Optimizing ECG Audits: Clustering-Based Identification of Ambiguous Exams

• Pedro B. Rigueira UFMG
• Guilherme H. G. Evangelista UFMG
• Luisa G. Porfírio UFMG
• Caio Souza Grossi UFMG
• Arthur Buzelin UFMG
• Gisele L. Pappa UFMG
• Gabriela M. M. Paixão Hospital das Clínicas da UFMG
• Antonio Ribeiro Hospital das Clínicas da UFMG
• Wagner Meira Jr. UFMG

DOI: https://doi.org/10.5753/eniac.2024.245283

Resumo

Electrocardiograms (ECG’s) are crucial tools for diagnosing heart diseases, and regular audits of these exams are essential to maintain diagnostic consistency, ensure quality standards, and secure the reliability of medical databases. However, the current practice of randomly selecting ECG’s for audit can be inefficient, as it often includes cases with clear, uncontroversial diagnoses. In this paper, we present an unsupervised method that uses clustering techniques to identify ECG’s with a higher likelihood of diagnostic ambiguity. Our approach identifies a group of exams with an average ambiguity rate of 38,98%, which is over three times higher than the 12% observed in conventional audit methods.

Palavras-chave: Electrocardiogram, ECG, Clustering, Audit, Machine Learning

Referências

Assent, I. (2012). Clustering high dimensional data. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2(4):340–350.

Banerjee, S. and Mitra, M. (2014). Application of cross wavelet transform for ecg pattern analysis and classification. IEEE Transactions on Instrumentation and Measurement, 63(2):326–333.

Berkaya, S. K., Uysal, A. K., Gunal, E. S., Ergin, S., Gunal, S., and Gulmezoglu, M. B. (2018). A survey on ecg analysis. Biomedical Signal Processing and Control, 43:216–235.

Bujang, M. A., Ab Ghani, P., Zolkepali, N. A., Adnan, T. H., Ali, M. M., Selvarajah, S., and Haniff, J. (2012). A comparison between convenience sampling versus systematic sampling in getting the true parameter in a population: Explore from a clinical database: The audit diabetes control management (adcm) registry in 2009. In 2012 international conference on statistics in science, business and engineering (ICSSBE), pages 1–5. IEEE.

Chiang, H.-T., Hsieh, Y.-Y., Fu, S.-W., Hung, K.-H., Tsao, Y., and Chien, S.-Y. (2019). Noise reduction in ecg signals using fully convolutional denoising autoencoders. IEEE Access, 7:60806–60813.

de Chazal, P., O’Dwyer, M., and Reilly, R. (2004). Automatic classification of heart-beats using ecg morphology and heartbeat interval features. IEEE Transactions on Biomedical Engineering, 51(7):1196–1206.

Fournier, Q. and Aloise, D. (2019). Empirical comparison between autoencoders and traditional dimensionality reduction methods. In 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), pages 211–214. IEEE.

Gomes, P. R. et al. (2020). Sistema de laudos de eletrocardiograma: a importância de ferramentas de suporte à decisão.

HSE (2013). A Practical Guide to Clinical Audit. Health Service Executive (HSE) Quality and Patient Safety Directorate, Dublin, Ireland.

Johnston, G., Crombie, I., Alder, E., Davies, H., and Millard, A. (2000). Reviewing audit: barriers and facilitating factors for effective clinical audit. BMJ Quality & Safety, 9(1):23–36.

Kiranyaz, S., Ince, T., and Gabbouj, M. (2016). Real-time patient-specific ecg classification by 1-d convolutional neural networks. IEEE Transactions on Biomedical Engineering, 63(3):664–675.

Leland, M., John, H., and James, M. (2018). Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426.

Lima, E. M., Ribeiro, A. H., Paixão, G. M. M., Ribeiro, M. H., Pinto-Filho, M. M., Gomes, P. R., Oliveira, D. M., Sabino, E. C., Duncan, B. B., Giatti, L., Barreto, S. M., Meira Jr, W., Schön, T. B., and Ribeiro, A. L. P. (2021). Deep neural network-estimated electrocardiographic age as a mortality predictor. Nature Communications, 12(1):5117.

Lyon, A., Mincholé, A., Martínez, J. P., Laguna, P., and Rodriguez, B. (2018). Computational techniques for ecg analysis and interpretation in light of their contribution to medical advances. Journal of The Royal Society Interface, 15(138):20170821.

Macfarlane, P., Devine, B., Latif, S., McLaughlin, S., Shoat, D., and Watts, M. (1990). Methodology of ecg interpretation in the glasgow program. Methods of Information in Medicine, 29(4):354 – 361. Cited by: 120.

Macfarlane, P. W. and Latif, S. (1996). Automated serial ecg comparison based on the minnesota code. Journal of Electrocardiology, 29:29–34.

McInnes, L., Healy, J., Astels, S., et al. (2017). hdbscan: Hierarchical density based clustering. J. Open Source Softw., 2(11):205.

Moulavi, D., Jaskowiak, P. A., Campello, R. J., Zimek, A., and Sander, J. (2014). Density-based clustering validation. In Proceedings of the 2014 SIAM international conference on data mining, pages 839–847. SIAM.

Nezamabadi, K., Sardaripour, N., Haghi, B., and Forouzanfar, M. (2023). Unsupervised ecg analysis: A review. IEEE Reviews in Biomedical Engineering, 16:208–224.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit-learn: Machine learning in python. Journal of machine learning research, 12(Oct):2825–2830.

Ribeiro, A. H., Paixao, G. M., Lima, E. M., Horta Ribeiro, M., Pinto Filho, M. M., Gomes, P. R., Oliveira, D. M., Meira Jr, W., Schon, T. B., and Ribeiro, A. L. P. (2021). CODE-15%: a large scale annotated dataset of 12-lead ECGs.

Ribeiro, A. H., Ribeiro, M. H., Paixão, G. M., Oliveira, D. M., Gomes, P. R., Canazart, J. A., Ferreira, M. P., Andersson, C. R., Macfarlane, P. W., Meira Jr, W., et al. (2020). Automatic diagnosis of the 12-lead ecg using a deep neural network. Nature communications, 11(1):1760.

Ribeiro, A. L. P., Paixão, G. M., Gomes, P. R., Ribeiro, M. H., Ribeiro, A. H., Canazart, J. A., Oliveira, D. M., Ferreira, M. P., Lima, E. M., de Moraes, J. L., Castro, N., Ribeiro, L. B., and Macfarlane, P. W. (2019). Tele-electrocardiography and big-data: The code (clinical outcomes in digital electrocardiography) study. Journal of Electrocardiology, 57:S75–S78.

Roopa, C. and Harish, B. (2017). A survey on various machine learning approaches for ecg analysis. International Journal of Computer Applications, 163(9):25–33.

Wang, W., Huang, Y., Wang, Y., and Wang, L. (2014). Generalized autoencoder: A neural network framework for dimensionality reduction. In 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 496–503.