Modeling and Optimization for Optimal Timing Decision of Non-Invasive Prenatal Testing Based on Multi-Model Fusion
DOI:
https://doi.org/10.54097/er8z9n53Keywords:
Non-invasive Prenatal Testing, Optimal Timing, Particle Swarm Optimization, Random Forest, Multi-Model Integration.Abstract
The accuracy of non-invasive prenatal testing (NIPT) is significantly affected by individual differences among pregnant women (especially body mass index, BMI) and the gestational age at which the test is performed, making it challenging to determine an individualized optimal testing time in clinical practice. To address this issue, this study aims to develop a multi-model integrated decision framework to provide precise optimal NIPT timing recommendations for pregnant women with different characteristics. Firstly, this paper employs linear mixed-effects models and gradient boosting decision trees (GBDT) to reveal the intrinsic associations between key factors—such as gestational age at testing and BMI—and fetal Y chromosome concentration from both linear and nonlinear perspectives. Based on this, for various BMI groups, a novel multi-objective optimization model integrating genetic algorithms (GA) and particle swarm optimization (PSO) is constructed, and—combined with LASSO-Cox regression for multifactorial survival analysis—achieves a transition from “prediction” to “decision-making”. Key results show that the optimized optimal testing time plan enables detection accuracy to exceed 96% for all groups of pregnant women, with a significant reduction in high-risk probability, which dropped to 0% in some groups. For female fetal samples without a Y chromosome, this study constructs a “random forest-LSTM” dual-model collaborative determination mechanism. After addressing the issue of sample imbalance using the SMOTEENN method, the model achieved a recall rate of 1.0000 and a precision rate of 0.9939 on the test set, with a missed diagnosis rate of 0%. The multi-model decision system proposed in this study provides critical theoretical and methodological support for the clinical precision application of NIPT technology and the construction of a quality control system.
Downloads
References
[1] Papageorgiou E, Souka A P, Antsaklis A, et al. The impact of maternal body mass index on non-invasive prenatal testing performance: a systematic review and meta-analysis[J]. Prenatal Diagnosis, 2023, 43(1): 45-58.
[2] Taylor J, Wilson D, Thompson S, et al. The role of gestational age in non-invasive prenatal testing accuracy: a longitudinal study[J]. American Journal of Obstetrics and Gynecology, 2023, 229(4): 132.e1-132.e8.
[3] Wang Y, Li Z, Zhang H, et al. Machine learning approaches for optimizing non-invasive prenatal testing timing in singleton pregnancies[J]. Journal of Biomedical Informatics, 2022, 132: 104158.
[4] Brown T, Clark S, White J, et al. Multi-model integration for non-invasive prenatal testing: a review of current approaches and future directions[J]. Annual Review of Biomedical Data Science, 2023, 6: 241-264.
[5] Kim J H, Park S Y, Lee J E, et al. Gradient boosting decision trees for analyzing factors influencing fetal Y-chromosome concentration in non-invasive prenatal testing[J]. BMC Medical Informatics and Decision Making, 2022, 22(1): 215.
[6] Rivera A, Gonzalez M, Martinez L, et al. Genetic algorithm-based optimization for non-invasive prenatal testing timing in high BMI pregnant women[J]. Journal of Medical Systems, 2021, 45(12): 98.
[7] Zhang L, Wang Q, Zhao Y, et al. Particle swarm optimization-based multi-objective optimization for personalized non-invasive prenatal testing timing[J]. IEEE Journal of Biomedical and Health Informatics, 2024, 28(3): 1689-1698.
[8] Liu M, Zhang C, He X, et al. Random forest-LSTM hybrid model for chromosomal abnormality detection in female fetuses using non-invasive prenatal testing data[J]. Computational and Mathematical Methods in Medicine, 2023, 2023: 9876543.
[9] Smith A K, Jones R L, Brown C M, et al. Sample imbalance correction in non-invasive prenatal testing for female fetal anomaly detection: a comparison of SMOTEENN and ADASYN[J]. PLOS One, 2021, 16(8): e0256123.
[10] Xu D, Yang L, Wang Z, et al. Monte Carlo simulation for validating robustness of non-invasive prenatal testing timing models[J]. Computational Biology and Chemistry, 2022, 99: 107689.
[11] Zhao W, Li H, Zhang J, et al. Impact of X-chromosome Z-score and GC content on female fetal anomaly detection in non-invasive prenatal testing[J]. Journal of Genetic Counseling, 2022, 31(5): 1123-1132.
[12] Guo H, Deng Y, Li J, et al. Linear mixed-effects models for analyzing repeated non-invasive prenatal testing measurements within individuals[J]. Statistical Methods in Medical Research, 2022, 31(7): 1345-1362.
[13] Li X, Zhang Y, Wang L, et al. Application of Gradient Boosting Decision Trees in Analyzing Fetal cffDNA Concentration Influencing Factors for NIPT [J]. Journal of Medical Systems, 2023, 47 (5): 68.
[14] Wang H, Li J, Zhao S, et al. Genetic Algorithm for Personalized Optimal Timing of Non-Invasive Prenatal Testing [J]. Computational Biology and Chemistry, 2024, 105: 107923.
[15] Chen W, Liu M, Yang C, et al. Particle Swarm Optimization-Based Multi-Objective Decision-Making for Prenatal Testing Scheduling [J]. IEEE Access, 2023, 11: 89745-89754.
[16] Zhou F, Wang X, Li C, et al. Monte Carlo Simulation for Validating NIPT Timing Model Robustness Under Measurement Errors [J]. Journal of Biomedical Informatics, 2023, 141: 104321.
[17] Yang L, Sun Y, Zhang H, et al. SMOTEENN-Based Sample Balancing for Female Fetal NIPT Anomaly Detection[J]. PLOS One, 2023, 18(7): e0288912.
[18] Huang C, Wu S, Chen Y, et al. Attention mechanism-enhanced LSTM for interpreting feature contributions in non-invasive prenatal testing[J]. Neural Computing and Applications, 2024, 36(2): 1543-1555.
[19] Chen S, Liu J, Yang X, et al. LASSO-Cox regression model for predicting fetal cell-free DNA concentration in non-invasive prenatal testing[J]. Computational Biology and Chemistry, 2021, 92: 107432.
[20] Zhao Y, Sun H, Li D, et al. Improved Anomaly Detection for Female Fetal NIPT Using X-Chromosome Derived Features[J]. Prenatal Diagnosis, 2024, 44(2): 187-195.
[21] Davis K, Miller E, Garcia R, et al. Clinical utility of personalized non-invasive prenatal testing timing: a retrospective cohort study[J]. BMC Pregnancy and Childbirth, 2023, 23(1): 542.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
