1
|
Yu Y, Xu W, Zhang S, Feng S, Feng F, Dai J, Zhang X, Tian P, Wang S, Zhao Z, Zhao W, Guan L, Qiu Z, Zhang J, Peng H, Lin J, Zhang Q, Chen W, Li H, Zhao Q, Xiao G, Li Z, Zhou S, Peng C, Xu Z, Zhang J, Zhang R, He X, Li H, Li J, Ruan X, Zhao L, He J. Non-invasive prediction of preeclampsia using the maternal plasma cell-free DNA profile and clinical risk factors. Front Med (Lausanne) 2024; 11:1254467. [PMID: 38695016 PMCID: PMC11061442 DOI: 10.3389/fmed.2024.1254467] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2023] [Accepted: 03/26/2024] [Indexed: 05/04/2024] Open
Abstract
Background Preeclampsia (PE) is a pregnancy complication defined by new onset hypertension and proteinuria or other maternal organ damage after 20 weeks of gestation. Although non-invasive prenatal testing (NIPT) has been widely used to detect fetal chromosomal abnormalities during pregnancy, its performance in combination with maternal risk factors to screen for PE has not been extensively validated. Our aim was to develop and validate classifiers that predict early- or late-onset PE using the maternal plasma cell-free DNA (cfDNA) profile and clinical risk factors. Methods We retrospectively collected and analyzed NIPT data of 2,727 pregnant women aged 24-45 years from four hospitals in China, which had previously been used to screen for fetal aneuploidy at 12 + 0 ~ 22 + 6 weeks of gestation. According to the diagnostic criteria for PE and the time of diagnosis (34 weeks of gestation), a total of 143 early-, 580 late-onset PE samples and 2,004 healthy controls were included. The wilcoxon rank sum test was used to identify the cfDNA profile for PE prediction. The Fisher's exact test and Mann-Whitney U-test were used to compare categorical and continuous variables of clinical risk factors between PE samples and healthy controls, respectively. Machine learning methods were performed to develop and validate PE classifiers based on the cfDNA profile and clinical risk factors. Results By using NIPT data to analyze cfDNA coverages in promoter regions, we found the cfDNA profile, which was differential cfDNA coverages in gene promoter regions between PE and healthy controls, could be used to predict early- and late-onset PE. Maternal age, body mass index, parity, past medical histories and method of conception were significantly differential between PE and healthy pregnant women. With a false positive rate of 10%, the classifiers based on the combination of the cfDNA profile and clinical risk factors predicted early- and late-onset PE in four datasets with an average accuracy of 89 and 80% and an average sensitivity of 63 and 48%, respectively. Conclusion Incorporating cfDNA profiles in classifiers might reduce performance variations in PE models based only on clinical risk factors, potentially expanding the application of NIPT in PE screening in the future.
Collapse
Affiliation(s)
- Yan Yu
- Department of Obstetrics, Shenzhen Baoan Women’s and Children’s Hospital, Shenzhen, China
| | - Wenqiu Xu
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | - Sufen Zhang
- Department of Clinical Laboratory (Institute of Medical Genetics), Zhuhai Center for Maternal and Child Health Care, Zhuhai, China
| | - Suihua Feng
- Department of Obstetrics and Gynecology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Feng Feng
- BGI-Tianjin, BGI-Shenzhen, Tianjin, China
| | - Junshang Dai
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Xiao Zhang
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | | | | | - Zhiguang Zhao
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | - Wenrui Zhao
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | - Liping Guan
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | - Zhixu Qiu
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | - Jianguo Zhang
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | | | - Jiawei Lin
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
| | - Qun Zhang
- Department of Obstetrics and Gynecology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Weiping Chen
- Department of Obstetrics and Gynecology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Huahua Li
- Department of Obstetrics and Gynecology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Qiang Zhao
- Department of Obstetrics and Gynecology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Gefei Xiao
- Department of Clinical Laboratory (Institute of Medical Genetics), Zhuhai Center for Maternal and Child Health Care, Zhuhai, China
| | - Zhongzhe Li
- Department of Prevention and Health Care, Zhuhai Center for Maternal and Child Health Care, Zhuhai, China
| | - Shihao Zhou
