Nonzero Coefficients Research Articles

Two effective models based on comprehensive lipidomics and metabolomics can distinguish BC versus HCs, and TNBC versus non-TNBC.

Lipidomics and metabolomics are closely related to tumor phenotypes, and serum lipoprotein subclasses and small-molecule metabolites are considered as promising biomarkers for breast cancer (BC) diagnosis. This study aimed to explore potential biomarker models based on lipidomic and metabolomic analysis that could distinguish BC from healthy controls (HCs) and triple-negative BC (TNBC) from non-TNBC. Blood samples were collected from 114 patients with BC and 75 HCs. A total of 112 types of lipoprotein subclasses and 30 types of small-molecule metabolites in the serum were detected by 1 H-NMR. All lipoprotein subclasses and small-molecule metabolites were subjected to a three-step screening process in the order of significance (p < 0.05), univariate regression (p < 0.1), and lasso regression (nonzero coefficient). Discriminant models of BC versus HCs and TNBC versus non-TNBC were established using binary logistic regression. We developed a valid discriminant model based on three-biomarker panel (formic acid, TPA2, and L6TG) that could distinguish patients with BC from HCs. The area under the receiver operating characteristic curve (AUC) was 0.999 (95% confidence interval [CI]: 0.995-1.000) and 0.990 (95% CI: 0.959-1.000) in the training and validation sets, respectively. Based on the panel (D-dimer, CA15-3, CEA, L5CH, glutamine, and ornithine), a discriminant model was established to differentiate between TNBC and non-TNBC, with AUC of 0.892 (95% CI: 0.778-0.967) and 0.905 (95% CI: 0.754-0.987) in the training and validation sets, respectively. This study revealed lipidomic and metabolomic differences between BC versus HCs and TNBC versus non-TNBC. Two validated discriminatory models established against lipidomic and metabolomic differences can accurately distinguish BC from HCs and TNBC from non-TNBC. Two validated discriminatory models can be used for early BC screening and help BC patients avoid time-consuming, expensive, and dangerous BC screening.

Development and Validation of an Ultrasound-Based Radiomics Nomogram for Identifying HER2 Status in Patients with Breast Carcinoma.

(1) Objective: To evaluate the performance of ultrasound-based radiomics in the preoperative prediction of human epidermal growth factor receptor 2-positive (HER2+) and HER2- breast carcinoma. (2) Methods: Ultrasound images from 309 patients (86 HER2+ cases and 223 HER2- cases) were retrospectively analyzed, of which 216 patients belonged to the training set and 93 patients assigned to the time-independent validation set. The region of interest of the tumors was delineated, and the radiomics features were extracted. Radiomics features underwent dimensionality reduction analyses using the intra-class correlation coefficient (ICC), Mann-Whitney U test, and the least absolute shrinkage and selection operator (LASSO) algorithm. The radiomics score (Rad-score) for each patient was calculated through a linear combination of the nonzero coefficient features. The support vector machine (SVM), K nearest neighbors (KNN), logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB) and XGBoost (XGB) machine learning classifiers were trained to establish prediction models based on the Rad-score. A clinical model based on significant clinical features was also established. In addition, the logistic regression method was used to integrate Rad-score and clinical features to generate the nomogram model. The leave-one-out cross validation (LOOCV) method was used to validate the reliability and stability of the model. (3) Results: Among the seven classifier models, the LR achieved the best performance in the validation set, with an area under the receiver operating characteristic curve (AUC) of 0.786, and was obtained as the Rad-score model, while the RF performed the worst. Tumor size showed a statistical difference between the HER2+ and HER2- groups (p = 0.028). The nomogram model had a slightly higher AUC than the Rad-score model (AUC, 0.788 vs. 0.786), but no statistical difference (Delong test, p = 0.919). The LOOCV method yielded a high median AUC of 0.790 in the validation set. (4) Conclusion: The Rad-score model performs best among the seven classifiers. The nomogram model based on Rad-score and tumor size has slightly better predictive performance than the Rad-score model, and it has the potential to be utilized as a routine modality for preoperatively determining HER2 status in BC patients non-invasively.

