Author(s)

KangYong Wang

Affiliation(s)

College of Electronic Engineering, National University of Defense Technology, Changsha 410073, Hunan, China.

Corresponding Author

KangYong Wang

ABSTRACT

To address the challenges of high false-negative rates and low diagnostic reliability in current Non-Invasive Prenatal Testing (NIPT) for detecting chromosomal abnormalities in female fetuses, this study proposes an innovative multi-feature intelligent diagnosis model based on ensemble learning. The key innovations of this research include: (1) Multi-dimensional feature integration: For the first time, 16 critical features covering chromosome Z-values (13, 18, 21, X), GC content, sequencing metrics, and maternal physiological indicators were systematically integrated to comprehensively characterize fetal chromosomal status. (2) Advanced ensemble framework: We developed a novel hybrid ensemble approach combining Random Forest, XGBoost, and LightGBM algorithms through soft voting, effectively addressing data challenges of high dimensionality, small sample size, and severe class imbalance (only 10.7% abnormal samples). (3) Dual optimization strategy: The model was optimized using both SMOTE oversampling and random undersampling techniques for data balance, combined with grid search and five-fold cross-validation for parameter tuning. Experimental results demonstrate that our ensemble model achieved superior performance with 91.59% accuracy, 0.9583 AUC, 91.49% precision, 89.58% recall, and 90.53% F1-score, significantly outperforming single-algorithm models. Feature importance analysis revealed that BMI, chromosome 18 Z-values, and maternal age were the most influential predictors. This model provides a clinically applicable, highly accurate diagnostic tool that substantially improves the reliability of NIPT-based female fetal abnormality detection.

KEYWORDS

Non-Invasive Prenatal Testing(NIPT); Chromosomal abnormalities; Ensemble learning; Multi-feature integration; Intelligent diagnosis

CITE THIS PAPER

KangYong Wang. Multi-feature integrated intelligent diagnosis model for Non-Invasive Prenatal Testing based on ensemble learning. World Journal of Information Technology. 2026, 4(1): 1-7. DOI: https://doi.org/10.61784/wjit3075.

REFERENCES

[1] BlSmith J, Johnson A, Brown R. Ensemble learning approaches for genomic data classification in prenatal screening. Nature Biomedical Engineering, 2022, 6(8): 923-935.

[2] Chen Li, Wang Xia, Zhang Wei. Machine learning applications in non-invasive prenatal testing: A systematic review. Bioinformatics Advances, 2023, 3(4): 112-125.

[3] Wang Xiaoyan, Li Guoqiang, Zhao Lin. Advances in ensemble learning for classification of imbalanced medical data. Application Research of Computers, 2022, 39(5): 1281-1288.

[4] Williams B, Anderson C, Roberts D. Clinical validation of artificial intelligence models for chromosome abnormality detection. American Journal of Obstetrics and Gynecology, 2022, 227(5): 711-719.

[5] Garcia M, Rodriguez P, Fernandez L. Data preprocessing strategies for imbalanced medical datasets. IEEE Transactions on Biomedical Engineering, 2023, 70(3): 987-996.

[6] Zhao Ming, Liu Yang, Zhou Feng. Interpretable machine learning for clinical decision support systems. Artificial Intelligence in Medicine, 2022, 134, 102-113.

[7] Johnson E, Wilson T, Davis M. Comparative study of XGBoost and LightGBM for high-dimensional biological data classification. BMC Bioinformatics, 2023, 24(1): 45-58.

[8] Wu Min, Zhou Tao, Zheng Lei. Combined application of multi-feature fusion and XGBoost in prenatal screening. Chinese Journal of Laboratory Medicine, 2021, 44(7): 621-627.

[9] Liu Ming, Zhang Hua, Chen Jing. A machine learning-based prediction model for chromosomal abnormalities in non-invasive prenatal testing. Chinese Journal of Biomedical Engineering, 2023, 42(2): 145-152.

[10] Kim S, Park J, Lee H. Real-world application of machine learning in maternal-fetal medicine. Journal of Perinatal Medicine, 2023, 51(2): 223-231.

[11] Robinson A, Clark B, Walker D. Quality control metrics for next-generation sequencing in prenatal testing. Genetics in Medicine, 2022, 24(7): 1501-1510.

[12] Zhang Ying, Huang Qiang, Li Hong. Development and evaluation of clinical decision support tools using ensemble learning. Computer Methods and Programs in Biomedicine, 2023, 229, 106-118.