Using simple clinical and ultrasound variables to develop a model to predict first trimester pregnancy viability.

INTRODUCTION: Early prediction of pregnancies destined to miscarry will allow couples to prepare for this common but often unexpected eventuality, and clinicians to allocate finite resources. We aimed to develop a prediction model combining clinical, demographic, and sonographic data as a clinical tool to aid counselling about first trimester pregnancy outcome. MATERIAL AND METHODS: This is a prospective, observational cohort study conducted at Queen Charlotte's and Chelsea Hospital, UK from March 2014 to May 2019. Women with confirmed intrauterine pregnancies between 5 weeks and their dating scan (11-14 weeks) were recruited. Participants attended serial ultrasound scans in the first trimester and at each visit recorded symptoms of vaginal bleeding, pelvic pain, nausea and vomiting using validated scoring tools. Pregnancies were followed up until the dating scan (11-14 weeks). Univariate and multivariate analyses were performed to predict first trimester viability. A model was developed with multivariable logistic regression, variables limited by feature selection, and bootstrapping with multiple imputation was used for internal validation. RESULTS: 1403 women were recruited and after exclusions, data were available for 1105. 160 women (14.5 %) experienced first trimester miscarriage and 945 women (85.5 %) had viable pregnancies at 11-14 weeks' gestation. The average gestational age at the initial visit (calculated from the menstrual dates) was 7 + 1 weeks (+/-12.2 days). A multivariable logistic regression model was developed to predict first trimester viability and included the variables: mean gestational sac diameter, presence of fetal heart pulsations, difference in gestational age from last menstrual period and from mean sac diameter on ultrasonography, current folic acid usage and maternal age. The model demonstrated good performance (optimism-corrected area under curve (AUC) 0.84, 95 % CI 0.81-0.87; optimism-corrected calibration slope 0.969). CONCLUSION: We have developed and internally validated a model to predict first trimester viability with good accuracy prior to the 11-14 week dating scan, which now needs to be externally validated prior to clinical use.

Gradient boosted trees with individual explanations: An alternative to logistic regression for viability prediction in the first trimester of pregnancy.

BACKGROUND: Clinical models to predict first trimester viability are traditionally based on multivariable logistic regression (LR) which is not directly interpretable for non-statistical experts like physicians. Furthermore, LR requires complete datasets and pre-established variables specifications. In this study, we leveraged the internal non-linearity, feature selection and missing values handling mechanisms of machine learning algorithms, along with a post-hoc interpretability strategy, as potential advantages over LR for clinical modeling. METHODS: The dataset included 1154 patients with 2377 individual scans and was obtained from a prospective observational cohort study conducted at a hospital in London, UK, from March 2014 to May 2019. The data were split into a training (70%) and a test set (30%). Parsimonious and complete multivariable models were developed from two algorithms to predict first trimester viability at 11-14 weeks gestational age (GA): LR and light gradient boosted machine (LGBM). Missing values were handled by multiple imputation where appropriate. The SHapley Additive exPlanations (SHAP) framework was applied to derive individual explanations of the models. RESULTS: The parsimonious LGBM model had similar discriminative and calibration performance as the parsimonious LR (AUC 0.885 vs 0.860; calibration slope: 1.19 vs 1.18). The complete models did not outperform the parsimonious models. LGBM was robust to the presence of missing values and did not require multiple imputation unlike LR. Decision path plots and feature importance analysis revealed different algorithm behaviors despite similar predictive performance. The main driving variable from the LR model was the pre-specified interaction between fetal heart presence and mean sac diameter. The crown-rump length variable and a proxy variable reflecting the difference in GA between expected and observed GA were the two most important variables of LGBM. Finally, while variable interactions must be specified upfront with LR, several interactions were ranked by the SHAP framework among the most important features learned automatically by the LGBM algorithm. CONCLUSIONS: Gradient boosted algorithms performed similarly to carefully crafted LR models in terms of discrimination and calibration for first trimester viability prediction. By handling multi-collinearity, missing values, feature selection and variable interactions internally, the gradient boosted trees algorithm, combined with SHAP, offers a serious alternative to traditional LR models.

Risk of Adverse Obstetric and Neonatal Outcomes by Maternal Age: Quantifying Individual and Population Level Risk Using Routine UK Maternity Data.

OBJECTIVE: The objective of this study was to investigate whether moderately increased maternal age is associated with obstetric and neonatal outcome in a contemporary population, and to consider the possible role of co-morbidities in explaining any increased risk. STUDY DESIGN: Secondary analysis of routinely collected data from a large maternity unit in London, UK. Data were available on 51,225 singleton deliveries (≥22 weeks) occurring to women aged ≥20 between 2004 and 2012. Modified Poisson regression was used to estimate risk ratios for the association between maternal age and obstetric and neonatal outcome (delivery type, postpartum haemorrhage, stillbirth, low birthweight, preterm birth, small for gestational age, neonatal unit admission), using the reference group 20-24 years. Population attributable fractions were calculated to quantify the population impact. RESULTS: We found an association between increasing maternal age and major postpartum haemorrhage (≥1000ml blood loss) (RR 1.36 95% CI 1.18-1.57 for age 25-29 rising to 2.41 95% CI 2.02-2.88 for age ≥40). Similar trends were observed for caesarean delivery, most notably for elective caesareans (RR 1.64 95% CI 1.36-1.96 for age 25-29 rising to 4.94 95% CI 4.09-5.96 for age ≥40). There was evidence that parity modified this association, with a higher prevalence of elective caesarean delivery in older nulliparous women. Women aged ≥35 were at increased risk of low birthweight and preterm birth. We found no evidence that the risk of stillbirth, small for gestational age, or neonatal unit admission differed by maternal age. CONCLUSIONS: Our results suggest a gradual increase in the risk of caesarean delivery and postpartum haemorrhage from age 25, persisting after taking into account maternal BMI, hypertension and diabetes. The risk of low birthweight and preterm birth was elevated in women over 35. Further research is needed to understand the reasons behind the high prevalence of elective caesarean delivery in nulliparous older mothers.