Ensemble learning-driven hybrid prediction model for improved prenatal down's syndrome screening: a comparative study with laboratory-based median equations.

Prenatal screening for trisomy 21 (Down syndrome) using first- and second-trimester biochemistry and nuchal translucency: A technical standard of the American College of Medical Genetics and Genomics (ACMG).

Down syndrome (DS) is one of the prevalent chromosomal disorders, representing distinctive craniofacial features and a range of developmental and medical challenges. Due to the lack of clinical expertise and high infrastructure costs, access to genetic testing is restricted to resource-constrained clinical settings. There is a demand for developing a non-invasive and equitable DS screening tool, facilitating DS diagnosis for a wide range of populations. In this study, we develop and validate a robust, interpretable deep learning model for the early detection of DS using facial images of infants. A hybrid feature extraction architecture combining RegNet X–MobileNet V3 and vision transformer (ViT)-Linformer is developed for effective feature representation. We use an adaptive attention-based feature fusion to enhance the proposed model’s focus on diagnostically relevant facial regions. Bayesian optimization with hyperband (BOHB) fine-tuned extremely randomized trees (ExtraTrees) is employed to classify the features. To ensure the model’s generalizability, stratified five-fold cross-validation is performed. Compared to the recent DS classification approaches, the proposed model demonstrates outstanding performance, achieving an accuracy of 99.10%, precision of 98.80%, recall of 98.87%, F1-score of 98.83%, and specificity of 98.81%, on the unseen data. The findings underscore the strengths of the proposed model as a reliable screening tool to identify DS in the early stages using the facial images. This study paves the foundation to build equitable, scalable, and trustworthy digital solution for effective pediatric care across the globe.

In this study, we sought to analyze the associations of global macroeconomic policy decisions on live births with Down syndrome (DS). As countries made prenatal screening more available and financially covered by their governments, we modeled the impact on the "reduction percentage" for DS-that is, the percentage of fetuses with DS that were not born as a consequence of selective terminations. The log-odds of the reduction in live births of children with DS (due to selective abortion) were estimated using maternal age-based prevalence models and actual birth data. These log-odds were then predicted using independent variables, including the availability and reimbursement of prenatal screening, maternal age, Gross National Income per capita, and country-specific effects. Data were analyzed using least squares regression with robust standard errors and model validation. When there is a full change from "no availability of screening" to "serum screening available and reimbursed," we observed a large effect on the reduction percentage (OR = 3.24, p = 0.0001). If a country, whose baseline reduction percentage was 5%, 25%, or 50%, were to make this policy switch, then the reduction would be expected to increase to about 15%, 52%, and 76%, respectively, when all other variables are held constant. Increases in maternal age and Gross National Income also were associated with increased reduction percentages. If a country were to expand the availability or reimbursement of prenatal screening for DS, while all other factors are constant, that country should also expect to have fewer live births with DS as a consequence.

Prenatal screening for Down syndrome (DS) is offered to expectant parents receiving antenatal care in many countries, with an emphasis on providing parents with the opportunity to make informed choices about their pregnancy. We examined experiences of prenatal screening among mothers of children with DS living in England, Scotland, or Wales. Mothers (N = 317) of a child with DS born between 2019 and 2022 responded to an online survey and answered closed and open-ended questions about their experiences of being offered initial screening and non-invasive prenatal testing, and of receiving screening results. The findings from quantitative and qualitative analyses indicated that while most mothers understood screening was optional, many accepted initial screening with little consideration and most perceived it as routine. Many mothers reported receiving insufficient information about DS and limited support to help them make sense of screening results. Many mothers reported that screening results were not presented neutrally, and some highlighted how communication which reflected negative attitudes or assumptions about DS was highly memorable and impactful. The importance of personalized discussion to support mothers' understanding of screening, and to legitimize the option of declining screening tests, is discussed. The findings highlight the importance of a neutral approach to the delivery of both higher and lower chance screening results and of welcoming a diversity of choices.

