Search

Abstract Background Electronic Health Records (EHR) are widely used to develop clinical prediction models (CPMs). However, one of the challenges is that there is often a degree of informative missing data. For example, laboratory measures are typically taken when a clinician is concerned that there is a need. When data are the so-called Not Missing at Random (NMAR), analytic strategies based on other missingness mechanisms are inappropriate. In this work, we seek to compare the impact of different strategies for handling missing data on CPMs performance. Methods We considered a predictive model for rapid inpatient deterioration as an exemplar implementation. This model incorporated twelve laboratory measures with varying levels of missingness. Five labs had missingness rate levels around 50%, and the other seven had missingness levels around 90%. We included them based on the belief that their missingness status can be highly informational for the prediction. In our study, we explicitly compared the various missing data strategies: mean imputation, normal-value imputation, conditional imputation, categorical encoding, and missingness embeddings. Some of these were also combined with the last observation carried forward (LOCF). We implemented logistic LASSO regression, multilayer perceptron (MLP), and long short-term memory (LSTM) models as the downstream classifiers. We compared the AUROC of testing data and used bootstrapping to construct 95% confidence intervals. Results We had 105,198 inpatient encounters, with 4.7% having experienced the deterioration outcome of interest. LSTM models generally outperformed other cross-sectional models, where embedding approaches and categorical encoding yielded the best results. For the cross-sectional models, normal-value imputation with LOCF generated the best results. Conclusion Strategies that accounted for the possibility of NMAR missing data yielded better model performance than those did not. The embedding method had an advantage as it did not require prior clinical knowledge. Using LOCF could enhance the performance of cross-sectional models but have countereffects in LSTM models.

Background: Cuproptosis may represent a potential biomarker for predicting prognosis and immunotherapy response, but the available evidence is insufficient. Methods: The multiple single-cell RNA sequencing (scRNA-seq) datasets were analyzed to investigate the specific occurrence of cuproptosis in distinct cell populations. Utilizing 28 scRNA-seq datasets, TCGA pan-cancer cohort, and 10 immunotherapy cohorts, we developed a cuproptosis signature (Cup.Sig). This signature was used to construct prediction models for immunotherapy response and identify potential prognostic biomarkers for pan-cancer using 11 different machine learning algorithms. Results: Malignant cells demonstrate the higher cuproptosis scores in comparison to other cell types across diverse cancer types. The Cup.Sig exhibits significant associations with cancer hallmarks and immune cell response in multiple cancer types. Leveraging the Cup.Sig, the robust pan-cancer immunotherapy prediction model and prognostic biomarker have been established and validated using diverse datasets from various platforms. Conclusions: We developed a pan-cancer cuproptosis signature for predicting survival and immunotherapy response.

The left-lateral Altyn Tagh Fault (ATF) system is the northern boundary of the Qinghai-Xizang Plateau, separating the Tarim Basin and the Qaidam Basin. The middle section of ATF has not recorded any large earthquakes since 1598 AD, so the potential seismic hazard is unclear. We develope an earthquake catalog using continuous waveform data recorded by the Tarim-Altyn-Qaidam dense nodal seismic array from September 17 to November 23, 2021 in the middle section of ATF. With the machine learning-based picker, phase association, location, match and locate workflow, we detecte 233 earthquakes with ML -1–3, far more than 6 earthquakes in the routine catalog. Combining with focal mechanism solutions and the local fault structure, we find that seismic events are clustered along the ATF with strike-slip focal mechanisms and on the southern secondary faults with thrusting focal mechanisms. This overall seismic activity in the middle section of the ATF might be due to the northeastward transpressional motion of the Qinghai-Xizang Plateau block at the western margin of the Qaidam Basin.

Abstract Background For medullary thyroid carcinoma (MTC) with no positive findings in the lateral neck before surgery, whether prophylactic lateral neck dissection (LND) is needed remains controversial. A better way to predict occult metastasis in the lateral neck is needed. Methods From January 2010 to January 2022, patients who were diagnosed with MTC and underwent primary surgery at our hospital were retrospectively reviewed. We collected the patients' baseline characteristics, surgical procedure, and rescored the ultrasound images of the primary lesions using American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI‐RADS). Regularized logistic regression, 5‐fold cross‐validation and decision curve analysis was applied for lateral lymph node metastasis (LLNM) model's development and validation. Then, we tested the predictive ability of the LLNM model for occult LLNM in cN0−1a patients. Results A total of 218 patients were enrolled. Five baseline characteristics and two TI‐RADS features were identified as high‐risk factors for LLNM: gender, baseline calcitonin (Ctn), tumor size, multifocality, and central lymph node (CLN) status, as well as TI‐RADS margin and level. A LLNM model was developed and showed a good discrimination with 5‐fold cross‐validation mean area under curve (AUC) = 0.92 ± 0.03 in the test dataset. Among cN0−1a patients, our LLNM model achieved an AUC of 0.91 (95% CI, 0.88–0.94) for predicting occult LLNM, which was significantly higher than the AUCs of baseline Ctn (0.83) and CLN status (0.64). Conclusions We developed a LLNM prediction model for MTC using machine learning based on clinical baseline characteristics and TI‐RADS. Our model can predict occult LLNM for cN0−1a patients more accurately, then benefit the decision of prophylactic LND.

Summary: Automatically and accurately segmenting skin lesions can be challenging, due to factors such as low contrast and fuzzy boundaries. This paper proposes a hybrid encoder-decoder model (CTH-Net) based on convolutional neural network (CNN) and Transformer, capitalizing on the advantages of these approaches. We propose three modules for skin lesion segmentation and seamlessly connect them with carefully designed model architecture. Better segmentation performance is achieved by introducing SoftPool in the CNN branch and sandglass block in the bottleneck layer. Extensive experiments were conducted on four publicly accessible skin lesion datasets, ISIC 2016, ISIC 2017, ISIC 2018, and PH2 to confirm the efficacy and benefits of the proposed strategy. Experimental results show that the proposed CTH-Net provides better skin lesion segmentation performance in both quantitative and qualitative testing when compared with state-of-the-art approaches. We believe the CTH-Net design is inspiring and can be extended to other applications/frameworks.

