Dataset Information

Development and performance evaluation of an artificial intelligence algorithm using cell-free DNA fragment distance for non-invasive prenatal testing (aiD-NIPT).

ABSTRACT: With advances in next-generation sequencing technology, non-invasive prenatal testing (NIPT) has been widely implemented to detect fetal aneuploidies, including trisomy 21, 18, and 13 (T21, T18, and T13). Most NIPT methods use cell-free DNA (cfDNA) fragment count (FC) in maternal blood. In this study, we developed a novel NIPT method using cfDNA fragment distance (FD) and convolutional neural network-based artificial intelligence algorithm (aiD-NIPT). Four types of aiD-NIPT algorithm (mean, median, interquartile range, and its ensemble) were developed using 2,215 samples. In an analysis of 17,678 clinical samples, all algorithms showed >99.40% accuracy for T21/T18/T13, and the ensemble algorithm showed the best performance (sensitivity: 99.07%, positive predictive value (PPV): 88.43%); the FC-based conventional Z-score and normalized chromosomal value showed 98.15% sensitivity, with 40.77% and 36.81% PPV, respectively. In conclusion, FD-based aiD-NIPT was successfully developed, and it showed better performance than FC-based NIPT methods.

SUBMITTER: Lee J

PROVIDER: S-EPMC9745024 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and performance evaluation of an artificial intelligence algorithm using cell-free DNA fragment distance for non-invasive prenatal testing (aiD-NIPT).

Lee Junnam J Lee Sae-Mi SM Ahn Jin Mo JM Lee Tae-Rim TR Kim Wan W Cho Eun-Hae EH Ki Chang-Seok CS

Frontiers in genetics 20221129

With advances in next-generation sequencing technology, non-invasive prenatal testing (NIPT) has been widely implemented to detect fetal aneuploidies, including trisomy 21, 18, and 13 (T21, T18, and T13). Most NIPT methods use cell-free DNA (cfDNA) fragment count (FC) in maternal blood. In this study, we developed a novel NIPT method using cfDNA fragment distance (FD) and convolutional neural network-based artificial intelligence algorithm (aiD-NIPT). Four types of aiD-NIPT algorithm (mean, medi ...[more]

PMID: 36523771

Similar Datasets

Project description:BackgroundGenomics-based noninvasive prenatal tests (NIPT) allow screening for chromosomal anomalies such as Down syndrome (trisomy 21). The technique uses cell-free fetal DNA (cffDNA) that circulates in the maternal blood and is detectable from 5 weeks of gestation onwards. Parents who choose to undergo this relatively new test (introduced in 2011) might be aware of its positive features (i.e. clinical safety and ease of use); however, they might be less aware of the required decisions and accompanying internal conflicts following a potential positive test result. To show the evidence on psychological and social consequences of the use of NIPT, we conducted a scoping review.MethodsWe systematically searched four electronic databases (MEDLINE (Ovid), Cochrane Library (Wiley), CINAHL (EBSCO) and PsychINFO (EBSCO)) for studies that investigated the psychological or social consequences of the use of NIPT by pregnant women or expecting parents. The search was limited to studies published between 2011 and August 8, 2018. We identified 2488 studies and, after removal of duplicates, screened 2007 titles and abstracts, and then assessed 99 articles in full text (both screenings were done independently in duplicate). We included 7 studies in our analysis.ResultsFive studies assessed anxiety, psychological distress and/or decisional regret among women with validated psychological tests like the Spielberger State Trait-Anxiety Inventory (STAI), the Pregnancy-Related Anxiety Questionnaire-Revised (PRAQ-R), the Kessler Psychological Distress Scale (K6) or the Decisional Regret Scale (DRS). Two studies assessed women's experiences with and feelings after NIPT in interviews or focus groups. The included studies were heterogeneous in location, study setting, inclusion criteria, outcome assessment, and other characteristics.ConclusionsOnly few studies on psychological consequences of NIPT have been identified. The studies assessed only short-term psychological consequences of NIPT at baseline and/or after receiving the results or after giving birth. Studies show that short term anxiety decreased when women received negative NIPT results and that decisional regret was generally low. We could not identify studies on long term consequences of NIPT, as well as studies on women's partners' short and long term outcomes, nor on social consequences of NIPT.

