| 1. |
- Khalil, Asma, et al.
(författare)
-
The Role of cfDNA Biomarkers and Patient Data in the Early Prediction of Preeclampsia: Artificial Intelligence Model.
- 2024
-
Ingår i: American journal of obstetrics and gynecology. - 1097-6868.
-
Tidskriftsartikel (refereegranskat)abstract
- Accurate individualized assessment of preeclampsia risk enables the identification of patients most likely to benefit from initiation of low-dose aspirin at 12-16 weeks' gestation when there is evidence for its effectiveness, as well as guiding appropriate pregnancy care pathways and surveillance. The primary objective of this study was to evaluate the performance of artificial neural network models for the prediction of preterm preeclampsia (<37 weeks' gestation) using patient characteristics available at the first antenatal visit and data from prenatal cell-free DNA (cfDNA) screening. Secondary outcomes were prediction of early onset preeclampsia (<34 weeks' gestation) and term preeclampsia (≥37 weeks' gestation).This secondary analysis of a prospective, multicenter, observational prenatal cfDNA screening study (SMART) included singleton pregnancies with known pregnancy outcomes. Thirteen patient characteristics that are routinely collected at the first prenatal visit and two characteristics of cfDNA, total cfDNA and fetal fraction (FF), were used to develop predictive models for early-onset (<34 weeks), preterm (<37 weeks), and term (≥37 weeks) preeclampsia. For the models, the 'reference' classifier was a shallow logistic regression (LR) model. We also explored several feedforward (non-linear) neural network (NN) architectures with one or more hidden layers and compared their performance with the LR model. We selected a simple NN model built with one hidden layer and made up of 15 units.Of 17,520 participants included in the final analysis, 72 (0.4%) developed early onset, 251 (1.4%) preterm, and 420 (2.4%) term preeclampsia. Median gestational age at cfDNA measurement was 12.6 weeks and 2,155 (12.3%) had their cfDNA measurement at 16 weeks' gestation or greater. Preeclampsia was associated with higher total cfDNA (median 362.3 versus 339.0 copies/ml cfDNA; p<0.001) and lower FF (median 7.5% versus 9.4%; p<0.001). The expected, cross-validated area under the curve (AUC) scores for early onset, preterm, and term preeclampsia were 0.782, 0.801, and 0.712, respectively for the LR model, and 0.797, 0.800, and 0.713, respectively for the NN model. At a screen-positive rate of 15%, sensitivity for preterm preeclampsia was 58.4% (95% CI 0.569, 0.599) for the LR model and 59.3% (95% CI 0.578, 0.608) for the NN model.The contribution of both total cfDNA and FF to the prediction of term and preterm preeclampsia was negligible. For early-onset preeclampsia, removal of the total cfDNA and FF features from the NN model was associated with a 6.9% decrease in sensitivity at a 15% screen positive rate, from 54.9% (95% CI 52.9-56.9) to 48.0% (95% CI 45.0-51.0).Routinely available patient characteristics and cfDNA markers can be used to predict preeclampsia with performance comparable to other patient characteristic models for the prediction of preterm preeclampsia. Both LR and NN models showed similar performance.
|
|
| 2. |
- Norton, Mary E., et al.
(författare)
-
Obstetrical, Perinatal, and Genetic Outcomes Associated With Nonreportable Prenatal Cell-Free DNA Screening Results
- 2024
-
Ingår i: OBSTETRICAL & GYNECOLOGICAL SURVEY. - 0029-7828 .- 1533-9866. ; 79:3, s. 146-148
-
Tidskriftsartikel (refereegranskat)abstract
- Although cell-free DNA (cfDNA) prenatal screening is widely used and has high sensitivity and specificity, there are circumstances in which the screening does not provide an interpretable result. Although this is relatively uncommon, it happens enough that clinical implications and potential reasons for follow-up should be studied and assessed. This study was designed to evaluate outcomes for pregnancies with nonreportable results on cfDNA screening tests. This study was a secondary analysis of the data from a multicenter prospective observational study of cfDNA screening for aneuploidy and 22q11.2 deletion syndrome. All patients were tested for trisomies 13, 18, and 21, as well as the 22q11.2 deletion syndrome, and all patients had confirmatory testing on the newborns in addition to collecting obstetric and perinatal outcomes. Inclusion criteria were women older than 18 years and at greater than 9 weeks of gestation with a singleton pregnancy. Exclusion criteria were having received cfDNA screening results before enrollment, organ transplant, ovum donation, vanishing twin, or being unwilling to provide a newborn sample. The primary outcome was the rate of adverse obstetrical and perinatal outcomes, including aneuploidy; preterm birth at less than 28, 34, or 37 weeks' gestation; preeclampsia; small for gestational age birth; and a composite outcome that included preterm birth before 37 weeks, preeclampsia, stillbirth at greater than 20 weeks, and small for gestational age. Final analyses included 17,851 individuals who had cfDNA screening, confirmatory genetic testing on the newborn, and obstetrical and perinatal outcomes recorded. Nonreportable results were found in 602 individuals (3.4%) after the first draw, with 32.2% of these due to low fetal fraction. Another third of the cohort had patterns where the risk of aneuploidy was uninterpretable but with an adequate fetal fraction, and in the final third, the fetal fraction could not be measured. Of the original 602 cases of nonreportable findings, 427 had a second draw, with 112 of these (26.2%) again having nonreportable results. There were no significant differences in baseline characteristics of age and parity for those with successful versus nonreportable test results; gestational age was significantly higher in individuals with nonreportable results (14.4 vs 13.4 weeks, P < 0.001), as was body mass index (26.2 vs 31.3), and the rate of chronic hypertension (4.0% vs 9.7%). In this cohort, there were 133 genetically confirmed trisomies, with 100 fetuses with trisomy 21, 18 individuals with trisomy 18, and 15 individuals with trisomy 13. Overall, the rate of aneuploidy was 1.7% in individuals with nonreportable results, versus 0.7% in those with reported results (P = 0.013; adjusted odds ratio [aOR] 2.1; 95% confidence interval [CI], 1.1-4.0). Rates of preterm birth were also higher in those with nonreportable test results, with delivery at less than 34 weeks at 1.5% in those with a test result, 4.6% in those with one nonreportable test result and 6.9% in those with a second nonreportable test result (aOR, 2.2 and 2.7; 95% CI, 1.4-3.4 and 1.2-6.0, respectively). Preeclampsia showed a similar trend, with rates climbing from 3.9% in those with a reported result to 9.4% with 1 nonreportable result and 16.8% with 2 (aOR, 1.4 and 2.0; 95% CI, 1.0-1.9 and 1.1-3.7, respectively). Chances of live birth were significantly reduced in pregnancies with a nonreportable results (aOR, 0.20; 95% CI, 0.13-0.30), with the chances decreasing more after a second nonreportable test result (aOR, 0. 11; 95% CI, 0.06-0.23). The study found that nonreportable cfDNA screening results are associated with an increased risk for aneuploidy, preterm birth, and preeclampsia, with a gradient of increased risk with a second failed test. This adds to literature with conflicting findings surrounding obstetrical complications in those with altered cfDNA levels and with most studies largely focused on characteristics that may be predictive of a nonreportable result rather than outcomes associated with nonreportable results. These results can inform clinicians who have patients with nonreportable test results in a way that may help them provide better care; future research should focus on more fully understanding the adverse outcomes associated with nonreportable tests to maximize this ability for clinicians in the future. Further research should also focus on specific populations or diagnoses to understand if there are fundamental differences in different groups of individuals.
|
|
