Browsing by Author "Molina, F. S."
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Risk of miscarriage after chorionic villus sampling.(Ultrasound in Obstetrics and Gynecology, 2020) Gil Mira, María del Mar; Molina, F. S.; Rodríguez Fernández, M.; Delgado, J. L.; Carrillo, M. P.; Jani, J.; Plasencia, W.; Stratieva, V.; Maíz, N.; Carretero, P.; Lismonde, A.; Chaveeva, P.; Burgos, J.; Santacruz Martín, Belén; Zamora, J.; De Paco Matallana, C.Objective To estimate the risk of miscarriage associated to chorionic villus sampling (CVS). Methods This was a retrospective cohort study performed in eight fetal‐medicine units in Spain, Belgium and Bulgaria. Two populations were included: first, all singleton pregnancies attending to their first‐trimester assessment in Murcia, Spain, and second, all singleton pregnancies having a CVS following first‐trimester assessment at any of the participating centers. We used propensity score matching analysis to estimate the association between CVS and miscarriage. We compared risks of miscarriage of CVS and non‐CVS groups after propensity score matching (1:1 ratio). This procedure creates two comparable groups balancing the maternal and pregnancy characteristics that lead to CVS, in a similar way in which randomization operates in a randomized clinical trial. Results The study population consisted of 22,250 participants in the non‐CVS group and 3,613 in the CVS group. The incidence of miscarriage in the CVS group was 2.1% (77/3,613), which was significantly higher than the 0.9% (207/22,250) in the non‐CVS group (p <0.001). The propensity score algorithm matched 2,122 CVS cases with 2,122 non‐CVS cases including 40 (1.9%) and 55 (2.6%) miscarriages in the CVS and non‐CVS groups, respectively (OR 0.72 [95% CI 0.48 to 1.10]; p = 0.146). However, we found a significant interaction between the CVS risk of miscarriage and the risk of aneuploidies, suggesting a different effect of the CVS for different baseline characteristics in such a way that, when the risk of aneuploidies is low, the risk after CVS increases (OR 2.87 [95% CI 1.13 to 7.30]) but when the risk is high, the risk after CVS is paradoxically reduced (OR 0.47 [95% CI 0.28 to 0.76]), presumably due to prenatal diagnosis and termination of major aneuploidies that would have otherwise resulted in spontaneous miscarriage. Conclusions The risk of miscarriage in women having a CVS is about 1% higher than in women without CVS, although this excess risk is not entirely due to the invasive procedure but to some extent the demographic and pregnancy characteristics of the patient undergoing CVS. After accounting for these risk factors and confining the analysis to low‐risk pregnancies, CVS seems to increase the risk of miscarriage about three times above the patient’s background‐risk. Although this is a substantial increase in relative terms, in pregnancies without risk factors, the risk of miscarriage after CVS will still remain low and similar to or slightly higher than that of the general population. For example, if her risk of aneuploidy is 1 in a 1,000 (0.1%), her risk of miscarriage after CVS will increase to 0.3% (0.2% higher).Item Validation of machine-learning model for first-trimester prediction of pre-eclampsia using cohort from PREVAL study.(Ultrasound in Obstetrics & Gynecology, 2024) Gil Mira, María del Mar; Cuenca Gómez, D.; Rolle, V.; Pertegal, M.; Valiño, N.; Revello, R.; Adiego, B.; Mendoza, M.; Molina, F. S.; Santacruz Martín, Belén; Ansbacher-Feldman, Z.; Meiri, H.; Martín Alonso, R.; Louzoun, Y.; De Paco Matallana, C.Objective Effective first-trimester screening for pre-eclampsia (PE) can be achieved using a competing-risks model that combines risk factors from the maternal history with multiples of the median (MoM) values of biomarkers. A new model using artificial intelligence through machine-learning methods has been shown to achieve similar screening performance without the need for conversion of raw data of biomarkers into MoM. This study aimed to investigate whether this model can be used across populations without specific adaptations. Methods Previously, a machine-learning model derived with the use of a fully connected neural network for first-trimester prediction of early (< 34 weeks), preterm (< 37 weeks) and all PE was developed and tested in a cohort of pregnant women in the UK. The model was based on maternal risk factors and mean arterial blood pressure (MAP), uterine artery pulsatility index (UtA-PI), placental growth factor (PlGF) and pregnancy-associated plasma protein-A (PAPP-A). In this study, the model was applied to a dataset of 10 110 singleton pregnancies examined in Spain who participated in the first-trimester PE validation (PREVAL) study, in which first-trimester screening for PE was carried out using the Fetal Medicine Foundation (FMF) competing-risks model. The performance of screening was assessed by examining the area under the receiver-operating-characteristics curve (AUC) and detection rate (DR) at a 10% screen-positive rate (SPR). These indices were compared with those derived from the application of the FMF competing-risks model. The performance of screening was poor if no adjustment was made for the analyzer used to measure PlGF, which was different in the UK and Spain. Therefore, adjustment for the analyzer used was performed using simple linear regression. Results The DRs at 10% SPR for early, preterm and all PE with the machine-learning model were 84.4% (95% CI, 67.2–94.7%), 77.8% (95% CI, 66.4–86.7%) and 55.7% (95% CI, 49.0–62.2%), respectively, with the corresponding AUCs of 0.920 (95% CI, 0.864–0.975), 0.913 (95% CI, 0.882–0.944) and 0.846 (95% CI, 0.820–0.872). This performance was achieved with the use of three of the biomarkers (MAP, UtA-PI and PlGF); inclusion of PAPP-A did not provide significant improvement in DR. The machine-learning model had similar performance to that achieved by the FMF competing-risks model (DR at 10% SPR, 82.7% (95% CI, 69.6–95.8%) for early PE, 72.7% (95% CI, 62.9–82.6%) for preterm PE and 55.1% (95% CI, 48.8–61.4%) for all PE) without requiring specific adaptations to the population. Conclusions A machine-learning model for first-trimester prediction of PE based on a neural network provides effective screening for PE that can be applied in different populations. However, before doing so, it is essential to make adjustments for the analyzer used for biochemical testing.