Search

• Multidimensional features were useful in separating pathological HFOs from physiological ones. • Machine learning classifier based on these features could well distinguish two types of HFOs. • The classification performance is robust among patients with different neuroimage finds and surgical outcomes. High-frequency oscillations (HFOs) are an efficient indicator to locate the epileptogenic zone (EZ). However, physiological HFOs produced in the normal brain region may interfere with EZ localization. The present study aimed to build a machine learning-based classifier to distinguish the properties of each HFO event based on features in different domains. HFOs were detected in focal epilepsy patients from two different hospitals who underwent stereoelectroencephalography and subsequent resection surgery. Subsequently, 37 features in four different domains (time, frequency and time-frequency, entropy-based and nonlinear) were extracted for each HFO. After extraction, a fast correlation-based filter (FCBF) algorithm was applied for feature selection. The machine learning classifier was trained on the feature matrix with and without FCBF and then tested on the data set from patients in another hospital. A dataset was compiled, consisting of 89,844 pathological HFOs and 23,613 physiological HFOs from 17 patients assigned to the training dataset. Additionally, 12,695 pathological HFOs and 5,599 physiological HFOs from 9 patients were assigned to the testing dataset. Four features (ripple band power, arithmetic mean, Petrosian fractal dimension and zero crossings) were obtained for classifier training after FCBF. The classifier showed an area under the curve (AUC) of 0.95/0.98 for FCBF/no FCBF features in the training dataset and AUC of 0.82/0.90 for FCBF/no FCBF features in the testing dataset. Our findings indicated that the classifier utilizing all features demonstrated superior performance compared to the one relying on FCBF-processed features. Our classifier could reliably differentiate pathological HFOs from physiological ones, which could promote the development of HFOs in EZ localization. [ABSTRACT FROM AUTHOR]

• A novel gated graph neural network is proposed for water quality prediction. • Masking greatly enhances prediction accuracy, addressing sensor data limitation. • The model exhibits robust node-level prediction, enabling network soft sensing. • Sensor location plays a bigger role than quantity in improving prediction accuracy. Ensuring the safety and reliability of drinking water supply requires accurate prediction of water quality in water distribution networks (WDNs). However, existing hydraulic model-based approaches for system state prediction face challenges in model calibration with limited sensor data and intensive computing requirements, while current machine learning models are lack of capacity to predict the system states at sites that are not monitored or included in model training. To address these gaps, this study proposes a novel gated graph neural network (GGNN) model for real-time water quality prediction in WDNs. The GGNN model integrates hydraulic flow directions and water quality data to represent the topology and system dynamics, and employs a masking operation for training to enhance prediction accuracy. Evaluation results from a real-world WDN demonstrate that the GGNN model is capable to achieve accurate water quality prediction across the entire WDN. Despite being trained with water quality data from a limited number of sensor sites, the model can achieve high predictive accuracies (Mean Absolute Error = 0.07 mg L−1 and Mean Absolute Percentage Error = 10.0 %) across the entire network including those unmonitored sites. Furthermore, water quality-based sensor placement significantly improves predictive accuracy, emphasizing the importance of careful sensor location selection. This research advances water quality prediction in WDNs by offering a practical and effective machine learning solution to address challenges related to limited sensor data and network complexity. This study provides a first step towards developing machine learning models to replace hydraulic models in WDN modelling. [Display omitted] [ABSTRACT FROM AUTHOR]