Improved bounds on the gain coefficients for digital nets in prime power base

We study randomized quasi-Monte Carlo integration by scrambled nets. The scrambled net quadrature has long gained its popularity because it is an unbiased estimator of the true integral, allows for a practical error estimation, achieves a high order decay of the variance for smooth functions, and works even for Lp-functions with any p≥1. The variance of the scrambled net quadrature for L2-functions can be evaluated through the set of the so-called gain coefficients.In this paper, based on the system of Walsh functions and the concept of dual nets, we provide improved upper bounds on the gain coefficients for digital nets in general prime power base. Our results explain the known bound by Owen (1997) for Faure sequences, the recently improved bound by Pan and Owen (2022) for digital nets in base 2 (including Sobol' sequences as a special case), and their finding that all the nonzero gain coefficients for digital nets in base 2 must be powers of two, all in a unified way.

A Transcriptomic-Based Tool to Predict Gemcitabine Sensitivity in Advanced Pancreatic Adenocarcinoma

A Transcriptomic-Based Tool to Predict Gemcitabine Sensitivity in Advanced Pancreatic Adenocarcinoma

Identification of a novel cell cycle-related risk signature predicting prognosis in patients with pancreatic adenocarcinoma.

Growing evidence have indicated that cell cycle-related genes (CRGs) play an essential role in the progression of pancreatic adenocarcinoma (PAAD). Nevertheless, the application of CRGs in estimating the prognosis of PAAD patients is still lacking. This study aimed to establish a risk signature based on CRGs that can predict patients' overall survival for PAAD. The expression and corresponding clinical data of PAAD patients from The Cancer Genome Atlas database and 200 cell cycle-related genes from the MSigDB were used for the generation and validation of the signature. LASSO Cox regression was applied to build the prediction model. The diagnostic value of signature was evaluated by receiver operating characteristic curves. Univariate and multivariate regression was used to construct the nomogram providing the clinicians a useful tool. A total of 103 CRGs were identified. Seven genes (RBM14, SMAD3, CENPA, KIF23, NUSAP1, INCENP, SMC4) with non-zero coefficients in LASSO analysis were used to construct the prognostic signature. The 7-gene signature significantly stratified patients into high- and low-risk groups in terms of overall survival, and the area under the receiver operating characteristic curve of 5-year survival reached 0.749. Multivariate analysis showed that the signature is an independent prognostic factor. We then mapped a nomogram to predict 1-, 3-, and 5-year survival for PAAD patients. The calibration curves indicated that the model was reliable. Finally, we discovered that TP53 and KRAS mutated most frequently in low and high-risk groups, respectively. Our findings suggested that the seven genes identified in this study are valuable prognostic predictors for patients with PAAD. These findings provided us with a novel insight that it is useful for understanding cell cycle mechanisms and for identifying patients with PAAD with poor prognosis.

Penalized empirical likelihood for high-dimensional generalized linear models with longitudinal data

In this paper, we consider the application of penalized empirical likelihood to the high-dimensional generalized linear models with longitudinal data. Under regular conditions, it is shown that the penalized empirical likelihood has the oracle property. That is, with probability converging to one, the penalized empirical likelihood identifies the true model and estimates the nonzero coefficients as efficiently as if the sparsity of the true model was known in advance. Also, we find the asymptotic distribution of the penalized empirical likelihood ratio test statistic is the chi-square distribution. Some simulations and a real data analysis are conducted to illustrate the proposed method.

On the integrated mean squared error of wavelet density estimation for linear processes

Let $\{X_n: n\in \N\}$ be a linear process with density function $f(x)\in L^2(\R)$. We study wavelet density estimation of $f(x)$. Under some regular conditions on the characteristic function of innovations, we achieve, based on the number of nonzero coefficients in the linear process, the minimax optimal convergence rate of the integrated mean squared error of density estimation. Considered wavelets have compact support and are twice continuously differentiable. The number of vanishing moments of mother wavelet is proportional to the number of nonzero coefficients in the linear process and to the rate of decay of characteristic function of innovations. Theoretical results are illustrated by simulation studies with innovations following Gaussian, Cauchy and chi-squared distributions.

