Diagnostic utility of clinicodemographic, biochemical and metabolite variables to identify viable pregnancies in a symptomatic cohort during early gestation.

A significant number of pregnancies are lost in the first trimester and 1-2% are ectopic pregnancies (EPs). Early pregnancy loss in general can cause significant morbidity with bleeding or infection, while EPs are the leading cause of maternal mortality in the first trimester. Symptoms of pregnancy loss and EP are very similar (including pain and bleeding); however, these symptoms are also common in live normally sited pregnancies (LNSP). To date, no biomarkers have been identified to differentiate LNSP from pregnancies that will not progress beyond early gestation (non-viable or EPs), defined together as combined adverse outcomes (CAO). In this study, we present a novel machine learning pipeline to create prediction models that identify a composite biomarker to differentiate LNSP from CAO in symptomatic women. This prospective cohort study included 370 participants. A single blood sample was prospectively collected from participants on first emergency presentation prior to final clinical diagnosis of pregnancy outcome: LNSP, miscarriage, pregnancy of unknown location (PUL) or tubal EP (tEP). Miscarriage, PUL and tEP were grouped together into a CAO group. Human chorionic gonadotrophin ß (ß-hCG) and progesterone concentrations were measured in plasma. Serum samples were subjected to untargeted metabolomic profiling. The cohort was randomly split into train and validation data sets, with the train data set subjected to variable selection. Nine metabolite signals were identified as key discriminators of LNSP versus CAO. Random forest models were constructed using stable metabolite signals alone, or in combination with plasma hormone concentrations and demographic data. When comparing LNSP with CAO, a model with stable metabolite signals only demonstrated a modest predictive accuracy (0.68), which was comparable to a model of ß-hCG and progesterone (0.71). The best model for LNSP prediction comprised stable metabolite signals and hormone concentrations (accuracy = 0.79). In conclusion, serum metabolite levels and biochemical markers from a single blood sample possess modest predictive utility in differentiating LNSP from CAO pregnancies upon first presentation, which is improved by variable selection and combination using machine learning. A diagnostic test to confirm LNSP and thus exclude pregnancies affecting maternal morbidity and potentially life-threatening outcomes would be invaluable in emergency situations.

Predictors of poor perinatal outcome following maternal perception of reduced fetal movements--a prospective cohort study.

BACKGROUND: Maternal perception of reduced fetal movement (RFM) is associated with increased risk of stillbirth and fetal growth restriction (FGR). RFM is thought to represent fetal compensation to conserve energy due to insufficient oxygen and nutrient transfer resulting from placental insufficiency. OBJECTIVE: To identify predictors of poor perinatal outcome after maternal perception of reduced fetal movements (RFM). DESIGN: Prospective cohort study. METHODS: 305 women presenting with RFM after 28 weeks of gestation were recruited. Demographic factors and clinical history were recorded and ultrasound performed to assess fetal biometry, liquor volume and umbilical artery Doppler. A maternal serum sample was obtained for measurement of placentally-derived or modified proteins including: alpha fetoprotein (AFP), human chorionic gonadotrophin (hCG), human placental lactogen (hPL), ischaemia-modified albumin (IMA), pregnancy associated plasma protein A (PAPP-A) and progesterone. Factors related to poor perinatal outcome were determined by logistic regression. RESULTS: 22.1% of pregnancies ended in a poor perinatal outcome after RFM. The most common complication was small-for-gestational age infants. Pregnancy outcome after maternal perception of RFM was related to amount of fetal activity while being monitored, abnormal fetal heart rate trace, diastolic blood pressure, estimated fetal weight, liquor volume, serum hCG and hPL. Following multiple logistic regression abnormal fetal heart rate trace (Odds ratio 7.08, 95% Confidence Interval 1.31-38.18), (OR) diastolic blood pressure (OR 1.04 (95% CI 1.01-1.09), estimated fetal weight centile (OR 0.95, 95% CI 0.94-0.97) and log maternal serum hPL (OR 0.13, 95% CI 0.02-0.99) were independently related to pregnancy outcome. hPL was related to placental mass. CONCLUSION: Poor perinatal outcome after maternal perception of RFM is closely related to factors which are connected to placental dysfunction. Novel tests of placental function and associated fetal response may provide improved means to detect fetuses at greatest risk of poor perinatal outcome after RFM.