Validation of machine-learning model for first-trimester prediction of pre-eclampsia using cohort from PREVAL study.

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. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Comparison of different methods of first-trimester screening for preterm pre-eclampsia: cohort study.

OBJECTIVE: To compare the predictive performance of three different mathematical models for first-trimester screening of pre-eclampsia (PE), which combine maternal risk factors with mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI) and serum placental growth factor (PlGF), and two risk-scoring systems. METHODS: This was a prospective cohort study performed in eight fetal medicine units in five different regions of Spain between September 2017 and December 2019. All pregnant women with singleton pregnancy and a non-malformed live fetus attending their routine ultrasound examination at 11 + 0 to 13 + 6 weeks' gestation were invited to participate in the study. Maternal characteristics and medical history were recorded and measurements of MAP, UtA-PI, serum PlGF and pregnancy-associated plasma protein-A (PAPP-A) were converted into multiples of the median (MoM). Risks for term PE, preterm PE (< 37 weeks' gestation) and early PE (< 34 weeks' gestation) were calculated according to the FMF competing-risks model, the Crovetto et al. logistic regression model and the Serra et al. Gaussian model. PE classification was also performed based on the recommendations of the National Institute for Health and Care Excellence (NICE) and the American College of Obstetricians and Gynecologists (ACOG). We estimated detection rates (DR) with their 95% CIs at a fixed 10% screen-positive rate (SPR), as well as the area under the receiver-operating-characteristics curve (AUC) for preterm PE, early PE and all PE for the three mathematical models. For the scoring systems, we calculated DR and SPR. Risk calibration was also assessed. RESULTS: The study population comprised 10 110 singleton pregnancies, including 32 (0.3%) that developed early PE, 72 (0.7%) that developed preterm PE and 230 (2.3%) with any PE. At a fixed 10% SPR, the FMF, Crovetto et al. and Serra et al. models detected 82.7% (95% CI, 69.6-95.8%), 73.8% (95% CI, 58.7-88.9%) and 79.8% (95% CI, 66.1-93.5%) of early PE; 72.7% (95% CI, 62.9-82.6%), 69.2% (95% CI, 58.8-79.6%) and 74.1% (95% CI, 64.2-83.9%) of preterm PE; and 55.1% (95% CI, 48.8-61.4%), 47.1% (95% CI, 40.6-53.5%) and 53.9% (95% CI, 47.4-60.4%) of all PE, respectively. The best correlation between predicted and observed cases was achieved by the FMF model, with an AUC of 0.911 (95% CI, 0.879-0.943), a slope of 0.983 (95% CI, 0.846-1.120) and an intercept of 0.154 (95% CI, -0.091 to 0.397). The NICE criteria identified 46.7% (95% CI, 35.3-58.0%) of preterm PE at 11% SPR and ACOG criteria identified 65.9% (95% CI, 55.4-76.4%) of preterm PE at 33.8% SPR. CONCLUSIONS: The best performance of screening for preterm PE is achieved by mathematical models that combine maternal factors with MAP, UtA-PI and PlGF, as compared to risk-scoring systems such as those of NICE and ACOG. While all three algorithms show similar results in terms of overall prediction, the FMF model showed the best performance at an individual level. © 2024 International Society of Ultrasound in Obstetrics and Gynecology.

Performance of first-trimester combined screening for preterm pre-eclampsia: findings from cohort of 10 110 pregnancies in Spain.

OBJECTIVE: To evaluate the diagnostic accuracy of the Fetal Medicine Foundation (FMF) competing-risks model, incorporating maternal characteristics, mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI) and placental growth factor (PlGF) (the 'triple test'), for the prediction at 11-13 weeks' gestation of preterm pre-eclampsia (PE) in a Spanish population. METHODS: This was a prospective cohort study performed in eight fetal medicine units in five different regions of Spain between September 2017 and December 2019. All pregnant women with a singleton pregnancy and a non-malformed live fetus attending a routine ultrasound examination at 11 + 0 to 13 + 6 weeks' gestation were invited to participate. Maternal demographic characteristics and medical history were recorded and MAP, UtA-PI, serum PlGF and pregnancy-associated plasma protein-A (PAPP-A) were measured following standardized protocols. Treatment with aspirin during pregnancy was also recorded. Raw values of biomarkers were converted into multiples of the median (MoM), and audits were performed periodically to provide regular feedback to operators and laboratories. Patient-specific risks for term and preterm PE were calculated according to the FMF competing-risks model, blinded to pregnancy outcome. The performance of screening for PE, taking into account aspirin use, was assessed by calculating the area under the receiver-operating-characteristics curve (AUC) and detection rate (DR) at a 10% fixed screen-positive rate (SPR). Risk calibration of the model was assessed. RESULTS: The study population comprised 10 110 singleton pregnancies, including 72 (0.7%) that developed preterm PE. In the preterm PE group, compared to those without PE, median MAP MoM and UtA-PI MoM were significantly higher, and median serum PlGF MoM and PAPP-A MoM were significantly lower. In women with PE, the deviation from normal in all biomarkers was inversely related to gestational age at delivery. Screening for preterm PE by a combination of maternal characteristics and medical history with MAP, UtA-PI and PlGF had a DR, at 10% SPR, of 72.7% (95% CI, 62.9-82.6%). An alternative strategy of replacing PlGF with PAPP-A in the triple test was associated with poorer screening performance for preterm PE, giving a DR of 66.5% (95% CI, 55.8-77.2%). The calibration plot showed good agreement between predicted risk and observed incidence of preterm PE, with a slope of 0.983 (95% CI, 0.846-1.120) and an intercept of 0.154 (95% CI, -0.091 to 0.397). CONCLUSIONS: The FMF model is effective in predicting preterm PE in the Spanish population at 11-13 weeks' gestation. This method of screening is feasible to implement in routine clinical practice, but it should be accompanied by a robust audit and monitoring system, in order to maintain high-quality screening. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Non-visualization of choroid plexus of fourth ventricle as first-trimester predictor of posterior fossa anomalies and chromosomal defects.

