Hierarchical Transformer Model with Uncertainty-Aware Attention for Predicting Delayed Cerebral Ischemia after Aneurysmal Subarachnoid Hemorrhage Using Hourly Neurological and Vital Sign Data

cirpublications.com-6vLd-1790874883-i719094821 1790874883 Clinical Intelligence Research Press info@cirpublications.com Clinical Intelligence Research Press Journal of Artificial Intelligence for Healthcare Systems J. Artif. Intell. Healthc. Syst. 3149-8981 2026 5 2 Hierarchical Transformer Model with Uncertainty-Aware Attention for Predicting Delayed Cerebral Ischemia after Aneurysmal Subarachnoid Hemorrhage Using Hourly Neurological and Vital Sign Data John Miller Mark Davis Ethan Clark 2026 10.68159/i719094821 https://cirpublications.com/pub/journal/1/article/i719094821 Hoh BL, Ko NU, Amin-Hanjani S, Chou SH, Cruz-Flores S, Dangayach NS, et al. 2023 guideline for the management of patients with aneurysmal subarachnoid hemorrhage: a guideline from the American Heart Association/American Stroke Association. Stroke. 2023;54(7):e314-70. 10.1161/STR.0000000000000436 Treggiari MM, Rabinstein AA, Busl KM, Caylor MM, Citerio G, Deem S, et al. Guidelines for the neurocritical care management of aneurysmal subarachnoid hemorrhage. Neurocrit Care. 2023;39(1):1-28. 10.1007/s12028-023-01713-8 Abdulazim A, Heilig M, Rinkel G, Etminan N. Diagnosis of delayed cerebral ischemia in patients with aneurysmal subarachnoid hemorrhage and triggers for intervention. Neurocrit Care. 2023;39(2):311-9. 10.1007/s12028-023-01741-4 Ramos LA, van der Steen WE, Barros RS, Majoie CB, van den Berg R, Verbaan D, et al. Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage. J Neurointerv Surg. 2019;11(5):497-502. 10.1136/neurintsurg-2018-014305 Savarraj JP, Hergenroeder GW, Zhu L, Chang T, Park S, Megjhani M, et al. Machine learning to predict delayed cerebral ischemia and outcomes in subarachnoid hemorrhage. Neurology. 2021;96(4):e553-62. 10.1212/WNL.0000000000011242 Willms JF, Inauen C, Bögli SY, Muroi C, Boss JM, Keller E. A longitudinal model for a dynamic risk score to predict delayed cerebral ischemia after subarachnoid hemorrhage. Bioengineering (Basel). 2024;11(10):988. 10.3390/bioengineering11100988 Che Z, Purushotham S, Cho K, Sontag D, Liu Y. Recurrent neural networks for multivariate time series with missing values. Sci Rep. 2018;8(1):6085. 10.1038/s41598-018-24271-9 Pramanik R, Sikdar R, Sarkar R. Transformer-based deep reverse attention network for multi-sensory human activity recognition. Eng Appl Artif Intell. 2023;122:106150. 10.1016/j.engappai.2023.106150 An Y, Liu Y, Chen X, Sheng Y. TERTIAN: Clinical endpoint prediction in ICU via time-aware transformer-based hierarchical attention network. Comput Intell Neurosci. 2022;2022:4207940. Tipirneni S, Reddy CK. Self-supervised transformer for sparse and irregularly sampled multivariate clinical time-series. ACM Trans Knowl Discov Data. 2022;16(6):1-27. 10.1145/3531290 Lim B, Arık SÖ, Loeff N, Pfister T. Temporal fusion transformers for interpretable multi-horizon time series forecasting. Int J Forecast. 2021;37(4):1748-64. 10.1016/j.ijforecast.2021.03.012 Li J, Wang C, Su W, Ye D, Wang Z. Uncertainty-aware self-attention model for time series prediction with missing values. Fractal Fract. 2025;9(3):181. 10.3390/fractalfract9030181 van der Steen WE, Leemans EL, van den Berg R, Roos YB, Marquering HA, Verbaan D, et al. Radiological scales predicting delayed cerebral ischemia in subarachnoid hemorrhage: systematic review and meta-analysis. Neuroradiology. 2019;61(3):247-56. 10.1007/s00234-018-2166-1 Santana LS, Diniz JB, Rabelo NN, Teixeira MJ, Figueiredo EG, Telles JP, et al. Machine learning algorithms to predict delayed cerebral ischemia after subarachnoid hemorrhage: a systematic review and meta-analysis. Neurocrit Care. 2024;40(3):1171-81. 