- Department of Genetics and Eugenics, Changsha Hospital for Maternal and Child Health Care, Changsha, China
- Hunan Provincial Key Laboratory of Regional Hereditary Birth Defects Prevention and Control, Changsha Hospital for Maternal and Child Health Care Affiliated to Hunan Normal University, Changsha, China
| | - Can Peng
- Department of Genetics and Eugenics, Changsha Hospital for Maternal and Child Health Care, Changsha, China
| | - Zhen Xu
- Department of Genetics and Eugenics, Changsha Hospital for Maternal and Child Health Care, Changsha, China
| | - Jingjing Zhang
- Hospital Office, Changsha Hospital for Maternal and Child Health Care, Changsha, China
| | - Rui Zhang
- Department of Medical Genetics and Prenatal Diagnosis, Baoan Women’s and Children’s Hospital, Jinan University, Shenzhen, China
| | - Xiaohong He
- Department of Medical Genetics and Prenatal Diagnosis, Baoan Women’s and Children’s Hospital, Jinan University, Shenzhen, China
| | - Hua Li
- Department of Clinical Laboratory (Institute of Medical Genetics), Zhuhai Center for Maternal and Child Health Care, Zhuhai, China
| | - Jia Li
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
| | - Xiaohong Ruan
- Department of Obstetrics and Gynecology, Jiangmen Central Hospital, Jiangmen, Guangdong, China
| | - Lijian Zhao
- BGI Genomics, BGI-Shenzhen, Shenzhen, China
- Hebei Industrial Technology Research Institute of Genomics in Maternal and Child Health, Shijiazhuang BGI Genomics, Shijiazhuang, Hebei, China
- Hebei Medical University, Shijiazhuang, Hebei, China
| | - Jun He
- Department of Genetics and Eugenics, Changsha Hospital for Maternal and Child Health Care, Changsha, China
- Hunan Provincial Key Laboratory of Regional Hereditary Birth Defects Prevention and Control, Changsha Hospital for Maternal and Child Health Care Affiliated to Hunan Normal University, Changsha, China
| |
Collapse
|
2
|
Rescinito R, Ratti M, Payedimarri AB, Panella M. Prediction Models for Intrauterine Growth Restriction Using Artificial Intelligence and Machine Learning: A Systematic Review and Meta-Analysis. Healthcare (Basel) 2023; 11:healthcare11111617. [PMID: 37297757 DOI: 10.3390/healthcare11111617] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2023] [Revised: 05/29/2023] [Accepted: 05/30/2023] [Indexed: 06/12/2023] Open
Abstract
BACKGROUND IntraUterine Growth Restriction (IUGR) is a global public health concern and has major implications for neonatal health. The early diagnosis of this condition is crucial for obtaining positive outcomes for the newborn. In recent years Artificial intelligence (AI) and machine learning (ML) techniques are being used to identify risk factors and provide early prediction of IUGR. We performed a systematic review (SR) and meta-analysis (MA) aimed to evaluate the use and performance of AI/ML models in detecting fetuses at risk of IUGR. METHODS We conducted a systematic review according to the PRISMA checklist. We searched for studies in all the principal medical databases (MEDLINE, EMBASE, CINAHL, Scopus, Web of Science, and Cochrane). To assess the quality of the studies we used the JBI and CASP tools. We performed a meta-analysis of the diagnostic test accuracy, along with the calculation of the pooled principal measures. RESULTS We included 20 studies reporting the use of AI/ML models for the prediction of IUGR. Out of these, 10 studies were used for the quantitative meta-analysis. The most common input variable to predict IUGR was the fetal heart rate variability (n = 8, 40%), followed by the biochemical or biological markers (n = 5, 25%), DNA profiling data (n = 2, 10%), Doppler indices (n = 3, 15%), MRI data (n = 1, 5%), and physiological, clinical, or socioeconomic data (n = 1, 5%). Overall, we found that AI/ML techniques could be effective in predicting and identifying fetuses at risk for IUGR during pregnancy with the following pooled overall diagnostic performance: sensitivity = 0.84 (95% CI 0.80-0.88), specificity = 0.87 (95% CI 0.83-0.90), positive predictive value = 0.78 (95% CI 0.68-0.86), negative predictive value = 0.91 (95% CI 0.86-0.94) and diagnostic odds ratio = 30.97 (95% CI 19.34-49.59). In detail, the RF-SVM (Random Forest-Support Vector Machine) model (with 97% accuracy) showed the best results in predicting IUGR from FHR parameters derived from CTG. CONCLUSIONS our findings showed that AI/ML could be part of a more accurate and cost-effective screening method for IUGR and be of help in optimizing pregnancy outcomes. However, before the introduction into clinical daily practice, an appropriate algorithmic improvement and refinement is needed, and the importance of quality assessment and uniform diagnostic criteria should be further emphasized.
