Temporal Dynamics in Intraoperative Monitoring: A Novel LSTM-Based Framework for Multivariate Time Series Classification in Critical Care Events
DOI:
https://doi.org/10.65405/jzcjpc82Keywords:
Deep learning, LSTM, time series classification, intraoperative monitoring, critical care events, MOVER dataset, multivariate physiological signalsAbstract
Using the MOVER dataset, a novel Temporal Context-Aware LSTM (TC-LSTM) for multivariate time-series classification of crucial intraoperative events is presented in this study. TC-LSTM clearly captures inter-observation intervals, uses context-aware imputation for missing values, and applies temporal attention to emphasize clinically significant windows, in contrast to traditional recurrent models that assume regular sampling or neglect temporal gaps. This research study model outperforms LSTM (82.1%), GRU (83.4%), T-LSTM (85.5%), Neural ODEs (84.3%), and Transformers (85.0%) under identical patient-disjoint splits, achieving a macro-F1 score of 89.7% and AUC of 92.3% on 1,247 surgical cases with five expert-annotated event types. TC-LSTM's ability to learn from sparse, irregular data without interpolation artifacts is demonstrated via the improvements, which are particularly noticeable for hemorrhage, a rare but high-mortality event, where it increases F1 via over 7 points relative to baselines. Each component contributes significantly, according to ablation experiments; performance is reduced via 2.4–4.7% when time embedding or attention are removed. Importantly, attention weights are in line with recognized hemodynamic antecedents, yet the architecture is nevertheless lightweight and comprehensible. This work fills a gap that is frequently overlooked in favor of architectural innovation via proposing a methodical, physiology-informed adaptation of current technologies to a real clinical situation rather than a new deep learning paradigm. In addition, The findings highlight the need of characterizing temporal irregularity as signal rather than noise for effective medical AI and set a new standard for time-series classification in operating room monitoring.
Downloads
References
1. Abdalla Almagalfata, Mehmet Etlioglu.(2025). The impact of using artificial intelligence to help Libyan students. December 2025. DOI: 10.13140/RG.2.2.15608.51208
2. Samad, M., Angel, M., Rinehart, J., Kanomata, Y., Baldi, P., & Cannesson, M. (2023). Medical Informatics Operating Room Vitals and Events Repository (MOVER): a public-access operating room database. JAMIA open, 6(4), ooad084.
4. Abdalla Almagalfata, Mehmet Etlioglu. (2025). Leveraging Artificial intelligence AI for Branding: Consumer Behavior Insights from Aljaied For Food Industries in Libya Case Study: Aljaied For Food Industries.DOI: 10.13140/RG.2.2.32158.60489
5. Ben Dalla, L. O. F., Medeni, T. D., Medeni, I. T., & Ulubay, M. (2025). Enhancing Healthcare Efficiency at Almasara Hospital: Distributed Data Analysis and Patient Risk Management. Economy: Strategy and Practice, 19(4), 54–72. https://doi.org/10.51176/1997-9967-2024-4-54-72
6. Aggarwal, N., Drew, D. A., Parikh, R. B., & Guha, S. (2024). Ethical implications of artificial intelligence in gastroenterology: the co-pilot or the captain?. Digestive diseases and sciences, 69(8), 2727-2733.
7. Celik, U., Korkmaz, A., & Stoyanov, I. (2025). Integrating Process Mining and Machine Learning for Surgical Workflow Optimization: A Real-World Analysis Using the MOVER EHR Dataset. Applied Sciences, 15(20), 11014.
8. Бен Далла Л., Медени Т.Д., Медени И.Т., Улубай М. Повышение эффективности здравоохранения в больнице Алмасара: анализ распределенных данных и управление рисками для пациентов. Economy: strategy and practice. 2024;19(4):54-72. https://doi.org/10.51176/1997-9967-2024-4-54-72
9. Hölzer, H. T., Niklas, C., Tenckhoff, S., Feisst, M., Hölle, T., Dugas, M., ... & Larmann, J. (2025). Heidelberg Perioperative Deep Data Registry and Biomaterial Bank (HeiPoDD Registry and Bio Bank): study protocol for a prospective single-centre registry and biobank for patients undergoing high-risk non-cardiac surgery in a German university hospital. BMJ open, 15(9), e098589.
10. Dalla, L. O. F. B. (2020). IT security Cloud Computing. In (2020 IT security Cloud Computing Conference (ISCC) (pp. 1-8). IEEE.