Project description:IntroductionOur objective was to evaluate the efficacy of expanded non-invasive prenatal testing (NIPT) that includes both trisomies and copy number variants (CNVs) in high-risk twin pregnancies.Material and methodsA prospective, double-blinded cohort study was conducted, enrolling 73 high-risk twin pregnancies characterized by increased risk of genetic disorders due to factors such as increased nuchal translucency, structural anomalies, fetal growth restriction, and other factors associated with chromosomal abnormality. Participants underwent invasive karyotyping and chromosomal microarray analysis, alongside separate expanded NIPT for research purposes. The sensitivity, specificity, positive predictive value, and negative predictive value of expanded NIPT were calculated.ResultsThe cohort included 24 monochorionic and 49 dichorionic twin pregnancies. The median cell-free fetal DNA concentration in expanded NIPT was 16.7% (range 3.86%-49.1%), with a test failure rate of 1.4% (1/73). High-risk findings for trisomy 21/13/18 were identified in five cases (6.8%), Turner syndrome in one case (1.4%), and CNVs indicative of high risk for clinically significant microdeletion/microduplication syndromes (MMS) in ten cases (13.7%). Of these, 56 cases (76.7%) tested NIPT negative, revealing one false-negative for 45, X and five false-negatives for CNVs. Expanded NIPT achieved a detection rate of 100% (5/5) for trisomy 21/13/18 with a false-positive rate of 0% (0/5), a detection rate of 33.3% (1/3) for sex chromosome abnormalities with a false-positive rate of 0% (0/3), and a detection rate of 66.7% (4/6) for MMS with a false-positive rate of 3.0% (2/67). The positive predictive values for trisomy T21/13/18, sex chromosome abnormalities, and known MMS were 100% (5/5), 100% (1/1), and 66.7% (4/6) in the expanded NIPT, respectively.ConclusionsThe expanded NIPT demonstrated high detection rates for common trisomies and moderate detection rates for prenatal MMS in high-risk twin pregnancies. Further studies with large sample sizes in low-risk populations are needed.

Project description:BackgroundNon-invasive prenatal testing (NIPT) allows women to access genetic information about their fetuses without the physical risk inherent to prior testing methods. The advent of NIPT technology has led to concerns regarding the quality and process of informed consent, as a view of NIPT as "routine" could impair women's considered approach when choosing to undergo testing. Prior studies evaluating NIPT decision-making have focused on the clinical encounter as the primary environment for acquisition of biomedical information and decision formation. While important, this conceptualization fails to consider how additional sources of knowledge, including embodied and empathetic experiential knowledge, shape perceptions of risk and the societal use of NIPT.MethodsIn order to address this issue, qualitative, semi-structured interviews with 25 women who had been offered NIPT were performed. Participants came from a well-resourced, rural setting near a major academic medical center in the US. Women were categorized by NIPT use/non-use as well as whether their described decision-making process was perceived as making a significant decision requiring contemplation ("significant") versus a rapid or immediate decision ("routinized"). A constructivist general inductive approach was used to explore themes in the data, develop a framework of NIPT decision-making, and compare the perceptions of women with differential decision-making processes and outcomes.ResultsA framework for decision-making regarding NIPT was developed based on three emergent factors: perceptions of the societal use of NIPT, expected emotional impact of genetic information, and perceived utility of genetic information. Analysis revealed that perceptions of widespread use of NIPT, pervasive societal narratives of NIPT use as "forward-thinking," and a perception of information as anxiety-relieving contributed to routinized uptake of NIPT. In contrast, women who displayed a lack of routinization expressed fewer stereotypes regarding the audience for NIPT and relied on communication with their social networks to consider how they might use the information provided by NIPT.ConclusionsThe findings of this study reveal the societal narratives and perceptions that shape differential decision-making regarding NIPT in the U.S.ContextUnderstanding and addressing these perceptions that influence NIPT decision-making, especially routinized uptake of NIPT, is important as the use and scope of this technology increases.

Dataset Information

Development and performance evaluation of an artificial intelligence algorithm using cell-free DNA fragment distance for non-invasive prenatal testing (aiD-NIPT).

Publications

Development and performance evaluation of an artificial intelligence algorithm using cell-free DNA fragment distance for non-invasive prenatal testing (aiD-NIPT).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets