Authors : Dipit Baidya

Volume/Issue : Volume 10 - 2025, Issue 5 - May

Google Scholar : https://tinyurl.com/ysuxc73b

DOI : https://doi.org/10.38124/ijisrt/25may502

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : In critical care settings, timely and accurate triage is essential to prevent patient deterioration. This study presents an integrated multimodal AI framework that combines chest X-ray imaging with vital signs data to improve the accuracy and speed of emergency triage decisions. By processing visual and physiological inputs in parallel, the proposed model predicts both the patient's current condition and the estimated time to a potential failure event. Experimental evaluation demonstrates that the multimodal model significantly outperforms unimodal baselines, achieving over 90% classification accuracy and a low mean absolute error in time-to-failure predictions. These findings suggest that combining diverse data sources can substantially enhance the effectiveness of clinical decision support systems [1], [2].

Keywords : AI in Healthcare, Emergency Triage, Multimodal Learning, Explainable AI, Clinical Workflow.

References :

1. R. Rajkomar, J. Dean, and I. Kohane, “Machine learning in medicine,” New England Journal of Medicine, vol. 380, no. 14, pp. 1347–1358, 2019.
2. M. Esteva et al., “A guide to deep learning in healthcare,” Nature Medicine, vol. 25, no. 1, pp. 24–29, 2019.
3. H. A. Haenssle et al., “Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition,” European Journal of Cancer, vol. 120, pp. 114–121, 2019.
4. Shickel, P. J. Tighe, A. Bihorac, and P. Rashidi, “Deep EHR: A survey of recent advances in deep learning techniques for electronic health record (EHR) analysis,” Journal of Biomedical Informatics, vol. 83, pp. 168–185, 2018.
5. J. Irvin et al., “CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison,” in Proc. AAAI Conf. Artificial Intelligence, vol. 33, pp. 590–597, 2019.
6. P. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning,” arXiv preprint arXiv:1711.05225, 2017.
7. Purushotham, C. Meng, Z. Che, and Y. Liu, “Benchmarking deep learning models on large healthcare datasets,” Journal of Biomedical Informatics, vol. 83, pp. 112–134, 2018.
8. Y. Zhang et al., “Multimodal deep learning for ECG and lab test-based cardiac risk prediction,” IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 2, pp. 492–503, 2022.
9. L. Li et al., “Fusion of CT and vitals data for trauma triage using deep learning,” in Proc. Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 701–711, 2023.
10. Khosla et al., “Multimodal AI for healthcare: Challenges and opportunities,” Nature Biomedical Engineering, vol. 6, no. 3, pp. 234–245, 2022.
11. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016.- 023-02367-1.
12. Niall Taylor, Andrey Kormilitzin, Isabelle Lorge, Alejo NevadoHolgado, Andrea Cipriani, Dan W. Joyce,Model development for bespoke large language models for digital triage assistance in mental health care,Artificial Intelligence in Medicine, Volume 157, 2024, 102988, ISSN09333657, https://doi.org/10.1016/j.a rtmed.2024.102988.
13. Yihao Liu, Xu Cao, Tingting Chen, Yankai Jiang, Junjie You, Minghua Wu, Xiaosong Wang, Mengling Feng, Yaochu Jin, Jintai Chen, From screens to scenes: A survey of embodied AI in healthcare, Information Fusion,  10.1016/j.inffus.2025.103033, 119, (103033), (2025). 
14. Chen YJ, Lin CS, Lin C, Tsai DJ, Fang WH, Lee CC, Wang CH, Chen SJ. An AIEnabled Dynamic Risk Stratification for Emergency Department Patients with ECG and CXR Integration. J Med Syst. 2023 Jul 31;47(1):81. doi:  10.1007/s10916-023-01980-x. PMID: 37523102. 
15. Enhancing Emergency Department Triage Equity With Artificial Intelligence: Outcomes From a Multisite Implementation, Annals of Emergency Medicine, Volume 85, Issue 3,2025,Pages 288-290,ISSN    0196-0644, https://doi.org/10.1016/j.annemergmed.2024.10.014.
16. (https://www.sciencedirect.com/science/article/pii/S0196064424011417)
17. Enhancing  Emergency Department Triage Equity With Artificial Intelligence: Outcomes From a Multisite Implementation,Annals of Emergency Medicine, Volume 85, Issue 3,2025,Pages 288-290,ISSN 01960644, https://doi.org/10.1016/j.annemergmed.2024.10.014.(httpse/article/pii/S0196064424011417)  
18. Peng Z, Ma R, Zhang Y, Yan M, Lu J, Cheng Q, Liao J, Zhang Y, Wang  J, Zhao Y, Zhu J, Qin B, Jiang Q, Shi F, Qian J, Chen X and Zhao C (2023) Development and evaluation of multimodal AI for diagnosis and triage of ophthalmic diseases using ChatGPT and anterior segment images: protocol for a two-stage cross-sectional study. Front. Artif. Intell.  6:1323924.  doi: 10.3389/frai.2023.1323924 
19. Q. Cai, H. Wang, Z. Li and X. Liu, "A Survey on Multimodal DataDriven Smart Healthcare Systems: Approaches and Applications," in IEEE Access, vol. 7, pp. 133583-133599,  2019,  doi: 10.1109/ACCESS.2019.2941419 
20. Porto, B.M. Improving triage performance in emergency departments using machine learning and natural language processing: a systematic review. BMC Emerg Med 24, 219 (2024). https://doi.org/10.1186/s12873024-01135-2