Open
Conversation
added 3 commits
April 4, 2026 00:56
…mark) - PTBXLDataset: inherits BaseDataset, parses ptbxl_database.csv into ptbxl-metadata-pyhealth.csv, supports 100/500 Hz sampling rates - PTBXLDiagnosis: multilabel task (ROC-AUC), maps SCP codes to 5 superclasses - PTBXLMulticlassDiagnosis: multiclass task (F1), selects dominant superclass - configs/ptbxl.yaml: BaseDataset config for the ptbxl table - 23 unit tests using synthetic data only (3s total) - Ablation script: examples/ptbxl_ecg_diagnosis_resnet.py - RST docs + toctree entries for datasets.rst and tasks.rst Reproduces: Nonaka, K. & Seita, D. (2021). In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis. PMLR 149, 414-424.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Contributor: Ankita Jain (ankitaj3@illinois.edu), Manish Singh (manishs4@illinois.edu)
University of Illinois Urbana-Champaign
Contribution Type: Dataset + Task (Option 1)
Original Paper: Nonaka, K., & Seita, D. (2021). In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis. Proceedings of Machine Learning Research, 149, 414–424.
https://proceedings.mlr.press/v149/nonaka21a.html
Description: Adds PTB-XL ECG dataset and two diagnosis tasks reproducing the benchmark from Nonaka & Seita (2021).
Files to Review:
pyhealth/datasets/ptbxl.py- Main dataset implementationpyhealth/datasets/configs/ptbxl.yaml- Dataset configpyhealth/tasks/ptbxl_diagnosis.py- PTBXLDiagnosis (multilabel) + PTBXLMulticlassDiagnosis (multiclass)tests/core/test_ptbxl.py- 27 tests, synthetic data onlyexamples/ptbxl_ecg_diagnosis_resnet.py- Ablation studydocs/api/datasets/pyhealth.datasets.PTBXLDataset.rst- Dataset docsdocs/api/tasks/pyhealth.tasks.PTBXLDiagnosis.rst- Task docs