Machine learning-based evaluation of application value of the USM combined with NIPT in the diagnosis of fetal chromosomal abnormalities

Xianfeng Xu; Liping Wang; Xiaohong Cheng; Weilin Ke; Shenqiu Jie; Shen Lin; Manlin Lai; Linlin Zhang; Zhenzhou Li; Xianfeng Xu; Liping Wang; Xiaohong Cheng; Weilin Ke; Shenqiu Jie; Shen Lin; Manlin Lai; Linlin Zhang; Zhenzhou Li

doi:10.3934/mbe.2022197

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 4: 4260-4276. doi: 10.3934/mbe.2022197

Previous Article Next Article

Research article

Machine learning-based evaluation of application value of the USM combined with NIPT in the diagnosis of fetal chromosomal abnormalities

1.
Department of Reproductive Medicine, Shenzhen Second People's Hospital, Guangdong Province, 518035, China
2.
Department of Obstetrics and Gynecology, Shenzhen Second People's Hospital, Guangdong Province, 518035, China
3.
Department of Ultrasonic Diagnosis, Shenzhen Second People's Hospital, Guangdong Province, 518035, China

Received: 07 July 2021 Revised: 29 September 2021 Accepted: 26 October 2021 Published: 25 February 2022

Objective
To explore the soft ultrasound marker (USM) combined with non-invasive prenatal testing (NIPT) in diagnosing fetal chromosomal abnormalities based on machine learning and data mining techniques.

Methods
To analyze the data of ultrasonic examination from 856 cases with high-risk single pregnancy during early and middle pregnancy stage. NIPT was applied in 642 patients. All 856 patients accepted amniocentesis and chromosome karyotype analysis to determine the efficacy of USM, Down's syndrome screening, and NIPT in detecting fetal chromosomal abnormalities.

Results
Among the 856 fetuses, 129 fetuses (15.07%) with single positive USM and 36 fetuses (4.21%) with two or more positive USM. There were 81 fetuses (9.46%) with chromosomal abnormalities. In the group with multiple USM, chromosomal abnormalities were found in 36.11% of them. It was higher than the group without USM, which was 6.22% (P < 0.01), and the group with just a single USM (19.38%, P < 0.05). The sensitivity, specificity and accuracy were 96.72%, 98.45% and 98.29% when the combination of USM, Down's syndrome screening and NIPT was used to diagnose fetal chromosomal abnormalities further evaluating the accuracy and effectiveness of the above diagnostic criteria and methods with mainstream Classifiers based evaluation indicators of accuracy, f1 score, AUC.

Conclusions
The combination of USM, Down's syndrome screening and NIPT is valuable for the diagnosis of fetal chromosomal abnormalities.
- USM,
- NIPT,
- chromosome,
- fetus,
- machine learning,
- data mining
Citation: Xianfeng Xu, Liping Wang, Xiaohong Cheng, Weilin Ke, Shenqiu Jie, Shen Lin, Manlin Lai, Linlin Zhang, Zhenzhou Li. Machine learning-based evaluation of application value of the USM combined with NIPT in the diagnosis of fetal chromosomal abnormalities[J]. Mathematical Biosciences and Engineering, 2022, 19(4): 4260-4276. doi: 10.3934/mbe.2022197

Related Papers:

Abstract

Objective

To explore the soft ultrasound marker (USM) combined with non-invasive prenatal testing (NIPT) in diagnosing fetal chromosomal abnormalities based on machine learning and data mining techniques.

Methods

To analyze the data of ultrasonic examination from 856 cases with high-risk single pregnancy during early and middle pregnancy stage. NIPT was applied in 642 patients. All 856 patients accepted amniocentesis and chromosome karyotype analysis to determine the efficacy of USM, Down's syndrome screening, and NIPT in detecting fetal chromosomal abnormalities.