10.1007/s12028-024-01935-2 Zhang H, Zou P, Luo P, Jiang X. Machine learning for the early prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage: systematic review and meta-analysis. J Med Internet Res. 2025;27:e54121. 10.2196/54121 Mohammadzadeh I, Niroomand B, Eini P, Khaledian H, Choubineh T, Luzzi S. Leveraging machine learning algorithms to forecast delayed cerebral ischemia following subarachnoid hemorrhage: a systematic review and meta-analysis of 5,115 participants. Neurosurg Rev. 2025;48(1):26. 10.1007/s10143-024-03311-1 Shukla SN, Marlin BM. Multi-time attention networks for irregularly sampled time series. arXiv [Preprint]. 2021:arXiv:2101.10318. Zhao D, Shi Y, Cheng L, Li H, Zhang L, Guo H. Time interval uncertainty-aware and text-enhanced based disease prediction. J Biomed Inform. 2023;139:104239. 10.1016/j.jbi.2023.104239 Wickstrøm K, Mikalsen KØ, Kampffmeyer M, Revhaug A, Jenssen R. Uncertainty-aware deep ensembles for reliable and explainable predictions of clinical time series. IEEE J Biomed Health Inform. 2021;25(7):2435-44. 10.1109/JBHI.2020.3046516 Du W, Côté D, Liu Y. SAITS: Self-attention-based imputation for time series. Expert Syst Appl. 2023;219:119619. 10.1016/j.eswa.2023.119619 Saleh H, El-Sappagh S, McCann M, Alsamhi SH, Breslin JG. Multivariate multi-horizon time-series forecasting for real-time patient monitoring based on cascaded fine tuning of attention-based models. Comput Biol Med. 2025;194:110406. 10.1016/j.compbiomed.2025.110406 Harerimana G, Kim JW, Jang B. A multi-headed transformer approach for predicting the patient’s clinical time-series variables from charted vital signs. IEEE Access. 2022;10:105993-6004. 10.1109/ACCESS.2022.3211662 Xu Y, Xu S, Ramprassad M, Tumanov A, Zhang C. TransEHR: Self-supervised transformer for clinical time series data. In: Proceedings of Machine Learning for Health (ML4H). PMLR; 2023. p. 623-35. He R, Chiang JN. Simultaneous forecasting of vital sign trajectories in the ICU. Sci Rep. 2025;15(1):14996. 10.1038/s41598-025-99433-4 Ma F, Chitta R, Zhou J, You Q, Sun T, Gao J. Dipole: Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2017 Aug 13; Halifax, Canada. ACM; 2017. p. 1903-11. 10.1145/3097983.3098088 Azzam AY, Vaishnav D, Essibayi MA, Unda SR, Jabal MS, Liriano G, et al. Prediction of delayed cerebral ischemia followed aneurysmal subarachnoid hemorrhage: a machine-learning based study. J Stroke Cerebrovasc Dis. 2024;33(4):107553. 10.1016/j.jstrokecerebrovasdis.2024.107553 Ge S, Chen J, Wang W, Zhang LB, Teng Y, Yang C, et al. Predicting who has delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage using machine learning approach: a multicenter, retrospective cohort study. BMC Neurol. 2024;24(1):177. 10.1186/s12883-024-03683-2 Liu Y, Li C, Wang H. Machine learning-driven risk prediction of delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage using peripheral inflammatory markers. Front Neurol. 2025;16:1713341. 10.3389/fneur.2025.1713341 Mao M, Zhou R, Chen Y, Wei J, Lin M, Li W. Construction of a nomogram model for predicting delayed cerebral ischemia in aneurysmal subarachnoid hemorrhage patients. Sci Rep. 2025;15(1):17739. 10.1038/s41598-025-02161-1 Chen S, Jiang H, He P, Tang X, Chen Q. New grading scale based on early factors for predicting delayed cerebral ischemia in patients with aneurysmal subarachnoid hemorrhage: a multicenter retrospective study. Front Neurol. 2024;15:1393733. 10.3389/fneur.2024.1393733 Schenck H, van Craenenbroeck C, van Kuijk S, Gommer E, Veldeman M, Temel Y, et al. Systematic review and meta-analysis of transcranial doppler biomarkers for the prediction of delayed cerebral ischemia following subarachnoid hemorrhage. J Cereb Blood Flow Metab. 2025;45(6):1031-47. 10.1177/0271678X251320145 Xu W, Dai Y, Yang Y, Loza M, Zhang W, Cui Y, et al. OmniTFT: Omni target forecasting for vital signs and laboratory result trajectories in multi center ICU data. arXiv [Preprint]. 2025 Nov 23:arXiv:2511.19485.