Screening and termination of pregnancy (TOP) for Down syndrome (DS) are both available in South Africa (SA), but DS is infrequently diagnosed prenatally in the public sector (7% in 2008), resulting in a high live-birth prevalence (1.33 - 2.1 per 1 000). In the SA public sector, DS screening and confirmatory genetic testing are fully state subsidised for women of advanced maternal age (AMA) but, owing to the low positive predictive value of AMA-based screening, ultrasound-based screening is also offered. Given the limited resources and the steady increase in the number of pregnant women of AMA, the value of DS screening in altering pregnancy outcome needs to be critically assessed. To determine the uptake of prenatal screening for DS, invasive testing and TOP in pregnant women of AMA, as well as factors influencing maternal decisions. This retrospective cohort study, based on prospectively captured data, includes all women of AMA (>37 years at conception) seen at a regional fetal medicine unit in Cape Town offering fully state subsidised DS screening and testing for a geographically defined area, including mostly women of African or mixed ancestry. Screening was age- and ultrasound-based, and DS risks were calculated using published algorithms. Non-directive genetic counselling was provided to all women ≥40 years old (pre-screen if feasible), women with a relevant history, a fetal anomaly or DS risk higher than that of a woman aged 37 years. Participant characteristics, results, decisions and reasons to decline testing were recorded prospectively, and compared between women <40 completed years and ≥40 years old, and between women accepting or declining invasive testing or TOP. During the study period, 1 196 women of AMA were seen. Ninety-three received pre-screen counselling, and 44 of these declined DS screening (47.3% (95% confidence interval (CI) 36.9 - 57.9)). Uptake of invasive testing after screening was low (18.1% (CI 15.2 - 21.3)). Age category was not an independent confounder for this, but uptake was lower after previous miscarriage(s), higher after high-risk screening results and highest with a fetal anomaly. The most common reason for declining testing was opposition to TOP. The uptake of TOP for DS, when offered to those who were screened and had accepted invasive testing, was 65.8% (48.7 - 80.4). The uptake of screening and/or testing was low, and this reflected strong views on TOP for DS. As uptake of testing and/or TOP was higher with abnormal ultrasound findings, a prenatal screening programme addressing structural anomalies and aneuploidies simultaneously (i.e. ultrasound) is preferred over other DS screening tools that target DS specifically.

Artificial intelligence and facial recognition have opened new avenues for early detection of even genetic conditions. This research paper applies a state-of-the-art object detection model, YOLOv8, to accurately identify children with Down syndrome from their faces. The model is then trained and fine-tuned on the face image dataset for high-performance metrics not seen earlier, using the real-time detection capability of YOLOv8. The model was precision at 0.958 and had a high recall at 0.967. That means that the model will mostly correctly identify all children with Down syndrome while keeping the false positives and false negatives to the minimum. Also, the mean Average Precision of the model is 0.988 out of 1.00 on the IoU threshold of 0.50, mAP50, showing near-perfect overlap between predicted and actual face regions. The model also maintained high performance at 0.746 mAP50-95, which informs the model's ability to make more accurate predictions over the stricter IoU thresholds. These findings suggest that YOLOv8 may be employed for effective early screening for Down syndrome, offering healthcare providers a non-invasive and efficient solution. More robust detection performance about relevant facial features indicative of the condition will support early diagnosis and, therefore, timely interventions that will significantly enhance the quality of life in children affected with Down syndrome. This study is probably the most noninvasive, inexpensive screening method for Down syndrome in the world. Its availability can help the least developed parts of the world intervene as early as possible and improve the outcomes for children worldwide, especially those from the most deprived areas.

To compare the performance of first-trimester serum screening (FTSS) and non-invasive prenatal testing (NIPT) in detecting fetal chromosomal aneuploidies trisomy 21 (T21) and trisomy 18 (T18), and to evaluate the cost-effectiveness and clinical feasibility of four screening strategies for the prevention of Down syndrome (DS) from a health economics perspective. This retrospective study included 33,559 pregnant women who underwent DS screening at Fujian Maternity and Child Health Hospital between February 25, 2022, and December 29, 2023. Participants were divided into an FTSS group (n = 23,136) and an NIPT group (n = 10,423) based on the type of screening received. All subjects were followed for eight months postpartum to collect pregnancy outcome data. Screening performance was compared between the two groups based on prenatal diagnostic results. Subsequently, four screening strategies were constructed and assessed using cost-effectiveness analysis and NIPT price sensitivity analysis to determine their health-economic value. A comparison of screening performance between the two groups showed that NIPT had significantly higher specificity (99.96%) and positive predictive value (55.56%) than FTSS (specificity: 92.93%, positive predictive value: 0.91%). Meanwhile, the false-positive rate of NIPT (0.04%) was notably lower than that of FTSS (7.07%). Cost-effectiveness analysis of the four strategies indicated that strategy 2 was the most cost-effective, with a cost-effectiveness ratio (CER) of 1,252,400 CNY and an incremental cost-effectiveness ratio (ICER) of -3,626,700 CNY, achieving improved screening outcomes while reducing costs. Sensitivity analysis further demonstrated that even when the screening scale expanded under strategy 4 or when NIPT prices fluctuated between 700 and 2,100 CNY, strategy 2 maintained the lowest CER. NIPT is superior to FTSS in terms of screening efficacy. Based on a health economic evaluation, among the four strategies, Strategy 2 (using NIPT as conditional screening) offers the best cost-effectiveness while improving detection efficacy, making it the optimal strategy recommended in this study.

