Test Set Research Articles

Deep-neural-network model for predicting ground motion parameters using earthquake horizontal-to-vertical spectral ratios

This study proposed a deep-neural-network (DNN) model for seismic ground motion prediction by utilizing a unified strong motion database by the National Research Institute for Earth Science and Disaster Resilience, and earthquake horizontal-to-vertical spectral ratio (EHVR) database in Japan. The model aims to enhance the accuracy of predictions by incorporating the EHVRs for complementing site effects, and utilizing existing ground motion prediction equations (GMPE) as the base model for source and propagation path effects. The hybrid approach enables the prediction of peak ground accelerations (PGAs), peak ground velocities (PGVs), and 5% damped absolute acceleration response spectra (SAs). After classifying the training and test sets from the database, the trained DNN models were applied on the test set to evaluate the performance of the predicted results. The accuracy assessment by the residuals, R-squared ( R2), and root mean square error (RMSE) between the predicted and observed values in the test set revealed the superior performance of the proposed model compared with the traditional GMPE with proxy-based site effects such as V S30s especially in predicting both the spectral amplitude and shape of SAs.

Construction and validation of a risk prediction model for extrauterine growth restriction in preterm infants born at gestational age less than 34 weeks

ObjectiveThis study aimed to develop and validate a model for predicting extrauterine growth restriction (EUGR) in preterm infants born ≤34 weeks gestation.MethodsPreterm infants from Guangxi Maternal and Child Health Hospital (2019–2021) were randomly divided into training (80%) and testing (20%) sets. Collinear clinical variables were excluded using Pearson correlation coefficients. Predictive factors were identified using Lasso regression. Random forest (RF), support vector machine (SVM), and logistic regression (LR) models were then built and evaluated using the confusion matrix, area under the curve (AUC), and the F1 score. Additionally, calibration curves and decision curve analysis (DCA) were plotted to assess the performance and practical utility of the models.ResultsThe study included 387 infants, with no significant baseline differences between training (n = 310) and testing (n = 77) sets. LR identified gestational age, birth weight, premature rupture of membranes, patent ductus arteriosus, cholestasis, and neonatal sepsis as key EUGR predictors. The RF model (19 variables) demonstrated an accuracy of greater than 90% during training, and superior AUC (0.62), F1 score (0.80), and accuracy (0.72) in testing compared to other models.ConclusionsGestational age, birth weight, premature rupture of membranes, patent ductus arteriosus, cholestasis, and neonatal sepsis are significant EUGR predictors in preterm infants ≤34 weeks. The model shows promise for early EUGR prediction in clinical practice, potentially enhancing screening efficiency and accuracy, thus saving medical resources.

Machine learning and multiple linear regression models can predict ascorbic acid and polyphenol contents, and antioxidant activity in strawberries.

Strawberry is a rich source of antioxidants, including ascorbic acid (ASA) and polyphenols, which have numerous health benefits. Antioxidant content and activity are often determined manually using laboratory equipment, which is destructive and time-consuming. This study constructs a prediction model for antioxidant compounds utilizing machine learning (ML) and multiple linear regression based on environmental, plant growth and agronomic fruit quality-related parameters as well as antioxidant levels. These were studied in three farms at two-week intervals during two years of cultivation. During the ML model screening, artificial neural network (ANN)-boosted models displayed a moderate coefficient of determination (R2) at 0.68-0.78 and relative root mean square error (RRMSE) at 3.8-4.8% in polyphenols and total ASA levels, as well as a high R2 of 0.96 and low RRMSE at <3.0% in antioxidant activity. Additionally, we developed variable selection models regarding the antioxidant activity, and variables two and five (environmental parameters and leaf length, respectively) with high accuracy were selected. The linear regression analysis between the actual and predicted data of antioxidants in the ANN-boosted models revealed high fitness with all parameters in almost all training, validation and test sets. Furthermore, environmental parameters are essential in developing such reliable models. We conclude that ANN-boosted, stepwise and double-Lasso regression models can predict antioxidant compounds with enhanced accuracy, and the relevant parameters can be easily acquired on-site without the need for any specific equipment. © 2024 Society of Chemical Industry.

