Masked Self-Attention Dynamic Imputation Model for Physiological Indicators

Shaofeng Wu

doi:10.54097/8k4nek67

Authors

Shaofeng Wu

DOI:

https://doi.org/10.54097/8k4nek67

Keywords:

Intraoperative physiological indicators, data imputation, dynamic weighting, self-attention mechanism.

Abstract

Accurate imputation of missing and outlier values in intraoperative physiological indicators can assist doctors in swiftly taking measures to prevent risks during surgery, which in turn helps improve postoperative prognosis for patients. Traditional data imputation methods have focused too much on the current data itself, neglecting the contextual information provided by surrounding data points. Addressing this issue, the imputation process for intraoperative physiological indicator data obtained through monitoring has been enhanced with a model that employs a self-attention mechanism focusing on the data context for dynamic weighting during imputation. Experimental results indicate that the proposed model achieves a MAE of 2.06%, a RMSE of 7.08%, and a MRE of 2.8%, outperforming other comparative models.

Downloads

Download data is not yet available.

References

Joosten A, Lucidi V, Ickx B, et al. Intraoperative hypotension during liver transplant surgery is associated with postopera-tive acute kidney injury: a historical cohort study[J]. BMC anesthesiology, 2021, 21(1): 1-10.

Salmasi V, Maheshwari K, Yang D, Mascha EJ, Singh A, Sessler DI, Kurz A. Relationship between Intraoperative Hypotension, Defined by Either Reduction from Baseline or Absolute Thresholds, and Acute Kidney and Myocardial In-jury after Noncardiac Surgery: A Retrospective Cohort Anal-ysis. Anesthesiology. 2017 Jan;126(1):47-65.

Lundberg S M, Nair B, Vavilala M S, et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery[J]. Nature biomedical engineering, 2018, 2(10): 749-760.

Healy M A, Mullard A J, Campbell D A, et al. Hospital and payer costs associated with surgical complications[J]. JAMA surgery, 2016, 151(9): 823-830.

Choe, Sooho, et al. "Short-term event prediction in the operating room (STEP-OP) of five-minute intraoperative hypotension using hybrid deep learning: retrospective observational study and model development." JMIR Medical Informatics 9.9 (2021): e31311.

Moore L, Hanley J A, Lavoie A, et al. Evaluating the validity of multiple imputation for missing physiological data in the national trauma data bank[J]. Journal of emergencies, trauma, and shock, 2009, 2(2): 73-79.

Choe, Sooho, et al. "Short-term event prediction in the operating room (STEP-OP) of five-minute intraoperative hypotension using hybrid deep learning: retrospective observational study and model development." JMIR Medical Informatics 9.9 (2021): e31311.

Ribeiro S M, de Castro C L. Missing data in time series: A review of imputation methods and case study[J]. Learning and Nonlinear Models-Revista Da Sociedade Brasileira De Redes Neurais-Special Issue: Time Series Analysis and Forecasting Using Computational Intelligence, 2021, 19(2).

Ahn H, Sun K, Kim K P. Comparison of missing data imputation methods in time series forecasting[J]. Computers, Materials & Continua, 2022, 70(1): 767-779.

Fang C, Wang C. Time series data imputation: A survey on deep learning approaches[J]. arXiv preprint arXiv:2011.11347, 2020.

Wang J, Du W, Cao W, et al. Deep Learning for Multivariate Time Series Imputation: A Survey[J]. arXiv preprint arXiv:2402.04059, 2024.

Cao W , Wang D , Li J ,et al.BRITS: Bidirectional Recurrent Imputation for Time Series[J]. 2018.DOI:10.48550/arXiv.1805.10572.

Chaudhari S, Mithal V, Polatkan G, et al. An attentive survey of attention models[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2021, 12(5): 1-32.

Galassi A, Lippi M, Torroni P. Attention in natural language processing[J]. IEEE transactions on neural networks and learning systems, 2020, 32(10): 4291-4308.

Wu H, Xu J, Wang J, et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting[J]. Advances in Neural Information Processing Systems, 2021, 34: 22419-22430.

Shukla S N, Marlin B M. Multi-time attention networks for irregularly sampled time series[J]. arXiv preprint arXiv:2101.10318, 2021.

Du W, Côté D, Liu Y. Saits: Self-attention-based imputation for time series[J]. Expert Systems with Applications, 2023, 219: 119619.