Surface-Enhanced Raman Spectroscopy (SERS) is a powerful analytical technique for detecting trace analytes using noble metal nanoparticles. In this paper, we present a novel approach to construct a high-performance SERS sensing platform using self-assembled gold nanoparticles on aminated glass capillaries. The surface self-assembly technology ensures uniformity and repeatability of the SERS substrate, addressing the challenges of poor reproducibility observed in conventional methods. The 30 nm gold nanoparticles exhibit excellent plasmonic properties and biocompatibility, making them ideal candidates for SERS applications. We conducted SERS detection using Rhodamine 6G (R6G) as probe molecules, achieving a minimum detectable concentration of 0.1 nM for the AuNPs/GS substrate and 0.1 pM for the S-AuNPs/GC substrate. The S-AuNPs/GC substrate demonstrated commendable uniformity and repeatability, with a relative standard deviation of 12.1 %. Machine learning techniques, including baseline correction, normalization, and smoothing, were employed for data processing, enhancing the accuracy and reliability of the SERS analysis. By employing the K-means clustering algorithm, we identified three distinct groups of spectral characteristics. Additionally, Principal Component Analysis (PCA) allowed visualization and understanding of the clustering results in a two-dimensional space, capturing approximately 86.74 % of the data's variance. The successful construction of a high-performance SERS sensing platform with enhanced sensitivity, accuracy, and reliability, assisted by machine learning, holds great potential for various applications in chemical sensing, environmental monitoring, and biomedical diagnostics.

Model predictive control is an effective approach for microgrid energy management. However, the main downside of such method is its expensive online computational cost, which is not amenable to most practical microgrid implementations. To address this issue, we propose a deep neural network assisted column generation approach that can accelerate the solution procedure of model predictive control. In each iteration, our approach leverages different deep neural networks to predict the optimal solutions of all the subproblems in column generation, which can accelerate the computation of all the subproblems and the entire process of column generation. The pre-existing knowledge of the microgrid is also exploited to guarantee the feasibility of the neural network outputs using multi-parametric programming theory. The numerical results show that our approach leads to a reduction in computational time of approximately 50% in a medium-sized microgrid compared with the full mixed integer solution based on traditional branch and bound method, while the optimality loss is only 0.02% in terms of operating costs.

Structural disclosure of biological materials can help our understanding of design disciplines in nature and inspire research for artificial materials. Synchrotron microfocus X-ray diffraction is one of the main techniques for characterizing hierarchically structured biological materials, especially the 3D orientation distribution of their interpenetrating nanofiber networks. However, extraction of 3D fiber orientation from X-ray patterns is still carried out by iterative parametric fitting, with disadvantages of time consumption and demand for expertise and initial parameter estimates. When faced with high-throughput experiments, existing analysis methods cannot meet the real time analysis challenges. In this work, using the assumption that the X-ray illuminated volume is dominated by two groups of nanofibers in a gradient biological composite, a machine-learning based method is proposed for fast and automatic fiber orientation metrics prediction from synchrotron X-ray micro-focused diffraction data. The simulated data were corrupted in the training procedure to guarantee the prediction ability of the trained machine-learning algorithm in real-world experimental data predictions. Label transformation was used to resolve the jump discontinuity problem when predicting angle parameters. The proposed method shows promise for application in the automatic data-processing pipeline for fast analysis of the vast data generated from multiscale diffraction-based tomography characterization of textured biomaterials.

Remediation projects of DNAPL-contaminated groundwater generally face difficulties of low contaminant removal rate and high remediation cost. Hence, a machine-learning-assisted mixed-integer multi-objective optimization technique was presented for efficiently programming remediation strategies. A swarm intelligence multi-kernel extreme learning machine (SI-MKELM) was proposed to build a reliable intelligent surrogate model of the multiphase flow numerical simulation model for reducing the computational cost of repetitive CPU-demanding remediation efficiency evaluations, and a hyper-heuristic homotopy algorithm was developed for progressively searching the global optimum of the remediation strategy. The results showed that: (1) The multi-kernel extreme learning machine improved by swarm intelligence algorithm significantly improved the approximation accuracy to the numerical model, and the mean residual and mean relative error were only 0.7596% and 1.0185%, respectively. (2) It only took 0.1 s to run the SI-MKELM. Replacing the numerical model with SI-MKELM considerably reduced the computational burden of the simulation–optimization process and maintained high computational accuracy for optimizing the DNAPL-contaminated aquifer remediation strategy. (3) The hyper-heuristic homotopy algorithm was capable of progressively searching the global optimum, and avoiding premature convergence in the optimization process. It effectively improved the searching ability of the traditional heuristic algorithms. HIGHLIGHTS A swarm intelligence multi-kernel extreme learning machine is proposed to sufficiently approximate the multiphase flow numerical model.; A mixed-integer multi-objective model is established to realize the comprehensive SEAR strategy optimization.; A hyper-heuristic homotopy algorithm is constructed as a more efficient tool for progressively searching the global optimum in wide areas.;

Dense-repeated jamming is highly related to the radar-transmitted signal, and it has suppression and deception jamming effects, which makes detecting the real target difficult for a radar system and seriously threatens the operational capability of radar. To solve this problem, an intelligent suppression method based on the Support Vector Machine (SVM) is proposed in this paper. The optimal SVM model is obtained through offline training on a random sample set to intelligently identify and classify targets and interference. Then, the interference sidelobe in the target range unit is further suppressed by smoothing filtering. Finally, high-resolution two-dimensional reconstruction is performed based on Compress Sensing (CS) theory to estimate the target parameter information. Simulation experiments and measured data processing results reveal that the proposed algorithm can effectively suppress dense-repeated jamming and accurately detect real targets in different scenarios.

