Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure.

Graph neural networks (GNNs) have achieved considerable success in dealing with graph-structured data by the message-passing mechanism. Actually, this mechanism relies on a fundamental assumption that the graph structure along which information propagates is perfect. However, the real-world graphs are inevitably incomplete or noisy, which violates the assumption, thus resulting in limited performance. Therefore, optimizing graph structure for GNNs is indispensable and important. Although current semi-supervised graph structure learning (GSL) methods have achieved a promising performance, the potential of labels and prior graph structure has not been fully exploited yet. Inspired by this, we examine GSL with dual reinforcement of label and prior structure in this article. Specifically, to enhance label utilization, we first propose to construct the prior label-constrained matrices to refine the graph structure by identifying label consistency. Second, to adequately leverage the prior structure to guide GSL, we develop spectral contrastive learning that extracts global properties embedded in the prior graph structure. Moreover, contrastive fusion with prior spatial structure is further adopted, which promotes the learned structure to integrate local spatial information from the prior graph. To extensively evaluate our proposal, we perform sufficient experiments on seven benchmark datasets, where experimental results confirm the effectiveness of our method and the rationality of the learned structure from various aspects.

Parallel Dual-Branch Fusion Network for Epileptic Seizure Prediction.

Epilepsy is a prevalent chronic disorder of the central nervous system. The timely and accurate seizure prediction using the scalp Electroencephalography (EEG) signal can make patients adopt reasonable preventive measures before seizures occur and thus reduce harm to patients. In recent years, deep learning-based methods have made significant progress in solving the problem of epileptic seizure prediction. However, most current methods mainly focus on modeling short- or long-term dependence in EEG, while neglecting to consider both. In this study, we propose a Parallel Dual-Branch Fusion Network (PDBFusNet) which aims to combine the complementary advantages of Convolutional Neural Network (CNN) and Transformer. Specifically, the features of the EEG signal are first extracted using Mel Frequency Cepstral Coefficients (MFCC). Then, the extracted features are delivered into the parallel dual-branches to simultaneously capture the short- and long-term dependencies of EEG signal. Further, regarding the Transformer branch, a novel feature fusion module is developed to enhance the ability of utilizing time, frequency, and channel information. To evaluate our proposal, we perform sufficient experiments on the public epileptic EEG dataset CHB-MIT, where the accuracy, sensitivity, specificity and precision are 95.76%, 95.81%, 95.71% and 95.71%, respectively. PDBFusNet shows superior performance compared to state-of-the-art competitors, which confirms the effectiveness of our proposal.

Molecular dynamics simulation on the displacement behaviour of crude oil by CO2/CH4 mixtures on a silica surface.

Produced gas re-injection is an effective and eco-friendly approach for enhancing oil recovery from shale oil reservoirs. However, the interactions between different gas phase components, and the oil phase and rocks are still unclear during the re-injection process. This study aims to investigate the potential of produced gas re-injection, particularly focusing on the effects of methane (CH4) content in the produced gas on shale oil displacement. Molecular dynamics simulations were employed to analyze the interactions between gas, oil, and matrix phases with different CH4 proportions (0%, 25%, 50%, and 100%), alkanes and under various burial depth. Results show that a 25% CH4 content in the produced gas achieves almost the same displacement effect as pure carbon dioxide (CO2) injection. However, when the CH4 content increases to 50% and 100%, the interaction between gas and quartz becomes insufficient to effectively isolate oil from quartz, causing only expansion and slight dispersion. Interestingly, the presence of CH4 has a synergistic effect on CO2, facilitating the diffusion of CO2 into the oil film. During the gas stripping process, CO2 is the main factor separating oil from quartz, while CH4 mainly contributes to oil expansion. In addition, for crude oil containing a large amount of light alkanes, extracting light components through mixed gas may be more effective than pure CO2. This study offers valuable insights for applications of produced gas re-injection to promote shale oil recovery.

Deep Survival Analysis With Latent Clustering and Contrastive Learning.

Survival analysis is employed to analyze the time before the event of interest occurs, which is broadly applied in many fields. The existence of censored data with incomplete supervision information about survival outcomes is one key challenge in survival analysis tasks. Although some progress has been made on this issue recently, the present methods generally treat the instances as separate ones while ignoring their potential correlations, thus rendering unsatisfactory performance. In this study, we propose a novel Deep Survival Analysis model with latent Clustering and Contrastive learning (DSACC). Specifically, we jointly optimize representation learning, latent clustering and survival prediction in a unified framework. In this way, the clusters distribution structure in latent representation space is revealed, and meanwhile the structure of the clusters is well incorporated to improve the ability of survival prediction. Besides, by virtue of the learned clusters, we further propose a contrastive loss function, where the uncensored data in each cluster are set as anchors, and the censored data are treated as positive/negative sample pairs according to whether they belong to the same cluster or not. This design enables the censored data to make full use of the supervision information of the uncensored samples. Through extensive experiments on four popular clinical datasets, we demonstrate that our proposed DSACC achieves advanced performance in terms of both C-index (0.6722, 0.6793, 0.6350, and 0.7943) and Integrated Brier Score (IBS) (0.1616, 0.1826, 0.2028, and 0.1120).

