IntroductionThere was limited evidence on the quality of reporting and methodological quality of prediction models using machine learning methods in preterm birth. This systematic review aimed to assess the reporting quality and risk of bias of a machine learning-based prediction model in preterm birth. Material and methodsWe conducted a systematic review, searching the PubMed, Embase, the Cochrane Library, China National Knowledge Infrastructure, China Biology Medicine disk, VIP Database, and WanFang Data from inception to September 27, 2021. Studies that developed (validated) a prediction model using machine learning methods in preterm birth were included. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement and Prediction model Risk of Bias Assessment Tool (PROBAST) to evaluate the reporting quality and the risk of bias of included studies, respectively. Findings were summarized using descriptive statistics and visual plots. The protocol was registered in PROSPERO (no. CRD 42022301623). ResultsTwenty-nine studies met the inclusion criteria, with 24 development-only studies and 5 development-with-validation studies. Overall, TRIPOD adherence per study ranged from 17% to 79%, with a median adherence of 49%. The reporting of title, abstract, blinding of predictors, sample size justification, explanation of model, and model performance were mostly poor, with TRIPOD adherence ranging from 4% to 17%. For all included studies, 79% had a high overall risk of bias, and 21% had an unclear overall risk of bias. The analysis domain was most commonly rated as high risk of bias in included studies, mainly as a result of small effective sample size, selection of predictors based on univariable analysis, and lack of calibration evaluation. ConclusionsReporting and methodological quality of machine learning-based prediction models in preterm birth were poor. It is urgent to improve the design, conduct, and reporting of such studies to boost the application of machine learning-based prediction models in preterm birth in clinical practice.

BACKGROUND: Preterm birth (PTB) is the leading cause of perinatal morbidity and mortality. Women with previous prenatal loss are at higher risk of preterm birth. A specialist antenatal clinic is considered as one approach to improve maternity and pregnancy outcomes. METHODS: A systematic review of quantitative, qualitative and mixed method studies conducted on women at high risk of preterm birth (PTB). The review primary outcomes were to report on the specialist antenatal clinics effect in preventing or reducing preterm birth, perinatal mortality and morbidity and women's perceptions and experiences of a specialist clinic whether compared or not compared with standard antenatal care. Other secondary maternal, infant and economic outcomes were also determined. A comprehensive search strategy was carried out in English within electronic databases as far back as 1980. The reviewers selected studies, assessed the quality, and extracted data independently. Results were summarized and tabulated. RESULTS: Eleven studies fully met the review inclusion criteria, ten were quantitative design studies and only one was a qualitative design study. No mixed method design study was included in the review. All were published after 1989, seven were conducted in the USA and four in the UK. Results from five good to low quality randomised controlled trials (RCTs), all conducted before 1990, did not illustrate the efficacy of the clinic in reducing preterm birth. Whereas results from more recent low quality cohort studies showed some positive neonatal outcomes. Themes from one good quality qualitative study reflected on the emotional and psychological need to reduce anxiety and stress of women referred to such a clinic. Women expressed their negative emotional responses at being labelled as high risk and positive responses to being assessed and treated in the clinic. Women also reported that their partners were struggling to cope emotionally. CONCLUSIONS: Findings from this review were mixed. Evidence from cohort studies indicated a specialist clinic may be a means of predicting or preventing preterm birth. Testing this in a randomised controlled trial is desirable, though may be hard to achieve due to the growing focus of such clinics on managing women at high risk of preterm birth. Ongoing research has to recognize women's experiences and perceptions of such a clinic. Further clarification of the optimal referral route and a clear and standardized management and cost economic evaluation plan are also required. Fathers support and experience of PTB clinics should also be included in further research.

OBJECTIVE: The aim of this study was to evaluate the incidence of cervical lacerations with cerclage removal planned before labor compared to after the onset of labor by a systematic review of published studies. STUDY DESIGN: Searches were performed in electronic databases from inception of each database to November 2014. We identified all studies reporting the rate of cervical lacerations and the timing of cerclage removal (either before or after the onset of labor). The primary outcome was the incidence of spontaneous and clinically significant intrapartum cervical lacerations (i.e. lacerations requiring suturing). RESULTS: Six studies, which met the inclusion criteria, were included in the analysis. The overall incidence of cervical lacerations was 8.9% (32/359). There were 23/280 (6.4%) cervical lacerations in the planned removal group, and 9/79 (11.4%) in the removal after labor group (odds ratio 0.70, 95% confidence interval 0.31-1.57). CONCLUSIONS: In summary, planned removal of cerclage before labor was not shown to be associated with statistically significant reduction in the incidence of cervical lacerations. However, since that our data probably did not reach statistical significance because of a type II error, further studies are needed