11. Hao, X., Wang, Y., Li, K., Zhu, T., & Herasevich, V. (2025). Applying machine learning for perioperative adverse event prediction: a narrative review toward better clinical efficacy and usability. Anesthesiology and Perioperative Science, 3(4), 1-17.
12. Dalla, L. O. B., Karal, Ö., Degirmenci, A., EL-Sseid, M. A. M., Essgaer, M., & Alsharif, A. (2025). Edge Intelligence for Real-Time Image Recognition: A Lightweight Neural Scheduler Via Using Execution-Time Signatures on Heterogeneous Edge Devices. Journal homepage: https://sjphrt. com. ly/index. php/sjphrt/en/index, 1(2), 74-85.
13. Lonsdale, H., Burns, M. L., Epstein, R. H., Hofer, I. S., Tighe, P. J., Delgado, J. A. G., ... & McCormick, P. J. (2025). Strengthening discovery and application of artificial intelligence in anesthesiology: A report from the Anesthesia Research Council. Anesthesia & Analgesia, 140(4), 920-930.
14. Ben Dalla, L., Medeni, T. M., Zbeida, S. Z., & Medeni, İ. M. (2024). Unveiling the Evolutionary Journey based on Tracing the Historical Relationship between Artificial Neural Networks and Deep Learning. The International Journal of Engineering & Information Technology (IJEIT), 12(1), 104-110.
15. Foy, B. H., Carlson, J. C., Aguirre, A. D., & Higgins, J. M. (2025). Platelet-white cell ratio is more strongly associated with mortality than other common risk ratios derived from complete blood counts. Nature Communications, 16(1), 1113.
16. Dalla, L. O. F. B. (2020). The Influence of hospital management framework by the usage of Electronic healthcare record to avoid risk management (Department of Communicable Diseases at Misurata Teaching Hospital: Case study). Nature Communications, 12(5), 7685.
17. Kauffman, J., Holmes, E., Vaid, A., Charney, A. W., Kovatch, P., Lampert, J., ... & Nadkarni, G. N. (2025). InfEHR: Clinical phenotype resolution through deep geometric learning on electronic health records. Nature Communications, 16(1), 8475.
18. Idrobo-Ávila, E., Bognár, G., Krefting, D., Penzel, T., Kovács, P., & Spicher, N. (2024). Quantifying the suitability of biosignals acquired during surgery for multimodal analysis. IEEE Open Journal of Engineering in Medicine and Biology, 5, 250-260.
19. Yuan, Y., Tamo, J. B., Shi, W., Zhong, Y., Nnamdi, M. C., Brenn, B. R., ... & Wang, M. D. (2025, October). Developing Fairness-Aware Task Decomposition to Improve Equity in Post-Spinal Fusion Complication Prediction. In Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 1-10).
20. Dalla, L. O. B., Karal, Ö., & Degirmenciyi, A. (2025). Leveraging LSTM for Adaptive Intrusion Detection in IoT Networks: A Case Study on the RT-IoT2022 Dataset implemented On CPU Computer Device Machine. 5th International Conference on Engineering, Natural and Social Sciences April 15-16, 2025: Konya, Turkey © 2025 Published by All Sciences Academy, https://www.icensos.com/
21. Degirmenci, A., & Karal, O. (2022). Efficient density and cluster based incremental outlier detection in data streams. Information Sciences, 607, 901-920.
22. Karal, O. (2017). Maximum likelihood optimal and robust support vector regression with lncosh loss function. Neural networks, 94, 1-12.
23. Karal, Ö. (2020). Performance comparison of different kernel functions in SVM for different k value in k-fold cross-validation. In 2020 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1-5). IEEE.
24. Ersoy, E., & Karal, Ö. (2012). Yapay sinir ağları ve insan beyni. İnsan ve Toplum Bilimleri Araştırmaları Dergisi, 1(2), 188-205.
25. Degirmenci, A., & Karal, O. (2021). Robust incremental outlier detection approach based on a new metric in data streams. IEEE Access, 9, 160347-160360.
26. KARAL, Ö. (2018). Destek vektör regresyon ile EKG verilerinin sıkıştırılması. Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 2018(2018).
27. Apaydın, M., Yumuş, M., Değirmenci, A., & Karal, Ö. (2022). Evaluation of air temperature with machine learning regression methods using Seoul City meteorological data. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 28(5), 737-747.
28. Degirmenci, A., & Karal, O. (2018). Evaluation of kernel effects on svm classification in the success of wart treatment methods. Am. J. Eng. Res, 7, 238-244.