Deep learning-based prediction of the dose-volume histograms for volumetric modulated arc therapy of left-sided breast cancer.

The advancements in artificial intelligence and computational power have made deep learning an attractive tool for radiotherapy treatment planning. Deep learning has the potential to significantly simplify the trial-and-error process involved in inverse planning required by modern treatment techniques such as volumetric modulated arc therapy (VMAT). In this study, we explore the ability of deep learning to predict organ-at-risk (OAR) dose-volume histograms (DVHs) of left-sided breast cancer patients undergoing VMAT treatment based solely on their anatomical characteristics. The predicted DVHs could be used to derive patient-specific dose constraints and dose objectives, streamlining the treatment planning process, standardizing the quality of the plans, and personalizing the treatment planning. This study aimed to develop a deep learning-based framework for the prediction of organ-specific dose-volume histograms (DVH) based on structures delineated for left-sided breast cancer treatment. We used a dataset of 249 left-sided breast cancer patients treated with tangential VMAT fields. We extracted delineated structures and dose distributions for each patient and derived slice-by-slice DVHs for planning target volume (PTV) and organs-at-risk. The patients were divided into training (70%, n=174), validation (10%, n=24), and test (20%, n=51) sets. Collected data were used to train a deep learning model for the prediction of the DVHs based on the delineated structures. The developed deep learning model comprised a modified DenseNet architecture followed by a recurrent neural network. In the independent test set (n=51), the point-wise differences in the slice-by-slice DVHs between the clinical and predicted DVHs were small; the mean squared errors were 3.53, 1.58, 2.28, 3.37, and 1.44 [×10-4] for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. With the derived cumulative DVHs, the mean absolute difference±standard deviation of mean doses between the clinical and the predicted DVH were 0.08± 0.04Gy, 0.24± 0.22Gy, 0.73± 0.46Gy, 0.07± 0.06Gy, and 0.14± 0.14Gy for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. The deep learning-based approach enabled automatic and reliable prediction of the DVH based on delineated structures. The predicted DVHs could potentially serve as patient-specific clinical goals used to aid treatment planning and avoid suboptimal plans or to derive optimization objectives and constraints for automated treatment planning.

Deep Learning-Based Biomimetic Identification Method for Mask Wearing Standardization

Deep learning technology can automatically learn features from large amounts of data, with powerful feature extraction and pattern recognition capabilities, thereby improving the accuracy and efficiency of object detection. [The objective of this study]: In order to improve the accuracy and speed of mask wearing deep learning detection models in the post pandemic era, the [Problem this study aimed to resolve] was based on the fact that no research work has been reported on standardized detection models for mask wearing with detecting nose targets specially. [The topic and method of this study]: A mask wearing normalization detection model (towards the wearing style exposing the nose to outside, which is the most obvious characteristic of non-normalized style) based on improved YOLOv5s (You Only Look Once v5s is an object detection network model) was proposed. [The improved method of the proposed model]: The improvement design work of the detection model mainly includes (1) the BottleneckCSP (abbreviation of Bottleneck Cross Stage Partial) module was improved to a BottleneckCSP-MASK (abbreviation of Bottleneck Cross Stage Partial-MASK) module, which was utilized to replace the BottleneckCSP module in the backbone architecture of the original YOLOv5s model, which reduced the weight parameters’ number of the YOLOv5s model while ensuring the feature extraction effect of the bonding fusion module. (2) An SE module was inserted into the proposed improved model, and the bonding fusion layer in the original YOLOv5s model was improved for better extraction of the features of mask and nose targets. [Results and validation]: The experimental results indicated that, towards different people and complex backgrounds, the proposed mask wearing normalization detection model can effectively detect whether people are wearing masks and whether they are wearing masks in a normalized manner. The overall detection accuracy was 99.3% and the average detection speed was 0.014 s/pic. Contrasted with original YOLOv5s, v5m, and v5l models, the detection results for two types of target objects on the test set indicated that the mAP of the improved model increased by 0.5%, 0.49%, and 0.52%, respectively, and the size of the proposed model compressed by 10% compared to original v5s model. The designed model can achieve precise identification for mask wearing behaviors of people, including not wearing a mask, normalized wearing, and wearing a mask non-normalized.

