NON-INVASIVE PRENATAL DETECTION MODEL FOR FEMALE FETAL CHROMOSOMAL ANEUPLOIDY BASED ON XGBOOST

Authors

  • RuiYing Chen (Corresponding Author) School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou 730050, Gansu, China.

Keywords:

Non-Invasive prenatal testing, Chromosomal aneuploidy, XGBoost, Feature fusion, Female fetal detection

Abstract

Addressing the challenge of limited accuracy in non-invasive prenatal testing (NIPT) for female fetal chromosomal aneuploidy due to the absence of Y chromosome reference, this study innovatively proposes a multi-feature fusion detection model based on XGBoost. The model's innovations are threefold: first, it constructs a three-dimensional feature system integrating "Z-score-GC content-clinical indicators", breaking through the limitation of traditional methods relying on single chromosomal indicators; second, it leverages XGBoost's powerful capability in capturing nonlinear relationships to deeply explore complex interaction effects among multi-chromosomal features; third, through feature importance ranking, it systematically reveals for the first time the critical roles of GC content in chromosome 13 and Z-scores of chromosomes 18 and X in female fetal abnormality detection. Experimental results demonstrate that the model achieves an accuracy of 75.45%, precision of 75.63%, recall of 75.45%, and F1-score of 75.47%, significantly outperforming traditional methods. This study provides a novel technical approach for detecting female fetal chromosomal aneuploidy with substantial clinical application value.

References

[1] Belabbes K, Benchekroun T, Bendala E, et al. Cell-Free Fetal DNA for Prenatal Screening of Aneuploidies and Autosomal Trisomies: A Systematic Review. International Journal of Pediatrics, 2024(1): 3037937.

[2] Junnam L, Mi S L, Mo J A, et al. Development and performance evaluation of an artificial intelligence algorithm using cell-free DNA fragment distance for non-invasive prenatal testing (aiD-NIPT). Frontiers in Genetics, 2022, 13: 999587.

[3] Kim D, Sohn J Y, Cho J H, et al. KF-NIPT: K-mer and fetal fraction-based estimation of chromosomal anomaly from NIPT data. BMC Bioinformatics, 2025, 26(1): 1-7.

[4] Kong Lingrong, Sun Luming. Application of non-invasive prenatal testing in screening for fetal chromosomal aneuploidies. Journal of Practical Obstetrics and Gynecology, 2023, 39(2): 98-102.

[5] Liu Bing, Zheng Nan, Liu Jing, et al. Risk prediction and interpretable analysis of left atrial thrombus or spontaneous echocardiographic contrast in patients with non-valvular atrial fibrillation based on XGBoost and SHAP. Chinese Journal of Cardiovascular Medicine, 2025: 1-10.

[6] Gil M S, Quezada M S, Bregant B, et al. Implementation of cell-free DNA-based non-invasive prenatal testing in a national health service: A cost-consequence analysis. Ultrasound in Obstetrics & Gynecology, 2023, 62(2): 205-214.

[7] Petersen A K, Cheung S W, Smith J L, et al. Positive predictive value estimates for cell-free noninvasive prenatal screening from data of a large referral population. Prenatal Diagnosis, 2022, 42(1): 112-120.

[8] Pertile M D, Flowers N, Vavoulis S, et al. Sensitive and scalable non-invasive prenatal aneuploidy detection using cell-free DNA sequencing. Genetics in Medicine, 2024, 26(3): 101025.

[9] Van der Meij K R M, Sistermans E A, Macville M V E, et al. TRIDENT-2: National implementation of genome-wide non-invasive prenatal testing as a first-tier screening test in the Netherlands. American Journal of Human Genetics, 2022, 109(11): 2000-2008.

[10] Lefkowitz R B, Tynan J A, Liu Y, et al. Genome-wide noninvasive prenatal screening for carriers of balanced reciprocal translocations. Genetics in Medicine, 2023, 25(4): 100813.

[11] Dar P, Jacobsson B, MacPherson C, et al. Cell-free DNA screening for trisomies 21, 18, and 13 in pregnancies at low and high risk for aneuploidy. American Journal of Obstetrics and Gynecology, 2023, 229(1): 61.e1-61.e10.

[12] Martin K, Iyengar S, Kalyan A, et al. Clinical experience with a single-nucleotide polymorphism-based non-invasive prenatal test for five clinically significant microdeletions. Journal of Clinical Medicine, 2024, 13(2): 489.

[13] Zhou Ying, Wang Zhenyu, Mao Qianqian, et al. Application value of non-invasive prenatal testing technology in screening for fetal chromosomal aneuploidies. Chinese Journal of Medical Genetics, 2019, 36(11): 1094-1096.

[14] Gross S J, Stosic M, McDonald-McGinn D M, et al. Clinical experience with genome-wide noninvasive prenatal screening in a large cohort of pregnancies. The Journal of Maternal-Fetal & Neonatal Medicine, 2022, 35(25): 8485-8492.

[15] Taylor-Phillips S, Freeman K, Geppert J, et al. Accuracy of non-invasive prenatal testing using cell-free DNA for detection of Down, Edwards and Patau syndromes: a systematic review and meta-analysis. BMJ Open, 2024, 14(1): e073565.

Downloads

Published

2025-12-03

Issue

Section

Research Article

DOI:

How to Cite

Chen, R. (2025). Non-Invasive Prenatal Detection Model For Female Fetal Chromosomal Aneuploidy Based On Xgboost. Eurasia Journal of Science and Technology, 7(3), 38-43. https://doi.org/10.61784/jpmr3054