Miniaturized electromechanical devices with multi-vibration modes achieved by orderly stacked structure with piezoelectric strain units

Piezoelectric devices based on a variety of vibration modes are widely utilized in high-tech fields to make a conversion between mechanical and electrical energies. The excitation of single or coupled vibration modes of piezoelectric devices is mainly related to the structure and property of piezoelectric materials. However, for the generally used piezoelectric materials, e.g., lead zirconate titanate ceramics, most of piezoelectric coefficients in the piezoelectric matrix are equal to zero, resulting in many piezoelectric vibration modes cannot be excited, which hinders the design of piezoelectric devices. In this work, an orderly stacked structure with piezoelectric strain units is proposed to achieve all nonzero piezoelectric coefficients, and consequently generate artificially coupled multi-vibration modes with ultrahigh strains. As an example, an orderly stacked structure with two piezoelectric strain units stator, corresponding to 31–36 coupled vibration mode, was designed and fabricated. Based on this orderly stacked structure with two piezoelectric strain units stator, we made a miniature ultrasonic motor (5 mmLength × 1.3 mmHeight × 1.06 mmWidth). Due to the ultrahigh strain of the 31–36 coupled vibration mode, the velocity per volume of the motor reached 4.66 s−1 mm−2. Furthermore, its moving resolution is around 3 nm, which is two orders higher than that of other piezoelectric motors. This work sheds a light on optimizing the performance of state-of-the-art electromechanical devices and may inspire new devices based on multi-vibration modes.

On the Support Recovery of Jointly Sparse Gaussian Sources via Sparse Bayesian Learning

In this work, we provide non-asymptotic, probabilistic guarantees for successful recovery of the common nonzero support of jointly sparse Gaussian sources in the multiple measurement vector (MMV) problem. The support recovery problem is formulated as the marginalized maximum likelihood (or type-II ML) estimation of the variance hyperparameters of a joint sparsity inducing Gaussian prior on the source signals. We derive conditions under which the resulting nonconvex constrained optimization perfectly recovers the nonzero support of a joint-sparse Gaussian source ensemble with arbitrarily high probability. The support error probability decays exponentially with the number of MMVs at a rate that depends on the smallest restricted singular value and the nonnegative null space property of the self Khatri-Rao product of the sensing matrix. Our analysis confirms that nonzero supports of size as high as <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$O(m^{2})$ </tex-math></inline-formula> are recoverable from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$m$ </tex-math></inline-formula> measurements per sparse vector. Our derived sufficient conditions for support consistency of the proposed constrained type-II ML solution also guarantee the support consistency of any global solution of the multiple sparse Bayesian learning (M-SBL) optimization whose nonzero coefficients lie inside a bounded interval. For the case of noiseless measurements, we further show that a single MMV is sufficient for perfect recovery of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -sparse support by M-SBL, provided all subsets of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k + 1$ </tex-math></inline-formula> columns of the sensing matrix are linearly independent.

Left-Invertibility of Rank-One Perturbations

For each isometry V acting on some Hilbert space and a pair of vectors f and g in the same Hilbert space, we associate a nonnegative number c(V; f, g) defined by $$\begin{aligned} c(V; f,g) = (\Vert f\Vert ^2 - \Vert V^*f\Vert ^2) \Vert g\Vert ^2 + |1 + \langle V^*f , g\rangle |^2. \end{aligned}$$We prove that the rank-one perturbation \(V + f \otimes g\) is left-invertible if and only if $$\begin{aligned} c(V;f,g) \ne 0. \end{aligned}$$We also consider examples of rank-one perturbations of isometries that are shift on some Hilbert space of analytic functions. Here, shift refers to the operator of multiplication by the coordinate function z. Finally, we examine \(D + f \otimes g\), where D is a diagonal operator with nonzero diagonal entries and f and g are vectors with nonzero Fourier coefficients. We prove that \(D + f\otimes g\) is left-invertible if and only if \(D+f\otimes g\) is invertible.

A Multidisciplinary Investigation into the Talent Development Processes at an English Football Academy: A Machine Learning Approach.

The talent development processes in youth football are both complex and multidimensional. The purpose of this two-fold study was to apply a multidisciplinary, machine learning approach to examine: (a) the developmental characteristics of under-9 to under-16 academy players (n = 98; Study 1), and (b) the characteristics of selected and deselected under-18 academy players (n = 18; Study 2). A combined total of 53 factors cumulated from eight data collection methods across two seasons were analysed. A cross-validated Lasso regression was implemented, using the glmnet package in R, to analyse the factors that contributed to: (a) player review ratings (Study 1), and (b) achieving a professional contract (Study 2). Results showed non-zero coefficients for improvement in subjective performance in 15 out of the 53 analysed features, with key findings revealing advanced percentage of predicted adult height (0.196), greater lob pass (0.160) and average dribble completion percentage (0.124), more total match-play hours (0.145), and an older relative age (BQ1 vs. BQ2: −0.133; BQ1 vs. BQ4: −0.060) were the most important features that contributed towards player review ratings. Moreover, PCDEQ Factor 3 and an ability to organise and engage in quality practice (PCDEQ Factor 4) were important contributing factors towards achieving a professional contract. Overall, it appears the key factors associated with positive developmental outcomes are not always technical and tactical in nature, where coaches often have their expertise. Indeed, the relative importance of these factors is likely to change over time, and with age, although psychological attributes appear to be key to reaching potential across the academy journey. The methodological techniques used here also serve as an impetus for researchers to adopt a machine learning approach when analysing multidimensional databases.

OBJECT DETECTION BASED ON SPECTRAL ANALYSIS USING SOBEL AND ROBERTS EDGE DETECTION ALGORITHM

Aim: This paper proposes novel object detection (OD) approach based on a thorough examination of the image's details and its approximate density chart. Results: Our proposed OD approach is divided into two phases. Knowledge about Spatial Distribution of Objects obtained from a density map that is used to compute initial object positions. With the aid of the original object positions estimated, a saliency map that provides entity boundaries is then used to calculate the bounding boxes with precision, which is inspired by human attention to detail. The scale variance of objects induced by uncertain perspective is a common problem in object density map estimation. A new method for estimating the prior focus for map for any image is proposed. Sobel and Roberts Edge Detection Algorithm are used in this study. The proposed approach is based on sparse defocus dictionary learning on a newly constructed dataset. The focus power is determined by the number of non-zero coefficients of the dictionary atoms. Conclusion: The algorithm's output can capture spatial features and pick the threshold type in a variety of ways. HIGHLIGHTS: Object detection based on spectral analysis using Sobel and Roberts edge detection algorithm proved to be effective when compared with existing methodologies.

Numerical investigation of forced convection heat transfer from a sphere at low Prandtl numbers

Direct numerical simulations of the flow and forced convective heat transfer around a sphere at Reynolds numbers between Re=500 and Re=1000 are performed. We investigate the effects of the Prandtl number (Pr) on the forced convective heat transfer from a sphere for various fluids having Pr=0.01,0.1,0.7. At the larger Prandtl number, the convective transport due to the vortex shedding process dominates over the diffusive transport. As the Prandtl number decreases, diffusive effects become important. Moreover, the thermal boundary layer increases with decrements of the Prandtl number, which results in a reduction in the local and mean non-dimensional heat transfer coefficient. It is seen that at Re=500 and Re=750, the vortex shedding process is asymmetric, which results not only in a non-zero lift coefficient, but in an asymmetric temperature field in the wake of the sphere at Pr≥0.1. The dual asymmetry in the flow and the convective heat transfer is smooth out when the Prandtl number reaches Pr=0.01 as the heat diffusion dominates and asymmetries in the vortex formation zone are no longer relevant in the heat transport. The descend in Prandtl number also produces an attenuation of the temperature fluctuations and thereby, in the turbulent heat transfer. As a direct consequence, two factors emerge at Pr=0.01: (1) a lower decay ratio of the temperature in the wake centreline, and (2) a larger wake spread compared to higher Prandtl numbers.