Collapse
Affiliation(s)
- Riccardo Rescinito
- Department of Translational Medicine (DiMeT), University of Eastern Piedmont/Piemonte Orientale (UPO), 28100 Novara, Italy
| | - Matteo Ratti
- Department of Translational Medicine (DiMeT), University of Eastern Piedmont/Piemonte Orientale (UPO), 28100 Novara, Italy
| | - Anil Babu Payedimarri
- Department of Translational Medicine (DiMeT), University of Eastern Piedmont/Piemonte Orientale (UPO), 28100 Novara, Italy
| | - Massimiliano Panella
- Department of Translational Medicine (DiMeT), University of Eastern Piedmont/Piemonte Orientale (UPO), 28100 Novara, Italy
| |
Collapse
|
4
|
Zhang M, Li K, Qu S, Guo Z, Wang Y, Yang X, Zhou J, Ouyang G, Weng R, Li F, Wu Y, Yang X. Integrative analyses of maternal plasma cell-free DNA nucleosome footprint differences reveal chromosomal aneuploidy fetuses gene expression profile. J Transl Med 2022; 20:536. [PMID: 36401256 PMCID: PMC9673457 DOI: 10.1186/s12967-022-03735-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2022] [Accepted: 10/30/2022] [Indexed: 11/19/2022] Open
Abstract
Background Chromosomal aneuploidy is the most common birth defect. However, the developmental mechanism and gene expression profile of fetuses with chromosomal aneuploidy are relatively unknown, and the maternal immune changes induced by fetal aneuploidy remain unclear. The inability to obtain the placenta multiple times in real-time is a bottleneck in research on aneuploid pregnancies. Plasma cell-free DNA (cfDNA) carries the gene expression profile information of its source cells and may be used to evaluate the development of fetuses with aneuploidy and the immune changes induced in the mother owing to fetal aneuploidy. Methods Here, we carried out whole-genome sequencing of the plasma cfDNA of 101 pregnant women carrying a fetus with trisomy (trisomy 21, n = 42; trisomy 18, n = 28; trisomy 13, n = 31) based on non-invasive prenatal testing (NIPT) screening and 140 normal pregnant women to identify differential genes according to the cfDNA nucleosome profile in the region around the transcription start sites (TSSs). Results The plasma cfDNA promoter profiles were found to differ between aneuploid and euploid pregnancies. A total of 158 genes with significant differences were identified, of which 43 genes were upregulated and 98 genes were downregulated. Functional enrichment and signaling pathway analysis were performed based on Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) databases found that these signal pathways were mainly related to the coordination of developmental signals during embryonic development, the control of cell growth and development, regulation of neuronal survival, and immune regulation, such as the MAPK, Hippo, TGF-β, and Rap1 signaling pathways, which play important roles in the development of embryonic tissues and organs. Furthermore, based on the results of differential gene analysis, a total of 14 immune-related genes with significant differences from the ImmPort database were collected and analyzed. These significantly different immune genes were mainly associated with the maintenance of embryonic homeostasis and normal development. Conclusions These results suggest that the distribution characteristics of cfDNA nucleosomes in maternal plasma can be used to reflect the status of fetal development and changes of the immune responses in trisomic pregnancies. Overall, our findings may provide research ideas for non-invasive detection of the physiological and pathological states of other diseases. Supplementary Information The online version contains supplementary material available at 10.1186/s12967-022-03735-7.