Results

Among the 856 fetuses, 129 fetuses (15.07%) with single positive USM and 36 fetuses (4.21%) with two or more positive USM. There were 81 fetuses (9.46%) with chromosomal abnormalities. In the group with multiple USM, chromosomal abnormalities were found in 36.11% of them. It was higher than the group without USM, which was 6.22% (P < 0.01), and the group with just a single USM (19.38%, P < 0.05). The sensitivity, specificity and accuracy were 96.72%, 98.45% and 98.29% when the combination of USM, Down's syndrome screening and NIPT was used to diagnose fetal chromosomal abnormalities further evaluating the accuracy and effectiveness of the above diagnostic criteria and methods with mainstream Classifiers based evaluation indicators of accuracy, f1 score, AUC.

Conclusions

The combination of USM, Down's syndrome screening and NIPT is valuable for the diagnosis of fetal chromosomal abnormalities.

References

[1]	M. Allyse, M. A. Minear, E. Berson, S. Sridhar, M. Rote, A. Hung, et al., Non-invasive prenatal testing: a review of international implementation and challenges, Int. J. Women's Health, 7 (2015), 113. https://doi.org/10.2147/IJWH.S67124 doi: 10.2147/IJWH.S67124
[2]	R. W. Chiu, Y. D. Lo, Non-invasive prenatal diagnosis by fetal nucleic acid analysis in maternal plasma: the coming of age, Semin. Fetal Neonatal Med., 16 (2011), 88–93. https://doi.org/10.1016/j.siny.2010.10.003 doi: 10.1016/j.siny.2010.10.003
[3]	Z. Ren, Z. Chai, Z. Zhou, China fertility report 2019, The Development research, 6 (2019), 20–40.
[4]	L. Yang, L. Hongtian, Z. Yubo, L. Jianmeng, Crowd fertility and fertility protection, Chin. J. Reprod. Health, 31 (2020), 401–403. https://doi.org/10.1016/j.cclet.2019.06.048 doi: 10.1016/j.cclet.2019.06.048
[5]	Z. Xuegui, Y. Jiang, X. Guige, Retrospective analysis of pregnancy risk of older parturients, J. Binzhou Med. Univ., 43 (2018), 118–121.
[6]	E. Hung, R. Chiu, Y. Lo, Detection of circulating fetal nucleic acids: a review of methods and applications, J. Clin. Pathol., 62 (2009), 308–313. https://doi.org/10.1136/jcp.2007.048470 doi: 10.1136/jcp.2007.048470
[7]	G. J. Liao, A. M. Gronowski, Z. Zhao, Non-invasive prenatal testing using cell-free fetal dna in maternal circulation, Clin. Chim. Acta, 428 (2014), 44–50. https://doi.org/10.1016/j.cca.2013.10.007 doi: 10.1016/j.cca.2013.10.007
[8]	K. H. Nicolaides, A. Syngelaki, G. Ashoor, C. Birdir, G. Touzet, Noninvasive prenatal testing for fetal trisomies in a routinely screened first-trimester population, Am. J. Obstet. Gynecol., 207 (2012), 374.e1–6. https://doi.org/10.1016/j.ajog.2012.08.033 doi: 10.1016/j.ajog.2012.08.033
[9]	D. W. Bianchi, L. D. Platt, J. D. Goldberg, A. Z. Abuhamad, A. J. Sehnert, R. P. Rava, Genome-wide fetal aneuploidy detection by maternal plasma dna sequencing, Obstet. Gynecol., 119 (2012), 890–901. https://doi.org/10.1097/AOG.0b013e31824fb482 doi: 10.1097/AOG.0b013e31824fb482
[10]	G. E. Palomaki, E. M. Kloza, G. M. Lambert-Messerlian, J. E. Haddow, L. M. Neveux, M. Ehrich, et al., Dna sequencing of maternal plasma to detect down syndrome: an international clinical validation study, Genet. Med., 13 (2011), 913–920. https://doi.org/10.1097/GIM.0b013e3182368a0e doi: 10.1097/GIM.0b013e3182368a0e
