This is the official repository for CardioDiag. An externally validated and explainable machine learning framework for the diagnoses of diverse non-cardiac conditions.

CardioDiag have been proposed in four main manuscrips:

1. Estimation of Cardiac and Non-cardiac Diagnosis from Electrocardiogram Features Accepted by the international conference of computing in cardiology (CinC) 2024.

2. Electrocardiogram-based diagnosis of liver diseases: an externally validated and explainable machine learning approach

3. Explainable machine learning for neoplasms diagnosis via electrocardiograms: an externally validated study

4. Neuropsychiatric

In terms of input features, we use demographics such as age and gender, as well as ECG features such as RR-interval, PR-interval, QRS-duration, QT-interval, QTc-interval in milliseconds, P-wave axis, QRS-axis, as well as T-wave axis in degrees. All of the diagnoses are well-defined diagnoses by means of ICD10-CM codes.

References

@misc{alcaraz2024estimationcardiacnoncardiacdiagnosis,
      title={Estimation of Cardiac and Non-cardiac Diagnosis from Electrocardiogram Features}, 
      author={Juan Miguel Lopez Alcaraz and Nils Strodthoff},
      year={2024},
      eprint={2408.17329},
      archivePrefix={arXiv},
      primaryClass={eess.SP},
      url={https://arxiv.org/abs/2408.17329}, 
}

@misc{alcaraz2024electrocardiogrambaseddiagnosisliverdiseases,
      title={Electrocardiogram-based diagnosis of liver diseases: an externally validated and explainable machine learning approach}, 
      author={Juan Miguel Lopez Alcaraz and Wilhelm Haverkamp and Nils Strodthoff},
      year={2024},
      eprint={2412.03717},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2412.03717}, 
}

@misc{alcaraz2024explainablemachinelearningneoplasms,
      title={Explainable machine learning for neoplasms diagnosis via electrocardiograms: an externally validated study}, 
      author={Juan Miguel Lopez Alcaraz and Wilhelm Haverkamp and Nils Strodthoff},
      year={2024},
      eprint={2412.07737},
      archivePrefix={arXiv},
      primaryClass={eess.SP},
      url={https://arxiv.org/abs/2412.07737}, 
}