Sentinel Lymph Node Gene Expression Signature Predicts Recurrence-Free Survival in Cutaneous Melanoma.

Simple SummaryDespite a negative SLN status, patients with Stage IIB/IIC melanoma demonstrate poor melanoma-specific survival when compared to Stage IIIA patients. In this study, we hypothesized that a molecular profile at the level of the SLN would provide potential insights into risk of disease recurrence and serve as a prognostic biomarker of patient outcomes regardless of the presence of SLN melanoma metastases. Gene expression profiling was performed on SLN biopsies using U133A 2.0 Affymetrix gene chips. Our study suggests a novel 12-gene SLN signature risk score which may predict disease recurrence in cutaneous melanoma patients managed with wide excision of the primary tumor and SLN biopsy.We sought to develop a sentinel lymph node gene expression signature score predictive of disease recurrence in patients with cutaneous melanoma. Gene expression profiling was performed on SLN biopsies using U133A 2.0 Affymetrix gene chips. The top 25 genes associated with recurrence-free survival (RFS) were selected and a penalized regression function was used to select 12 genes with a non-zero coefficient. A proportional hazards regression model was used to evaluate the association between clinical covariates, gene signature score, and RFS. Among the 45 patients evaluated, 23 (51%) had a positive SLN. Twenty-one (46.7%) patients developed disease recurrence. For the top 25 differentially expressed genes (DEG), 12 non-zero penalized coefficients were estimated (CLGN, C1QTNF3, ADORA3, ARHGAP8, DCTN1, ASPSCR1, CHRFAM7A, ZNF223, PDE6G, CXCL3, HEXIM1, HLA-DRB). This 12-gene signature score was significantly associated with RFS (p < 0.0001) and produced a bootstrap C index of 0.888. In univariate analysis, Breslow thickness, presence of primary tumor ulceration, SLN positivity were each significantly associated with RFS. After simultaneously adjusting for these prognostic factors in relation to the gene signature, the 12-gene score remained a significant independent predictor for RFS (p < 0.0001). This SLN 12-gene signature risk score is associated with melanoma recurrence regardless of SLN status and may be used as a prognostic factor for RFS.

Battery energy storage train routing and security constrained unit commitment under solar uncertainty

The location of solar parks far from load areas may lead to transmission congestion and thus solar curtailment for secure system operation. Battery energy storage (BES) Train as mobile storage can transmit solar energy from site to load centers using a transport network while relieving lines from congestion. Therefore, stochastic security-constrained unit commitment (SCUC) with BES Train is modeled in this paper under solar uncertainty and N-1 critical line contingency. Time-space network models transportation constraints of BES Train routing problem. To reduce the computational burden, this paper proposes modeling of line outage distribution factor (LODF) for DC power flow that reduces the nonzero coefficients of post-contingency network constraints. The benders decomposition technique simplifies stochastic optimization for the mixed-integer linear programming (MILP) problem. BES Train integrated modified IEEE reliability test and 118-bus system is investigated as a case study. Simulations evaluate the effect of BES Train, solar uncertainty and critical line contingency state with LODF on operation costs, BES Train scheduling, solar curtailment, congestion and computational time. The proposed model shows that BES Train is an economical option for large solar integration to reduce transmission congestion and curtail solar power effectively.

Integration of ultrasound radiomics features and clinical factors: A nomogram model for identifying the Ki-67 status in patients with breast carcinoma.

