Emerging Molecular Biomarkers and AI-Integrated Models for Early Prediction of Preeclampsia: A Systematic Review
Keywords:
Pre-eclampsia; Cell-free DNA; cfDNA fragmentomics; Extracellular vesicles; Artificial intelligence; First-trimester screening; Placental dysfunction; Non-invasive biomarkersAbstract
Background Pre-eclampsia (PE) remains one of the leading causes of maternal and perinatal morbidity and mortality, particularly in low- and middle-income countries (LMICs). Existing first-trimester screening approaches, which combine maternal risk factors, Doppler studies, and biochemical markers, have shown variable and often modest predictive accuracy. This has led to growing interest in molecular markers that reflect early placental pathology, including circulating cell-free DNA (cfDNA) and biomarkers derived from extracellular vehicles (EVs). Objective This review aimed to summarise evidence published between 2020 and 2025 on the role of cfDNA and EV-based biomarkers in the early prediction of PE, and to examine their potential clinical usefulness, especially in LMIC settings. Methods A systematic literature search was performed in PubMed, Scopus, Web of Science, and the Cochrane Library, following PRISMA recommendations. Studies assessing cfDNA levels, fragment size patterns, epigenetic features, and EV-associated biomarkers for PE prediction were included. Study quality and risk of bias were evaluated using the QUADAS-2 and PROBAST tools. Results Most studies reported that higher cfDNA concentrations, changes in cfDNA fragment characteristics, and altered EV-derived microRNA expression were associated with the subsequent development of PE, with several markers detectable during the first trimester. When these markers were analysed using machine-learning approaches, predictive accuracy improved, particularly for early-onset and preterm PE, and in many studies exceeded that of conventional screening methods. Conclusion Emerging molecular markers, particularly cfDNA fragment analysis combined with computational prediction models, appear to offer a meaningful improvement in early PE risk assessment. The possibility of using established non-invasive prenatal testing platforms may support their gradual incorporation into routine antenatal practice.
Bangladesh Journal of Medical Science Vol. 25 No. 03 July’26 Page: 692-701
1
0
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ayesha Ahmad, Suman Nishad, Asma Nigar, Uma Gupta, Himanshu Arora, Priyam Mittal
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in the Bangladesh Journal of Medical Science agree to the following terms that:
- Authors retain copyright and grant Bangladesh Journal of Medical Science the right of first publication of the work.
Articles in Bangladesh Journal of Medical Science are licensed under a Creative Commons Attribution 4.0 International License CC BY-4.0.This license permits use, distribution and reproduction in any medium, provided the original work is properly cited.- Authors are able to enter into separate, additional contractual arrangements for the distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as greater citation of published work.