Collapse
|
5
|
Lu Q, Guo Z, Zhang J, Wang K, Tian Q, Liu S, Li K, Xu C, Li C, Lv Z, Zhang Z, Yang X, Yang F. Performance of whole-genome promoter nucleosome profiling of maternal plasma cell-free DNA for prenatal noninvasive prediction of fetal macrosomia: a retrospective nested case-control study in mainland China. BMC Pregnancy Childbirth 2022; 22:698. [PMID: 36088304 PMCID: PMC9463826 DOI: 10.1186/s12884-022-05027-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2022] [Accepted: 09/06/2022] [Indexed: 11/10/2022] Open
Abstract
Background Fetal macrosomia is common occurrence in pregnancy, which is associated with several adverse prognosis both of maternal and neonatal. While, the accuracy of prediction of fetal macrosomia is poor. The aim of this study was to develop a reliable noninvasive prediction classifier of fetal macrosomia. Methods A total of 3600 samples of routine noninvasive prenatal testing (NIPT) data at 12+ 0–27+ 6 weeks of gestation, which were subjected to low-coverage whole-genome sequencing of maternal plasma cell-free DNA (cfDNA), were collected from three independent hospitals. We identified set of genes with significant differential coverages by comparing the promoter profiling between macrosomia cases and controls. We selected genes to develop classifier for noninvasive predicting, by using support vector machine (SVM) and logistic regression models, respectively. The performance of each classifier was evaluated by area under the curve (AUC) analysis. Results According to the available follow-up results, 162 fetal macrosomia pregnancies and 648 matched controls were included. A total of 1086 genes with significantly differential promoter profiling were found between pregnancies with macrosomia and controls (p < 0.05). With the AUC as a reference,the classifier based on SVM (CMA-A2) had the best performance, with an AUC of 0.8256 (95% CI: 0.7927–0.8586). Conclusions Our study provides that assessing the risk of fetal macrosomia by whole-genome promoter nucleosome profiling of maternal plasma cfDNA based on low-coverage next-generation sequencing is feasible. Supplementary Information The online version contains supplementary material available at 10.1186/s12884-022-05027-w.
Collapse
|
7
|
Nowakowska BA, Pankiewicz K, Nowacka U, Niemiec M, Kozłowski S, Issat T. Genetic Background of Fetal Growth Restriction. Int J Mol Sci 2021; 23:ijms23010036. [PMID: 35008459 PMCID: PMC8744929 DOI: 10.3390/ijms23010036] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2021] [Revised: 12/17/2021] [Accepted: 12/19/2021] [Indexed: 12/14/2022] Open
Abstract
Fetal growth restriction (FGR) is one of the most formidable challenges in present-day antenatal care. Pathological fetal growth is a well-known factor of not only in utero demise in the third trimester, but also postnatal morbidity and unfavorable developmental outcomes, including long-term sequalae such as metabolic diseases, diabetic mellitus or hypertension. In this review, the authors present the current state of knowledge about the genetic disturbances responsible for FGR diagnosis, divided into fetal, placental and maternal causes (including preeclampsia), as well as their impact on prenatal diagnostics, with particular attention on chromosomal microarray (CMA) and noninvasive prenatal testing technique (NIPT).
Collapse
Affiliation(s)
- Beata Anna Nowakowska
- Department of Medical Genetics, Institute of Mother and Child, Kasprzaka 17a, 01-211 Warsaw, Poland;
- Correspondence: (B.A.N.); (K.P.); Tel.: +48-22-3277131 (B.A.N.); +48-22-3277044 (K.P.)
| | - Katarzyna Pankiewicz
- Department of Obstetrics and Gynecology, Institute of Mother and Child in Warsaw, Kasprzaka 17a, 01-211 Warsaw, Poland; (U.N.); (S.K.); (T.I.)
- Correspondence: (B.A.N.); (K.P.); Tel.: +48-22-3277131 (B.A.N.); +48-22-3277044 (K.P.)
| | - Urszula Nowacka
- Department of Obstetrics and Gynecology, Institute of Mother and Child in Warsaw, Kasprzaka 17a, 01-211 Warsaw, Poland; (U.N.); (S.K.); (T.I.)
| | - Magdalena Niemiec
- Department of Medical Genetics, Institute of Mother and Child, Kasprzaka 17a, 01-211 Warsaw, Poland;
| | - Szymon Kozłowski
- Department of Obstetrics and Gynecology, Institute of Mother and Child in Warsaw, Kasprzaka 17a, 01-211 Warsaw, Poland; (U.N.); (S.K.); (T.I.)
