Related Links
Statistics
| Number of Journals | 8 |
| Number of Issues | 59 |
| Number of Articles | 438 |
| Article View | 160,434 |
| PDF Download | 105,373 |
Integration of Artificial Intelligence, Multi-Omics, and Digital Health for Precision Prevention of Preterm Birth: A Structured Narrative Review | ||
| World Journal of Peri & Neonatology | ||
| Articles in Press, Accepted Manuscript, Available Online from 20 July 2026 | ||
| Document Type: Scientific Review | ||
| Authors | ||
| Mahshid Bokaie1, 2; Roghayeh Ijabi* 3 | ||
| 1Research Center for Nursing and Midwifery Care, Comprehensive Research Institute for Maternal and Child Health, Shahid Sadoughi University of Medical Sciences, Yazd, Iran | ||
| 2School of Nursing and Midwifery, Shahid Sadoughi University of Medical Sciences, Yazd, Iran | ||
| 3Student research committee, School of Nursing and Midwifery, Shahid Sadoughi University of Medical Sciences, Yazd, Iran | ||
| Abstract | ||
| Background: Preterm birth (PTB) remains a leading cause of neonatal morbidity and mortality worldwide. Conventional prediction methods have limited accuracy, highlighting the need for precision prevention strategies that integrate molecular, clinical, and digital health data. Methods: A structured narrative review was conducted using PubMed, Scopus, and Web of Science to identify relevant studies published between 2010 and 2024. A total of 21 relevant studies were included and narratively synthesized into three thematic areas: multi-omics technologies, artificial intelligence (AI)-based prediction models, and digital health approaches for PTB prevention. Results: Multi-omics technologies, including genomics, transcriptomics, proteomics, metabolomics, and microbiome profiling, improved understanding of PTB pathophysiology and identified biomarkers associated with inflammation, immune dysregulation, oxidative stress, extracellular matrix remodeling, and placental dysfunction. AI models integrating clinical, imaging, laboratory, and molecular data demonstrated promising predictive performance, with reported area under the receiver operating characteristic curve (AUC) values ranging from approximately 0.61 to 0.94 where available. Ensemble machine learning and deep learning algorithms generally outperformed conventional statistical approaches. Digital health technologies, including wearable devices and remote monitoring systems, supported continuous maternal assessment and facilitated earlier identification of women at increased risk. However, limited external validation, heterogeneous datasets, model interpretability, and data privacy remain important challenges to clinical implementation. Conclusion: The integration of multi-omics technologies, AI, and digital health represents a promising strategy for precision prevention of PTB. Future research should prioritize multicenter validation, standardized data integration, and the development of transparent and clinically applicable AI models to facilitate translation into routine obstetric care. | ||
| Keywords | ||
| Preterm birth; Precision prevention; Artificial intelligence; Machine learning; Multi-omics; Digital health | ||
|
Statistics Article View: 1 |
||