Surgical evidence-based comparison of [68Ga]Ga-FAPI-04 PET and MRI-DWI for assisting debulking surgery in ovarian cancer patients.

PURPOSE: Imaging assessment of abdominopelvic tumor burden is crucial for debulking surgery decision in ovarian cancer patients. This study aims to compare the efficiency of [68Ga]Ga-FAPI-04 FAPI PET and MRI-DWI in the preoperative evaluation and its potential impact to debulking surgery decision. METHODS: Thirty-six patients with suspected/confirmed ovarian cancer were enrolled and underwent integrated [68Ga]Ga-FAPI-04 PET/MRI. Nineteen patients (15 stage III-IV and 4 I-II stage) who underwent debulking surgery were involved in the diagnostic efficiency analysis. The images of [68Ga]Ga-FAPI-04 PET and MRI-DWI were visually analyzed respectively. Immunohistochemistry on FAP was performed in metastatic lesions to investigate the radiological missing of [68Ga]Ga-FAPI-04 PET as well as its different performance in primary debulking surgery (PDS) and interval debulking surgery (IDS) patients. Potential imaging impact on management was also studied in 35 confirmed ovarian cancer patients. RESULTS: [68Ga]Ga-FAPI-04 PET displayed higher sensitivity (76.8% vs.59.9%), higher accuracy (84.9% vs. 80.7%), and lower missing rate (23.2% vs. 40.1%) than MRI-DWI in detecting abdominopelvic metastasis. The diagnostic superiority of [68Ga]Ga-FAPI-04 PET is more obvious in PDS patients but diminished in IDS patients. [68Ga]Ga-FAPI-04 PET outperformed MRI-DWI in 70.8% abdominopelvic regions (17/24), which contained seven key regions that impact the resectability and surgical complexity. MRI-DWI hold advantage in the peritoneal surface of the bladder and the central tendon of the diaphragm. Of the contradictory judgments between the two modalities (14.9%), [68Ga]Ga-FAPI-04 PET correctly identified more lesions, particularly in PDS patients (73.8%). In addition, FAP expression was independent of lesion size and decreased in IDS patients. [68Ga]Ga-FAPI-04 PET changed 42% of surgical planning that was previously based on MRI-DWI. CONCLUSION: [68Ga]Ga-FAPI-04 PET is more efficient in assisting debulking surgery in ovarian cancer patients than MRI-DWI. Integrated [68Ga]Ga-FAPI-04 PET/MR imaging is a potential method for planning debulking surgery in ovarian cancer patients.

Machine learning models developed and internally validated for predicting chronicity in pediatric immune thrombocytopenia.

BACKGROUND: Primary immune thrombocytopenia (ITP) in children is typically self-limiting; however, 20% to 30% of patients may experience prolonged thrombocytopenia lasting over a year. The challenge is predicting chronicity to ensure personalized treatment approaches. OBJECTIVES: To address this issue, we developed and internally validated 4 machine learning (ML) models using demographic and immunologic characteristics to predict the likelihood of chronicity. METHODS: The present study was conducted at Beijing Children's Hospital from June 2018 to December 2021, aiming to develop predictive models for determining the chronicity of pediatric ITP. Four ML models, based on a logistic regression classifier, random forest classifier, eXtreme Gradient Boosting (XGBoost), and support vector machine, were employed. These models used a set of 16 variables, including 14 immunologic and 2 demographic predictors. The performance evaluation criteria included prediction accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve (AUROC). RESULTS: Data were collected from 662 patients who were randomly assigned to either a training dataset or a testing dataset using a random number generator. Among them, 26.5% had chronic disease. All models performed well, with AUROC values ranging from 0.81 to 0.84, and XGBoost was selected for its highest AUROC score and interpretability in constructing the predictive model. Age, T helper 17, T helper 17-to-regulatory T cell ratio, T helper 1, and double-negative T cells were identified as significant predictors by the XGBoost algorithm. CONCLUSION: We developed a precise predictive model for chronicity in pediatric ITP using ML during the initial phase. The XGBoost model achieved high predictive accuracy by using individual patient clinical parameters and demonstrated commendable interpretability.

