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.

Sugar-sweetened beverages (SSBs), artificially sweetened beverages (ASBs), and 100% fruit juices are frequently consumed and have been documented that they could lead to serious disease burden. However, inconsistent evidence on the association between SSBs, ASBs, and 100% fruit juices consumption and mortality have been presented. PubMed, Embase, Web of Science, Cochrane Central Register of Controlled Trials, and PsycINFO were systematically searched. We conducted a random-effects meta-analysis and dose-response meta-analysis to assess the association and calculated the pooled hazard ratio with 95% confidence interval. And we evaluated the certainty of evidence using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach. Thirteen studies with 1,539,127 participants proved eligible. An SSB-consumption increase per 250 mL/day was associated with a 4% greater risk of all-cause mortality (5 more per 1000 persons; low certainty) and 8% greater risk of cardiovascular disease mortality (3 more per 1000 persons; low certainty). ASB-consumption increase per 250 mL/day demonstrated a 4% greater risk of all-cause mortality (5 more per 1000 persons; low certainty) and 4% greater risk of cardiovascular disease mortality (2 more per 1000 persons; low certainty). The association of SSBs and ASBs with cancer mortality was not significant, with a very low certainty of evidence. There was evidence of a linear dose-response association between SSB intake and cancer mortality, as well as between ASB intake and all-cause mortality and cancer mortality. We observed a non-linear dose-response association between ASB intake and CVD mortality and SSB intake and all-cause and CVD mortality. Low certainty of evidence demonstrated that per 250 mL/day consumption increase in SSBs and ASBs had a small impact on all-cause and cardiovascular disease mortality but not on cancer mortality. The association of 100% fruit juice consumption with all-cause and cardiovascular disease mortality was uncertain.