Intelligent diagnostic method for developmental hip dislocation

BackgroundDevelopmental dislocation of the hip joint (DDH) is a condition that severely threatens children’s healthy growth. Without timely and correct treatment, it will lead to osteoarthritis and hip dysfunction in the evolution of children.ObjectiveIt is essential to develop an intelligent model for diagnosing hip dislocation and performing accurate quantitative analysis.MethodsIn this paper, 46 cases of computed tomography (CT) images were retrospectively collected, including 19 cases of hip dislocation and 27 cases of healthy people. The experiment first uses ITK-SNAP to sketch the ilium and femoral head in the original image. Then, it uses 3D U-Net to send the label of the background, ilium, and femoral head into three channels, respectively, to realize the three-dimensional segmentation of the ilium and femoral head. Next, the extraction of the surface of the acetabulum and femoral head is performed. Subsequently, the erroneous points are eliminated, and the spherical surfaces of the acetabulum and femoral head are fitted using the least squares method. Ultimately, the spherical center distance is calculated quantitatively to predict whether the hip joint is dislocated.ResultsUnder the independent test set, the segmentation average dice coefficients of the ilium and femoral head are 89% and 93%, respectively. The spherical center distance between the acetabulum and femoral head is calculated quantitatively. If the value exceeds 10 mm, it is considered a hip dislocation. Compared with the doctor’s diagnosis, the accuracy result is 94.4%.ConclusionThis paper successfully implements a precise and automated intelligent diagnostic system for the identification of hip dislocation. Commencing with the development of a 3D segmentation algorithm for the ilium and femoral head, we further introduce a novel method that computes the spherical distance for the prediction of hip dislocation. This approach provides robust quantitative analysis, thereby facilitating more informed clinical decision-making.

Accurate Inspection and Super-Resolution Reconstruction for Additive Manufactured Defects Based on Stokes Vector Method and Deep Learning

Defects in additive manufacturing processes are closely related to the mechanical and physical properties of the components. However, the extreme conditions of high temperatures, intense light, and powder during the manufacturing process present significant challenges for defect detection. Additionally, the high reflectivity of metallic components can cause pixels in image sensors to become overexposed, resulting in the loss of many defect signals. Thus, this paper mainly focuses on proposing an accurate inspection and super-resolution reconstruction method for additive manufactured defects based on Stokes vector and deep learning, where the Stokes vectors, polarization degree, and polarization angles of the inspected defects are effectively utilized to suppress the high reflectivity of metallic surfaces, enhance the contrast of defect regions, and highlight the boundaries of defects. Furthermore, a modified SRGAN model designated SRGAN-H is presented by employing an additional convolutional layer and activation functions, including Harswish and Tanh, to accelerate the convergence of the SRGAN-H network and improve the reconstruction of the additive manufactured defect region. The experiment results demonstrated that the SRGAN-H model outperformed SRGAN and traditional SR reconstruction algorithms in terms of the images of Stokes vectors, polarization degree, and polarization angles. For the scratch and hole test sets, the PSNR values were 33.405 and 31.159, respectively, and the SSIM values were 0.890 and 0.896, respectively. These results reflect the effectiveness of the SRGAN-H model in super-resolution reconstruction of scratch and hole images. For the scratch and hole images chosen in this study, the PSNR values of SRGAN-H for single image super-resolution reconstruction ranged from 31.86786 to 43.82374, higher than the results obtained by the pre-improvement SRGAN algorithm.

