IRO Journals
Journal of Trends in Computer Science and Smart Technology

Diagnostic Preservation After ECG Digitization: From Risk Stratification to Reliability Assurance

Open Access
Published: 12 October, 2026
Pages: 978-992
  • Thai Nho Nguyen , Thai Nho Nguyen
    Faculty of Information Technology, Industrial University of Ho Chi Minh City, Vietnam / Faculty of Mechanical Engineering, Saigon Technology University, Ho Chi Minh City, Vietnam
    Faculty of Information Technology, Industrial University of Ho Chi Minh City, Vietnam / Faculty of Mechanical Engineering, Saigon Technology University, Ho Chi Minh City, Vietnam
  • Van Thang Doan Van Thang Doan
    Faculty of Mechanical Engineering, Saigon Technology University, Ho Chi Minh City, Vietnam
    Faculty of Mechanical Engineering, Saigon Technology University, Ho Chi Minh City, Vietnam
view PDF
view PDF

How to Cite

Nguyen, Thai Nho, and Van Thang Doan. 2026. “Diagnostic Preservation After ECG Digitization: From Risk Stratification to Reliability Assurance”. Journal of Trends in Computer Science and Smart Technology 8 (4): 978-92. https://doi.org/10.36548/jtcsst.2026.4.004.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

ECG Digitization
Diagnostic Information Preservation
Reliability Assessment
Risk Stratification
Decision Stability
Calibration

Abstract

As Electrocardiogram (ECG) digitization becomes increasingly accurate, waveform similarity alone does not establish preservation of diagnostically relevant information. This study investigates whether post-digitization diagnostic instability can be identified without access to the native digital ECG and whether such reference-free observability is sufficient to support reliability assurance. PTB-XL waveforms were rendered as 3×4 ECG pages at 25 mm/s, 10 mm/mV, and 4 pixels/mm and re-digitized with a fixed image-based trace-recovery pipeline. Analyses on PTB-XL showed that unobserved lead-time regions contributed only limited incremental diagnostic information under the tested setting, indicating that missing temporal support alone could not explain the observed preservation loss. A reference-free instability score derived solely from digitized ECGs retained above-chance record-level discrimination on a patient-disjoint cohort (AUROC 0.614, unitless, for distinguishing ECGs with versus without at least one probe-defined new diagnostic error), but calibration deteriorated after population transfer. Selective acceptance reduced the occurrence of probe-defined new diagnostic errors without satisfying the multimetric preservation requirements, while class-wise analysis revealed strongly directional and diagnosis-dependent failures. Application to 99 real-world ECGs from Tam Duc Hospital further showed that the representation remained technically applicable despite structured feature-domain shifts. These findings establish a distinction between risk observability and preservation assurance: diagnostic instability can be partially stratified without an oracle reference, but successful ranking alone is insufficient to guarantee stable diagnostic decisions or calibrated reliability

