Prediction of successful expectant management of first trimester miscarriage: development and validation of a new mathematical model

A simple scoring system for the prediction of early pregnancy loss developed by following 13,977 infertile patients after in vitro fertilization

A retrospective study was conducted to investigate a convenient simple scoring system for the prediction of early pregnancy loss (EPL) based on simple demographics. A total of 13,977 women undergoing transvaginal ultrasound scans on Days 27-29 after in vitro fertilization-embryo transfer (IVF-ET) from June 2016 and December 2017 were included. The first trimester pregnancy outcome was recorded at 12 weeks of gestation. The areas under the curve of this scoring system were 0.884 (95% confidence interval (CI) 0.870-0.899) and 0.890 (95% CI 0.878-0.903) in the training set and test set, respectively. The score totals ranged from -8 to 14 points. A score of 5 points, which offered the highest predictive accuracy (94.01%) and corresponded to a 30% miscarriage risk, was chosen as the cutoff value, with a sensitivity of 62.84%, specificity of 98.79%, positive predictive value (PPV) of 88.87% and negative predictive value (NPV) of 94.54% for the prediction of EPL in the training set. In the test set, a score of 5 points had a sensitivity of 64.69%, specificity of 98.78%, PPV of 89.87% and NPV of 93.62%, and 93.91% of the cases were correctly predicted. Therefore, the simple scoring system using conventionally collected data can be conveniently used to predict EPL after ET. However, considering the limitations, its predictive value needs to be further verified in future clinical practice.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

Background

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

Objective

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making.

Methods

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ² and I².

Results

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I²=86%; τ²=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I²=75%; τ²=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I²=75%; τ²=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I²=83%; τ²=0.07).

Conclusions

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

Trial Registration

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106

Predictors of complete miscarriage after expectant management or misoprostol treatment of non-viable early pregnancy in women with vaginal bleeding

Purpose

To identify predictors of complete miscarriage after expectant management or misoprostol treatment of non-viable early pregnancy in women with vaginal bleeding.

Methods

This was a planned secondary analysis of data from a published randomized controlled trial comparing expectant management with vaginal single dose of 800 µg misoprostol treatment of women with embryonic or anembryonic miscarriage. Predefined variables—serum-progesterone, serum-β-human chorionic gonadotropin, parity, previous vaginal deliveries, gestational age, clinical symptoms (bleeding and pain), mean diameter and shape of the gestational sac, crown-rump-length, type of miscarriage, and presence of blood flow in the intervillous space—were tested as predictors of treatment success (no gestational sac in the uterine cavity and maximum anterior–posterior intracavitary diameter was ≤ 15 mm as measured with transvaginal ultrasound on a sagittal view) in univariable and multivariable logistic regression.

Results

Variables from 174 women (83 expectant management versus 91 misoprostol) were analyzed for prediction of complete miscarriage at ≤ 17 days. In patients managed expectantly, the rate of complete miscarriage was 62.7% (32/51) in embryonic miscarriages versus 37.5% (12/32) in anembryonic miscarriages (P = 0.02). In multivariable logistic regression, the likelihood of success increased with increasing gestational age, increasing crown-rump-length and decreasing gestational sac diameter. Misoprostol treatment was successful in 80.0% (73/91). No variable predicted success of misoprostol treatment.

Conclusions

Complete miscarriage after expectant management is significantly more likely in embryonic miscarriage than in anembryonic miscarriage. Gestational age, crown-rump-length, and gestational sac diameter are independent predictors of success of expectant management. Predictors of treatment success may help counselling women with early miscarriage.

Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration

The TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) Statement includes a 22-item checklist, which aims to improve the reporting of studies developing, validating, or updating a prediction model, whether for diagnostic or prognostic purposes. The TRIPOD Statement aims to improve the transparency of the reporting of a prediction model study regardless of the study methods used. This explanation and elaboration document describes the rationale; clarifies the meaning of each item; and discusses why transparent reporting is important, with a view to assessing risk of bias and clinical usefulness of the prediction model. Each checklist item of the TRIPOD Statement is explained in detail and accompanied by published examples of good reporting. The document also provides a valuable reference of issues to consider when designing, conducting, and analyzing prediction model studies. To aid the editorial process and help peer reviewers and, ultimately, readers and systematic reviewers of prediction model studies, it is recommended that authors include a completed checklist in their submission. The TRIPOD checklist can also be downloaded from www.tripod-statement.org.