Optimization of damping function parameters for -D3 and -D4 dispersion models for Hartree-Fock based symmetry-adapted perturbation theory.

Symmetry-adapted perturbation theory (SAPT) directly computes intermolecular interaction energy in terms of electrostatics, exchange-repulsion, induction/polarization, and London dispersion components. In SAPT based on Hartree-Fock ("SAPT0") or based on density functional theory, the most time-consuming step is the computation of the dispersion terms. Previous work has explored the replacement of these expensive dispersion terms with simple damped asymptotic models. We recently examined [Schriber et al. J. Chem. Phys. 154, 234107 (2021)] the accuracy of SAPT0 when replacing its dispersion term with Grimme's popular -D3 correction, reducing the computational cost scaling from O(N5) to O(N3). That work optimized damping function parameters for SAPT0-D3/jun-cc-pVDZ using estimates of the coupled-cluster complete basis set limit [CCSD(T)/CBS] on a 8299 dimer dataset. Here, we explore the accuracy of SAPT0-D3 with additional basis sets, along with an analogous model using -D4. Damping parameters are rather insensitive to basis sets, and the resulting SAPT0-D models are more accurate on average for total interaction energies than SAPT0. Our results are surprising in several respects: (1) improvement of -D4 over -D3 is negligible for these systems, even charged systems where -D4 should, in principle, be more accurate; (2) addition of Axilrod-Teller-Muto terms for three-body dispersion does not improve error statistics for this test set; and (3) SAPT0-D is even more accurate on average for total interaction energies than the much more computationally costly density functional theory based SAPT [SAPT(DFT)] in an aug-cc-pVDZ basis. However, SAPT0 and SAPT0-D3/D4 interaction energies benefit from significant error cancellation between exchange and dispersion terms.

Excited-State Forces with the Gaussian and Augmented Plane Wave Method for the Tamm-Dancoff Approximation of Time-Dependent Density Functional Theory.

Augmented plane wave methods enable an efficient description of atom-centered or localized features of the electronic density, circumventing high energy cutoffs and thus prohibitive computational costs of pure plane wave formulations. To complement existing implementations for ground-state properties and excitation energies, we present the extension of the Gaussian and augmented plane wave method to excited-state nuclear gradients within the Tamm-Dancoff approximation of time-dependent density functional theory and its implementation in the CP2K program package. Benchmarks for a test set of 35 small molecules demonstrate that maximum errors in the nuclear forces for excited states of singlet and triplet spin multiplicity are smaller than 0.1 eV/Å. The method is furthermore applied to the calculation of the zero-phonon line of defective hexagonal boron nitride. This spectral feature is reproduced with an error of 0.6 eV in comparison to GW-Bethe-Salpeter reference computations and 0.4 eV in comparison to experimental measurements. Accuracy assessments and applications thus demonstrate the potential use of the outlined developments for large-scale applications on excited-state properties of extended systems.

Age estimation from median palatine suture using computed tomography reconstructed 3D images: a comparison of Northern and Southwestern Chinese populations.