ObjectiveThe aim of this study was to develop and validate an ultrasound-based radiomics nomogram model by integrating the clinical risk factors and radiomics score (Rad-Score) to predict the Ki-67 status in patients with breast carcinoma.MethodsUltrasound images of 284 patients (196 high Ki-67 expression and 88 low Ki-67 expression) were retrospectively analyzed, of which 198 patients belonged to the training set and 86 patients to the test set. The region of interest of tumor was delineated, and the radiomics features were extracted. Radiomics features underwent dimensionality reduction analysis by using the independent sample t test and least absolute shrinkage and selection operator (LASSO) algorithm. The support vector machine (SVM), logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB) and XGBoost (XGB) machine learning classifiers were trained to establish prediction model based on the selected features. The classifier with the highest AUC value was selected to convert the output of the results into the Rad-Score and was regarded as Rad-Score model. In addition, the logistic regression method was used to integrate Rad-Score and clinical risk factors to generate the nomogram model. The leave group out cross-validation (LGOCV) method was performed 200 times to verify the reliability and stability of the nomogram model.ResultsSix classifier models were established based on the 15 non-zero coefficient features. Among them, the LR classifier achieved the best performance in the test set, with the area under the receiver operating characteristic curve (AUC) value of 0.786, and was obtained as the Rad-Score model, while the XGB performed the worst (AUC, 0.615). In multivariate analysis, independent risk factor for high Ki-67 status was age (odds ratio [OR] = 0.97, p = 0.04). The nomogram model based on the age and Rad-Score had a slightly higher AUC than that of Rad-Score model (AUC, 0.808 vs. 0.798) in the test set, but no statistical difference (p = 0.144, DeLong test). The LGOCV yielded a median AUC of 0.793 in the test set.ConclusionsThis study proposed a convenient, clinically useful ultrasound radiomics nomogram model that can be used for the preoperative individualized prediction of the Ki-67 status in patients with BC.

Application of MRI-Based Radiomics in Preoperative Prediction of NF2 Alteration in Intracranial Meningiomas.

PurposeThis study aimed to investigate the feasibility of predicting NF2 mutation status based on the MR radiomic analysis in patients with intracranial meningioma.MethodsThis retrospective study included 105 patients with meningiomas, including 60 NF2-mutant samples and 45 wild-type samples. Radiomic features were extracted from magnetic resonance imaging scans, including T1-weighted, T2-weighted, and contrast T1-weighted images. Student’s t-test and LASSO regression were performed to select the radiomic features. All patients were randomly divided into training and validation cohorts in a 7:3 ratio. Five linear models (RF, SVM, LR, KNN, and xgboost) were trained to predict the NF2 mutational status. Receiver operating characteristic curve and precision-recall analyses were used to evaluate the model performance. Student’s t-tests were then used to compare the posterior probabilities of NF2 mut/loss prediction for patients with different NF2 statuses.ResultsNine features had nonzero coefficients in the LASSO regression model. No significant differences was observed in the clinical features. Nine features showed significant differences in patients with different NF2 statuses. Among all machine learning algorithms, SVM showed the best performance. The area under curve and accuracy of the predictive model were 0.85; the F1-score of the precision-recall curve was 0.80. The model risk was assessed by plotting calibration curves. The p-value for the H-L goodness of fit test was 0.411 (p> 0.05), which indicated that the difference between the obtained model and the perfect model was statistically insignificant. The AUC of our model in external validation was 0.83.ConclusionA combination of radiomic analysis and machine learning showed potential clinical utility in the prediction of preoperative NF2 status. These findings could aid in developing customized neurosurgery plans and meningioma management strategies before postoperative pathology.

A Machine Learning-Based Predictive Model of Epidermal Growth Factor Mutations in Lung Adenocarcinomas.