[11]	K. Song, T. J. Musci, A. B. Caughey, Clinical utility and cost of non-invasive prenatal testing with cfdna analysis in high-risk women based on a us population, J. Matern.-Fetal Neonatal Med., 26 (2013), 1180–1185. https://doi.org/10.3109/14767058.2013.770464 doi: 10.3109/14767058.2013.770464
[12]	M. Allyse, L. C. Sayres, T. A. Goodspeed, M. K. Cho, Attitudes towards non-invasive prenatal testing for aneuploidy among us adults of reproductive age, J. Perinatol., 34 (2014), 429–434. https://doi.org/10.1038/jp.2014.30 doi: 10.1038/jp.2014.30
[13]	L. S. Chitty, D. W. Bianchi, Noninvasive prenatal testing: the paradigm is shifting rapidly, 2013. https://doi.org/10.1002/pd.4136
[14]	Y. D. Lo, K. A. Chan, H. Sun, E. Z. Chen, P. Jiang, F. M. Lun, et al., Maternal plasma dna sequencing reveals the genome-wide genetic and mutational profile of the fetus, Sci. Transl. Med., 2 (2010), 61ra91–61ra91. https://doi.org/10.1126/scitranslmed.3001720 doi: 10.1126/scitranslmed.3001720
[15]	S. Morris, S. Karlsen, N. Chung, M. Hill, L. S. Chitty, Model-based analysis of costs and outcomes of non-invasive prenatal testing for down's syndrome using cell free fetal dna in the uk national health service, PloS One, 9 (2014), e93559. https://doi.org/10.1371/journal.pone.0093559 doi: 10.1371/journal.pone.0093559
[16]	A. C. Neocleous, K. H. Nicolaides, C. N. Schizas, First trimester noninvasive prenatal diagnosis: A computational intelligence approach.
[17]	WANGhui, Pregnancy risk analysis for older parturients, Chin. Commun. Physician, 19, 2019.
[18]	G. ZHAN, Study on risk assessment and prevention and control strategies of adverse pregnancy outcomes for women in the third trimester, Ph.D. dissertation, Changchun: Jilin University, 2019.
[19]	W. Wu, S. Pirbhulal, G. Li, Adaptive computing-based biometric security for intelligent medical applications, Neural Comput. Appl., 32 (2020), 11 055–11 064.
[20]	A. H. Sodhro, M. S. Al-Rakhami, L. Wang, H. Magsi, N. Zahid, S. Pirbhulal, et al., Decentralized energy efficient model for data transmission in iot-based healthcare system, in 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring). IEEE, 2021, pp. 1–5. https://doi.org/10.1109/VTC2021-Spring51267.2021.9448886
[21]	A. H. Sodhro, A. Gurtov, N. Zahid, S. Pirbhulal, L. Wang, M. M. U. Rahman, et al., Toward convergence of ai and iot for energy-efficient communication in smart homes, IEEE Internet Things, 8 (2020), 9664–9671. https://doi.org/10.1109/JIOT.2020.3023667 doi: 10.1109/JIOT.2020.3023667
[22]	A. Koivu, T. Korpimäki, P. Kivelä, T. Pahikkala, M. Sairanen, Evaluation of machine learning algorithms for improved risk assessment for down's syndrome, Comput. Biol. Med., 98 (2018), 1–7. https://doi.org/10.1016/j.compbiomed.2018.05.004 doi: 10.1016/j.compbiomed.2018.05.004
[23]	L. Davidson, M. R. Boland, Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes, Brief. Bioinformatics, 2021. https://doi.org/10.1093/bib/bbaa369 doi: 10.1093/bib/bbaa369
[24]	J. Yang, X. Ding, W. Zhu, Improving the calling of non-invasive prenatal testing on 13-/18-/21-trisomy by support vector machine discrimination, BioRxiv, p. 216689, 2017. https://doi.org/10.1101/216689 doi: 10.1101/216689
[25]	H.-G. Zhang, Y.-T. Jiang, S.-D. Dai, L. Li, X.-N. Hu, R.-Z. Liu, Application of intelligent algorithms in down syndrome screening during second trimester pregnancy, World J. Clin. Cases, 9 (2021), 4573. https://doi.org/10.12998/wjcc.v9.i18.4573 doi: 10.12998/wjcc.v9.i18.4573