ObjectiveOxidative stress plays a pivotal role in the pathogenesis of Down syndrome (Trisomy 21), as chromosome 21 harbors multiple genes involved in redox homeostasis and antioxidant defense mechanisms. This study aimed to evaluate the roles of transcription factors nuclear factor erythroid 2-related factor 2 (NRF2) and nuclear factor-kappa B (NFKB), along with antioxidant enzymes cystathionine-γ-lyase (CSE) and NAD(P)H dehydrogenase [quinone] 1 (NQO1) in amniotic fluid (AF) and maternal serum (MS) as potential biomarkers for prenatal screening of Down syndrome (DS).MethodsThis prospective case-control study included singleton pregnant women undergoing amniocentesis between 16 and 24 weeks of gestation at Haseki Training and Research Hospital, Istanbul. Participants were divided into two groups: 28 pregnancies with DS confirmed by karyotype analysis (DS group) and 37 pregnancies with normal karyotype results (non-DS group). Amniotic fluid and maternal blood samples were analyzed using enzyme-linked immunosorbent assay (ELISA) kits to measure the levels of selected biomarkers.ResultsNQO1 levels were significantly higher in the DS group compared to the non-DS group in both amniotic fluid (924.84 ± 475.94 vs. 505.62 ± 358.17 ng/ml, p < 0.001) and maternal serum (716.216 ± 242.91 vs. 394.87 ± 344.86 ng/ml, p < 0.001). NRF2 levels were significantly lower in the DS group in both amniotic fluid (3.77 ± 4.20 vs. 6.47 ± 5.53 ng/ml, p = 0.029) and maternal serum (7.54 ± 5.68 vs. 14.46 ± 16.53 ng/ml, p = 0.022).ConclusionThe study highlights the importance of further research to validate the use of these antioxidant enzymes and transcription factors in non-invasive prenatal testing, which may reduce the need for invasive procedures and associated complications.Clinical trial numberNot applicable.

Recent advancements in high-throughput sequencing have validated the accuracy, safety, and effectiveness of non-invasive prenatal testing (NIPT) for Down syndrome (DS). This study aims to assess the effectiveness and economic implications of NIPT versus second-trimester serum screening (STSS) for DS and the different screening strategies through retrospectively analyzing data from 140,472 pregnant women who completed both NIPT and STSS (provided for free by local public welfare programs) between March 1, 2018 and December 31, 2020. Data were categorized into eight groups based on different screening strategies. The sensitivity, specificity, and positive predictive value of NIPT for detecting trisomy 21 were significantly higher compared with those of STSS. The universal NIPT screening strategy demonstrated the best effectiveness, detecting 163 DS cases with the highest net benefit and a cost-effectiveness ratio of 1:9.53. The STSS and NIPT combined screening strategy detected 128 DS cases with the lowest cost-effectiveness at RMB 341,800. The incremental cost-effectiveness ratio of the universal NIPT screening strategy was RMB 1,186,200, significantly lower than the socioeconomic burden associated with a DS case. NIPT demonstrated significantly superior testing performance compared to STSS. At a unit cost of RMB 600, the universal NIPT screening strategy is the most effective and holds substantial health economic value.

Down Syndrome or Trisomy 21 (T21) is a complex genetic disease characterized by the presence of an extra chromosome 21, which leads to multiple clinical features and manifestations that severely affect the patient's quality of life. Various methods of prenatal screening have been developed over time, allowing informed decision-making. However, a common drawback of the current methods for detecting T21 is their invasive nature. Over the past years, mass-spectrometry-based omics technologies have become a key tool for discovering biomarkers for the prenatal screening of T21, particularly focusing on proteins, peptide sequences, or metabolites in samples, like amniotic fluid, umbilical cord blood, and others. Recently, there has been a noticeable shift towards using less invasive biological sample types (e.g., maternal serum, plasma, and urine) reflecting a growing interest in non-invasive methods for prenatal screening. These advances aim to improve the sensitivity and accuracy for T21 detection while reducing the risks associated with more invasive procedures. The first section of this paper offers an in-depth review of studies utilizing mass-spectrometry-based omics for the prenatal screening of T21. This part provides an overview of the methodologies employed and their key findings. Instead, the subsequent section offers a comprehensive examination of the differentially expressed proteins (DEPs) and metabolites (DEMs) reported in the literature in T21 prenatal screening. Additionally, pathway analysis is carried out to explore the biological pathways that these molecules are involved in and how they relate to the clinical features of the syndrome. These findings aim to guide future research in the field and foster the development of more advanced, less invasive prenatal screening techniques for T21.

