Figure 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Boxplots and receiver operator characteristic (ROC) curves for the nine differentially expressed RNAs following Bonferroni correction for false discovery rate.
Source publication
Prenatal trisomy 21 (T21) screening commonly involves testing a maternal blood sample for fetal DNA aneuploidy. It is reliable but poses a cost barrier to universal screening. We hypothesized maternal plasma RNA screening might provide similar reliability but at a lower cost. Discovery experiments used plasma cell-free RNA from 20 women 11–13 weeks...
Context in source publication
Context 1
... Figure 2, nine differentially expressed RNAs are plotted individually to compare differential expression and a ROC curve. Summarizing the qRT-PCR findings presented so far: (1) PCR RNA from an independent and more diverse patient cohort than used in the discovery phase indicates validation of 9-15 RNAs originally suggested by microarray/qPCR as being differentially expressed between T21 case and normal control; (2) the AUC indicates that the predictive power of each of the 9 differentially expressed RNAs falls into a "fair" 0.6-0.7 range of accuracy, similar to what was found modeling maternal age, alone. ...
Similar publications
Detection of embryonic trisomy 21 using maternal cell free RNA.
Citations
... Real-time fluorescence quantitative PCR (RT-qPCR) is a widely utilized method due to its high sensitivity, good quantification, and suitability for the detection of specific RNA sequences [78]. However, it is limited to the detection of known RNA sequences and requires prior knowledge of the target RNA's sequence information [79,80]. Next-generation sequencing (NGS) provides the ability to comprehensively detect RNA sequencing (RNA-seq) in plasma with high throughput, including known and unknown sequences, making it suitable for the discovery of new RNA markers and offering detailed transcriptomic information [10,81]. ...
Circulating cfRNA in plasma has emerged as a fascinating area of research with potential applications in disease diagnosis, monitoring, and personalized medicine. Circulating RNA sequencing technology allows for the non-invasive collection of important information about the expression of target genes, eliminating the need for biopsies. This comprehensive review aims to provide a detailed overview of the current knowledge and advancements in the study of plasma cfRNA, focusing on its diverse landscape and biological functions, detection methods, its diagnostic and prognostic potential in various diseases, challenges, and future perspectives.
... Villous trophoblast tissue fragments are physiologically deported into the intervillous space and thereafter into the maternal circulation by the shedding of syncytial knots [212]. This results from the normal apoptosis of the ST and turnover of the placental villi [213][214][215]. Trophoblast tissue fragments are increased in complicated pregnancies, particularly in preeclampsia, reflecting ST necrosis. ...
... Increased levels of fetal cells and fetal DNA have been reported in aneuploidies, especially in trisomy 21, by the analysis of enriched fetal cells and PCR [215,[218][219][220][221][222]. Moreover, seven miRNAs have been shown to be up-regulated in trisomic 21 placentas, three of them (miR-99a, miR-1125b, let-7c) being located on chromosome 21. ...
It is now well established that maternal serum markers are often abnormal in fetal trisomy 21. Their determination is recommended for prenatal screening and pregnancy follow-up. However, mechanisms leading to abnormal maternal serum levels of such markers are still debated. Our objective was to help clinicians and scientists unravel the pathophysiology of these markers via a review of the main studies published in this field, both in vivo and in vitro, focusing on the six most widely used markers (hCG, its free subunit hCGβ, PAPP-A, AFP, uE3, and inhibin A) as well as cell-free feto–placental DNA. Analysis of the literature shows that mechanisms underlying each marker’s regulation are multiple and not necessarily directly linked with the supernumerary chromosome 21. The crucial involvement of the placenta is also highlighted, which could be defective in one or several of its functions (turnover and apoptosis, endocrine production, and feto–maternal exchanges and transfer). These defects were neither constant nor specific for trisomy 21, and might be more or less pronounced, reflecting a high variability in placental immaturity and alteration. This explains why maternal serum markers can lack both specificity and sensitivity, and are thus restricted to screening.
