EUVIMEDEUVIMED entdecken
Crossref

Deep learning-based multimodal fusion of vibrational spectroscopy and clinical data for aortic dissection diagnosis and prognosis

Guangyao Ma, Lei Yan, Xuguang Zhou, Hui Yang, Chen Chen, Jing Tao, Hao Liu, Cheng Chen, Yining Yang

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-12 · 363 · 128391

DOI: 10.1016/j.saa.2026.128391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-12. Verfasst von Guangyao Ma und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, Xinjiang University, Urumqi 830046, China. Hauptthemen laut MEDLINE: Aortic Dissection, Spectrum Analysis, Raman, Deep Learning. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Xinjiang Uygur Autonomous Region Department of Science and Technology, National Natural Science Foundation of China, Excellent Young Scientists Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Aortic dissection and myocardial infarction are two life-threatening acute cardiovascular conditions with similar clinical presentations but fundamentally different treatment strategies. Misdiagnosis between these diseases can severely endanger patient survival, highlighting the urgent need for efficient and non-invasive differential diagnostic methods. Vibrational spectroscopy, characterized by its non-invasiveness, high throughput, and molecular sensitivity, offers a promising approach for early biochemical disease identification. However, single spectral modalities are limited in diagnostic performance due to insufficient complementary information. RESULTS: To address these limitations, we propose MSFusion, a multimodal deep learning model that integrates infrared and Raman spectroscopy data for precise diagnosis and survival prognosis prediction of aortic dissection. MSFusion employs a three-branch multiscale convolutional architecture to extract hierarchical spectral representations, incorporates a cross-modal attention module to promote semantic synergy and complementary interaction between modalities, and utilizes a bidirectional multiscale fusion mechanism to align local and global features across multiple granularities.Experimental results demonstrate that MSFusion achieves 95.63% accuracy and 98.79% AUC in distinguishing aortic dissection from myocardial infarction, significantly outperforming unimodal and conventional fusion approaches. For survival prognosis, the model is further extended by incorporating clinical indicators to predict postoperative survival outcomes, achieving 81.82% accuracy and 70.00% AUC, showing its capability for effective clinical risk stratification. SIGNIFICANCE: This study presents a multimodal deep learning framework that combines vibrational spectroscopy with clinical data for rapid and non-invasive diagnosis of aortic dissection. MSFusion effectively enhances diagnostic precision and prognostic reliability, providing a promising tool for intelligent cardiovascular disease assessment and clinical decision support.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Aortic DissectionSpectrum Analysis, RamanDeep LearningPrognosisHumansMyocardial InfarctionSpectrophotometry, InfraredDissection, Thoracic Aorta

Stichwörter der Autor:innen

Aortic dissectionCross-modal attentionFTIR spectroscopyMultiscale fusionPrognosis predictionRaman spectroscopy

Autor:innen und Institutionen

  • School of Software, Xinjiang University, Urumqi 830046, China.
  • College of Life Science and Technology, Xinjiang University, Urumqi, 830049, China; Department of Anesthesiology, People's Hospital of Xinjiang Uygur Autonomous Region, Xinjiang, 830001, China.
  • School of Computer Science and Technology, Xinjiang University, Urumqi 830049, China.
  • Xinjiang Cloud Computing Application Laboratory, Karamay, 830001, China; Xinjiang Hongyou Software Co., Ltd., Karamay, 830001, China.
  • Department of Cardiology, People's Hospital of Xinjiang Uygur Autonomous Region, Xinjiang, 830001, China; Xinjiang Key Laboratory of Cardiovascular Homeostasis and Regeneration Research, Xinjiang, 830001, China.
  • School of Software, Xinjiang University, Urumqi 830046, China; Xinjiang Key Laboratory of Cardiovascular Homeostasis and Regeneration Research, Xinjiang, 830001, China; MOE Key Laboratory of Bioinformatics, BNRIST Bioin…

Förderung

  • Xinjiang Uygur Autonomous Region Department of Science and Technology
  • National Natural Science Foundation of China
  • Excellent Young Scientists Fund
  • Natural Science Foundation for Young Scientists of Shanxi Province

Zitieren

APA

Ma, G., Yan, L., Zhou, X., Yang, H., Chen, C., Tao, J., Liu, H., Chen, C., & Yang, Y. (2026). Deep learning-based multimodal fusion of vibrational spectroscopy and clinical data for aortic dissection diagnosis and prognosis. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 363, 128391. https://doi.org/10.1016/j.saa.2026.128391

Vancouver

Ma G, Yan L, Zhou X, Yang H, Chen C, Tao J, et al. Deep learning-based multimodal fusion of vibrational spectroscopy and clinical data for aortic dissection diagnosis and prognosis. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;363:128391. doi:10.1016/j.saa.2026.128391

BibTeX
@article{Ma2026,
  author = {Ma, Guangyao and Yan, Lei and Zhou, Xuguang and Yang, Hui and Chen, Chen and Tao, Jing and Liu, Hao and Chen, Cheng and Yang, Yining},
  title = {Deep learning-based multimodal fusion of vibrational spectroscopy and clinical data for aortic dissection diagnosis and prognosis},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {363},
  pages = {128391},
  doi = {10.1016/j.saa.2026.128391}
}
Kostenlos starten →