High Prediction Efficiency Research Articles

Combined inflammation-related biomarkers and clinicopathological features for the prognosis of stage II/III colorectal cancer by machine learning

BackgroundInflammation-related biomarkers, such as systemic inflammation score (SIS) and neutrophil–lymphocyte ratio (NLR), are associated with colorectal cancer prognosis. However, the combined role of SIS, NLR, and clinicopathological factors in stage II/III colorectal cancer remains unclear. This study developed a nomogram to predict long-term prognosis for these patients.MethodsThis retrospective study included 1540 patients (training set) from the First Affiliated Hospital of Kunming Medical University and 152 patients (testing set) from The Honghe Third People's Hospital. Cox regression identified independent prognostic factors, and machine learning established predictive models. Model performance was evaluated by the C-index, area under the curve (AUC), and decision curve analysis (DCA).ResultsIn the training set, a total of 1540 patients with stage II/III colorectal cancer were included. More than 70 years old (HR = 1.830, p = 0.000); SIS = 2 (HR = 1.693, p = 0.002); Preoperative CEA more than 5 ng/mL (HR = 1.614, p = 0.000); and Moderately differentiated (HR = 1.438, p = 0.011); or Low/undifferentiated (HR = 2.126, p = 0.000); The pN1 (HR = 2.040, p = 0.000) and pN2 (HR = 3.297, p = 0.000) stages were considered independent prognostic risk factors of stage II/III colorectal cancer. Negative perineural invasion (HR = 0.733, p = 0.014) and NLR less than 4 (HR = 0.696, p = 0.022) were considered independent prognostic protective factors of stage II/III colorectal cancer. A nomogram was established based on SIS, NLR, and the clinicopathological results for predicting and validating the overall survival in the training and testing sets. The C-index of the training set was 0.746, and the C-index of the testing set was 0.708, indicating the high prediction efficiency of the nomogram.ConclusionsA nomogram combining SIS, NLR, and clinicopathological factors provides an effective, cost-efficient tool for predicting the prognosis of stage II/III colorectal cancer. Future studies will validate its long-term predictive performance in larger, multicenter cohorts.

Influencing Factors of Urinary Tract Stones Complicated by Urinary Tract Infections and the Construction of a Column Chart Prediction Model.

Objective: To analyze the influencing factors of urinary tract stones complicated by urinary tract infections and construct a column chart prediction model. Patients and Methods: From July 2020 to October 2023, 345 patients with urinary tract stones admitted to our hospital were collected as the training set, they were separated into an infection group of 51 cases and a non-infection group of 294 cases on the basis of the presence or absence of concurrent urinary tract infections; 192 patients with urinary tract stones were used as the testing set and were divided into an infection group of 26 cases and a non-infection group of 166 cases on the basis of the presence or absence of concurrent urinary tract infections. Data such as gender, age, and procalcitonin (PCT) were recorded. Multi-variable logistic regression analysis was applied to screen predictive factors, R4.0.2 software was applied to construct a column chart model, the calibration curve and Receiver Operating Characteristic (ROC) curve were applied to evaluate the discrimination and calibration of the column chart model; decision curve analysis curve was applied to evaluate the predictive performance of column chart models. Results: The proportions of female, diabetes mellitus, indwelling time of urinary catheter ≥7 days, the PCT, and urine pH in the infected group were greater than those in the non-infected group (p < 0.05). Female, diabetes mellitus, catheter retention time ≥7 days, high PCT, and high urine pH were independent risk factors for urinary calculi complicated with urinary tract infection (p < 0.05). Training set: C-index was 0.913, Area Under Curve (AUC) was 0.943 [95% Confidence Interval (CI) = 0.912-0.973], sensitivity was 86.36%, and specificity was 89.81%, testing set: C-index was 0.905, AUC was 0.959 (95% CI = 0.928-0.989), sensitivity was 84.65%, and specificity was 95.84%, indicating good discriminability of the line graph model; Hosmer-Lemeshow test showed χ2 = 2.843, 2.894, p = 0.944, 0.941, the calibration curve approached the ideal curve, and the line graph model had good calibration. When the risk threshold for urinary tract stones complicated by urinary tract infections was between 0.08 and 0.86, this column chart model provided clinical net benefits. Conclusion: The column chart prediction model for urinary tract stones complicated by urinary tract infections constructed in this study has high predictive efficiency and clinical practical value, and can provide reference for medical staff.

