Abstract
BACKGROUND: Placenta accreta spectrum (PAS) disorders seriously threaten the safety of the mother and infant in the perinatal period. Moreover, PAS is associated with poor maternal and perinatal outcomes once complicated with cervical implantation. Dismally, there are few reports about PAS complicated with cervical involvement currently, and the early warning models are also rarely reported. To screen the risk factors of PAS complicated with cervical implantation and construct an early risk warning model, we performed the analysis of clinical indicators and images of PAS patients by artificial intelligence (AI) data processing methods. METHODS: The clinical data of 166 patients with PAS in our hospital from January 2016 to September 2020 were retrospectively analyzed. The patients were divided into cervical implantation group and lower uterine implantation group according to the position of placenta implantation. Then, we compared the pregnancy outcomes of the two groups, screened the possible related factors of PAS complicated with cervical implantation by univariate analysis, and established the early warning model by logistic regression analysis. RESULTS: The maternal outcome of PAS complicated with cervical implantation was worse than that of the lower uterine implantation group. Through univariate analysis and logistic regression analysis, we found that the cervical width, abundant cervical blood flow, and bladder line interruption were all risk factors of PAS complicated with cervical implantation, and their contribution to the establishment of the regression model was statistically significant. CONCLUSION: PAS complicated with cervical implantation was extremely severe. Early identification of risk factors and establishment of a risk warning model have certain guiding significance for clinical formulation of a reasonable treatment plan.