This paper combines feature selection with machine learning algorithms to achieve object-oriented classification of crops in Gaofen-6 remote sensing images. The study provides technical support and methodological references for research on regional monitoring of food crops and precision agriculture management. “Staple-food-shifting” refers to the planting of other cash crops on cultivated land that should have been planted with staple crops such as wheat, rice, and maize, resulting in a change in the type of arable land cultivated. An accurate grasp of the spatial and temporal patterns of “staple-food-shifting” on arable land is an important basis for rationalizing land use and protecting food security. In this study, the Shihezi Reclamation Area in Xinjiang is selected as the study area, and Gaofen-6 satellite images are used to study the changes in the cultivated area of staple food crops and their regional distribution. Firstly, the images are segmented at multiple scales and four types of features are extracted, totaling sixty-five feature variables. Secondly, six feature selection algorithms are used to optimize the feature variables, and a total of nine feature combinations are designed. Finally, k-Nearest Neighbor (KNN), Random Forest (RF), and Decision Tree (DT) are used as the basic models of image classification to explore the best combination of feature selection method and machine learning model suitable for wheat, maize, and cotton classification. The results show that our proposed optimal feature selection method (OFSM) can significantly improve the classification accuracy by up to 15.02% compared to the Random Forest Feature Importance Selection (RF-FI), Random Forest Recursive Feature Elimination (RF-RFE), and XGBoost Feature Importance Selection (XGBoost-FI) methods. Among them, the OF-RF-RFE model constructed based on KNN performs the best, with the overall accuracy, average user accuracy, average producer accuracy, and kappa coefficient reaching 90.68%, 87.86%, 86.68%, and 0.84, respectively.

Abstract Objectives To explore the diagnostic value of radiomics in differentiating between lung adenocarcinomas appearing as ground‐glass opacity nodules (GGO) with high‐ and low Ki‐67 expression levels. Materials and Methods From January 2018 to January 2021, patients with pulmonary GGO who received lung resection were evaluated for potential enrollment. The included GGOs were then randomly divided into a training cohort and a validation cohort with a ratio of 7:3. Logistic regression (LR), decision tree (DT), support vector machines (SVM), and adaboost (AB) were applied for radiomic model construction. Area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to evaluate the diagnostic efficacy of the established models. Results Seven hundred and sixty‐nine patients with 769 GGOs were included in this study. Two hundred and forty‐five GGOs were confirmed to be of high Ki‐67 labeling index (LI). In the training cohort, gender, age, spiculation sign, pleural indentation sign, bubble sign, and maximum 2D diameter of the nodule were found to be significantly different between high‐ and low Ki‐67 LI groups (p

Objective: Ferroptosis, a novel form of cell death, is closely associated with excessive iron accumulated within the substantia nigra in Parkinson’s disease (PD). Despite extensive research, the underlying molecular mechanisms driving ferroptosis in PD remain elusive. Here, we employed a bioinformatics and machine learning approach to predict the genes associated with ferroptosis in PD and investigate the interactions between natural products and their active ingredients with these genes.Methods: We comprehensively analyzed differentially expressed genes (DEGs) for ferroptosis associated with PD (PDFerDEGs) by pairing 3 datasets (GSE7621, GSE20146, and GSE202665) from the NCBI GEO database and the FerrDb V2 database. A machine learning approach was then used to screen PDFerDEGs for signature genes. We mined the interacted natural product components based on screened signature genes. Finally, we mapped a network combined with ingredients and signature genes, then carried out molecular docking validation of core ingredients and targets to uncover potential therapeutic targets and ingredients for PD.Results: We identified 109 PDFerDEGs that were significantly enriched in biological processes and KEGG pathways associated with ferroptosis (including iron ion homeostasis, iron ion transport and ferroptosis, etc.). We obtained 29 overlapping genes and identified 6 hub genes (TLR4, IL6, ADIPOQ, PTGS2, ATG7, and FADS2) by screening with two machine learning algorithms. Based on this, we screened 263 natural product components and subsequently mapped the “Overlapping Genes-Ingredients” network. According to the network, top 5 core active ingredients (quercetin, 17-beta-estradiol, glycerin, trans-resveratrol, and tocopherol) were molecularly docked to hub genes to reveal their potential role in the treatment of ferroptosis in PD.Conclusion: Our findings suggested that PDFerDEGs are associated with ferroptosis and play a role in the progression of PD. Taken together, core ingredients (quercetin, 17-beta-estradiol, glycerin, trans-resveratrol, and tocopherol) bind well to hub genes (TLR4, IL6, ADIPOQ, PTGS2, ATG7, and FADS2), highlighting novel biomarkers for PD.

BackgroundRecently, the incidence rate of renal fibrosis has been increasing worldwide, greatly increasing the burden on society. However, the diagnostic and therapeutic tools available for the disease are insufficient, necessitating the screening of potential biomarkers to predict renal fibrosis.MethodsUsing the Gene Expression Omnibus (GEO) database, we obtained two gene array datasets (GSE76882 and GSE22459) from patients with renal fibrosis and healthy individuals. We identified differentially expressed genes (DEGs) between renal fibrosis and normal tissues and analyzed possible diagnostic biomarkers using machine learning. The diagnostic effect of the candidate markers was evaluated using receiver operating characteristic (ROC) curves and verified their expression using Reverse transcription quantitative polymerase chain reaction (RT-qPCR). The CIBERSORT algorithm was used to determine the proportions of 22 types of immune cells in patients with renal fibrosis, and the correlation between biomarker expression and the proportion of immune cells was studied. Finally, we developed an artificial neural network model of renal fibrosis.ResultsFour candidate genes namely DOCK2, SLC1A3, SOX9 and TARP were identified as biomarkers of renal fibrosis, with the area under the ROC curve (AUC) values higher than 0.75. Next, we verified the expression of these genes by RT-qPCR. Subsequently, we revealed the potential disorder of immune cells in the renal fibrosis group through CIBERSORT analysis and found that immune cells were highly correlated with the expression of candidate markers.ConclusionDOCK2, SLC1A3, SOX9, and TARP were identified as potential diagnostic genes for renal fibrosis, and the most relevant immune cells were identified. Our findings provide potential biomarkers for the diagnosis of renal fibrosis.

Summary: Deep learning method is applied to spectral detection due to the advantage of not needing feature engineering. In this work, the deep neural network (DNN) model is designed to perform data mining on the laser-induced breakdown spectroscopy (LIBS) spectra of the ore. The potential of heat diffusion for an affinity-based transition embedding model is first used to perform nonlinear mapping of fully connected layer data in the DNN model. Compared with traditional methods, the DNN model has the highest recognition accuracy rate (75.92%). A training set update method based on DNN output is proposed, and the final model has a recognition accuracy of 85.54%. The method of training set update proposed in this work can not only obtain the sample labels quickly but also improve the accuracy of deep learning models. The results demonstrate that LIBS combined with the DNN model is a valuable tool for ore classification at a high accuracy rate.