29. Karim, A. M., Karal, Ö., & Çelebi, F. V. (2018, July). A new automatic epilepsy serious detection method by using deep learning based on discrete wavelet transform. In Proceedings of the 3rd International Conference on Engineering Technology and Applied Sciences (ICETAS) (Vol. 4, pp. 15-18).
30. Degirmenci, A., & Karal, O. (2022). iMCOD: Incremental multi-class outlier detection model in data streams. Knowledge-Based Systems, 258, 109950.
31. Yalman, Y., Uyanık, T., Atlı, İ., Tan, A., Bayındır, K. Ç., Karal, Ö., ... & Guerrero, J. M. (2022). Prediction of voltage sag relative location with data-driven algorithms in distribution grid. Energies, 15(18), 6641.
32. AteGçi, Y. Z., AydoLdu, Ö., Karaköse, A., Pekedis, M., & Karal, Ö. (2014). Erratum to ‘‘Does Urinary Bladder Shape Affect Urinary Flow Rate in Men with Lower Urinary Tract Symptoms?’’.
33. Karaoglu, A. N., Caglar, H., Degirmenci, A., & Karal, O. (2021). Performance improvement with decision tree in predicting heart failure. In 2021 6th International Conference on Computer Science and Engineering (UBMK) (pp. 781-784). IEEE.
34. Yumuş, M., Apaydın, M., Değirmenci, A., & Karal, Ö. (2020). Missing data imputation using machine learning based methods to improve HCC survival prediction. In 2020 28th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
35. Karal, O., & Tokgoz, N. (2023). Dose optimization and image quality measurement in digital abdominal radiography. Radiation Physics and Chemistry, 205, 110724.
36. Esen, F., Degirmenci, A., & Karal, O. (2021). Implementation of the object detection algorithm (YOLOV3) on FPGA. In 2021 innovations in intelligent systems and applications conference (ASYU) (pp. 1-6). IEEE.
37. Tokgöz, N., Değirmenci, A., & Karal, Ö. (2024). Machine Learning-Based Classification of Turkish Music for Mood-Driven Selection. Journal of Advanced Research in Natural and Applied Sciences, 10(2), 312-328.
38. Yang, H., Steinbach, M., Melton, G., Kumar, V., & Simon, G. (2025). Combining self-supervision and privileged information for representation learning from tabular data. Knowledge and Information Systems, 1-29.
39. Karal, Ö., & Dalla, L. O. F. B. Lung Nodule Characterization in CT Scans Using Hybrid 3D Attention U-Net Segmentation and Transfer Learning-Based Classification Approach.
40. Kale, G., Bostancı, G. E., & Celebi, F. V. (2024). Evolutionary feature selection for machine learning based malware classification. Engineering Science and Technology, an International Journal, 56, 101762.
41. Murin, P. J., Prabhune, A. S., & Martins, Y. C. (2025). Optimizing Multivariable Logistic Regression for Identifying Perioperative Risk Factors for Deep Brain Stimulator Explantation: A Pilot Study. Clinics and Practice, 15(7), 132.
42. Keles, A., Algin, O., Ozisik, P. A., ŞEN, B., & Vehbi Çelebi, F. (2023). Segmentation of spinal subarachnoid lumen with 3D attention U-Net. Journal of Mechanics in Medicine and Biology, 23(04), 2340011.
43. Çelebi, F., Duran, M., & Bicakci, A. A. (2023). Comparison of pain perception caused by aligner and conventional fixed orthodontic treatments. IP Indian Journal of Orthodontics and Dentofacial Research, 8(4), 231-236.
44. Keles, A., Ozisik, P. A., Algin, O., Celebi, F. V., & Bendechache, M. (2024). Decoding pulsatile patterns of cerebrospinal fluid dynamics through enhancing interpretability in machine learning. Scientific Reports, 14(1), 17854.
45. Gergerli, B., Çelebi, F. V., Rahebi, J., & Şen, B. (2023). An Approach Using in Communication Network Apply in Healthcare System Based on the Deep Learning Autoencoder Classification Optimization Metaheuristic Method. Wireless Personal Communications, 1-24.
46. Celebi, F., Arici, N., & Canli, E. (2017). The effects of non-extraction fixed orthodontic treatment on the vertical mandibular bone level. Indian Journal of Orthodontics and Dentofacial Research, 3(1), 48-52.
47. Ruffolo, I., Siddiqui, A., Nguyen, B., Dixon, W., Assadi, A., Greer, R., ... & Goodwin, A. (2025). High-Fidelity Measurement of Pulse Arrival Time in Critically Ill Children Using Standard Bedside Monitoring Equipment. medRxiv, 2025-03.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Comprehensive Journal of Science
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
