EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-driven transcriptomic biomarker discovery for early identification of pediatric deterioration in Acute Care

Qing Wang, Lina Sun, Wei Meng, Chen Chen

SLAS Technology · 2025

DOI: 10.1016/j.slast.2025.100357 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SLAS Technology, 2025. Verfasst von Qing Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Pediatric Internal Medicine, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang City, Heilongjiang Province,China. Electronic ad…. Hauptthemen laut MEDLINE: Biomarkers, Gene Expression Profiling, Artificial Intelligence, Transcriptome. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early detection of juvenile clinical deterioration in acute care settings remains a significant problem in modern healthcare. This paper presents an AI-powered predictive analytics platform that combines transcriptome biomarker signals with structured vital signs, laboratory data, and unstructured clinical notes to improve early warning capabilities. The system uses ClinicalBERT to extract insights from clinical narratives, XGBoost to analyze tabular clinical information, and long short-term memory (LSTM) networks to simulate temporal dynamics. A meta-classifier combines multimodal data to produce real-time risk ratings for clinical deterioration. The performance evaluation utilizing five-fold cross-validation showed great accuracy, with an AUROC of 0.91, AUPRC of 0.83, and an average early warning lead time of 5.6 hours. Predictive markers included higher lactate levels, heart rate patterns, SpO₂ variability, and transcriptome signals indicating systemic inflammatory activation. Ablation investigations proved the importance of multimodal data fusion in increasing prediction robustness. The suggested strategy provides a scalable, interpretable, and high-performing hospital integration system that enables biomarker-informed, precision-based pediatric intervention options.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BiomarkersGene Expression ProfilingArtificial IntelligenceTranscriptomeClinical DeteriorationHumansChildEarly Diagnosis

Stichwörter der Autor:innen

Artificial intelligenceClinical decision supportClinicalBERTLSTMPediatric deteriorationPredictive analyticsTranscriptomic Biomarkers

Substanzen

Biomarkers

Autor:innen und Institutionen

  • Pediatric Internal Medicine, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang City, Heilongjiang Province,China. Electronic address: Qing_wang_edu@outlook.com.
  • Pediatric Internal Medicine, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang City, Heilongjiang Province,China. Electronic address: Lina_Sun_edu@outlook.com.
  • Pediatric Internal Medicine, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang City, Heilongjiang Province,China. Electronic address: Wei_meng123@outlook.com.
  • Department of Nursing Care,Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang City, Heilongjiang Province,China. Electronic address: Chen_Chen_123@outlook.com.

Zitieren

APA

Wang, Q., Sun, L., Meng, W., & Chen, C. (2025). AI-driven transcriptomic biomarker discovery for early identification of pediatric deterioration in Acute Care. SLAS Technology. https://doi.org/10.1016/j.slast.2025.100357

Vancouver

Wang Q, Sun L, Meng W, Chen C. AI-driven transcriptomic biomarker discovery for early identification of pediatric deterioration in Acute Care. SLAS Technology. 2025. doi:10.1016/j.slast.2025.100357

BibTeX
@article{Wang2025,
  author = {Wang, Qing and Sun, Lina and Meng, Wei and Chen, Chen},
  title = {AI-driven transcriptomic biomarker discovery for early identification of pediatric deterioration in Acute Care},
  journal = {SLAS Technology},
  year = {2025},
  doi = {10.1016/j.slast.2025.100357}
}
Kostenlos starten →