Objective: We aimed to explore the value of chromosome microarray analysis (CMA) and karyotyping in fetuses with a high risk for Down syndrome (DS) by serological screening and prenatal cell-free DNA(cfDNA) screening in Southwest China. Methods: We performed CMA and karyotype in 3028 pregnant women at high risk of DS. Results: Among 2,830 individuals identified as high-risk through serological screening for DS, 280 (9.89%) returned positive results. Subsequent karyotyping confirmed 51 cases of DS, 13 cases of sex chromosome aneuploidy, and 11 cases of trisomy 18. Moreover, CMA revealed 45 cases of pathogenic/likely pathogenic copy number ­variations (p/lpCNVs), 128 cases of uncertain significance(VOUS), and 32 cases of regions of homozygosity(ROH), with a 13.04% (205/280) increase in CMA yield compared to the karyotype analysis. Among 227 who had a high risk of prenatal cfDNA screening for DS, 181 (79.74%) exhibited positive results, including 179 cases with DS. Conclusion: Serological screening cannot be replaced by prenatal cfDNA screening. CMA, combined with karyotyping, has a high diagnostic value for DS and should be promoted.

Down syndrome (DS) is a chromosomal disorder linked to intellectual impairment and developmental delays in babies. The primary prenatal indicator for detecting DS during the initial stages of gestation is the thickness of nuchal translucency (NT). This paper introduces a GoogLeNet model based on convolutional neural networks (CNN) for the semantic segmentation of the NT region from ultrasound fetal images, facilitating rapid and cost-effective diagnosis in the early stages of the gestational period. A transfer learning methodology with AlexNet is employed to train the NT regions for the detection of DS. The Inception module of GoogLeNet enables the model to simultaneously capture characteristics at various sizes of images. The capacity to extract both intricate and broad characteristics can improve the model’s performance in precisely identifying the NT area. This will function as an exceptional tool for physicians in screening of DS, enhancing the detection rate and providing a substantial opinion for early diagnosis. The proposed deep learning approach attained an accuracy of 96.18% and Jaccard index of 0.967 for NT region segmentation utilizing GoogLeNet. A confusion matrix was used to evaluate the image classification by AlexNet model's effectiveness, and the results showed an overall accuracy of 97.84%, ROC-AUC of 98.45%, recall of 99.64%, precision of 96.04%, and F1 score of 97.80%. The proposed deep learning method produced remarkable outcomes and can be applied to the identification of DS in medical field. This method identifies individuals at increased risk for this condition and enables termination in the early stages of pregnancy.

Advocating a specific risk calculation of trisomy 18 in case of low maternal serum markers during screening for fetal Down syndrome.

The use of machine learning (ML) in biomarker analysis for predicting Down syndrome exemplifies an innovative strategy that enhances diagnostic accuracy and enables early detection. Recent studies demonstrate the effectiveness of ML algorithms in identifying genetic variations and expression patterns associated with Down syndrome by comparing genomic data from affected individuals and their typically developing peers. This review examines how ML and biomarker analysis improve prenatal screening for Down syndrome. Advancements show that integrating maternal serum markers, nuchal translucency measurements, and ultrasonographic images with algorithms, such as random forests and deep learning convolutional neural networks, raises detection rates to above 85% while keeping false positive rates low. Moreover, non-invasive prenatal testing with soft ultrasound markers has increased diagnostic sensitivity and specificity, marking a significant shift in prenatal care. The review highlights the importance of implementing robust screening protocols that utilize ultrasound biomarkers, along with developing personalized screening tools through advanced statistical methods. It also explores the potential of combining genetic and epigenetic biomarkers with ML to further improve diagnostic accuracy and understanding of Down syndrome pathophysiology. The findings stress the need for ongoing research to optimize algorithms, validate their effectiveness across diverse populations, and incorporate these cutting-edge approaches into routine clinical practice. Ultimately, blending advanced imaging techniques with ML shows promise for enhancing prenatal care outcomes and aiding informed decision-making for expectant parents.

