Placenta accreta spectrum (PAS) is a severe obstetric complication characterized by abnormal placental villous invasion into the myometrium, serving as a primary driver of life-threatening postpartum hemorrhage. Prenatal diagnosis currently depends on operator-dependent ultrasonography and adjunctive magnetic resonance imaging, both of which exhibit limited sensitivity in early gestation. Consequently, many cases remain undiagnosed until delivery, highlighting the need for objective, non-invasive biomarkers.

In a study published in the journal Genes & Diseases, researchers from Nanjing Medical University, Southeast University, Nantong University, Shanghai University and Peking University First Hospital investigated whether machine learning-enabled profiling of cell-free DNA (cfDNA) promoter regions from routine non-invasive prenatal testing (NIPT) could facilitate early prediction and subtype risk stratification of PAS.

The investigators conducted a multicenter nested case-control study involving 1,060 pregnant women with a history of uterine surgery, comprising 126 increta/percreta cases, 139 accreta cases, and 795 matched controls. Plasma cfDNA was analyzed using low-coverage whole-genome sequencing. Pairwise differential analyses identified 211 genes with altered promoter coverage across the groups.

Unsupervised hierarchical clustering of these genes demonstrated clear molecular separation between controls, accreta, and increta/percreta. To select the most informative features, recursive feature elimination was applied across five machine learning algorithms within a nested stratified 10-fold cross-validation framework. A support vector machine with a radial basis function (SVM-RBF) was identified as the optimal classifier.

By integrating prioritized features from binary classifiers, the researchers developed the 15-gene multiclass 4P-model. This panel includes genes associated with vascular remodeling (such as MAPK10), cell cycle regulation (CEP192, C1GALT1C1), and aberrant cellular signaling (ZDHHC6, KRT33A). In the training set, the 4P-model achieved a macro-average area under the curve (AUC) of 0.973, with 0.900 accuracy, 0.900 sensitivity, and 0.938 specificity in differentiating controls, accreta, and increta/percreta. This performance was validated across independent cohorts, yielding macro-average AUCs of 0.937 on BGI, 0.908 on Illumina, 0.882 on Life platforms, and 0.946 in a deep-sequencing cohort.

In conclusion, this study demonstrates that machine learning-driven cfDNA promoter profiling derived from routine NIPT data can be leveraged for early risk assessment and subtype stratification of PAS. This approach extends the diagnostic window into early pregnancy without requiring additional blood sampling. The authors note that prospective validation in larger, unselected obstetric populations is required to confirm the clinical utility of this model.

Reference

Title of Original Paper: 4P-Model: A machine learning-driven approach to expand non-invasive prenatal testing for early risk stratification of placenta accreta spectrum via genome-wide cfDNA promoter profiling

Journal: Genes & Diseases
Genes & Diseases is a journal for molecular and translational medicine. The journal primarily focuses on publishing investigations on the molecular bases and experimental therapeutics of human diseases. Publication formats include full length research article, review article, short communication, correspondence, perspectives, commentary, views on news, and research watch.
DOI: https://doi.org/10.1016/j.gendis.2026.102305

Funding Information:
The Noncommunicable Chronic Diseases-National Science and Technology Major Project (China) (No. 2024ZD0532100, 2024ZD0532103)
The National Key R&D Program of China (No. 2022YFC2703500)
The National Natural Science Foundation of China (No. 82371697, 81971410, 61906040, 61972085)
The Natural Science Foundation of Jiangsu, China (No. BK20251773)
The Key Project of Changzhou Medical Center of Nanjing Medical University (Jiangsu, China) (No. CMCM202312)
The Changzhou Key Laboratory of Maternal and Child Health Medicine (China) (No. CM20240013)
The Graduate Research and Practice Innovation Plan of Jiangsu Province, China (No. SJCX24_0749)

# # # # # #

Genes & Diseases publishes rigorously peer-reviewed and high quality original articles and authoritative reviews that focus on the molecular bases of human diseases. Emphasis is placed on hypothesis-driven, mechanistic studies relevant to pathogenesis and/or experimental therapeutics of human diseases. The journal has worldwide authorship, and a broad scope in basic and translational biomedical research of molecular biology, molecular genetics, and cell biology, including but not limited to cell proliferation and apoptosis, signal transduction, stem cell biology, developmental biology, gene regulation and epigenetics, cancer biology, immunity and infection, neuroscience, disease-specific animal models, gene and cell-based therapies, and regenerative medicine.

Scopus Cite Score: 10.4 | Impact Factor: 14.6

# # # # # #

More information: https://www.keaipublishing.com/en/journals/genes-and-diseases/
Editorial Board: https://www.keaipublishing.com/en/journals/genes-and-diseases/editorial-board/
All issues and articles in press are available online in ScienceDirect (https://www.sciencedirect.com/journal/genes-and-diseases).
Submissions to Genes & Diseases may be made using Editorial Manager (https://www.editorialmanager.com/gendis/default.aspx).
Print ISSN: 2352-4820
eISSN: 2352-3042
CN: 50-1221/R
Contact Us: editor@genesndiseases.cn
X (formerly twitter): @GenesNDiseases (https://x.com/GenesNDiseases)

# # # # # #