Abstract Background An aging population with a burden of chronic diseases puts increasing pressure on health care systems. Early prediction of the hospital length of stay (LOS) can be useful in optimizing the allocation of medical resources, and improving healthcare quality. However, the data available at the point of admission (PoA) are limited, making it difficult to forecast the LOS accurately. Methods In this study, we proposed a novel approach combining network analytics and machine learning to predict the LOS in elderly patients with chronic diseases at the PoA. Two networks, including multimorbidity network (MN) and patient similarity network (PSN), were constructed and novel network features were created. Five machine learning models (eXtreme Gradient Boosting, Gradient Boosting Decision Tree, Random Forest, Linear Support Vector Machine, and Deep Neural Network) with different input feature sets were developed to compare their performance. Results The experimental results indicated that the network features can bring significant improvements to the performances of the prediction models, suggesting that the MN and PSN are useful for LOS predictions. Conclusion Our predictive framework which integrates network science with data mining can forecast the LOS effectively at the PoA and provide decision support for hospital managers, which highlights the potential value of network-based machine learning in healthcare field.

Background and purpose: Early detection, diagnosis, and treatment of colorectal cancer and its precancerous lesions can significantly improve patients' survival rates. The purpose of this research is to identify methylation markers specific to colorectal cancer tissues and validate their diagnostic capability in colorectal cancer and precancerous changes by measuring the level of DNA methylation in stool samples. Method: We analyzed samples from six cancer tissues and adjacent normal tissues and fecal samples from 758 participants, including 62 patients with interfering diseases. Bioinformatics databases were used to screen for candidate biomarkers for CRC, and quantitative methylation-specific PCR methods were applied for identification. The methylation levels of the candidate biomarkers in fecal and tissue samples were measured. Logistic regression and random forest models were built and validated using fecal sample data from one of the centers, and the independent or combined diagnostic value of the candidate biomarkers in fecal samples for CRC and precancerous lesions was analyzed. Finally, the diagnostic capability and stability of the model were validated at another medical center. Results: This study identified two colorectal cancer CpG sites with tissue specificity. These two biomarkers have certain diagnostic power when used individually, but their diagnostic value for colorectal cancer and colorectal adenoma is more significant when they are used in combination. Conclusion: The results indicate that a DNA methylation biomarker combined diagnostic model based on two CpG sites, cg13096260 and cg12587766, has the potential for screening and diagnosing precancerous lesions and colorectal cancer. Additionally, compared to traditional diagnostic models, machine learning algorithms perform better but may yield more false-positive results, necessitating further investigation. [ABSTRACT FROM AUTHOR]

Disulfide bonds, covalently formed by sulfur atoms in cysteine residues, play a crucial role in protein folding and structure stability. Considering their significance, artificial disulfide bonds are often introduced to enhance protein thermostability. Although an increasing number of tools can assist with this task, significant amounts of time and resources are often wasted owing to inadequate consideration. To enhance the accuracy and efficiency of designing disulfide bonds for protein thermostability improvement, we initially collected disulfide bond and protein thermostability data from extensive literature sources. Thereafter, we extracted various sequence‐ and structure‐based features and constructed machine‐learning models to predict whether disulfide bonds can improve protein thermostability. Among all models, the neighborhood context model based on the Adaboost‐DT algorithm performed the best, yielding "area under the receiver operating characteristic curve" and accuracy scores of 0.773 and 0.714, respectively. Furthermore, we also found AlphaFold2 to exhibit high superiority in predicting disulfide bonds, and to some extent, the coevolutionary relationship between residue pairs potentially guided artificial disulfide bond design. Moreover, several mutants of imine reductase 89 (IR89) with artificially designed thermostable disulfide bonds were experimentally proven to be considerably efficient for substrate catalysis. The SS‐bond data have been integrated into an online server, namely, ThermoLink, available at guolab.mpu.edu.mo/thermoLink. [ABSTRACT FROM AUTHOR]

The flow field distribution of compressor blades is critical to the performance of aero-engine. To efficiently obtain the aerodynamic loads on the blades, this study employs machine learning models to predict the aerodynamic characteristics of compressor blade surfaces. The predictive performances of these models are evaluated by applying random forest, multi-layer perceptron (MLP), one-dimensional convolutional neural network, and long short-term memory network based on simulation data of computational fluid dynamics (CFD). The results indicate that the MLP model performs exceptionally well among all test metrics, with its predictions closely matching the CFD simulation results. Further analysis using SHapley Additive exPlanations methods is performed to interpret the MLP model and reveal the importance of various input features. The research demonstrates the significant potential of machine learning methods in predicting the aerodynamics of compressor blades and providing accurate and reliable results. [ABSTRACT FROM AUTHOR]

Prediction of molecular parameters and material functions from the macroscopic viscoelastic properties of complex fluids are of great significance for molecular and formulation design in fundamental research as well as various industrial applications. A general learning method for computing molecular parameters of a viscoelastic constitutive model by solving an inverse problem is proposed. The accuracy, convergence and robustness of a deep neural network (DNN)-based numerical solver have been validated by considering the Rolie-Poly model for modeling the linear and non-linear steady rheometric properties of entangled polymer solutions in a wide range of concentrations. The results show that as long as the DNN could be trained with a sufficiently high accuracy, the DNN-based numerical solver would rapidly converge to its solution in solving an inverse problem. The solution is robust against small white noise disturbances to the input stress data. However, if the input stress significantly deviates from the original stress, the DNN-based solver could readily converge to a different solution. Hence, the resolution of the numerical solver for inversely computing molecular parameters is demonstrated. Moreover, the molecular parameters computed by the DNN-based numerical solver not only reproduce accurately the steady viscoelastic stress of completely monodisperse linear lambda DNA solutions over a wide range of shear rates and various concentrations, but also predict a power law concentration scaling with a nearly same scaling exponent as those estimated from experimental results.