OBJECTIVE: To assess non-visualization of the choroid plexus of the fourth ventricle (CP-4V) as a simple, qualitative and reproducible first-trimester ultrasound feature of the posterior fossa for the prediction of central nervous system (CNS) anomalies and chromosomal defects. METHODS: First-trimester three-dimensional ultrasound datasets of the fetal brain were obtained prospectively from 65 consecutive normal singletons and retrospectively from 27 fetuses identified as having an abnormal posterior fossa on first-trimester ultrasound examination, and randomly combined to form the final study group. The stored ultrasound volumes were analyzed offline by two accredited sonologists, who were not aware of the final diagnoses. The CP-4V was assessed by multiplanar navigation and classified as visible or non-visible in its normal position depending on whether or not the echogenic structure that separates the fourth ventricle from the cisterna magna was identified in both midsagittal and axial planes. Correlation with subsequent second-trimester ultrasound, fetal magnetic resonance imaging, or postmortem or postnatal findings was performed to determine the predictive value of the first-trimester findings. RESULTS: Among the 92 ultrasound datasets analyzed, 73 (79%) were acquired transabdominally and 19 (21%) transvaginally. The CP-4V was classified as visible in 64 cases and non-visible in 28 cases, with agreement between the two observers in both sagittal and axial planes in all but one case. Twelve of the 28 (43%) fetuses with non-visible CP-4V were subsequently diagnosed as having a CNS malformation (open spina bifida (n = 6), Dandy-Walker malformation (n = 2), Blake's pouch cyst (n = 2), cephalocele (n = 1) and megacisterna magna (n = 1)). In addition, 20 of these 28 (71%) fetuses had aneuploidy (trisomy 18 (n = 10), triploidy (n = 5), trisomy 13 (n = 3), Turner syndrome (n = 1) or trisomy 21 (n = 1)). There was only one false-positive case, in which the CP-4V was classified as absent in a normal fetus. CONCLUSIONS: Non-visualization of the CP-4V in the first trimester appears to be a strong marker of posterior fossa anomalies and chromosomal defects. Qualitative evaluation of this anatomic structure is simple, feasible and reproducible, and its routine assessment during the first-trimester scan may facilitate the early detection of CNS anomalies and associated fetal aneuploidy. Copyright © 2017 ISUOG. Published by John Wiley & Sons Ltd.

First-trimester assessment of nasal bone using retronasal triangle view: a prospective study.

OBJECTIVE: To examine the feasibility and accuracy of fetal nasal bone (NB) assessment in the retronasal triangle (RNT) view for aneuploidy screening in the first trimester of pregnancy. METHODS: Consecutive women with singleton pregnancies undergoing sonographic screening at 11-13 weeks' gestation were prospectively evaluated. In all cases, assessment of the NB by using the RNT view was attempted and classified as present (if one or both of the NBs were clearly seen) or absent/hypoplastic (if the NB was not visualized or if it was small and less echogenic than the surrounding bones). The detection rate of fetal karyotypic abnormalities by the assessment of the NB in the RNT view was calculated. RESULTS: In total, 1977 women were scanned. The RNT was successfully examined in 1970 fetuses (99.6%). Fetal outcome was available in 1767 (89.7%) of evaluated cases, and of these, 39 (2.2%) cases of aneuploidy were documented (trisomy 21, n=17; trisomy 18, n=8; trisomy 13, n=5; Turner syndrome, n=5; and triploidy, n=4). The prevalence of absent/hypoplastic NB was 12/1728 (0.7%) in chromosomally normal fetuses and 12/17 (70.6%) in trisomy 21 fetuses. Sensitivity, specificity and positive and negative predictive values of absent/hypoplastic NB for trisomy 21 were 70.6%, 99.3%, 50.0% and 99.7%, respectively. The positive and negative likelihood ratios of NB assessment were 101 (95% CI, 53-193) and 0.3 (95% CI, 0.14-0.62), respectively. CONCLUSIONS: The RNT view is a useful technique for assessing the NB during the first trimester of pregnancy. With this new approach, performance of absent/hypoplastic NB as a marker of aneuploidy, mainly trisomy 21, appears to be similar to that previously reported by using the mid-sagittal plane.