[26]	F. He, B. Lin, K. Mou, L. Jin, J. Liu, A machine learning model for the prediction of down syndrome in second trimester antenatal screening, Clinica Chimica Acta, 521 (2021), 206–211. https://doi.org/10.1016/j.cca.2021.07.015 doi: 10.1016/j.cca.2021.07.015
[27]	Ö. Uzun, H. Kaya, F. Gürgen, and F. G. Varol, Prenatal risk assessment of trisomy 21 by probabilistic classifiers, in 2013 21st Signal Process. Commun. Appl. Conf. (SIU). IEEE, 2013, pp. 1–4. https://doi.org/10.1109/SIU.2013.6531604
[28]	H. Ocak, A medical decision support system based on support vector machines and the genetic algorithm for the evaluation of fetal well-being, J. Med. Syst., 37 (2013), 1–9. https://doi.org/10.1007/s10916-012-9913-4 doi: 10.1007/s10916-012-9913-4
[29]	I. Vovsha, A. Rajan, A. Salleb-Aouissi, A. Raja, A. Radeva, H. Diab, et al., Predicting preterm birth is not elusive: Machine learning paves the way to individual wellness, in 2014 AAAI Spring Symposium Series, 2014.
[30]	L. Zhen, Y.-D. Yang, Y.-J. Li, L.-L. Xu, D.-Z. Li, The role of ultrasound in the choice between chorionic villus sampling and amniocentesis for patients with a positive nipt result for trisomy 18/13, Prenat. Diagn., 39 (2019), 1155–1158. https://doi.org/10.1002/pd.5524 doi: 10.1002/pd.5524
[31]	S. K. Alldred, Y. Takwoingi, B. Guo, M. Pennant, J. J. Deeks, J. P. Neilson, et al., First trimester ultrasound tests alone or in combination with first trimester serum tests for down's syndrome screening, Cochrane Database Syst. Rev., no. 3, 2017. https://doi.org/10.1002/14651858.CD012600 doi: 10.1002/14651858.CD012600
[32]	K. M. Wojda, H. Moczulska, P. J. Sieroszewski, The absence of fetal nasal bones in ultrasound examination between 11+ 0 and 13+ 6 weeks of gestation versus the occurrence of trisomies 21, 18, and 13, Ginekol. Pol., 90 (2019), 604–606. https://doi.org/10.5603/GP.2019.0104 doi: 10.5603/GP.2019.0104
[33]	Y. Nan, Z. Liu, J. Zhang, R. Yang, Q. Yu, F. Wang, et al., Relationship between the choroid plexus cyst and the aneuploidy, Zhonghua Yi Xue Za Zhi, 98 (2018), 2987–2990.
[34]	A. Åhman, O. Axelsson, G. Maras, C. Rubertsson, A. Sarkadi, P. Lindgren, Ultrasonographic fetal soft markers in a low-risk population: prevalence, association with trisomies and invasive tests, Acta Obstet. Gynecol. Scand., 93 (2014), 367–373. https://doi.org/10.1111/aogs.12334 doi: 10.1111/aogs.12334
[35]	T. S. Hartwig, L. Ambye, L. Werge, M. K. Weiergang, P. Nørgaard, S. Sørensen, et al., Non-invasive prenatal testing (nipt) in pregnancies with trisomy 21, 18 and 13 performed in a public setting–factors of importance for correct interpretation of results, Eur. J. Obstet. Gynecol. Reprod. Biol., 226 (2018), 35–39. https://doi.org/10.1016/j.ejogrb.2018.04.042 doi: 10.1016/j.ejogrb.2018.04.042
[36]	J. Harraway, Non-invasive prenatal testing, Aust. Fam. Physician, 46 (2017), 735–739.
[37]	A. J. Ainsworth, M. A. Holman, E. Codsi, M. Wick, Use of genetic testing after abnormal screening ultrasound: A descriptive cohort study, Gynecol. Obstet. Invest., 83 (2018), 466–470. https://doi.org/10.1159/000484242 doi: 10.1159/000484242

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)