Simple SummaryTargeted therapy against epidermal growth factor (EGFR) mutations has become the standard of care for non-small cell lung cancer, and there has not been an efficient genetic test for non-small cell lung cancer patients. The present study aims to find a novel data-driven genetic testing method that can effectively predict the mutation status of EGFR based on a prediction model combining clinical features. The results of this study provide a powerful theoretical basis for the establishment of an effective mutation prediction model. The prediction model can provide a high reference value aiding in EGFR mutation diagnosis and subsequent treatment course.Data from 758 patients with lung adenocarcinoma were retrospectively collected. All patients had undergone computed tomography imaging and EGFR gene testing. Radiomic features were extracted using the medical imaging tool 3D-Slicer and were combined with the clinical features to build a machine learning prediction model. The high-dimensional feature set was screened for optimal feature subsets using principal component analysis (PCA) and the least absolute shrinkage and selection operator (LASSO). Model prediction of EGFR mutation status in the validation group was evaluated using multiple classifiers. We showed that six clinical features and 622 radiomic features were initially collected. Thirty-one radiomic features with non-zero correlation coefficients were obtained by LASSO regression, and 24 features correlated with label values were obtained by PCA. The shared radiomic features determined by these two methods were selected and combined with the clinical features of the respective patient to form a subset of features related to EGFR mutations. The full dataset was partitioned into training and test sets at a ratio of 7:3 using 10-fold cross-validation. The area under the curve (AUC) of the four classifiers with cross-validations was: (1) K-nearest neighbor (AUCmean = 0.83, Acc = 81%); (2) random forest (AUCmean = 0.91, Acc = 83%); (3) LGBM (AUCmean = 0.94, Acc = 88%); and (4) support vector machine (AUCmean = 0.79, Acc = 83%). In summary, the subset of radiographic and clinical features selected by feature engineering effectively predicted the EGFR mutation status of this NSCLC patient cohort.

Novel soliton solutions for the fractional three-wave resonant interaction equations

Abstract In this article, we obtained new infinite sets of exact soliton solutions for the nonlinear evolution system of three-wave resonant interaction equations. The solved system contains the non-zero second-order dispersion coefficients, the non-zero phase velocity mismatch, and the conformable fractional time derivative of order between zero and one. The solution method is a constructed ansatz that consists of linear combinations of the tan and cotan hyperbolic functions with complex coefficients. We stated clear systematic steps toward writing an exact soliton solution for the studied system. To show the efficiency of this method, we introduced some numerical examples on each obtained set of solutions. The computations showed that similar solutions can be obtained if one replaces the tan and cotan hyperbolic functions with the tan and cotan trigonometric functions. The new obtained fractional solutions could be useful in studying the broad applications of triad resonances in plasma physics and in nonlinear optics.

Construction and analysis of an ulcer risk prediction model after endoscopic submucosal dissection for early gastric cancer.

BACKGROUNDEndoscopic submucosal dissection (ESD) has been widely used in the treatment of early gastric cancer (EGC). A personalized and effective prediction method for ESD with EGC is urgently needed.AIMTo construct a risk prediction model for ulcers after ESD for EGC based on LASSO regression.METHODSA total of 196 patients with EGC who received ESD treatment were prospectively selected as the research subjects and followed up for one month. They were divided into an ulcer group and a non-ulcer group according to whether ulcers occurred. The general data, pathology, and endoscopic characteristics of the groups were compared, and the best risk predictor subsets were screened by LASSO regression and tenfold cross-validation. Multivariate logistic regression was applied to analyze the risk factors for ulcers after ESD in patients with EGC. A receiver operating characteristic (ROC) curve was used to estimate the predictive model performance.RESULTSOne month after the operation, no patient was lost to follow-up. The incidence of ulcers was 20.41% (40/196) (ulcer group), and the incidence of no ulcers was 79.59% (156/196) (non-ulcer group). There were statistically significant differences in the course of disease, Helicobacter pylori infection history, smoking history, tumor number, clopidogrel medication history, lesion diameter, infiltration depth, convergent folds, and mucosal discoloration between the groups. Gray's medication history, lesion diameter, convergent folds, and mucosal discoloration, which were the 4 nonzero regression coefficients, were screened by LASSO regression analysis. Further multivariate logistic analysis showed that lesion diameter [Odds ratios (OR) = 30.490, 95%CI: 8.584-108.294], convergent folds (OR = 3.860, 95%CI: 1.060-14.055), mucosal discoloration (OR = 3.191, 95%CI: 1.016-10.021), and history of clopidogrel (OR = 3.554, 95%CI: 1.009-12.515) were independent risk factors for ulcers after ESD in patients with EGC (P < 0.05). The ROC curve showed that the area under the curve of the risk prediction model for ulcers after ESD in patients with EGC was 0.944 (95%CI: 0.902-0.972).CONCLUSIONClopidogrel medication history, lesion diameter, convergent folds, and mucosal discoloration can predict the occurrence of ulcers after ESD in patients with EGC.