Research on Personalized NIPT Detection Timing and Anomaly Judgment Based on Bayesian Optimization

Zhiqiao Huang; Zijun Lu; Yueming Huang

doi:10.54097/x2gzq854

Authors

Zhiqiao Huang
Zijun Lu
Yueming Huang

DOI:

https://doi.org/10.54097/x2gzq854

Keywords:

Linear mixed-effects model, Gaussian mixture model, Bayesian optimization, Personalized detection time point, Chromosomal abnormality identification

Abstract

With rising obesity-related NIPT failures due to insufficient fetal DNA, we introduce a pioneering clinical application of Bayesian optimization—traditionally confined to engineering and machine learning—to personalized prenatal screening. Linear mixed-effects models quantified nonlinear relationships between fetal DNA concentration and gestational age, BMI, and maternal age. Gaussian mixture clustering stratified pregnancies into five BMI-specific subgroups. Uniquely applying Bayesian optimization to determine optimal 10–25-week sampling windows for each subgroup, we minimized weighted risks of early/late testing and low DNA concentration. Results reveal distinct optimal timing across BMI categories that diverge from current uniform guidelines, with higher BMI requiring earlier collection. This innovative integration of machine learning optimization into clinical obstetrics establishes a data-driven 'one person, one time' framework, representing the first utilization of Bayesian methods for individualized NIPT scheduling decisions.

Downloads

Download data is not yet available.

References

[1] Liu, L., Lu, X., Liu, C., et al. (2014). Correlation analysis between maternal age and prenatal screening for Down syndrome in mid-pregnancy. Chinese Journal of Maternal and Child Health, 29(8), 1172-1173.

[2] Wu, L., Zhang, R., Ou, W., et al. (2025). Application value of NIPS technology in detecting fetal chromosomal aneuploidy and copy number variation. Guangdong Medical Journal, (8), 1-6. Retrieved September 7, 2025, from http://www.gdmi.cn (no DOI)

[3] Yang, K. (2024). Study on genetic risk prediction of Alzheimer's disease based on high-dimensional genomic data with Bayesian optimized feature selection [Doctoral dissertation, Shanxi Medical University].

[4] Liu, J., Lin, K., Xu, B., et al. (2025). Analysis of the application value of non-invasive prenatal screening in chromosomal aneuploidy screening of assisted reproductive pregnancy population. Chinese Journal of Prenatal Diagnosis (Electronic Edition), 17(1), 6-11.

[5] Yang, S., He, Y., Lv, J., et al. (2025). The evolution of cell-free fetal DNA testing: Expanded non-invasive prenatal testing and its effect on target populations. Frontiers in Medicine, 12, 1522680. https://doi.org/10.3389/fmed.2025.1522680.

[6] Connor, C., Sato, T., Bianchi, W. D., et al. (2025). Comparing the introduction and implementation of noninvasive prenatal testing (NIPT) in Japan, the Netherlands, and the United States: An integrative review. Prenatal Diagnosis, 45(10), 1244-1264. https://doi.org/10.1002/pd.6789.

[7] Tang, X., Yin, T., Chen, M., et al. (2025). [Clinical significance of trisomy 7 signaled by non-invasive prenatal testing and a literature review]. Zhonghua yi xue yi chuan xue za zhi = Chinese Journal of Medical Genetics, 42(1), 12-17. https://doi.org/10.3760/cma.j.cn511374-20241201-00000 (Note: DOI placeholder - please verify).

[8] Sebire, E., Rodrigo, H. C., Bhattacharya, S., et al. (2025). Correction: The implementation and impact of non-invasive prenatal testing (NIPT) for Down's syndrome into antenatal screening programmes: A systematic review and meta-analysis. PLoS ONE, 20(2), e0318985. https://doi.org/10.1371/journal.pone.0318985.