First-trimester diagnosis of cleft lip and palate using three-dimensional ultrasound.

OBJECTIVE: To determine whether systematic examination of primary and secondary palates using three-dimensional (3D) ultrasound aids in the identification of orofacial clefts in the first trimester. METHODS: 3D datasets were acquired prospectively from women undergoing first-trimester ultrasound screening for aneuploidy. Multiplanar mode display was used for offline analysis of (1) the primary palate in the coronal plane at the base of the retronasal triangle and (2) the secondary palate by virtual navigation in the axial plane. In addition, 3D datasets from three fetuses with a cleft palate diagnosed in the first trimester were retrospectively identified and included randomly in the study group. RESULTS: A total of 240 3D datasets from 237 pregnancies (including three sets of twins), 89% of which were obtained transabdominally and 11% transvaginally, were examined independently by three operators. The quality of the 3D datasets was classified subjectively as good, fair and poor in 76%, 20% and 4% of cases, respectively. Seven fetuses had an orofacial cleft; all involved both the primary palate and the secondary palate. Using 3D offline analysis, the primary palate was classified as intact in 229 (95%), cleft in nine (4%) and indeterminate in two (1%). Seven of the nine fetuses suspected to have a cleft affecting the primary palate had the cleft confirmed at birth or at postmortem examination (false-positive rate 0.9% (2/231)). The secondary palate was classified as intact in 217 (90%), cleft in six (3%) and indeterminate in 17 (7%). Clefts of the secondary palate were confirmed in all six suspected cases and missed in one, which was diagnosed at 16 weeks. The visualization rate was affected by the quality of the 3D dataset (P < 0.001) and gestational age at evaluation (P < 0.01). CONCLUSION: In our series, all cases of clefting of the primary palate and 86% of cases involving the secondary palate were visualized using 3D ultrasound with a satisfactory false-positive rate. Virtual navigation of the fetal palate using the multiplanar mode display seems to be useful in the diagnosis of clefting in the first trimester.

Three-dimensional ultrasound diagnosis of cleft palate: 'reverse face', 'flipped face' or 'oblique face'--which method is best?

OBJECTIVES: To compare the performance of three sonographic techniques, the 'reverse-face', 'flipped-face' and 'oblique-face' methods, for visualizing the hard and soft palate in diagnosing cleft lip and palate (CLP). METHODS: A total of 60 fetuses (10 with CLP) with a gestational age ranging from 20 to 33 weeks were examined. We compared visualization of the secondary palate with the previously described reverse-face and flipped-face methods (the latter modified by us) and the oblique-face method developed by us using Oblique View imaging technology. RESULTS: Among the 10 fetuses with CLP the defect involved the lip, alveolus and secondary palate in seven, and the primary palate only in the remaining three. The upper lip and alveolar ridge were well visualized in all cases with all three methods. Involvement of the hard palate was diagnosed correctly in 71% (5/7) of the cases using the reverse-face view, in 86% (6/7) with the flipped-face view, and in 100% (7/7) with the oblique-face view; the hard palate was correctly found to be intact in 78%, 84% and 86%, respectively, of the 50 normal fetuses examined with each view. Involvement of the soft palate was diagnosed correctly in only one of the seven fetuses with defects of the secondary palate in flipped-face and oblique-face views, and was correctly considered intact in only 16% of normal fetuses in flipped-face view and in 26% in oblique-face images. CONCLUSIONS: Accurate visualization of the soft palate requires an excellent initially acquired volume, fluid between the fetal tongue and palate, and curving of the plane to follow the structure of the palate. The oblique-face or flipped-face views make it possible to visualize the soft palate well in selected cases.

Is Rotavirus contributing to an increase of diarrhoea in a region of Spain?

