Explanatory variables and nomogram of a clinical prediction model to estimate the risk of caesarean section after term induction

Ensemble learning for fetal ultrasound and maternal-fetal data to predict mode of delivery after labor induction

Providing adequate counseling on mode of delivery after induction of labor (IOL) is of utmost importance. Various AI algorithms have been developed for this purpose, but rely on maternal-fetal data, not including ultrasound (US) imaging. We used retrospectively collected clinical data from 808 subjects submitted to IOL, totaling 2024 US images, to train AI models to predict vaginal delivery (VD) and cesarean section (CS) outcomes after IOL. The best overall model used only clinical data (F1-score: 0.736; positive predictive value (PPV): 0.734). The imaging models employed fetal head, abdomen and femur US images, showing limited discriminative results. The best model used femur images (F1-score: 0.594; PPV: 0.580). Consequently, we constructed ensemble models to test whether US imaging could enhance the clinical data model. The best ensemble model included clinical data and US femur images (F1-score: 0.689; PPV: 0.693), presenting a false positive and false negative interesting trade-off. The model accurately predicted CS on 4 additional cases, despite misclassifying 20 additional VD, resulting in a 6.0% decrease in average accuracy compared to the clinical data model. Hence, integrating US imaging into the latter model can be a new development in assisting mode of delivery counseling.

Development and assessment of a predictive model for early diagnosis of rheumatoid arthritis in southwest China: A new nomogram

Rheumatoid arthritis (RA) is a disease complicated with inflammatory synovitis, which seriously affects the life quality of patients. Early diagnosis is important for prognosis of RA. Here, we aimed to develop and assess a model for early diagnosis of RA in southwest China. A nomogram including 44 patients with an early diagnosis of RA was developed. Variables were filtered by least absolute contraction selection operator and multiple logistic regression. The efficiency and clinical application range were evaluated. This nomogram showed that rheumatoid factor, erythrocyte sedimentation rate, RA33, facet joint and knee joint had high positive predictive value for RA. The area under curve was 0.920 [95% confidence interval (CI): 0.865-0.975]. In the validation model, area under curve was 0.942 (95% CI: 0.893-0.991). Calibration and decision curve suggested that this nomogram was helpful within the threshold probability range of 0.02 to 1.00. Using this nomogram will help clinicians in the early diagnosis of RA. Laboratory indicators such as rheumatoid factor, erythrocyte sedimentation rate, RA33, and clinical symptoms such as morning stiffness, facet joint and knee joint are very important, which deserves the attention of clinicians.

Can maternal hormones play a significant role in delivery mode?

The aim of this study was primarily to evaluate the levels of progesterone, oestradiol and relaxin during different delivery modes and secondarily to assess specific traits and changes in maternal pelvic dimensions during pregnancy and childbirth, in correlation with foetal size and maternal hormonal profile. Nulliparous women (n = 448) were evaluated at three different stages, during first trimester, at the time of admission for childbirth and finally just before childbirth. Each examination included clinical internal pelvimetry, blood sample collection for defining the hormones levels in peripheral maternal circulation and ultrasonographic measurements of specific variables of the pubic symphysis and the foetus. We included 304 nulliparous women divided in three groups. According to our results, there was statistically significant difference at the mean progesterone, oestradiol and relaxin range during different modes of childbirth (p-value < .01). We also found significant correlation between the newborn's weight and the changes in pubic symphysis dimensions. However, no significant association was noted between maternal hormones studied and the changes in pelvic dimensions.IMPACT STATEMENTWhat is already known on this subject? Mode of childbirth can be affected by various aspects, like maternal pelvic anatomy, foetal size and hormonal status at the time of labour. Hormonal fluctuations along with mechanical forces caused by the foetus are believed to lead to morphological alterations to promote natural vaginal childbirth.What do the results of this study add? Our results clearly showed that successful vaginal delivery is characterised by the prevalence of a hyperoestrogenic environment with higher values of intrapartum oestradiol range and significant increase in maternal serum relaxin levels. We also proved that progesterone levels do not decrease during vaginal childbirth, and we concluded that foetal size seems to be the most crucial factor causing alterations in maternal pelvis during parturition.What are the implications of these findings for clinical practice and further research? Our findings could form part of a set of key factors included in future algorithms or computerised biomechanical models for predicting potential childbirth mode. Larger multicenter studies should confirm our results and evaluate their clinical significance in the decision making to ensure safe childbirth and optimal maternal and perinatal outcomes.