... Recently, machine learning and deep learning methods have become widespread in healthcare, such as arrhythmias classification [3], coronary artery disease diagnosis [4], cancer diagnosis [5], and COVID-19 detection [6]. In prenatal screening for DS, many traditional machine learning algorithms have been used to detect DS cases from the antenatal screening data, such as support vector machine (SVM) [7]- [9], decision tree [7], [9]- [11], random forest [8]- [10], ensemble learning [8], [12] or multilayer perceptron (MLP) [11], [13]. However, as no traditional machine learning model can beat all others in every dataset and task, numerous experiments are required to find the most suitable model. ...
... Recently, machine learning and deep learning methods have become widespread in healthcare, such as arrhythmias classification [3], coronary artery disease diagnosis [4], cancer diagnosis [5], and COVID-19 detection [6]. In prenatal screening for DS, many traditional machine learning algorithms have been used to detect DS cases from the antenatal screening data, such as support vector machine (SVM) [7]- [9], decision tree [7], [9]- [11], random forest [8]- [10], ensemble learning [8], [12] or multilayer perceptron (MLP) [11], [13]. However, as no traditional machine learning model can beat all others in every dataset and task, numerous experiments are required to find the most suitable model. ...
... The result showed a detection rate of about 60%-65%, which was not a high performance and needed to be improved. In another work, instead of maternal blood test used in other works, Weiner et al. used maternal plasma RNA screening data [9]. Eleven models were trained and showed very high accuracy. ...
One of the most common congenital anomalies in fetuses is known to be Down syndrome (DS). DS causes various adverse effects on the quality and length of life of children having DS and their families. Therefore, prenatal screening and diagnosis for DS are essential and valuable in antenatal care. Recently, machine learning methods for DS detection have become widespread. However, the existing methods, which use the traditional machine learning models, usually have several limitations while facing imbalanced data and missing data. This paper proposes a multi-branch CNN model combined with a feature rearrangement approach to improve the quality of DS prediction from prenatal screening data. The proposed feature rearrangement approach utilizes Pearson correlation testing and feature grouping to create a proper arrangement for the CNN model. Despite the imbalanced and highly missing data, the experiments show promising results with a Recall of 0.9023, F1-score of 0.8969, and balanced accuracy of 0.9314. These achievements outperform several traditional machine learning and attention-based deep learning models.
... One of the latest research related to DS and SMOTE-based methods is the work of Weiner et al. [15] in 2022. This research used features extracted from RNA instead of marker tests as in other works. ...
Down’s Syndrome (DS) is one of the most prevalent types of chromosomal abnormality. Developmental delays and disabilities on the physical and mental levels result from this syndrome. Hence, it must be detected as soon as possible. However, Down syndrome screening data tend to have a large overall data pool with a small proportion of positive cases, leading to an imbalanced class problem that causes classifiers to become biased. Moreover, the number of these data is also another problem, especially in Vietnam. These data are often private and challenging to collect correctly. This study utilizes synthetic data generating methods to maximize the detection rate of some traditional classification models. The final results of this study indicate that it is possible to improve the down syndrome prediction quality of the classifiers by adequately incorporating the SMOTE-based and GANs-based methods to generate synthetic data.
For prenatal screening, ultrasound imaging allows for real-time observation of developing fetal anatomy. Understanding normal and aberrant forms through extensive fetal structural assessment enables for early detection and intervention. However, the reliability of anomaly diagnosis varies depending on operator expertise and device limits. First trimester scans in conjunction with circulating biochemical markers are critical in identifying high-risk pregnancies, but they also pose technical challenges. Recent engineering advancements in automated diagnosis, such as AI-based ultrasound image processing and multimodal data fusion, are developing to improve screening efficiency, accuracy, and consistency. Still, creating trust in these data-driven solutions is necessary for integration and acceptability in clinical settings. Transparency can be promoted by explainable AI (XAI) technologies that provide visual interpretations and illustrate the underlying diagnostic decision making process. An explanatory framework based on deep
learning is suggested to construct charts depicting anomaly screening results from ultrasound video feeds. AI modeling can then be applied to these charts to connect defects with probable deformations. Overall, engineering approaches that increase
imaging, automation, and interpretability hold enormous promise for altering traditional workflows and expanding diagnostic capabilities for better prenatal care.