References

  1. Wagner, Patrick, Nils Strodthoff, Ralf-Dieter Bousseljot, Dieter Kreiseler, Fatima I. Lunze, Wojciech Samek, and Tobias Schaeffter. ”PTB-XL, A Large Publicly Available Electrocardiography Dataset.” Scientific data 7, no. 1 (2020): 154.
  2. Strodthoff, Nils, Patrick Wagner, Tobias Schaeffter, and Wojciech Samek. ”Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL.” IEEE journal of biomedical and health informatics 25, no. 5 (2020): 1519-1528.
  3. Ribeiro, Antônio H., Manoel Horta Ribeiro, Gabriela MM Paixão, Derick M. Oliveira, Paulo R. Gomes, Jéssica A. Canazart, Milton PS Ferreira et al. ”Automatic Diagnosis of the 12-lead ECG Using a Deep Neural Network.” Nature communications 11, no. 1 (2020): 1760.
  4. Reyna, Matthew A., Weigle J. Deepanshi, Zuzana Koscova, Andoni Elola, Salman Seyedi, Kiersten Campbell, Gari D. Clifford, and Reza Sameni. ”Digitization and classification of ECG Images: The George b. Moody Physionet Challenge 2024.” Computing in Cardiology 51 (2024): 1-4.
  5. Shivashankara, Kshama Kodthalu, Deepanshi, Afagh Mehri Shervedani, Gari D. Clifford, Matthew A. Reyna, and Reza Sameni. ”ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization.” Physiological measurement 45, no. 5 (2024): 055019.
  6. Demolder, Anthony, Viera Kresnakova, Michal Hojcka, Vladimir Boza, Andrej Iring, Adam Rafajdus, Simon Rovder et al. ”High Precision ECG Digitization Using Artificial Intelligence.” medRxiv (2024): 2024-08.
  7. Stenhede, Elias, Agnar Martin Bjørnstad, and Arian Ranjbar. ”Digitizing Paper ECGs at Scale: An Open-Source Algorithm for Clinical Research.” NPJ Digital Medicine 9, no. 1 (2026): 145.
  8. Sahiner, Berkman, Weijie Chen, Ravi K. Samala, and Nicholas Petrick. ”Data Drift in Medical Machine Learning: Implications and Potential Remedies.” The British Journal of Radiology 96, no. 1150 (2023): 20220878.
  9. Liou, Lathan, Erick Scott, Prathamesh Parchure, Yuxia Ouyang, Natalia Egorova, Robert Freeman, Ira S. Hofer et al. ”Assessing Calibration and Bias of a Deployed Machine Learning Malnutrition Prediction Model Within a Large Healthcare System.” NPJ Digital Medicine 7, no. 1 (2024): 149.
  10. dos Santos Silva, Gabriel Ferreira, Fabiano Novaes Barcellos Filho, Roberta Moreira Wichmann, Francisco Costa da Silva Junior, and Alexandre Dias Porto Chiavegatto Filho. ”Strategies for Detecting and Mitigating Dataset Shift in Machine Learning for Health Predictions: A Systematic Review.” Journal of Biomedical Informatics (2025): 104902.
  11. Obianom, Ekenedirichukwu N., G. André Ng, and Xin Li. ”Reconstruction of 12-lead ECG: A Review of Algorithms.” Frontiers in Physiology 16 (2025): 1532284.
  12. Presacan, Oriana, Alexandru Dorobanţiu, Jonas L. Isaksen, Tobias Willi, Claus Graff, Michael A. Riegler, Arun R. Sridhar, Jørgen K. Kanters, and Vajira Thambawita. ”Evaluating the Feasibility of 12-lead Electrocardiogram Reconstruction from Limited Leads Using Deep Learning.” Communications medicine 5, no. 1 (2025): 139.
  13. Nakanishi, Ryuichi, Akimasa Hirata, and Yoshiki Kubota. ”Deep Learning-Based Multi-Lead ECG Reconstruction from Lead I with Metadata Integration and Uncertainty Estimation.” Sensors 26, no. 1 (2025): 212.
  14. Hu, Haoyang, Zekai Yu, Feiwei Qin, and Fei Yang. ”From One to Twelve: Feasibility and Clinical Utility of Deep Learning-Derived 12-lead ECGs for Remote Cardiac Monitoring.” Frontiers in Cardiovascular Medicine 13 (2026): 1856637.
  15. Chen, Xingyu, Xianyou Zeng, Quansheng Xu, Lei Dai, and Yonghong Xu. ”Arbitrary Single-lead to 12-lead ECG Reconstruction via Convolutional Mamba-UNet with Physiological Constraints.” Neurocomputing (2026): 134590.
  16. Wei, Xiaoyang, Zhiyuan Li, Yuanyuan Tian, Mengxiao Wang, Yanrui Jin, Weiping Ding, and Chengliang Liu. ”Condition-Fusion-and-Hiding Denoising Diffusion Model for Electrocardiogram Lead Reconstruction.” Iscience 29, no. 4 (2026).
  17. Zhang, Xinyu, Hailing Cai, Huilong Duan, and Xudong Lu. ”Systematic Benchmark of Reduced-Lead Configurations for 12-lead ECG Reconstruction: Multi-Model Evaluation Across All Possible Subsets.” Frontiers in Cardiovascular Medicine 13 (2026): 1856211.
  18. Rajagopal, Anjali, Shant Ayanian, Alexander J. Ryu, Ray Qian, Sean R. Legler, Eric A. Peeler, Meltiady Issa, Trevor J. Coons, and Kensaku Kawamoto. ”Machine Learning Operations in Health Care: A Scoping Review.” Mayo Clinic Proceedings: Digital Health 2, no. 3 (2024): 421-437.
  19. Rafiei, Alireza, Trisha Dwivedi, Joel Xue, Daphne E. Schlesinger, Nasim Katebi, David E. Albert, and Gari D. Clifford. ”Toward Self-validating ECG Systems: A Personalized, Uncertainty-Aware Approach for Detecting and Estimating Lead Misplacement.” Journal of Electrocardiology (2026): 154204.
  20. Yu, Xiankai, Jian Wu, Jiahao Wang, Mingjie Wang, Yi-Gang Li, and Wenjie Cai. ”SLPM: A Lightweight Deep Learning Model for End-to-End Paper ECG Digitization.” Physiological Measurement 47, no. 2 (2026): 025005.
  21. Wang, Xiang, and Jie Yang. ”A Systematic Method Combining Rotated Convolution and State Space Augmented Transformer for Digitizing and Classifying Paper ECGs.” Symmetry 17, no. 1 (2025): 120.