Background: The rapid onset of COVID-19 placed immense strain on many already overstretched healthcare systems. The unique physiological changes of pregnancy, amplified by the complex effects of COVID-19 in pregnant women, rendered prioritization of infected expectant mothers more challenging. This work aims to use state-of-the-art machine learning techniques to predict whether a COVID-19-infected pregnant woman will be admitted to ICU (Intensive Care Unit). Methods: A retrospective study using data from COVID-19 infected women admitted to 2 hospital 1 in Astana and 1 in Shymkent, Kazakhstan, from May to July 2021. The developed machine learning platform implements and compares the performance of eight binary classifiers including Gaussian naïve Bayes, K-nearest neighbors, logistic regression with L2 regularization, random forest, AdaBoost, gradient boosting, eXtreme gradient boosting, and linear discriminant analysis. Results: Data from 1168 pregnant women with COVID-19 was analyzed. From them, 9.4% were admitted to ICU. Logistic regression with L2 regularization achieved the highest F1-score during the model selection phase while achieving an AUC of 0.84 on the test set during the evaluation stage. Furthermore, the feature importance analysis conducted by calculating Shapley Additive Explanation values points to leucocyte counts, C-reactive protein, pregnancy week, and eGFR and hemoglobin as the most important features for predicting ICU admission. Conclusion: The predictive model here obtained may be an efficient support tool for prioritizing care of COVID-19 infected pregnant women in clinical practice.
Background: The rapid onset of COVID-19 placed immense strain on many already overstretched healthcare systems. The unique physiological changes in pregnancy, amplified by the complex effects of COVID-19 in pregnant women, rendered prioritization of infected expectant mothers more challenging. This work aims to use state-of-the-art machine learning techniques to predict whether a COVID-19-infected pregnant woman will be admitted to ICU (Intensive Care Unit). Methods: A retrospective study using data from COVID-19-infected women admitted to one hospital in Astana and one in Shymkent, Kazakhstan, from May to July 2021. The developed machine learning platform implements and compares the performance of eight binary classifiers, including Gaussian naïve Bayes, K-nearest neighbors, logistic regression with L2 regularization, random forest, AdaBoost, gradient boosting, eXtreme gradient boosting, and linear discriminant analysis. Results: Data from 1292 pregnant women with COVID-19 were analyzed. Of them, 10.4% were admitted to ICU. Logistic regression with L2 regularization achieved the highest F1-score during the model selection phase while achieving an AUC of 0.84 on the test set during the evaluation stage. Furthermore, the feature importance analysis conducted by calculating Shapley Additive Explanation values points to leucocyte counts, C-reactive protein, pregnancy week, and eGFR and hemoglobin as the most important features for predicting ICU admission. Conclusions: The predictive model obtained here may be an efficient support tool for prioritizing care of COVID-19-infected pregnant women in clinical practice.
Background: Early-onset preeclampsia (EOPE) is frequently complicated by fetal growth restriction (FGR). The sFlt-1/PlGF ratio reflects maternal angiogenic imbalance but provides limited insight into placental pathology-the root cause of preeclampsia. Collagen XVIIA1 (COLXVIIA1), a transmembrane hemidesmosomal collagen expressed in trophoblasts, may serve as a biomarker of placental injury. Methods: Circulating COLXVIIA1 was first measured in gestational age–matched peripheral blood samples from EOPE and normotensive pregnancies (n = 6 per group). Placental origin was assessed using paired uterine and peripheral vein samples (n = 9). Placental COLXVIIA1 expression, localisation, and processing were analysed in normotensive and EOPE placentas. Trophoblast-derived extracellular vesicles (TB-sEVs) were isolated from ex vivo perfused placentas to assess COLXVIIA1 packaging. In a prospective cohort of 167 women with suspected preeclampsia, circulating COLXVIIA1 was analysed alongside PlGF and sFlt-1, and diagnostic performance of the COLXVIIA1/PlGF ratio was compared with sFlt-1/PlGF. Findings: Circulating COLXVIIA1 levels were significantly elevated in EOPE compared with gestational age–matched controls, indicating independence from gestational age. Uterine vein levels exceeded peripheral levels, consistent with placental release. COLXVIIA1 expression was localised to trophoblasts and amniotic epithelium. In EOPE placentas, COLXVIIA1-enriched hotspots co-localised with fibrin nodules, perivillous fibrin deposition, and peri-infarct regions. Increased proteolytic processing (∼120 kDa ectodomain) and preferential packaging of transmembrane COLXVIIA1 into TB-sEVs were observed. The COLXVIIA1/PlGF ratio performed comparably to sFlt-1/PlGF for overall preeclampsia and showed strong predictive accuracy for EOPE with FGR (AUC = 0.858), confirmed by bootstrap analysis. Interpretation: Abnormal COLXVIIA1 expression, processing and release reflects trophoblast response to structural injury and provides a circulating signal complementary to angiogenic markers. The COLXVIIA1/PlGF ratio captures a distinct dimension of placental pathology and may improve risk stratification in EOPE, particularly in pregnancies complicated by FGR.