Indirect estimation of pediatric reference interval via density graph deep embedded clustering.

Establishing reference intervals (RIs) for pediatric patients is crucial in clinical decision-making, and there is a critical gap of pediatric RIs in China. However, the direct sampling technique for establishing RIs is resource-intensive and ethically challenging. Indirect estimation methods, such as unsupervised clustering algorithms, have emerged as potential alternatives for predicting reference intervals. This study introduces deep graph clustering methods into indirect estimation of pediatric reference intervals. Specifically, we propose a Density Graph Deep Embedded Clustering (DGDEC) algorithm, which incorporates a density feature extractor to enhance sample representation and provides additional perspectives for distinguishing different levels of health status among populations. Additionally, we construct an adjacency matrix by computing the similarity between samples after feature enhancement. The DGDEC algorithm leverages the adjacency matrix to capture the interrelationships between patients and divides patients into different groups, thereby estimating reference intervals for the potential healthy population. The experimental results demonstrate that when compared to other indirect estimation techniques, our method ensures the predicted pediatric reference intervals in different age and gender groups are closer to the true values while maintaining good generalization performance. Additionally, through ablation experiments, our study confirms that the similarity between patients and the multi-scale density features of samples can effectively describe the potential health status of patients.

Sensibilidad de la escala ampliada del estado de discapacidad (EDSS) a la progresión de la enfermedad y la intervención terapéutica en las formas progresivas de la esclerosis múltiple / Responsiveness of the Expanded Disability Status Scale (EDSS) to disease progression and therapeutic intervention in progressive forms of multiple sclerosis

Introducción. El planteamiento habitual en las formas recidivantes de la esclerosis múltiple (EM) ha consistido en medir los efectos del tratamiento sobre las exacerbaciones clínicas y la discapacidad física determinados por la escala ampliada del estado de discapacidad (EDSS). Sin embargo, medir las recidivas clínicas no constituye una opción viable en las formas progresivas de la EM debido a su baja frecuencia y, por consiguiente, el planteamiento habitual en los ensayos clínicos centrados en las formas progresivas de la EM ha consistido en utilizar la EDSS como criterio de valoración primario. Pacientes y métodos. Se examina la sensibilidad de la EDSS a la progresión de la enfermedad y los efectos del tratamiento en el contexto de ensayos clínicos de la EM secundaria progresiva (EMSP) y primaria progresiva (EMPP), y se compara con la correspondiente a las tres tareas funcionales de la escala funcional compuesta de la EM (MSFC): el Timed 25 Foot Walk (T25FW), el 9 Hole PEG (9HP) y el Paced Auditory Serial Attention Test (PASAT). Resultados. El tamaño del efecto de la EDSS tras dos años con placebo apenas alcanzó un valor de 0,2-0,3, tanto en la EMSP como en la EMPP, un resultado similar al obtenido en el 9HP y en el PASAT. Por el contrario, el tamaño del efecto del T25FW fue mucho mayor y estuvo condicionado en gran medida por los pacientes que no pudieron acabar la prueba. Conclusiones. Se confirma la escasa sensibilidad de la EDSS frente a la progresión de la enfermedad y los efectos del tratamiento en el ámbito de la EMSP y la EMPP. Así, es recomendable utilizar otros criterios de valoración primarios en los ensayos terapéuticos de la EM progresiva (AU)

Introduction. The standard approach in relapsing forms of multiple sclerosis (MS) has been to measure therapeutic effects on clinical exacerbations and physical disability as determined by the Expanded Disability Status Scale (EDSS). However, measuring clinical relapses is not a viable option in the progressive forms of MS because of their low frequency. Therefore, the standard approach in clinical trials of progressive forms of MS has been to use the EDSS as primary outcome measure. Patients and methods. We examined the responsiveness of the EDSS to disease progression and treatment effects in the context of clinical trials of secondary progressive (SPMS) and primary progressive (PPMS) MS and compared it to the three functional tasks of the Multiple Sclerosis Functional Composite (MSFC): the Timed 25 Foot Walk (T25FW), the 9 Hole PEG (9HP), and the Paced Auditory Serial Attention Test (PASAT). Results. The effect size of the EDSS after two years on placebo was only 0.2-0.3 in both SPMS and PPMS, similar to the 9HP and the PASAT. In contrast, the effect size of the T25FW was much greater and driven to a large extent by subjects who could not complete the task. Conclusions. The EDSS shows poor responsiveness to both disease progression and treatment effects in SPMS and PPMS. The use of alternative primary outcome measures is recommended for therapeutic trials of progressive MS (AU)