QTc interval prolongation and risk of atrial fibrillation recurrence: a meta-analysis and observational cohort study.

Corrected QT interval (QTc) is a ventricular repolarization marker on electrocardiography. Previous studies evaluated its value in predicting atrial fibrillation (AF) occurrence. However, its predictive efficacy for AF recurrence remains controversial. We searched PubMed and Google databases for studies before January 2024 evaluating the association between QTc interval and AF incidence. A meta-analysis of the eligible datasets was conducted using Bazett's formula, with subgroup analysis to explore the heterogeneity. Additionally, thirty-eight patients with AF who underwent radiofrequency catheter ablation were enrolled and followed-up for 3-36 months. Univariate and multivariate Cox models were used to calculate the hazard ratios (HRs) and determine the relationship between clinical factors and AF recurrence. Kaplan-Meier survival analysis and ROC curve were conducted to assess the impact and predictive efficacy of individual factors. Eleven datasets from nine eligible studies were enrolled and meta-analysed. We found that patients with prolonged QTc interval was associated with a significantly higher AF incidence risk, and the risk increased with every 10-ms prolongation. However, this association was not significant in the AF recurrence subgroup. In our prospective cohort, the preoperative body mass index, QTc, left atrial diameter (LAD), and uric acid levels influenced AF recurrence. Multivariate Cox regression analysis identified LAD as an independent factor affecting AF recurrence in patients with a high predictive efficiency. Kaplan-Meier survival analysis showed that increased LAD (>4.5 cm) was associated with postoperative AF recurrence. Therefore, LAD has better predictive power and can be an indicator for predicting postoperative AF recurrence.

Construction and validation of a diagnostic model for high-risk papillary thyroid microcarcinoma.

The purpose of this study was to construct a diagnostic model by exploring the potential predictors of high-risk Papillary Thyroid Microcarcinoma (PTMC) and verifying its reliability. A retrospective analysis of PTMC patients who underwent surgical treatment from 2004 to 2015 in the SEER database (training set) and the clinical pathological ultrasound information of PTMC patients at the Sichuan Provincial People's Hospital from 2020 to 2022 (external validation set) was conducted. In the training set, univariate and multivariate logistic regression analyses were used to screen independent predictive factors for high-risk PTMC patients in pathology. A nomogram diagnostic model was further constructed. Additionally, ROC curves and calibration curves were drawn to evaluate the efficiency of the model. In the external validation set, the diagnostic model was indirectly evaluated based on preoperative ultrasound imaging features to explore the feasibility and reliability of diagnosing high-risk PTMC through preoperative ultrasound imaging features. A total of 1628 patients were included in the training set, and 530 patients were included in the test set. The independent risk factors for pathological high-risk PTMC were sex, age, tumor maximum diameter, tumor invasive, and cervical lymph nodes (P<0.05). The C-index of the nomogram constructed based on these five factors was 0.947, with an optimal sensitivity of 96.7% and a specificity of 86.0%. The calibration curve showed that the model had high consistency. The area under the curve (AUC) value of the ROC curve for high-risk PTMC predicted by the risk score based on ultrasound features was 0.824 [95% CI (0.789, 0.860)], which was highly consistent with the risk score based on pathological features (κ= 0.758, P<0.05). Indirect evaluation of a high-risk PTMC diagnostic model based on preoperative ultrasound imaging features had high predictive efficiency and potential value for clinical application.

