Machine learning-based prediction of postpartum hemorrhage after vaginal delivery: combining bleeding high risk factors and uterine contraction curve

Development of a machine learning approach for prediction of red blood cell transfusion in patients undergoing Cesarean section at a single institution

Despite recent advances in surgical techniques and perinatal management in obstetrics for reducing intraoperative bleeding, blood transfusion may occur during a cesarean section (CS). This study aims to identify machine learning models with an optimal diagnostic performance for intraoperative transfusion prediction in parturients undergoing a CS. Additionally, to address model performance degradation due to data imbalance, this study further investigated the variation in predictive model performance depending on the ratio of event to non-event data (1:1, 1:2, 1:3, and 1:4 model datasets and raw data).The area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) were evaluated to compare the predictive accuracy of different machine learning algorithms, including XGBoost, K-nearest neighbor, decision tree, support vector machine, multilayer perceptron, logistic regression, random forest, and deep neural network. We compared the predictive performance of eight prediction algorithms that were applied to five types of datasets. The intraoperative transfusion in maternal CS was 7.2% (1020/14,254). XGBoost showed the highest AUROC (0.8257) and AUPRC (0.4825) among the models. The most significant predictors for transfusion in maternal CS as per machine learning models were placenta previa totalis, haemoglobin, placenta previa partialis, and platelets. In all eight prediction algorithms, the change in predictive performance based on the AUROC and AUPRC according to the resampling ratio was insignificant. The XGBoost algorithm exhibited optimal performance for predicting intraoperative transfusion. Data balancing techniques employed to alter the event data composition ratio of the training data failed to improve the performance of the prediction model.

The value of fibrinogen combined with D-dimer and neonatal weight in predicting postpartum hemorrhage in vaginal delivery

OBJECTIVES

The purpose of this study was to explore whether fibrinogen (Fib) can be used as a predictor of postpartum hemorrhage (PPH) in parturients with vaginal delivery, and the value of combining Fib with other indexes to predict postpartum hemorrhage in vaginal delivery.

METHODS

A total of 207 parturients who delivered via vagina were divided into PPH group (n=102) and non-PPH group (n=105). The PPH group was further divided into mild PPH group and severe PPH group. The differences of Fib, platelet (PLT), mean platelet volume (MPV), platelet distribution width (PDW), D-dimer (D-D), hemoglobin (HGB) and neonatal weight (Nw) between the two groups were compared to explore the significance of these indexes in predicting PPH.

RESULTS

Fib, PLT and PDW in PPH group were significantly lower than those in non-PPH group, while D-D and Nw in PPH group were significantly higher than those in non-PPH group. In the binary logistic regression model, we found that Fib, D-D and Nw were independently related to PPH. The risk of PPH increased by 9.87 times for every 1 g/L decrease in Fib. The cut-off value of Fib is 4.395 (sensitivity 0.705, specificity 0.922). The AUC value of PPH predicted by Fib combined with D-D and Nw was significantly higher than that of PPH predicted by Fib (p<0.05, 95 % CI 0.00313-0.0587).

CONCLUSIONS

Fib, D-D and Nw have good predictive value for PPH of vaginal delivery, among which Fib is the best. The combination of three indexes of Fib, D-D and Nw can predict PPH more systematically and comprehensively, and provide a basis for clinical prevention and treatment of PPH.

Quantitative prediction of postpartum hemorrhage in cesarean section on machine learning

BACKGROUND

Cesarean section-induced postpartum hemorrhage (PPH) potentially causes anemia and hypovolemic shock in pregnant women. Hence, it is helpful for obstetricians and anesthesiologists to prepare pre-emptive prevention when predicting PPH occurrence in advance. However, current works on PPH prediction focus on whether PPH occurs rather than assessing PPH amount. To this end, this work studies quantitative PPH prediction with machine learning (ML).

METHODS

The study cohort in this paper was selected from individuals with PPH who were hospitalized at Shijiazhuang Obstetrics and Gynecology Hospital from 2020 to 2022. In this study cohort, we built a dataset with 6,144 subjects covering clinical parameters, anesthesia operation records, laboratory examination results, and other information in the electronic medical record system. Based on our built dataset, we exploit six different ML models, including logistic regression, linear regression, gradient boosting, XGBoost, multilayer perceptron, and random forest, to automatically predict the amount of bleeding during cesarean section. Eighty percent of the dataset was used as model training, and 20 % was used for verification. Those ML models are constantly verified and improved by root mean squared error(RMSE) and mean absolute error(MAE). Moreover, we also leverage the importance of permutation and partial dependence plot (PDP) to discuss their feasibility.

RESULT

The experiment results show that random forest obtains the highest accuracy for PPH amount prediction compared to other ML methods. Random forest reaches the mean absolute error of 21.7, less than 5.4 % prediction error. It also gains the root mean squared error of 33.75, less than 9.3 % prediction error. On the other hand, the experimental results also disclose indicators that contributed most to PPH prediction, including Ca, hemoglobin, white blood cells, platelets, Na, and K.

CONCLUSION

It effectively predicts the amount of PPH during a cesarean section by ML methods, especially random forest. With the above insight, ML predicting PPH amounts provides early warning for clinicians, thus reducing complications and improving cesarean sections' safety. Furthermore, the importance of ML and permutation, complemented by incorporating PDP, promises to provide clinicians with a transparent indication of individual risk prediction.

An Explainable Artificial Intelligence Model Proposed for the Prediction of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome and the Identification of Distinctive Metabolites

BACKGROUND

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a complex and debilitating illness with a significant global prevalence, affecting over 65 million individuals. It affects various systems, including the immune, neurological, gastrointestinal, and circulatory systems. Studies have shown abnormalities in immune cell types, increased inflammatory cytokines, and brain abnormalities. Further research is needed to identify consistent biomarkers and develop targeted therapies. This study uses explainable artificial intelligence and machine learning techniques to identify discriminative metabolites for ME/CFS.

MATERIAL AND METHODS

The model investigates a metabolomics dataset of CFS patients and healthy controls, including 26 healthy controls and 26 ME/CFS patients aged 22-72. The dataset encapsulated 768 metabolites into nine metabolic super-pathways: amino acids, carbohydrates, cofactors, vitamins, energy, lipids, nucleotides, peptides, and xenobiotics. Random forest methods together with other classifiers were applied to the data to classify individuals as ME/CFS patients and healthy individuals. The classification learning algorithms' performance in the validation step was evaluated using a variety of methods, including the traditional hold-out validation method, as well as the more modern cross-validation and bootstrap methods. Explainable artificial intelligence approaches were applied to clinically explain the optimum model's prediction decisions.

RESULTS

The metabolomics of C-glycosyltryptophan, oleoylcholine, cortisone, and 3-hydroxydecanoate were determined to be crucial for ME/CFS diagnosis. The random forest model outperformed the other classifiers in ME/CFS prediction using the 1000-iteration bootstrapping method, achieving 98% accuracy, precision, recall, F1 score, 0.01 Brier score, and 99% AUC. According to the obtained results, the bootstrap validation approach demonstrated the highest classification outcomes.

CONCLUSION

The proposed model accurately classifies ME/CFS patients based on the selected biomarker candidate metabolites. It offers a clear interpretation of risk estimation for ME/CFS, aiding physicians in comprehending the significance of key metabolomic features within the model.

Development and validation of an artificial neural network prediction model for postpartum hemorrhage with placenta previa

BACKGROUND

Postpartum hemorrhage (PPH) is a leading cause of maternal morbidity worldwide and placenta previa is one of the major risk factors for PPH in overall population. However, the clinical prediction of PPH remains challenging. This study aimed to investigate an ideal machine learning-based prediction model for PPH in placenta previa parturients with cesarean section.

METHODS

The clinical data of 223 placenta previa parturients who underwent cesarean delivery in our hospital from 2016 to 2019 were retrospectively collected for analysis. An artificial neural network model was designed to predict PPH, defined as blood loss exceeding 1000 mL with 24h after delivery. Twenty clinical variables were selected as predictors. We also applied six conventional machine learning methods as reference models, including support vector machine, decision tree, random forest, gradient boosting decision tree, adaboost and logistic regression. All the models were validated using 5-fold cross-validation. The area under the receiver operating characteristic curve (AUC), precision, recall and the prediction accuracy of each model were reported.

RESULTS

A total of 223 pregnant women were enrolled in this study, including 101 cases (45.29%) experienced PPH. The proposed model achieved superior prediction performance with an AUC of 0.917, an accuracy of 0.851, a precision score of 0.829 and a recall score of 0.851, which outperformed other six conventional machine learning methods.

CONCLUSIONS

Compared to the conventional machine learning approaches, artificial neural network model shows discriminative ability in identifying women's risk of PPH with placenta previa during cesarean section.

Prediction of postpartum hemorrhage using traditional statistical analysis and a machine learning approach

BACKGROUND

Early detection of postpartum hemorrhage risk factors by healthcare providers during pregnancy and the postpartum period may allow healthcare providers to act to prevent it. Developing a prediction model that incorporates several risk factors and accurately calculates the overall risk for postpartum hemorrhage is necessary.

OBJECTIVE

This study used a traditional analytical approach and a machine learning model to predict postpartum hemorrhage.

STUDY DESIGN

Women who gave birth at the Khaleej-e-Fars Hospital in Bandar Abbas, Iran, were evaluated retrospectively between January 1, 2020, and January 1, 2022. These pregnant women were divided into 2 groups, namely those who had postpartum hemorrhage and those who did not. We used 2 approaches for the analysis. At the first level, we used the traditional analysis methods. Demographic factors, maternal comorbidities, and obstetrical factors were compared between the 2 groups. A bivariate logistic regression analysis of the risk factors for postpartum hemorrhage was done to estimate the crude odds ratios and their 95% confidence intervals. In the second level, we used machine learning approaches to predict postpartum hemorrhage.

RESULTS

Of the 8888 deliveries, we identified 163 women with recorded postpartum hemorrhage, giving a frequency of 1.8%. According to a traditional analysis, factors associated with an increased risk for postpartum hemorrhage in a bivariate logistic regression analysis were living in a rural area (odds ratio, 1.41; 95% confidence interval, 1.08-1.98); primiparity (odds ratio, 3.16; 95% confidence interval, 1.90-4.75); mild to moderate anemia (odds ratio, 5.94; 95% confidence interval 2.81-8.34); severe anemia (odds ratio, 6.01; 95% confidence interval 3.89-11.09); abnormal placentation (odds ratio, 7.66; 95% confidence interval, 2.81-17.34); fetal macrosomia (odds ratio, 8.14; 95% confidence interval, 1.02-14.47); shoulder dystocia (odds ratio, 7.88; 95% confidence interval, 1.07-13.99); vacuum delivery (odds ratio, 2.01; 95% confidence interval, 1.15-5.98); cesarean delivery (odds ratio, 1.86; 95% confidence interval, 1.12-3.79); and general anesthesia during cesarean delivery (odds ratio, 7.66; 95 % confidence interval, 3.11-9.36). According to machine learning analysis, the top 5 algorithms were XGBoost regression (area under the receiver operating characteristic curve of 99%), XGBoost classification (area under the receiver operating characteristic curve of 98%), LightGBM (area under the receiver operating characteristic curve of 94%), random forest regression (area under the receiver operating characteristic curve of 86%), and linear regression (area under the receiver operating characteristic curve of 78%). However, after considering all performance parameters, the XGBoost classification was found to be the best model to predict postpartum hemorrhage. The importance of the variables in the linear regression model, similar to traditional analysis methods, revealed that macrosomia, general anesthesia, anemia, shoulder dystocia, and abnormal placentation were considered to be weighted factors, whereas XGBoost classification considered living residency, parity, cesarean delivery, education, and induced labor to be weighted factors.

CONCLUSION

Risk factors for postpartum hemorrhage can be identified using traditional statistical analysis and a machine learning model. Machine learning models were a credible approach for improving postpartum hemorrhage prediction with high accuracy. More research should be conducted to analyze appropriate variables and prepare big data to determine the best model.

Development and validation of a machine learning-based predictive model for secondary post-tonsillectomy hemorrhage

Background

The main obstacle to a patient's recovery following a tonsillectomy is complications, and bleeding is the most frequent culprit. Predicting post-tonsillectomy hemorrhage (PTH) allows for accurate identification of high-risk populations and the implementation of protective measures. Our study aimed to investigate how well machine learning models predict the risk of PTH.

Methods

Data were obtained from 520 patients who underwent a tonsillectomy at The 940th Hospital of Joint Logistics Support Force of Chinese People's Liberation Army. The age range of the patients was 2-57 years, and 364 (70%) were male. The prediction models were developed using five machine learning models: decision tree, support vector machine (SVM), extreme gradient boosting (XGBoost), random forest, and logistic regression. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) was used to interpret the results of the best-performing model.

Results

The frequency of PTH was 11.54% among the 520 patients, with 10.71% in the training group and 13.46% in the validation set. Age, BMI, season, smoking, blood type, INR, combined secretory otitis media, combined adenoidectomy, surgical wound, and use of glucocorticoids were selected by mutual information (MI) method. The XGBoost model had best AUC (0.812) and Brier score (0.152). Decision curve analysis (DCA) showed that the model had a high clinical utility. The SHAP method revealed the top 10 variables of MI according to the importance ranking, and the average of the age was recognized as the most important predictor variable.

Conclusion

This study built a PTH risk prediction model using machine learning. The XGBoost model is a tool with potential to facilitate population management strategies for PTH.