Contamination events in water distribution networks (WDN) pose significant threats to water supply and public health. Rapid and accurate contamination source identification (CSI) can facilitate the development of remedial measures to reduce impacts. Though many machine learning (ML) methods have been proposed for fast detection, there is a critical need for approaches capturing complex spatial dynamics in WDNs to enhance prediction accuracy. This study proposes a gated graph neural network (GGNN) for CSI in the WDN, incorporating both spatiotemporal water quality data and flow directionality between network nodes. Evaluated across various contamination scenarios, the GGNN demonstrates high prediction accuracy even with limited sensor coverage. Notably, directional connections significantly enhance the GGNN CSI accuracy, underscoring the importance of network topology and flow dynamics in ML-based WDN CSI approaches. Specifically, the method achieves a 92.27% accuracy in narrowing the contamination source to 5 points using just 2 h of sensor data. The GGNN showcases resilience under model and measurement uncertainties, reaffirming its potential for real-time implementation in practice. Moreover, our findings highlight the impact of sensor sampling frequency and measurement accuracy on CSI accuracy, offering practical insights for ML methods in water network applications. • A gated graph neural network is proposed for contamination source identification. • The new model utilizes network topology and flow directions for enhanced performance. • Improved sensor sampling frequency and measurement accuracy boost model performance. • Model exhibits resilience to demand and measurement uncertainties. [ABSTRACT FROM AUTHOR]

• A novel automated approach was proposed for localizing seizure onset zone (SOZ) by cortico-cortical evoked potentials (CCEPs). • Cortical hyperexcitability at the stim-SOZ/rec-SOZ sites was increased in patients with hippocampus sclerosis compared to those with focal cortical dysplasia IIa. • The patients with complex partial seizures have more distinctive characteristics of CCEP than those with generalized tonic-clonic seizures in areas with different epileptogenicity. We aimed to develop a new approach for identifying the localization of the seizure onset zone (SOZ) based on corticocortical evoked potentials (CCEPs) and to compare the connectivity patterns in patients with different clinical phenotypes. Fifty patients who underwent stereoelectroencephalography and CCEP procedures were included. Logistic regression was used in the model, and six CCEP metrics were input as features: root mean square of the first peak (N1RMS) and second peak (N2RMS), peak latency, onset latency, width duration, and area. The area under the curve (AUC) for localizing the SOZ ranged from 0.88 to 0.93. The N1RMS values in the hippocampus sclerosis (HS) group were greater than that of the focal cortical dysplasia (FCD) IIa group (p < 0.001), independent of the distance between the recorded and stimulated sites. The sensitivity of localization was higher in the seizure-free group than in the non-seizure-free group (p = 0.036). This new method can be used to predict the SOZ localization in various focal epilepsy phenotypes. This study proposed a machine-learning approach for localizing the SOZ. Moreover, we examined how clinical phenotypes impact large-scale abnormality of the epileptogenic networks. [ABSTRACT FROM AUTHOR]

Introduction: Levodopa has become the main therapy for motor symptoms of Parkinson's disease (PD). This study aimed to test whether the amplitude of low-frequency fluctuation (ALFF) computed by fMRI could predict individual patient's response to levodopa treatment.Methods: We included 40 patients. Treatment efficacy was defined based on motor symptoms improvement from the state of medication off to medication on, as assessed by the Unified Parkinson's Disease Rating Scale score III. Two machine learning models were constructed to test the prediction ability of ALFF. First, the ensemble method was implemented to predict individual treatment responses. Second, the categorical boosting (CatBoost) classification was used to predict individual levodopa responses in patients classified as moderate and superior responders, according to the 50% threshold of improvement. The age, disease duration and treatment dose were controlled as covariates.Results: No significant difference in clinical data were observed between moderate and superior responders. Using the ensemble method, the regression model showed a significant correlation between the predicted and the observed motor symptoms improvement (r = 0.61, p < 0.01, mean absolute error = 0.11 ± 0.02), measured as a continuous variable. The use of the Catboost algorithm revealed that ALFF was able to differentiate between moderate and superior responders (area under the curve = 0.90). The mainly contributed regions for both models included the bilateral primary motor cortex, the occipital cortex, the cerebellum, and the basal ganglia.Conclusion: Both continuous and binary ALFF values have the potential to serve as promising predictive markers of dopaminergic therapy response in patients with PD. [ABSTRACT FROM AUTHOR]