Despite the potential risks, assisted reproductive technology has provided hope and opportunities for individuals and couples struggling with infertility to conceive and have children. This study presents a case report that describes an occurrence where a pregnancy achieved through in vitro fertilization (IVF) and embryo transfer had to be ended because of the presence of trisomy 21 syndrome. Two 26-year-old women who were diagnosed with primary infertility due to polycystic ovary syndrome manifested with overweight and hirsutism. These 2 cases were regarded as a diagnosis of Down syndrome, which resulted in the decision to legally terminate the pregnancy when the mother was, in her 12th week and 4 days of gestation. Upon examining the makeup of the cells in the chorionic villi it was discovered that all cells had a chromosomal composition of 47, XX. In these case reports, 2 26-year-old woman with polycystic ovary syndrome underwent assisted reproductive technology and IVF to conceive. The first IVF transfer was unsuccessful, but the second attempt resulted in a successful transfer in both cases. However, a positive screening for Down syndrome led to a legal abortion at 12 + 4 weeks gestation. Genetic counseling revealed no family history of genetic diseases, and the couple opted for IVF without preimplantation genetic testing. During the trimester of their pregnancies the expectant mothers were initially screened at 12 + 4 weeks after conception. Nuchal translucency examination showed thickening of the fluid at the back of the fetal neck. Moreover, there was an increase in the levels of pregnancy related plasma protein and β human chorionic gonadotropin. These 2 cases underscore the significance of genetic counseling and prenatal screening for couples who are undergoing assisted reproductive technologies, with the purpose of detecting and effectively addressing any possible genetic abnormalities that may arise in their progeny.

Successful Pregnancies during Crizotinib Therapy for ALK+ Lymphoma

Down syndrome (DS) is a congenital disorder caused by the presence of an extra copy of all or part of chromosome 21. It is characterized by significant intellectual disability, distinct facial features, and growth and developmental challenges. The utilization of metabolomics to analyze specific metabolic markers in maternal amniotic fluid may provide innovative tools and screening methods for investigating the early pathophysiology of trisomy 21 at the functional level. Amniotic fluid samples were obtained via amniocentesis from 57 pregnancies with DS and 55 control pregnancies between 173/7 and 240/7weeks of gestation. The targeted metabolomics focused on 34 organic acids, 17 amino acids, and 5 acylcarnitine metabolites. The untargeted metabolomics analysis concentrated on lipid profiles and included 602 metabolites that met quality control standards. Principal Component Analysis, Orthogonal Partial Least Squares Discriminant Analysis (OPLS-DA), and false discovery rate (FDR) adjustments were applied. MetaboAnalystR 5.0 was used to perform the metabolic pathway analysis on the identified differential metabolites. Fifty differential metabolites, including L-glutamine, eight organic acids, and 41 lipids, were significantly altered in DS based on three criteria: VIP > 1 in the OPLS-DA model, FDR-adjusted p-value < 0.05, and |log2FC|>log2(1.5) from a volcano plot of all detected metabolites. An analysis of 212 differential metabolites, selected from both targeted and untargeted approaches (VIP > 1 in the OPLS-DA model and FDR-adjusted p-value < 0.05), revealed significant changes in nine metabolic pathways. Fourteen key metabolites were identified to establish a screening model for DS, achieving an area under the curve of 1.00. Our results underscore the potential of metabolomics approaches in identifying concise and reliable biomarker combinations that demonstrate promising screening performance in DS.

Exploring efficient and easily implementable prenatal screening strategies aims at birth defect prevention and control. However, there have been limited economic evaluations of non-invasive prenatal screening (NIPS) strategies in China. Furthermore, these studies were predominantly confined to local or geographically proximate provinces and lacked universality and representativeness. This study assesses the health economics of current prenatal screening strategies and NIPS as first-line screening programs, analyzing their efficacy to determine an optimal strategy. From the perspective of health economics, cost-effectiveness, cost-benefit, and single-factor sensitivity were conducted for five different screening strategies using a decision tree model. Among pregnant women aged < 35 years who underwent only one screening for foetal Down syndrome (DS), the detection rate, false positive rate and positive predictive value of NIPS for foetuses with DS were superior to those of the other four serological screening methods. Although applying NIPS as first-line screening method yields the highest efficacy and benefits, it currently lacks cost-effectiveness when compared to serological screening and sequential NIPS screening strategies.

Exploring free pregnancy associated plasma protein a (fPAPP-A) as a biomarker in early pregnancy