Diarrhoeal illnesses are the most frequent of notifiable diseases in Aragon. Physicians notify diarrhoea cases with presumed infectious origin on a weekly basis. Following an increase in 2005-2006, we aimed to identify the responsible organism(s) in order to inform control measures. We described seasonality of diarrhoea notifications for 1998-2004 and 2005-2006. We calculated correlations between diarrhoea notifications and enteric pathogens diagnosed in two Aragonese laboratories, and applied linear regression using coefficients of determination (r2). In 2005-2006 the winter peak of diarrhoea notifications increased from 2494 to 3357 weekly cases (34.6%) and the peak in Rotavirus diagnoses from 15 to 39 weekly cases. The correlation of diarrhoea notifications with Rotavirus was 0.05 in 1998-2004 and 0.42 in 2005-2006. The model for 1998-2004 included Salmonella enterica, Giardia lamblia and Clostridium difficile (r2=0.08) and for 2005-2006 Rotavirus and Astrovirus (r2=0.24). Our results suggest that Rotavirus contributed to the increase of diarrhoea notifications. We recommend determining the disease burden of Rotavirus in order to guide vaccination policies.

Translucencia nucal aumentada y cariotipo normal / Increased nuchal translucency and normal kariotype

Antecedentes: La exploración ecográfica entre las semanas 11 y 14 tiene un papel fundamental en el cribado de anomalías cromosómicas, siendo la medida de la translucencia nucal un método bien establecido y ampliamente aceptado para este fin. Objetivo: Evaluar retrospectivamente la evolución de los fetos con translucencia nucal aumentada y cariotipo normal. Método: Se recogieron los datos de 104 fetos con TN >percentil 95 (p95) entre las semanas 11 y 14, evaluados en nuestro centro. En los 61 que resultaron eu-ploides, se estudió la incidencia de anomalías estructurales diagnosticadas tanto prenatalmente como tras el nacimiento, así como las pérdidas fetales anteparto. De estos fetos, nacieron sanos el 80 por ciento cuando la TN estaba entre p95 y 3,4 mm, el 50 por ciento con TN entre 3,5 y 4,4 mm, el 30 por ciento con TN entre 4,5 y 5,4 mm, y el 18 por ciento con TN > 5,5 mm. Entre los 4 recién nacidos euploides con patología, hubo 3 con cardiopatía. Conclusión: La presencia de TN aumentada entre las 11 -14 semanas en fetos euploides se asocia a un incremento del riesgo de anomalías estructurales mayores, principalmente cardiacas. La prevalencia de malformaciones aumenta significativamente con TN >3,5 mm, y el pronóstico gestacional adverso empeora conforme aumenta la medida de la TN.

Background: Ultrasound scan has a main role at the 11-14 weeks screening for chromosomal abnormalities. The measurement of nuchal translucency (NT) thickness is a widespread stablished method to achieve this target. Objective: To assess retrospectively the outcome of fetuses with increased nuchal translucency and normal karyotype. Method: Data were collected from 104 fetuses with NT > 95th percentile at 11 to 14 weeks of gestation, followed in our institution. The sixty one euploid fetuses were studied in order to determine the incidence of structural abnormalities, diagnosed either before or after delivery, as well as antenatal fetal loss. Among these fetuses, there were no malformations at birth in 80 percent for NT between the 95th percentile and 3.4 mm; 50 percent for NT between 3.5 and 4.4 mm; 30 percent for NT of 4.5-5.4 mm; and 18 percent for NT > 5.5 mm. There were 4 euploid newborns with some kind of structural defect at birth, 3 of them presented a cardiac malformation. Conclusion: The presence of increased NT at 11-14 weeks scan in euploid fetuses it's associated with a higher risk of major structural abnormalities, mainly cardiac ones. The prevalence of malformations is significantly increased for NT > 3.5 mm, and the adverse perinatal outcome is directly associated with the thickness of NT.

Gestación multifetal yatrogénica / Iatrogenic multifetal pregnancy

Los embarazos múltiples ocurren de forma espontánea, en una de cada 90 gestaciones en el caso de las gemelares, y en una de cada 8.100 en las triples. Sin embargo, desde el desarrollo de las unidades de reproducción humana se ha identificado un incremento del 52% de gestaciones gemelares y del 404% en las de mayor orden. Ante la elevada morbimortalidad perinatal y materna de estos embarazos y con el fin de incrementar las posibilidades de supervivencia de los fetos resultantes y minimizar la morbilidad a largo plazo en los recién nacidos, surge la embriorreducción selectiva. A pesar de ser una técnica rentable, puede implicar compromisos éticos y es un procedimiento no exento de riesgos. Por todo esto, consideramos que la actitud más eficaz ante las gestaciones múltiples es su prevención primaria (AU)

Multiple pregnancies spontaneously occur in one out of 90 pregnancies for twins and in one out of 8,100 for triplets. However, since the introduction of human reproduction units, there has been a 52% increase in twins, and a 404% increase in high-order pregnancies. Given the high perinatal and maternal morbidity and mortality in these pregnancies, selective embryo reduction was developed to increase fetal survival and reduce long-term morbidity in neonates. Although effective, this procedure represents a technical and ethical challenge for the practitioner. Consequently, we believe that the most effective approach to multifetal pregnancies is primary prevention (AU)