Mikko Sairanen

Performance of a third trimester combined screening model for the prediction of adverse perinatal outcome

To explore the potential value of third‐trimester combined screening for the prediction of adverse perinatal outcome (APO) in the general population and among small‐for‐gestational‐age (SGA) fetuses.

Fetal nuchal translucency in severe congenital heart defects: experiences in Northern Finland

Abstract Objective: To evaluate the performance of first-trimester measurement of fetal nuchal translucency (NT) in the detection of severe congenital heart defects (CHDs). Methods: During the study period of 1 January 2008 – 31 December 2011, NT was measured in 31,144 women as a part of voluntary first-trimester screening program for Down’s syndrome in Northern Finland. NT was measured by personnel trained on the job by the experienced staff. No certification or annual audits are required in Finland. However, the recommendation is that the examiner should perform 200 scans on average per year. Severe CHD was classified as a defect requiring surgery in the first year of life or a defect that led to the termination of the pregnancy. All severe CHDs diagnosed during the study period in Northern Finland could not be included in this study since all women did not participate in the first-trimester screening and some cases were missing important data. Results: Fourteen (17.7%) out of 79 severe CHDs were found with NT cutoff of 3.5 mm. Amongst the 79 severe CHD cases, there were 17 chromosomal abnormalities. With NT cutoffs of 2.0 and 1.5 mm the detection rates would have increased to 25.3% (n = 20) and 46.8% (n = 37). Using a randomly selected control group of 762 women with normal pregnancy outcomes, false positive rates (FPRs) were calculated. For NT cutoffs of 1.5, 2.0 and 3.5 mm, the FPRs were, 18.5, 3.3 and 0.4%, respectively. Conclusions: A greater than 3.5 mm NT measurement in the first-trimester ultrasound is an indication to suspect a fetal heart defect but its sensitivity to detect severe CHD is poor. In our study, only 17.7% of severe CHDs would have been detected with an NT cutoff of 3.5 mm.

A first trimester prediction model for gestational diabetes utilizing aneuploidy and pre-eclampsia screening markers

Abstract Objective: We examined whether first trimester aneuploidy and pre-eclampsia screening markers predict gestational diabetes mellitus (GDM) in a large multi-ethnic cohort and the influence of local population characteristics on markers. Methods: Clinical and first trimester markers (mean arterial pressure (MAP), uterine artery pulsatility index (UtA PI), pregnancy associated plasma protein A (PAPP-A), free-β human chorionic gonadotropin (free-hCGβ)) were measured in a case-control study of 980 women (248 with GDM, 732 controls) at 11 to 13 + 6 weeks’ gestation. Clinical parameters, MAP-, UtA PI-, PAPP-A-, and free-hCGβ-multiples-of-the-median (MoM) were compared between GDM and controls; stratified by ethnicity, parity, and GDM diagnosis <24 versus ≥24 weeks’ gestation. GDM model screening performance was evaluated using AUROC. Results: PAPP-A- and UtA PI-MoM were significantly lower in GDM versus controls (median ((IQR) PAPP-A-MoM 0.81 (0.58–1.20) versus 1.00 (0.70–1.46); UtA PI-MoM 1.01 (0.82–1.21) versus 1.05 (0.84–1.29); p < .05). Previous GDM, family history of diabetes, south/east Asian ethnicity, parity, BMI, MAP, UtA PI, and PAPP-A were significant predictors in multivariate analysis (p < .05). The AUC for a model based on clinical parameters was 0.88 (95%CI 0.85–0.92), increasing to 0.90 (95%CI 0.87–0.92) with first trimester markers combined. The combined model best predicted GDM <24 weeks’ gestation (AUC 0.96 (95%CI 0.94–0.98)). Conclusions: Addition of aneuploidy and pre-eclampsia markers is cost-effective and enhances early GDM detection, accurately identifying early GDM, a high-risk cohort requiring early detection, and intervention. Ethnicity and parity modified marker association with GDM, suggesting differences in pathophysiology and vascular risk.

First trimester combined screening biochemistry in detection of congenital heart defects

Abstract Objective: To evaluate the performance of first trimester biochemical markers, pregnancy-associated plasma protein-A (PAPP-A), free beta human chorionic gonadotropin (fβ-hCG), and nuchal translucency (NT) in detection of severe congenital heart defects (CHDs). Methods: During the study period from 1 January 2008 to 31 December 2011, biochemical markers and NT were measured in 31,144 women as part of voluntary first trimester screening program for Down’s syndrome in Northern Finland. Data for 71 severe CHD cases and 762 controls were obtained from the hospital records and from the National Medical Birth Register, which records the birth of all liveborn and stillborn infants, and from the National Register of Congenital Malformations that receives information about all the CHD cases diagnosed in Finland. Results: Both PAPP-A and fβ-hCG multiple of median (MoM) values were decreased in all severe CHDs: 0.71 and 0.69 in ventricular septal defects (VSDs), 0.58 and 0.88 in tetralogy of Fallot cases (TOFs), 0.82 and 0.89 in hypoplastic left heart syndromes (HLHSs), and 0.88 and 0.96 in multiple defects, respectively. NT was increased in all study groups except of VSD group. ROC AUC was 0.72 for VSD when combining prior risk with PAPP-A and fβ-hCG. Adding NT did not improve the detection rate. With normal NT but decreased (<0.5 MoM) PAPP-A and fβ-hCG odds ratios for VSD and HLHS were 19.5 and 25.6, respectively. Conclusions: Maternal serum biochemistry improves the detection of CHDs compared to NT measurement only. In cases with normal NT measurement but low concentrations of both PAPP-A and fβ-hCG, an alert for possible CHD, especially VSD, could be given with thorough examination of fetal heart in later ultrasound scans.