Multi-omics analysis and response prediction of PD-1 monoclonal antibody containing regimens in patients with relapsed/refractory diffuse large B-cell lymphoma

Patients with relapsed/refractory (r/r) diffuse large B-cell lymphoma (DLBCL) show varied responses to PD-1 monoclonal antibody (mAb) containing regimens. The mechanisms and predictive biomarkers for the efficacy of this regimen are unclear. This study retrospectively collected r/r DLBCL patients who received PD-1 mAb and rituximab regimens as salvage therapy. Clinical and genomic features were collected, and mechanisms were explored by multiplex immunofluorescence and digital spatial profiling. An artificial neural network (ANN) model was constructed to predict the response. Between October 16th, 2018 and May 4th, 2023, 50 r/r DLBCL patients were collected, 29 were response patients and 21 were non-response patients. CREBBP (p = 0.029) and TP53 (p = 0.015) alterations were statistically higher in non-response patients. Patients with PD-L1 CPS ≥ 5 were correlated with a longer overall survival (OS) than those with PD-L1 CPS < 5 (median OS: not reached vs. 9.7 months, hazard ratio [HR]: 3.8, 95% confidence interval [CI] 0.64–22.44, p = 0.016). Immune-related pathways were activated in response patients. The proportion and spatial organization of tumor-infiltrating immune cells affect the response. PD-L1 CPS level, age, and alterations of TP53, MYD88, CREBBP, EP300, GNA13 were used to build an ANN predictive model that showed high prediction efficiency (training set area under curve [AUC] of 0.97 and test set AUC of 0.94). The proportion and spatial distribution of tumor-infiltrating immune cells may be related to the function of immune-related pathways, thereby influencing the efficacy of PD-1 mAb containing regimens. The ANN predictive model showed potential value in predicting the responses of r/r DLBCL patients received PD-1 mAb and rituximab regimens.

Preoperative monocyte-to-lymphocyte ratio as a prognosis predictor after curative hepatectomy for intrahepatic cholangiocarcinoma

BackgroundSeveral inflammatory indicators have been reported to have predictive value in many types of malignant cancer. This research was aimed to explore the ability of the monocyte-to-lymphocyte ratio (MLR) to predict prognosis in patients with intrahepatic cholangiocarcinoma (ICC) who subjected to curative hepatectomy.MethodsThis retrospective analysis included 196 patients with ICC who underwent curative hepatectomy between May 2018 and April 2023. The predictive abilities of the preoperative MLR in assessing overall survival (OS) and disease-free survival (DFS) in those patients were compared with other inflammation-based scores, including monocyte-to-white ratio, neutrophil-to-lymphocyte ratio, neutrophil-to-white ratio, platelet-to-lymphocyte ratio, platelet-to-white ratio, and systemic immune-inflammation index, as well as tumor markers, like carcinoembryonic antigen (CEA) and carbohydrate antigen 19 − 9 (CA19-9).ResultsThe area under the time-dependent receiver operating characteristic curve indicated that the preoperative MLR had higher predictive efficiency in contrast with other inflammation-based scores and tumor markers in assessing OS and DFS. Stratifying patients according to the optimal cut-off value for the preoperative MLR, the data showed that both OS and DFS in the high MLR group were significantly worse than those in the low MLR group (p < 0.05 for all). Univariable and multivariable Cox analyses revealed that the preoperative MLR was an independent risk factor for OS and DFS in patients with ICC. In addition to predicting OS in patients with high CEA levels and predicting DFS in patients with high CA19-9 levels, patients with different CEA and CA19-9 levels were divided into completely different OS and DFS subgroups based on the risk stratification of the preoperative MLR.ConclusionsOur results demonstrated that the preoperative MLR was a good prognosis indicator to predict DFS and OS following curative hepatectomy in patients with ICC.

Multi-view learning framework for predicting unknown types of cancer markers via directed graph neural networks fitting regulatory networks.

