|
基于改进的LF-Transformer脓毒症早期预测方法
|
Abstract:
在ICU电子病历脓毒症早期预测任务中,传统机器学习方法因难以捕捉稀疏表格数据中的动态特征交互而导致性能受限。为此,本研究提出改进的LF-Transformer深度学习模型,通过构建基于乘法算术块的特征交互增强方法,结合交互候选生成器(ICG)的动态top-k特征选择机制,有效提升了模型对稀疏医疗数据的表征能力。采用MIMIC-IV数据集验证模型性能,实验结果表明改进模型在脓毒症预测任务中AUROC达到0.841,特异度0.763,敏感性0.759,显著优于传统方法。该研究成果为开发ICU脓毒症智能预警系统提供了有效的算法支持,具有一定的临床实践价值。
In the task of early sepsis prediction using ICU electronic medical records, traditional machine learning methods suffer from performance limitations due to their inability to capture dynamic feature interactions in sparse tabular data. To address this, we propose an improved LF-Transformer deep learning model. By constructing a feature interaction enhancement method based on multiplicative arithmetic blocks and integrating a dynamic top-k feature selection mechanism via an Interaction Candidate Generator (ICG), the model significantly improves its representational capability for sparse medical data. Validated on the MIMIC-IV dataset, experimental results demonstrate that the enhanced model achieves an AUROC of 0.841, specificity of 0.763, and sensitivity of 0.759 in sepsis prediction, outperforming traditional methods significantly. This research provides effective algorithmic support for developing intelligent sepsis early warning systems in ICUs, offering practical clinical value.
[1] | Singer, M., Deutschman, C.S., Seymour, C.W., Shankar-Hari, M., Annane, D., Bauer, M., et al. (2016) The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA, 315, 801. https://doi.org/10.1001/jama.2016.0287 |
[2] | World Health Organization (2017) Improving the Prevention, Diagnosis, and Clinical Management of Sepsis. https://apps.who.int/gb/ebwha/pdf_files/eb140/b140_12-en.pdf |
[3] | Hu, C., Li, L., Huang, W., Wu, T., Xu, Q., Liu, J., et al. (2022) Interpretable Machine Learning for Early Prediction of Prognosis in Sepsis: A Discovery and Validation Study. Infectious Diseases and Therapy, 11, 1117-1132. https://doi.org/10.1007/s40121-022-00628-6 |
[4] | Srimedha, B.C., Naveen Raj, R. and Mayya, V. (2022) A Comprehensive Machine Learning Based Pipeline for an Accurate Early Prediction of Sepsis in ICU. IEEE Access, 10, 105120-105132. https://doi.org/10.1109/access.2022.3210575 |
[5] | Al-Mualemi, B.Y. and Lu, L. (2021) A Deep Learning-Based Sepsis Estimation Scheme. IEEE Access, 9, 5442-5452. https://doi.org/10.1109/access.2020.3043732 |
[6] | Zhou, A., Beyah, R. and Kamaleswaran, R. (2022) OnAI-Comp: An Online AI Experts Competing Framework for Early Sepsis Detection. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 19, 3595-3603. https://doi.org/10.1109/tcbb.2021.3122405 |
[7] | Dai, H., Hwang, H. and Tseng, V.S. (2023) Poems: Policy Network-Based Early Warning Monitoring System for Sepsis in Intensive Care Units. IEEE Journal of Biomedical and Health Informatics, 27, 3610-3621. https://doi.org/10.1109/jbhi.2023.3272486 |
[8] | Na, K., Lee, J. and Kim, E. (2024) LF-Transformer: Latent Factorizer Transformer for Tabular Learning. IEEE Access, 12, 10690-10698. https://doi.org/10.1109/access.2024.3354972 |
[9] | Cheng, Y., Hu, R., Ying, H., Shi, X., Wu, J. and Lin, W. (2024) Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 11516-11524. https://doi.org/10.1609/aaai.v38i10.29033 |