Basalt fiber-reinforced concrete (BFRC) represents a form of high-performance concrete. In structural design, a 28-day resting period is required to achieve compressive strength. This study extended an extreme gradient boosting tree (XGBoost) hybrid model by incorporating genetic algorithm (GA) optimization, named GA-XGBoost, for the projection of compressive strength (CS) on BFRC. GA optimization may reduce many debugging efforts and provide optimal parameter combinations for machine learning (ML) algorithms. The XGBoost is a powerful integrated learning algorithm with efficient, accurate, and scalable features. First, we created and provided a common dataset using test data on BFRC strength from the literature. We segmented and scaled this dataset to enhance the robustness of the ML model. Second, to better predict and evaluate the CS of BFRC, we simultaneously used five other regression models: XGBoost, random forest (RF), gradient-boosted decision tree (GBDT) regressor, AdaBoost, and support vector regression (SVR). The analysis results of test sets indicated that the correlation coefficient and mean absolute error were 0.9483 and 2.0564, respectively, when using the GA-XGBoost model. The GA-XGBoost model demonstrated superior performance, while the AdaBoost model exhibited the poorest performance. In addition, we verified the accuracy and feasibility of the GA-XGBoost model through SHAP analysis. The findings indicated that the water–binder ratio (W/B), fine aggregate (FA), and water–cement ratio (W/C) in BFRC were the variables that had the greatest effect on CS, while silica fume (SF) had the least effect on CS. The results demonstrated that GA-XGBoost exhibits exceptional accuracy in predicting the CS of BFRC, which offers a valuable reference for the engineering domain.

ObjectiveThis cross-sectional research aims to develop reliable predictive short-term prediction models to predict the number of RTIs in Northeast China through comparative studies.MethodologySeasonal auto-regressive integrated moving average (SARIMA), Long Short-Term Memory (LSTM), and Facebook Prophet (Prophet) models were used for time series prediction of the number of RTIs inpatients. The three models were trained using data from 2015 to 2019, and their prediction accuracy was compared using data from 2020 as a test set. The parameters of the SARIMA model were determined using the autocorrelation function (ACF) and the partial autocorrelation function (PACF). The LSTM uses linear as the activation function, the mean square error (MSE) as the loss function and the Adam optimizer to construct the model, while the Prophet model is built on the Python platform. The root mean squared error (RMSE), mean absolute error (MAE) and Mean Absolute Percentage Error (MAPE) are used to measure the predictive performance of the model.FindingsIn this research, the LSTM model had the highest prediction accuracy, followed by the Prophet model, and the SARIMA model had the lowest prediction accuracy. The trend in medical expenditure of RTIs inpatients overlapped highly with the number of RTIs inpatients.ConclusionBy adjusting the activation function and optimizer, the LSTM predicts the number of RTIs inpatients more accurately and robustly than other models. Compared with other models, LSTM models still show excellent prediction performance in the face of data with seasonal and drastic changes. The LSTM can provide a better basis for planning and management in healthcare administration.ImplicationThe results of this research show that it is feasible to accurately forecast the demand for healthcare resources with seasonal distribution using a suitable forecasting model. The prediction of specific medical service volumes will be an important basis for medical management to allocate medical and health resources.

Ferroelectric tunnel junction (FTJ) has attracted considerable attention for its potential applications in nonvolatile memory and neuromorphic computing. However, the experimental exploration of FTJs with high ON/OFF ratios is a challenging task due to the vast search space comprising of ferroelectric and electrode materials, fabrication methods and conditions and so on. Here, machine learning (ML) is demonstrated to be an effective tool to guide the experimental search of FTJs with high ON/OFF ratios. A dataset consisting of 152 FTJ samples with nine features and one target attribute (i.e., ON/OFF ratio) is established for ML modeling. Among various ML models, the gradient boosting classification model achieves the highest prediction accuracy. Combining the feature importance analysis based on this model with the association rule mining, it is extracted that the utilizations of {graphene/graphite (Gra) (top), LaNiO3 (LNO) (bottom)} and {Gra (top), Ca[Formula: see text]Ce[Formula: see text]MnO3 (CCMO) (bottom)} electrode pairs are likely to result in high ON/OFF ratios in FTJs. Moreover, two previously unexplored FTJs: Gra/BaTiO3 (BTO)/LNO and Gra/BTO/CCMO, are predicted to achieve ON/OFF ratios higher than 1000. Guided by the ML predictions, the Gra/BTO/LNO and Gra/BTO/CCMO FTJs are experimentally fabricated, which unsurprisingly exhibit [Formula: see text]1000 ON/OFF ratios ([Formula: see text]8540 and [Formula: see text]7890, respectively). This study demonstrates a new paradigm of developing high-performance FTJs by using ML.

Background and objectives: In light of the growing burden of chronic kidney disease (CKD), it is of particular importance to create disease prediction models that can assist healthcare providers in identifying cases of CKD individual risk and integrate risk-based care for disease progress management. The objective of this study was to develop and validate a new pragmatic end-stage kidney disease (ESKD) risk prediction utilizing the Cox proportional hazards model (Cox) and machine learning (ML). Design, setting, participants, and measurements: The Chinese Cohort Study of Chronic Kidney Disease (C-STRIDE), a multicenter CKD cohort in China, was employed as the model’s training and testing datasets, with a split ratio of 7:3. A cohort from Peking University First Hospital (PKUFH cohort) served as the external validation dataset. The participants’ laboratory tests in those cohorts were conducted at PKUFH. We included individuals with CKD stages 1~4 at baseline. The incidence of kidney replacement therapy (KRT) was defined as the outcome. We constructed the Peking University-CKD (PKU-CKD) risk prediction model employing the Cox and ML methods, which include extreme gradient boosting (XGBoost) and survival support vector machine (SSVM). These models discriminate metrics by applying Harrell’s concordance index (Harrell’s C-index) and Uno’s concordance (Uno’s C). The calibration performance was measured by the Brier score and plots. Results: Of the 3216 C-STRIDE and 342 PKUFH participants, 411 (12.8%) and 25 (7.3%) experienced KRT with mean follow-up periods of 4.45 and 3.37 years, respectively. The features included in the PKU-CKD model were age, gender, estimated glomerular filtration rate (eGFR), urinary albumin–creatinine ratio (UACR), albumin, hemoglobin, medical history of type 2 diabetes mellitus (T2DM), and hypertension. In the test dataset, the values of the Cox model for Harrell’s C-index, Uno’s C-index, and Brier score were 0.834, 0.833, and 0.065, respectively. The XGBoost algorithm values for these metrics were 0.826, 0.825, and 0.066, respectively. The SSVM model yielded values of 0.748, 0.747, and 0.070, respectively, for the above parameters. The comparative analysis revealed no significant difference between XGBoost and Cox, in terms of Harrell’s C, Uno’s C, and the Brier score (p = 0.186, 0.213, and 0.41, respectively) in the test dataset. The SSVM model was significantly inferior to the previous two models (p < 0.001), in terms of discrimination and calibration. The validation dataset showed that XGBoost was superior to Cox, regarding Harrell’s C, Uno’s C, and the Brier score (p = 0.003, 0.027, and 0.032, respectively), while Cox and SSVM were almost identical concerning these three parameters (p = 0.102, 0.092, and 0.048, respectively). Conclusions: We developed and validated a new ESKD risk prediction model for patients with CKD, employing commonly measured indicators in clinical practice, and its overall performance was satisfactory. The conventional Cox regression and certain ML models exhibited equal accuracy in predicting the course of CKD.

