.SEResNetBottleneck1d
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.models.SEResNet50ECG
+    :members:
+    :undoc-members:
+    :show-inheritance: