×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerPredicting the risk of operative delivery, especially Cesarean section, is important for improving outcomes for both mothers and newborns. In this study, a machine-learning-based framework is developed using explainable artificial intelligence techniques across three clinical datasets: fetal cardiotocography, maternal health parameters, and pregnancy outcome data.Three classification models—Logistic Regression, Decision Tree, and Random Forest—were evaluated to identify the most effective approach. Among these, the Random Forest model achieved the best performance, with an F1 Score of 0.88 and an Area Under the Curve of 0.99 on the fetal health dataset.To enhance interpretability in a clinical context, a dual-layer explanation strategy was adopted. SHapley Additive exPlanations was used to analyze global feature importance, while Local Interpretable Model-agnostic Explanations was applied to explain individual predictions. The results indicate that abnormal short-term variability is a key factor influencing operative delivery risk. The explanations generated by both methods were consistent with established clinical understanding, making the model both accurate and interpretable.
Women’s safety remains an urgent challenge, particularly in moments when conventional panic button devices fail due to a victim’s inability to act or poor network coverage. To overcome these shortcomings, TRIAD-Lite is introduced as an IoT-enabled wearable framework that unites multimodal physiological sensing with lightweight deep learning for proactive distress identification. The system captures heart rate, blood pressure, galvanic skin response, and motion patterns, while incorporating a triple-tap gesture to confirm user intent, all processed locally on a Raspberry Pi for real-time inference. Unlike reactive mechanisms, this design anticipates danger by analyzing variations in physiological signals that often precede visible distress. Communication reliability is reinforced through a hybrid strategy: alerts are transmitted via GSM or Wi-Fi under normal conditions, but in the event of limited connectivity, a LoRa-based backup ensures long-range transmission. Experimental analysis using simulated datasets yielded an AUC of 1.000 with flawless precision and recall, highlighting the model’s reliability and calibration. Further field evaluation demonstrated that LoRa maintained connectivity across 5.7 kilometers with complete packet delivery, proving effective for both rural and urban environments. By combining predictive analytics, gesture-based confirmation, and dual communication layers, TRIAD-Lite offers a scalable, privacy-conscious, and highly resilient framework that strengthens women’s safety and extends protective technology into regions where conventional systems often fail.