Background: Electronic Health Records (EHR) are widely used to develop clinical prediction models (CPMs). However, one of the challenges is that there is often a degree of informative missing data. For example, laboratory measures are typically taken when a clinician is concerned that there is a need. When data are the so-called Not Missing at Random (NMAR), analytic strategies based on other missingness mechanisms are inappropriate. In this work, we seek to compare the impact of different strategies for handling missing data on CPMs performance. Methods: We considered a predictive model for rapid inpatient deterioration as an exemplar implementation. This model incorporated twelve laboratory measures with varying levels of missingness. Five labs had missingness rate levels around 50%, and the other seven had missingness levels around 90%. We included them based on the belief that their missingness status can be highly informational for the prediction. In our study, we explicitly compared the various missing data strategies: mean imputation, normal-value imputation, conditional imputation, categorical encoding, and missingness embeddings. Some of these were also combined with the last observation carried forward (LOCF). We implemented logistic LASSO regression, multilayer perceptron (MLP), and long short-term memory (LSTM) models as the downstream classifiers. We compared the AUROC of testing data and used bootstrapping to construct 95% confidence intervals. Results: We had 105,198 inpatient encounters, with 4.7% having experienced the deterioration outcome of interest. LSTM models generally outperformed other cross-sectional models, where embedding approaches and categorical encoding yielded the best results. For the cross-sectional models, normal-value imputation with LOCF generated the best results. Conclusion: Strategies that accounted for the possibility of NMAR missing data yielded better model performance than those did not. The embedding method had an advantage as it did not require prior clinical knowledge. Using LOCF could enhance the performance of cross-sectional models but have countereffects in LSTM models. [ABSTRACT FROM AUTHOR]

To retrospectively assess the effectiveness of deep learning (DL) model, based on breast magnetic resonance imaging (MRI), in predicting preoperative lymphovascular invasion (LVI) status in patients diagnosed with invasive breast cancer who have negative axillary lymph nodes (LNs). Data was gathered from 280 patients, including 148 with LVI-positive and 141 with LVI-negative lesions. These patients had undergone preoperative breast MRI and were histopathologically confirmed to have invasive breast cancer without axillary LN metastasis. The cohort was randomly split into training and validation groups in a 7:3 ratio. Radiomics features for each lesion were extracted from the first post-contrast dynamic contrast-enhanced (DCE)-MRI. The Least Absolute Shrinkage and Selection Operator (LASSO) regression method and logistic regression analyses were employed to identify significant radiomic features and clinicoradiological variables. These models were established using four machine learning (ML) algorithms and one DL algorithm. The predictive performance of the models (radiomics, clinicoradiological, and combination) was assessed through discrimination and compared using the DeLong test. Four clinicoradiological parameters and 10 radiomic features were selected by LASSO for model development. The Multilayer Perceptron (MLP) model, constructed using both radiomic and clinicoradiological features, demonstrated excellent performance in predicting LVI, achieving a high area under the curve (AUC) of 0.835 for validation. The DL model (MLP-radiomic) achieved the highest accuracy (AUC = 0.896), followed by DL model (MLP-combination) with an AUC of 0.835. Both DL models were significantly superior to the ML model (RF-clinical) with an AUC of 0.720. The DL model (MLP), which integrates radiomic features with clinicoradiological information, effectively aids in the preoperative determination of LVI status in patients with invasive breast cancer and negative axillary LNs. This is beneficial for making informed clinical decisions. [ABSTRACT FROM AUTHOR]

Self‐powered pressure detection using smart wearable devices is the subject of intense research attention, which is intended to address the critical need for prolonged and uninterrupted operations. Current piezoelectric and triboelectric sensors well respond to dynamic stimuli while overlooking static stimuli. This study proposes a dual‐response potentiometric pressure sensor that responds to both dynamic and static stimuli. The proposed sensor utilizes interdigital electrodes with MnO2/carbon/polyvinyl alcohol (PVA) as the cathode and conductive silver paste as the anode. The electrolyte layer incorporates a mixed hydrogel of PVA and phosphoric acid. The optimized interdigital electrodes and sandpaper‐like microstructured surface of the hydrogel electrolyte contribute to enhanced performance by facilitating an increased contact area between the electrolyte and electrodes. The sensor features an open‐circuit voltage of 0.927 V, a short‐circuit current of 6 µA, a higher sensitivity of 14 mV/kPa, and outstanding cycling performance (>5000 cycles). It can accurately recognize letter writing and enable capacitor charging and LED lighting. Additionally, a data acquisition and display system employing the proposed sensor, which facilitates the monitoring of athletes' rehabilitation training, and machine learning algorithms that effectively guide rehabilitation actions are presented. This study offers novel solutions for the future development of smart wearable devices. [ABSTRACT FROM AUTHOR]