The discovery of diagnostic and therapeutic biomarkers for complex diseases, especially cancer, has always been a central and long-term challenge in molecular association prediction research, offering promising avenues for advancing the understanding of complex diseases. To this end, researchers have developed various network-based prediction techniques targeting specific molecular associations. However, limitations imposed by reductionism and network representation learning have led existing studies to narrowly focus on high prediction efficiency within single association type, thereby glossing over the discovery of unknown types of associations. Additionally, effectively utilizing network structure to fit the interaction properties of regulatory networks and combining specific case biomarker validations remains an unresolved issue in cancer biomarker prediction methods. To overcome these limitations, we propose a multi-view learning framework, CeRVE, based on directed graph neural networks (DGNN) for predicting unknown type cancer biomarkers. CeRVE effectively extracts and integrates subgraph information through multi-view feature learning. Subsequently, CeRVE utilizes DGNN to simulate the entire regulatory network, propagating node attribute features and extracting various interaction relationships between molecules. Furthermore, CeRVE constructed a comparative analysis matrix of three cancers and adjacent normal tissues through The Cancer Genome Atlas and identified multiple types of potential cancer biomarkers through differential expression analysis of mRNA, microRNA, and long noncoding RNA. Computational testing of multiple types of biomarkers for 72 cancers demonstrates that CeRVE exhibits superior performance in cancer biomarker prediction, providing a powerful tool and insightful approach for AI-assisted disease biomarker discovery.

Network traffic prediction based on PSO-LightGBM-TM

Network traffic prediction is critical in wireless network management by allowing a good estimate of the traffic trend, which is also an important approach for detecting traffic anomalies in order to enhance network security. Deep-learning-based method has been widely adopted to predict network traffic matrix (TM) though with the main drawbacks in high complexity and low efficiency. In this paper, we propose a traffic prediction model based on Particle Swarm Optimization (PSO) and LightGBM (PSO-LightGBM-TM), which optimizes the LightGBM parameters for each network flow by PSO so that LightGBM can adapt to each of the network traffic flow. Compared with existing commonly used deep learning models, our model has a more straightforward structure and yet outperforms existing deep learning models. Sufficient comparison tests on three real network traffic datasets, Abilene, GÉANT, and CERNET have been conducted, and the results show that our model provides more accurate results and higher prediction efficiency.

Efficiency evaluation of dual-energy CT to predict the postoperative early recurrence of pancreatic ductal adenocarcinoma

ObjectivesTo evaluate the efficacy of quantitative parameters from dual-energy CT (DECT) and basic CT features in predicting the postoperative early recurrence (ER) of pancreatic ductal adenocarcinoma (PDAC). MethodsIn this study, patients with PDAC who underwent radical resection and DECT from 2018 to 2022 were enrolled and categorised into ER and non-ER groups. The clinical data, basic CT features and DECT parameters of all patients were analyzed. Independent predictors of ER were identified with Logistic regression analyses. Three models (model A: basic CT features; model B: DECT parameters; model C: basic CT features + DECT parameters) were established. Receiver operating characteristic curve analysis was utilized to evaluate predictive performance. ResultsA total of 150 patients were enrolled (ER group: n = 63; non-ER group: n = 87). Rim enhancement (odds ratio [OR], 3.32), peripancreatic strands appearance (OR, 2.68), electron density in the pancreatic parenchymal phase (P-Rho; OR, 0.90), arterial enhancement fraction (AEF; OR, 0.05) and pancreatic parenchyma fat fraction in the delayed phase (OR, 1.25) were identified as independent predictors of ER. Model C showed the highest area under the curve of 0.898. In addition, the corresponding ER risk factors were identified separately for resectable and borderline resectable PDAC subgroups. ConclusionsDECT quantitative parameters allow for the noninvasive prediction of postoperative ER in patients with PDAC, and the combination of DECT parameters and basic CT features shows a high prediction efficiency. Our model can help to identify patients with high-risk factors to guide preoperative decision making.

Machine learning based prognostics and statistical optimization of the performance of biogas-biodiesel blends powered engine

In this study, waste biomass-derived biogas was employed as the main fuel while the biodiesel-diesel blend was used as pilot fuel. This paper describes the development of a Decision Tree and Response Surface methodology-based statistical framework for prediction modeling and optimization. The compression ratio, fuel injection time, fuel injection pressure, and biogas flow rate were employed as controllable inputs, and brake thermal efficiency, peak combustion pressure, and exhaust emission were selected as responses. The experimental data for model development was gathered for the development of prediction models and optimization. The decision tree-based models were robust with almost negligible mean squared errors and R2 values of more than 0.9487 for all models. Response surface methodology-based optimized engine parameters were validated with the following results compression ratio was 17.9, fuel injection pressure was 225 bar, fuel injection timing was 26.3-degree crank angle after top dead center, and the biogas flow rate was 0.85 kg/h. Validation results were within 5 % of the model-optimized results. The prognostic models for all control factors were developed with decision tree-based machine learning with high predictive efficiency and low errors.

An attention-neural-processes approach to reconstructing unsteady water load for seaplanes

The distribution of holographic unsteady water load offers important information for evaluating the hydrodynamic performance of seaplanes. However, traditional tank test is limited by the number of sensors that can be deployed on the bottom of hull, thus only providing sparse data for estimating load distribution and leading to inaccurate evaluation of seaplane performance. To achieve accurate and rapid reconstruction of holographic load distribution, a machine learning load-reconstruction model based on Attention Neural Processes is proposed. This model performs spatiotemporal modeling of seaplane water load utilizing sparse sensor data. It directly learns the load patterns across multiple time steps and employs Attention modules to capture the spatial distribution of load. Comparisons with alternative methods demonstrate the model's superior ability to simultaneously capture spatial and temporal dependencies of the unsteady load data. In addition, the model's robust generalization capability is also validated by reducing the number of sensors in the training data. The results indicate that the proposed model exhibits high prediction efficiency, accuracy, and generalization for the reconstruction of unsteady water load distribution, which is of great significance for comprehensively evaluating the hydrodynamic performance of seaplanes.

Intratumoral and peritumoral radiomics combined with computed tomography features for predicting the invasiveness of lung adenocarcinoma presenting as a subpleural ground-glass nodule with a consolidation-to-tumor ratio ≤50.

Preoperative accurate judgment of the degree of invasiveness in subpleural ground-glass lung adenocarcinoma (LUAD) with a consolidation-to-tumor ratio (CTR) ≤50% is very important for the choice of surgical timing and planning. This study aims to investigate the performance of intratumoral and peritumoral radiomics combined with computed tomography (CT) features for predicting the invasiveness of LUAD presenting as a subpleural ground-glass nodule (GGN) with a CTR ≤50%. A total of 247 patients with LUAD from our hospital were randomly divided into two groups, i.e., the training cohort (n=173) and the internal validation cohort (n=74) (7:3 ratio). Furthermore, 47 patients from three other hospitals were collected as the external validation cohort. In the training cohort, the differences in clinical-radiological features were compared using univariate and multivariate analyses. The gross tumor volume (GTV) and gross peritumoral tumor volume (GPTV5, GPTV10, and GPTV15) radiomics models were constructed based on intratumoral and peritumoral (5, 10, and 15 mm) radiomics features. Additionally, the radscore of the best radiomics model and clinical risk factors were used to construct a combined model and the predictive efficacy of the model was evaluated in the validation cohorts. Finally, the receiver operating characteristics (ROC) curve and area under the curve (AUC) value were used to evaluate the discriminative ability of the model. Tumor size and CTR were independent risk factors for predicting the invasiveness of LUAD. The GPTV10 model outperformed the other radiomics models, with AUC values of 0.910, 0.870, and 0.887 in the three cohorts. The AUC values of the combined model were 0.912, 0.874, and 0.892. A nomogram based on GPTV10-radscore, tumor size, and CTR exhibited high predictive efficiency for predicting the invasiveness of LUAD.

Analysis of Risk Factors of Postoperative Arrhythmia in Patients with Coronary Heart Disease and Establishment of Nomogram Risk Model

Background: To explore the risk factors of postoperative arrhythmia in patients with coronary heart disease (CHD) and to establish a Nomogram model for predicting the risk of postoperative arrhythmia in CHD patients. Methods: Retrospectively, the medical data of CHD patients (from January 2021 to January 2024, n = 390) were collected. According to whether arrhythmia occurred after percutaneous coronary intervention surgery, patients were divided into the arrhythmia group (n = 130) and non-arrhythmia group (n = 260). The risk factors of postoperative arrhythmia were obtained by multi-factor logistic regression analysis. A Nomogram model for predicting the risk of postoperative arrhythmia in CHD patients was established using R language and underwent verification. Results: The results of multi-factor logistic regression analysis showed that diastolic pressure, heart function grade at III–IV, creatinine, C-reactive protein (CRP), N-terminal pro-brain natriuretic peptide (NT-ProBNP) peak value, total bilirubin (TBIL) and red cell distribution width (RDW) were the risk factors inducing postoperative arrhythmia in CHD patients. Based on these risk factors, a Nomogram model was successfully established. The verification results revealed that the predicted values were basically consistent with the actual values, indicating that the Nomogram model had good prediction ability. The area under the curve (AUC) value was 0.974, suggesting the high prediction efficiency of Nomogram model. Conclusion: Diastolic pressure, heart function grade at III–IV, creatinine, CRP, NT-ProBNP peak value, TBIL and RDW are the risk factors of postoperative arrhythmia in CHD patients. Nomogram model based on these risk factors has good prediction efficiency and underlying clinical value.

Gear Fault Detection Method Based on Convex Hull Clustering of Autoencoder’s Latent Space

This paper presents a method of pitting failure detection in toothed gears based on the reconstruction of the gear case vibrational signal. The effectiveness of the proposed method was tested in an experiment on a power circulation test stand. The autoencoder deep neural network architecture, semi-supervised training, and validation, along with the latent data convex hull-based clustering, are presented. The proposed method offers high efficiency (0.99 F1-measure) in gear state prediction (100% in failure detection, 98.9% in normal state prediction) and provides more capabilities in terms of generalization in comparison with linear machine learning techniques such as principal component analysis and nonlinear like the generative adversarial network. Moreover, it is distinguished by high sensitivity while also being able to detect even slight surface damage (initial pitting). These findings will be of particular relevance to a range of scientists and practitioners working with gear drives who are willing to implement machine learning in signal processing and diagnosis.

Development and validation of a social alienation predictive model for older maintenance hemodialysis patients based on latent profile analysis—a cross-sectional study

BackgroundSocial alienation refers to the state of feeling isolated, helpless, and unsatisfied due to maintaining distance from others or avoiding social interaction and activities. This phenomenon is caused by a lack of social skills, social anxiety, physical health problems, and other reasons. Older maintenance hemodialysis patients are exposed to a higher risk of social alienation. However, previous studies have been performed using the total score of the scale, which does not allow the identification of the characteristics of various patient groups with different levels of social alienation. In contrast, latent profile analysis can classify individuals into different categories based on continuous observational indicators, which improves accuracy and provides a more objective assessment by accounting for the uncertainty of variables. Given the concealed nature of social alienation and the differences in characteristics and treatment measures between different profiles, developing a predictive model for social alienation in older maintenance hemodialysis patients holds significance.ObjectiveTo explore the latent profile analysis of social alienation in older maintenance hemodialysis patients and to develop and validate a predictive model for social alienation in this population.MethodsA total of 350 older maintenance hemodialysis patients were selected as the study subjects using convenience sampling. A cross-sectional survey was conducted using a general information questionnaire, the Generalized Alienation Scale, and the Self-Perceived Burden Scale. Based on the results of the Generalized Alienation Scale, a latent profile analysis was performed, followed by univariate analysis and multinomial logistic regression to develop a predictive model. The effectiveness of the predictive model was evaluated in terms of its authenticity, reliability, and predictive ability.ResultsThree hundred nineteen valid questionnaires were collected. The social alienation of older maintenance hemodialysis patients based on latent profile analysis were divided into three profiles, which were named the low/medium/high-symptom groups, comprising 21%, 38.9%, and 40.1% of participants, respectively. Based on male, monthly social activity hours, Age-Adjusted Charlson Comorbidity Index, dialysis age, and Self-Perceived Burden Scale, a predictive model of social alienation for older maintenance hemodialysis patients was developed, and the Hosmer–Lemeshow tests showed no statistical significance (P > 0.05). The model has high predictive efficiency in authenticity, reliability and predictability.ConclusionOlder maintenance hemodialysis patients exhibited moderate to high levels of social alienation. The latent profile analysis based method was used to divide patients into low/medium/high-symptom profiles, and the predictive model demonstrates excellent authenticity, reliability, and predictability.

CT-based radiomics analysis of different machine learning models for differentiating gnathic fibrous dysplasia and ossifying fibroma.

In this study, our aim was to develop and validate the effectiveness of diverse radiomic models for distinguishing between gnathic fibrous dysplasia (FD) and ossifying fibroma (OF) before surgery. We enrolled 220 patients with confirmed FD or OF. We extracted radiomic features from nonenhanced CT images. Following dimensionality reduction and feature selection, we constructed radiomic models using logistic regression, support vector machine, random forest, light gradient boosting machine, and eXtreme gradient boosting. We then identified the best radiomic model using receiver operating characteristic (ROC) curve analysis. After combining radiomics features with clinical features, we developed a comprehensive model. ROC curve and decision curve analysis (DCA) demonstrated the models' robustness and clinical value. We extracted 1834 radiomic features from CT images, reduced them to eight valuable features, and achieved high predictive efficiency, with area under curves (AUC) exceeding 0.95 for all the models. Ultimately, our combined model, which integrates radiomic and clinical data, displayed superior discriminatory ability (AUC: training cohort 0.970; test cohort 0.967). DCA highlighted its optimal clinical efficacy. Our combined model effectively differentiates between FD and OF, offering a noninvasive and efficient approach to clinical decision-making.

A parameterised model for link prediction using node centrality and similarity measure based on graph embedding

Link prediction is a crucial aspect of graph machine learning, with applications as diverse as disease prediction, social network recommendations, and drug discovery. It involves the prediction of potential new links between nodes within a network. Despite its importance, current models for link prediction exhibit notable limitations. Graph Convolutional Networks have shown high efficiency in link prediction across various datasets. However, they face significant challenges when applied to short-path networks and ego networks, resulting in poor performance. This issue represents a critical area of concern that our work seeks to address. This paper introduces the Node Centrality and Similarity-based Parameterised Model (NCSM), a novel method for link prediction tasks. NCSM uniquely integrates node centrality and similarity measures as edge features in a customised Graph Neural Network (GNN) layer, effectively leveraging the topological information of large networks. This model represents the first parameterised GNN-based link prediction model that considers topological information. The proposed model was evaluated on five benchmark graph datasets, each comprising thousands of nodes and edges. Experimental results highlight NCSM's superiority over existing state-of-the-art models like Graph Convolutional Networks and Variational Graph Autoencoder, as it outperforms them across various metrics and datasets. This exceptional performance can be attributed to NCSM's innovative integration of node centrality, similarity measures, and its efficient use of topological information.

Hybrid Intelligent Control System for Adaptive Microgrid Optimization: Integration of Rule-Based Control and Deep Learning Techniques

Microgrids (MGs) have evolved as critical components of modern energy distribution networks, providing increased dependability, efficiency, and sustainability. Effective control strategies are essential for optimizing MG operation and maintaining stability in the face of changing environmental and load conditions. Traditional rule-based control systems are extensively used due to their interpretability and simplicity. However, these strategies frequently lack the flexibility for complex and changing system dynamics. This paper provides a novel method called hybrid intelligent control for adaptive MG that integrates basic rule-based control and deep learning techniques, including gated recurrent units (GRUs), basic recurrent neural networks (RNNs), and long short-term memory (LSTM). The main target of this hybrid approach is to improve MG management performance by combining the strengths of basic rule-based systems and deep learning techniques. These deep learning techniques readily enhance and adapt control decisions based on historical data and domain-specific rules, leading to increasing system efficiency, stability, and resilience in adaptive MG. Our results show that the proposed method optimizes MG operation, especially under demanding conditions such as variable renewable energy supply and unanticipated load fluctuations. This study investigates special RNN architectures and hyperparameter optimization techniques with the aim of predicting power consumption and generation within the adaptive MG system. Our promising results show the highest-performing models indicating high accuracy and efficiency in power prediction. The finest-performing model accomplishes an R2 value close to 1, representing a strong correlation between predicted and actual power values. Specifically, the best model achieved an R2 value of 0.999809, an MSE of 0.000002, and an MAE of 0.000831.

Prediction of Diffuse Attenuation Coefficient Based on Informer: A Case Study of Hangzhou Bay and Beibu Gulf

Marine water quality significantly impacts human livelihoods and production such as fisheries, aquaculture, and tourism. Satellite remote sensing facilitates the predictions of large-area marine water quality without the need for frequent field work and sampling. Prediction of diffuse attenuation coefficient (Kd), which describes the speed at which light decays as it travels through water, obtained from satellite-derived ocean color products can reflect the overall water quality trends. However, current models inadequately explore the complex nonlinear features of Kd, and there are difficulties in achieving accurate long-term predictions and optimal computational efficiency. This study innovatively proposes a model called Remote Sensing-Informer-based Kd Prediction (RSIKP). The proposed RSIKP is characterized by a distinctive Multi-head ProbSparse self-attention mechanism and generative decoding structure. It is designed to comprehensively and accurately capture the long-term variation characteristics of Kd in complex water environments while avoiding error accumulation, which has a significant advantage in multi-dataset experiments due to its high efficiency in long-term prediction. A multi-dataset experiment is conducted at different prediction steps, using 70 datasets corresponding to 70 study areas in Hangzhou Bay and Beibu Gulf. The results show that RSIKP outperforms the five prediction models based on Artificial Neural Networks (ANN, Convolutional Neural Networks (CNN), Gated Recurrent Unit (GRU), Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN), and Long Short-Term Memory Networks (LSTM)). RSIKP captures the complex influences on Kd more effectively to achieve higher prediction accuracy compared to other models. It shows a mean improvement of 20.6%, 31.1%, and 22.9% on Mean Absolute Error (MAE), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE). Particularly notable is its outstanding performance in the long time-series predictions of 60 days. This study develops a cost-effective and accurate method of marine water quality prediction, providing an effective prediction tool for marine water quality management.

Prediction Model for Trends in Submarine Cable Burial Depth Variation Considering Dynamic Thermal Resistance Characteristics

Fault problems associated with submarine cables caused by variations in their burial depth are becoming increasingly prominent. To address the difficulty of detecting the burial depth of submarine cables and trends in its variation, a prediction model for submarine cable burial depth was proposed which considers the dynamic characteristics of thermal resistance. First, a parallel thermal circuit model of a three-core submarine cable was established, and a formula for calculating the submarine cable’s burial depth was derived based on a formula for calculating the submarine cable’s core temperature. Then, the calculation result was corrected by considering the dynamic characteristics of the thermal resistance of the submarine cable’s structural materials. On this basis, feature vectors associated with the seabed cable burial depth calculation data and time nodes were mined by a convolutional neural network and used as the input parameters of a long short-term memory network for optimization and training, and a prediction model for trends in seabed cable burial depth variation was obtained. Finally, an example analysis was carried out based on the actual electrical parameter data of submarine cables buried by an offshore oil and gas platform. The results showed that the prediction model for trends in variations in the burial depth of submarine cables based on the CNN-LSTM neural network can achieve high prediction accuracy and prediction efficiency.