| | - Tadeusz Issat
- Department of Obstetrics and Gynecology, Institute of Mother and Child in Warsaw, Kasprzaka 17a, 01-211 Warsaw, Poland; (U.N.); (S.K.); (T.I.)
| |
Collapse
|
8
|
Han BW, Yang X, Qu SF, Guo ZW, Huang LM, Li K, Ouyang GJ, Cai GX, Xiao WW, Weng RT, Xu S, Huang J, Yang XX, Wu YS. A Deep-Learning Pipeline for TSS Coverage Imputation From Shallow Cell-Free DNA Sequencing. Front Med (Lausanne) 2021; 8:684238. [PMID: 34926480 PMCID: PMC8678047 DOI: 10.3389/fmed.2021.684238] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2021] [Accepted: 11/15/2021] [Indexed: 11/13/2022] Open
Abstract
Cell-free DNA (cfDNA) serves as a footprint of the nucleosome occupancy status of transcription start sites (TSSs), and has been subject to wide development for use in noninvasive health monitoring and disease detection. However, the requirement for high sequencing depth limits its clinical use. Here, we introduce a deep-learning pipeline designed for TSS coverage profiles generated from shallow cfDNA sequencing called the Autoencoder of cfDNA TSS (AECT) coverage profile. AECT outperformed existing single-cell sequencing imputation algorithms in terms of improvements to TSS coverage accuracy and the capture of latent biological features that distinguish sex or tumor status. We built classifiers for the detection of breast and rectal cancer using AECT-imputed shallow sequencing data, and their performance was close to that achieved by high-depth sequencing, suggesting that AECT could provide a broadly applicable noninvasive screening approach with high accuracy and at a moderate cost.
Collapse
Affiliation(s)
- Bo-Wei Han
- Key Laboratory of Antibody Engineering of Guangdong Higher Education Institutes, School of Laboratory Medicine and Biotechnology, Southern Medical University, Guangzhou, China
| | - Xu Yang
- Key Laboratory of Antibody Engineering of Guangdong Higher Education Institutes, School of Laboratory Medicine and Biotechnology, Southern Medical University, Guangzhou, China
| | - Shou-Fang Qu
- Division of in vitro Diagnostic Reagents, National Institutes for Food and Drug Control (NIFDC), Beijing, China
| | - Zhi-Wei Guo
- Key Laboratory of Antibody Engineering of Guangdong Higher Education Institutes, School of Laboratory Medicine and Biotechnology, Southern Medical University, Guangzhou, China
| | - Li-Min Huang
- Key Laboratory of Antibody Engineering of Guangdong Higher Education Institutes, School of Laboratory Medicine and Biotechnology, Southern Medical University, Guangzhou, China
| | - Kun Li
- Key Laboratory of Antibody Engineering of Guangdong Higher Education Institutes, School of Laboratory Medicine and Biotechnology, Southern Medical University, Guangzhou, China.,Guangzhou XGene Co., Ltd., Guangzhou, China
| | - Guo-Jun Ouyang
- Guangzhou Darui Biotechnology Co., Ltd., Guangzhou, China
| | - Geng-Xi Cai
- Department of Breast Surgery, The First People's Hospital of Foshan, Foshan, China.,Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Wei-Wei Xiao
- Department of Medical Oncology, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China
| | - Rong-Tao Weng
- Guangzhou Darui Biotechnology Co., Ltd., Guangzhou, China
| | - Shun Xu
- Guangzhou Darui Biotechnology Co., Ltd., Guangzhou, China
| | - Jie Huang
- Division of in vitro Diagnostic Reagents, National Institutes for Food and Drug Control (NIFDC), Beijing, China
| | - Xue-Xi Yang
- Key Laboratory of Antibody Engineering of Guangdong Higher Education Institutes, School of Laboratory Medicine and Biotechnology, Southern Medical University, Guangzhou, China
| | - Ying-Song Wu
- Key Laboratory of Antibody Engineering of Guangdong Higher Education Institutes, School of Laboratory Medicine and Biotechnology, Southern Medical University, Guangzhou, China
| |
Collapse
|