Background: For medullary thyroid carcinoma (MTC) with no positive findings in the lateral neck before surgery, whether prophylactic lateral neck dissection (LND) is needed remains controversial. A better way to predict occult metastasis in the lateral neck is needed. Methods: From January 2010 to January 2022, patients who were diagnosed with MTC and underwent primary surgery at our hospital were retrospectively reviewed. We collected the patients' baseline characteristics, surgical procedure, and rescored the ultrasound images of the primary lesions using American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI‐RADS). Regularized logistic regression, 5‐fold cross‐validation and decision curve analysis was applied for lateral lymph node metastasis (LLNM) model's development and validation. Then, we tested the predictive ability of the LLNM model for occult LLNM in cN0−1a patients. Results: A total of 218 patients were enrolled. Five baseline characteristics and two TI‐RADS features were identified as high‐risk factors for LLNM: gender, baseline calcitonin (Ctn), tumor size, multifocality, and central lymph node (CLN) status, as well as TI‐RADS margin and level. A LLNM model was developed and showed a good discrimination with 5‐fold cross‐validation mean area under curve (AUC) = 0.92 ± 0.03 in the test dataset. Among cN0−1a patients, our LLNM model achieved an AUC of 0.91 (95% CI, 0.88–0.94) for predicting occult LLNM, which was significantly higher than the AUCs of baseline Ctn (0.83) and CLN status (0.64). Conclusions: We developed a LLNM prediction model for MTC using machine learning based on clinical baseline characteristics and TI‐RADS. Our model can predict occult LLNM for cN0−1a patients more accurately, then benefit the decision of prophylactic LND. [ABSTRACT FROM AUTHOR]

Appropriate needle manipulation to avoid abrupt deformation of fragile vessels is a critical determinant of the success of microvascular anastomosis. However, no study has yet evaluated the area changes in surgical objects using surgical videos. The present study therefore aimed to develop a deep learning-based semantic segmentation algorithm to assess the area change of vessels during microvascular anastomosis for objective surgical skill assessment with regard to the "respect for tissue." The semantic segmentation algorithm was trained based on a ResNet-50 network using microvascular end-to-side anastomosis training videos with artificial blood vessels. Using the created model, video parameters during a single stitch completion task, including the coefficient of variation of vessel area (CV-VA), relative change in vessel area per unit time (ΔVA), and the number of tissue deformation errors (TDE), as defined by a ΔVA threshold, were compared between expert and novice surgeons. A high validation accuracy (99.1%) and Intersection over Union (0.93) were obtained for the auto-segmentation model. During the single-stitch task, the expert surgeons displayed lower values of CV-VA (p < 0.05) and ΔVA (p < 0.05). Additionally, experts committed significantly fewer TDEs than novices (p < 0.05), and completed the task in a shorter time (p < 0.01). Receiver operating curve analyses indicated relatively strong discriminative capabilities for each video parameter and task completion time, while the combined use of the task completion time and video parameters demonstrated complete discriminative power between experts and novices. In conclusion, the assessment of changes in the vessel area during microvascular anastomosis using a deep learning-based semantic segmentation algorithm is presented as a novel concept for evaluating microsurgical performance. This will be useful in future computer-aided devices to enhance surgical education and patient safety. [ABSTRACT FROM AUTHOR]

Considering that titanium alloy is a critical aviation resource, ensuring its machining quality is of significant importance. Surface roughness remains a key parameter for surface quality inspection. This article introduces a multi-sensor titanium alloy milling monitoring system aimed at accurately monitoring surface quality during titanium alloy processing. Principal component analysis is conducted on three-dimensional milling force and vibration. We propose a multi-objective cutting parameter optimization procedure to simultaneously optimize multiple cutting parameters to improve surface roughness and tool life. Considering the high dependence of visual measurement on the light source, we strive to mitigate this limitation and improve prediction accuracy by considering one-dimensional and two-dimensional feature values. We establish a multidimensional signal feature surface roughness prediction system based on milling parameters, milling vibration, milling force, and texture image features. Using particle swarm algorithm and machine learning models, the undetermined parameters in the prediction system are obtained. The results show that the prediction accuracy of the multi-signal feature fusion surface roughness prediction system is 99.12%, with a mean square error of less than 0.01. The research can provide some theoretical guidance for the accurate monitoring of the surface quality of titanium alloy processing. [ABSTRACT FROM AUTHOR]

Estimation of human age is important in the fields of forensic medicine and the detection of neurodegenerative diseases of the brain. Particularly, the age estimation methods using brain magnetic resonance (MR) images are greatly significant because these methods not only are noninvasive but also do not lead to radiation exposure. Although several age estimation methods using brain MR images have already been investigated using deep learning, there are no reports involving younger subjects such as children. This study investigated the age estimation method using T1-weighted (sagittal plane) two-dimensional brain MR imaging (MRI) of 1000 subjects aged 5–79 (31.64 ± 18.04) years. This method uses a regression model based on ResNet-50, which estimates the chronological age (CA) of unknown brain MR images by training brain MR images corresponding to the CA. The correlation coefficient, coefficient of determination, mean absolute error, and root mean squared error were used as the evaluation indices of this model, and the results were 0.9643, 0.9299, 5.251, and 6.422, respectively. The present study showed the same degree of correlation as those of related studies, demonstrating that age estimation can be performed for a wide range of ages with higher estimation accuracy.

The population of Caragana tibetica, situated on the edge of the typical grassland-to-desert transition in the Mu Us Sandy Land, plays a vital ecological role in maintaining stability within the regional fragile ecosystem. Despite the consistent growth of C. tibetica following animal grazing, the biological mechanisms underlying its compensatory growth in response to livestock consumption remain unclear. Analyzing 48 metabolomic profiles from C. tibetica, our study reveals that the grazing process induces significant changes in the metabolic pathways of C. tibetica branches. Differential metabolites show correlations with soluble protein content, catalase, peroxidase, superoxide dismutase, malondialdehyde, and proline levels. Moreover, machine learning models built on these differential metabolites accurately predict the intensity of C. tibetica grazing (with an accuracy of 83.3%). The content of various metabolites, indicative of plant stress responses, including Enterolactone, Narceine, and Folcepri, exhibits significant variations in response to varying grazing intensities (P<0.05). Our investigation reveals that elevated grazing intensity intensifies the stress response in C. tibetica, triggering heightened antioxidative defenses and stress-induced biochemical activities. Distinctive metabolites play a pivotal role in responding to stress, facilitating the plant's adaptation to environmental challenges and fostering regeneration. [ABSTRACT FROM AUTHOR]