Evaluation of machine learning algorithms for improved risk assessment for Down's syndrome

Prenatal screening generates a great amount of data that is used for predicting risk of various disorders. Prenatal risk assessment is based on multiple clinical variables and overall performance is defined by how well the risk algorithm is optimized for the population in question. This article evaluates machine learning algorithms to improve performance of first trimester screening of Down syndrome. Machine learning algorithms pose an adaptive alternative to develop better risk assessment models using the existing clinical variables. Two real-world data sets were used to experiment with multiple classification algorithms. Implemented models were tested with a third, real-world, data set and performance was compared to a predicate method, a commercial risk assessment software. Best performing deep neural network model gave an area under the curve of 0.96 and detection rate of 78% with 1% false positive rate with the test data. Support vector machine model gave area under the curve of 0.95 and detection rate of 61% with 1% false positive rate with the same test data. When compared with the predicate method, the best support vector machine model was slightly inferior, but an optimized deep neural network model was able to give higher detection rates with same false positive rate or similar detection rate but with markedly lower false positive rate. This finding could further improve the first trimester screening for Down syndrome, by using existing clinical variables and a large training data derived from a specific population.

Prediction of fetal growth restriction using estimated fetal weight vs a combined screening model in the third trimester

To compare the performance of third‐trimester screening, based on estimated fetal weight centile (EFWc) vs a combined model including maternal baseline characteristics, fetoplacental ultrasound and maternal biochemical markers, for the prediction of small‐for‐gestational‐age (SGA) neonates and late‐onset fetal growth restriction (FGR).

A Novel Early Pregnancy Risk Prediction Model for Gestational Diabetes Mellitus

Introduction: Accurate early risk prediction for gestational diabetes mellitus (GDM) would target intervention and prevention in women at the highest risk. We evaluated novel biomarker predictors to develop a first-trimester risk prediction model in a large multiethnic cohort. Methods: Maternal clinical, aneuploidy and pre-eclampsia screening markers (PAPP-A, free hCGβ, mean arterial pressure, uterine artery pulsatility index) were measured prospectively at 11–13+6 weeks’ gestation in 980 women (248 with GDM; 732 controls). Nonfasting glucose, lipids, adiponectin, leptin, lipocalin-2, and plasminogen activator inhibitor-2 were measured on banked serum. The relationship between marker multiples-of-the-median and GDM was examined with multivariate regression. Model predictive performance for early (< 24 weeks’ gestation) and overall GDM diagnosis was evaluated by receiver operating characteristic curves. Results: Glucose, triglycerides, leptin, and lipocalin-2 were higher, while adiponectin was lower, in GDM (p < 0.05). Lipocalin-2 performed best in Caucasians, and triglycerides in South Asians with GDM. Family history of diabetes, previous GDM, South/East Asian ethnicity, parity, BMI, PAPP-A, triglycerides, and lipocalin-2 were significant independent GDM predictors (all p < 0.01), achieving an area under the curve of 0.91 (95% confidence interval [CI] 0.89–0.94) overall, and 0.93 (95% CI 0.89–0.96) for early GDM, in a combined multivariate prediction model. Conclusions: A first-trimester risk prediction model, which incorporates novel maternal lipid markers, accurately identifies women at high risk of GDM, including early GDM.

Performance of first trimester biochemical markers and mean arterial pressure in prediction of early-onset pre-eclampsia

OBJECTIVE To develop a predictive risk model for early-onset pre-eclampsia (EO-PE) using maternal characteristics, combined screening markers, previously reported biomarkers for PE and mean arterial pressure (MAP). METHODS This retrospective study was conducted at Oulu University hospital between 2006 and 2010. Maternal serum from first trimester combined screening was further analyzed for alpha fetoprotein (AFP), placental growth factor (PlGF), soluble tumor necrosis factor receptor-1 (sTNFR1), retinol binding protein-4 (RBP4), a disintegrin and metalloprotease-12 (ADAM12), soluble P-selectin (sP-selectin), follistatin like-3 (FSTL3), adiponectin, angiopoietin-2 (Ang-2) and sex hormone binding globulin (SHBG). First, the training sample set with 29 cases of EO-PE and 652 controls was developed to study whether these biomarkers separately or in combination with prior risk (maternal characteristics, first trimester pregnancy associated plasma protein-A (PAPP-A) and free beta human chorionic gonadotrophin (fβ-hCG)) could be used to predict the development of EO-PE. Second, the developed risk models were validated with a test sample set of 42 EO-PE and 141 control subjects. For the test set MAP data was also available. RESULTS Single marker statistically significant (ANOVA p<0.05) changes between control and EO-PE pregnancies were observed with AFP, RBP4 and sTNFR1 with both training and test sample sets. Based on the test sample set performances, the best detection rate, 47% for a 10% false positive rate, was achieved with PlGF and sTNFR1 added with prior risk and MAP. CONCLUSION Based on our results, the best first trimester biomarkers to predict the subsequent EO-PE were AFP, PlGF, RBP4 and sTNFR1. The risk models that performed best for the prediction of EO-PE included prior risk, MAP, sTNFR1 and AFP or PlGF or RBP4.