Objectives: The purpose of this research is to summarize the structure of radiomics-based knowledge and to explore potential trends and priorities by using bibliometric analysis. Methods: Select radiomics-related publications from 2012 to October 2022 from the Science Core Collection Web site. Use VOSviewer (version 1.6.18), CiteSpace (version 6.1.3), Tableau (version 2022), Microsoft Excel and Rstudio's free online platforms (http://bibliometric.com) for co-writing, co-citing, and co-occurrence analysis of countries, institutions, authors, references, and keywords in the field. The visual analysis is also carried out on it. Results: The study included 6428 articles. Since 2012, there has been an increase in research papers based on radiomics. Judging by publications, China has made the largest contribution in this area. We identify the most productive institutions and authors as Fudan University and Tianjie. The top three magazines with the most publications are《FRONTIERS IN ONCOLOGY》, 《EUROPEAN RADIOLOGY》, and 《CANCERS》. According to the results of reference and keyword analysis, "deep learning, nomogram, ultrasound, f-18-fdg, machine learning, covid-19, radiogenomics" has been determined as the main research direction in the future. Conclusion: Radiomics is in a phase of vigorous development with broad prospects. Cross-border cooperation between countries and institutions should be strengthened in the future. It can be predicted that the development of deep learning-based models and multimodal fusion models will be the focus of future research. Advances in knowledge: This study explores the current state of research and hot spots in the field of radiomics from multiple perspectives, comprehensively, and objectively reflecting the evolving trends in imaging-related research and providing a reference for future research. [ABSTRACT FROM AUTHOR]

This paper combines feature selection with machine learning algorithms to achieve object-oriented classification of crops in Gaofen-6 remote sensing images. The study provides technical support and methodological references for research on regional monitoring of food crops and precision agriculture management. "Staple-food-shifting" refers to the planting of other cash crops on cultivated land that should have been planted with staple crops such as wheat, rice, and maize, resulting in a change in the type of arable land cultivated. An accurate grasp of the spatial and temporal patterns of "staple-food-shifting" on arable land is an important basis for rationalizing land use and protecting food security. In this study, the Shihezi Reclamation Area in Xinjiang is selected as the study area, and Gaofen-6 satellite images are used to study the changes in the cultivated area of staple food crops and their regional distribution. Firstly, the images are segmented at multiple scales and four types of features are extracted, totaling sixty-five feature variables. Secondly, six feature selection algorithms are used to optimize the feature variables, and a total of nine feature combinations are designed. Finally, k-Nearest Neighbor (KNN), Random Forest (RF), and Decision Tree (DT) are used as the basic models of image classification to explore the best combination of feature selection method and machine learning model suitable for wheat, maize, and cotton classification. The results show that our proposed optimal feature selection method (OFSM) can significantly improve the classification accuracy by up to 15.02% compared to the Random Forest Feature Importance Selection (RF-FI), Random Forest Recursive Feature Elimination (RF-RFE), and XGBoost Feature Importance Selection (XGBoost-FI) methods. Among them, the OF-RF-RFE model constructed based on KNN performs the best, with the overall accuracy, average user accuracy, average producer accuracy, and kappa coefficient reaching 90.68%, 87.86%, 86.68%, and 0.84, respectively. [ABSTRACT FROM AUTHOR]

Coronary inflammation can alter the perivascular fat phenotype. Hence, we aimed to assess the diagnostic performance of radiomics features of pericoronary adipose tissue (PCAT) in coronary computed tomography angiography (CCTA) for in-stent restenosis (ISR) after percutaneous coronary intervention. In this study, 165 patients with 214 eligible vessels were included, and ISR was found in 79 vessels. After evaluating clinical and stent characteristics, peri-stent fat attenuation index, and PCAT volume, 1688 radiomics features were extracted from each peri-stent PCAT segmentation. The eligible vessels were randomly categorized into training and validation groups in a ratio of 7:3. After performing feature selection using Pearson's correlation, F test, and least absolute shrinkage and selection operator analysis, radiomics models and integrated models that combined selected clinical features and Radscore were established using five different machine learning algorithms (logistic regression, support vector machine, random forest, stochastic gradient descent, and XGBoost). Subgroup analysis was performed using the same method for patients with stent diameters of ≤ 3 mm. Nine significant radiomics features were selected, and the areas under the curves (AUCs) for the radiomics model and the integrated model were 0.69 and 0.79, respectively, for the validation group. The AUCs of the subgroup radiomics model based on 15 selected radiomics features and the subgroup integrated model were 0.82 and 0.85, respectively, for the validation group, which showed better diagnostic performance. CCTA-based radiomics signature of PCAT has the potential to identify coronary artery ISR without additional costs or radiation exposure. [ABSTRACT FROM AUTHOR]

Memristive neural networks have extensively been investigated for their capability in handling various artificial intelligence tasks. The training performance of memristive neural networks depends on the pulse scheme applied to the constituent memristors. However, the design of the pulse scheme in most previous studies was approached in an empirical manner or through a trial-and-error method. Here, we choose ferroelectric tunnel junction (FTJ) as a model memristor and demonstrate a physics-based predictive model for the pulse design to achieve high training performance. This predictive model comprises a physical model for FTJ that can adequately describe the polarization switching and memristive switching behaviors of the FTJ and an FTJ-based neural network that uses the long-term potentiation (LTP)/long-term depression (LTD) characteristics of the FTJ for the weight update. Simulation results based on the predictive model demonstrate that the LTP/LTD characteristics with a good trade-off between ON/OFF ratio, nonlinearity, and asymmetry can lead to high training accuracies for the FTJ-based neural network. Moreover, it is revealed that an amplitude-increasing pulse scheme may be the most favorable pulse scheme as it offers the widest ranges of pulse amplitudes and widths for achieving high accuracies. This study may provide useful guidance for the pulse design in the experimental development of high-performance memristive neural networks. [ABSTRACT FROM AUTHOR]