To investigate the potential of computed tomography (CT) images of median palatine suture (MP) for adult age estimation in the Northern and Southwestern Chinese populations. A total of 1110 cranial CT scans from individuals aged 10-79years, including 557 northern Chinese and 553 southwestern Chinese, were collected for analysis. After volume reformation and multiplanar reconstruction, a total of 20 slices of median palatine suture were selected from each individual. The closure of sutures was analyzed into four stages, and the cumulative scores of 20 slices were recorded as the suture closure score (SCS). The correlations between SCS and age were compared among the two Chinese populations residing in diverse geographic regions. Regression models were established for age estimation. The estimation accuracy was evaluated based on the test set. The mean absolute error (MAE) and the correlation between predicted age and chronological age were calculated to evaluate estimation accuracy. The SCS of MP exhibited a significant correlation with age (0.613, northern male; 0.678, southwestern male; 0.730, northern female; 0.704, Southwestern female; 0.662, total). Furthermore, there were statistically significant differences in SCS among different regions and sex groups (p < 0.001). The cubic regression model had the highest R2 value in all subjects, especially among Northern females and Southwestern males, while the power and quadratic regression models showed the highest R2 value in Northern males and Southwestern females, respectively. In the test set, the Northern cohort demonstrated a lower MAE (9.06 ± 7.32years, males; 9.17 ± 5.28years, females) compared to the Southwestern cohort (9.19 ± 7.49years, male; 10.61 ± 6.83years, female). Additionally, it was observed that males exhibited a lower MAE than females in both regional groups. This study demonstrated the potential utility of CT images of the MP for age estimation in Chinese populations, emphasizing the significance of incorporating regional and sex factors within this context.

Modeling serum M-protein response for early detection of biochemical relapse in myeloma patients treated with bortezomib, lenalidomide and dexamethasone.

Multiple myeloma (MM) treatment guidelines recommend waiting for formal progression criteria (FPC) to be met before proceeding to the next line of therapy. As predicting progression may allow early switching to next-line therapy while the disease burden is relatively low, we evaluated the predictive accuracy of a mathematical model to anticipate relapse 180 days before the FPC is met. A subset of 470/1143 patients from the IA16 dataset who were initially treated with VRd (Velcade (bortezomib), Revlimid (lenalidomide), and dexamethasone) in the CoMMpass study (NCT01454297) were randomly split 2:1 into training and testing sets. A model of M-protein dynamics was developed using the training set and used to predict relapse probability in patients in the testing set given their response histories up to 12 or more months of treatment. The predictive accuracy of this model and M-protein "velocity" were assessed via receiver operating characteristics (ROC) analysis. The final model was a two-population tumor growth inhibition model with additive drug effect and transit delay compartments for cell killing. The ROC area under the curve value of relapse prediction 180 days ahead of observed relapse by FPC was 0.828 using at least 360 days of response data, which was superior to the M-protein velocity ROC score of 0.706 under the same conditions. The model can predict future relapse from early M-protein responses and can be used in a future clinical trial to test whether early switching to second-line therapy results in better outcomes in MM.

Application of machine learning algorithms to predict postoperative surgical site infections and surgical site occurrences following inguinal hernia surgery.

This study aimed to develop, validate, and evaluate machine learning (ML) algorithms for predicting Surgical site infections (SSI) and surgical site occurrences (SSO) after elective open inguinal hernia surgery. A cohort of 491 patients who underwent elective open inguinal hernia surgery at Fudan University Affiliated Huadong Hospital between December 2019 and December 2020 was enrolled. To create a strong prediction model, we employed five ML methods: generalized linear model, random forest (RF), support vector machines, neural network, and gradient boosting machine. Based on the best performing model, we devised online calculators to facilitate clinicians' access to a linear predictor for patients. The receiver operating characteristic curve was utilized to evaluate the model's discriminatory capability and predictive accuracy. The incidence rates of SSI and SSO were 4.68% and 13.44%, respectively. Four variables (diabetes, recurrence, antibiotic prophylaxis, and duration of surgery) were identified for SSI prediction, while four variables (diabetes, size of hernias, albumin levels, and antibiotic prophylaxis) were included for SSO prediction. In the test set, the RF model showed the best predictive ability (SSI: area under the curve (AUC) = 0.849, sensitivity = 0.769, specificity = 0.769, and accuracy = 0.769; SSO: AUC = 0.740, sensitivity = 0.513, specificity = 0.821, and accuracy = 0.667). Online calculators have been developed to assess patients' risk of SSI ( https://wuqian17.shinyapps.io/predictionSSI/ ) and SSO ( https://wuqian17.shinyapps.io/predictionSSO/ ) after surgery. This study developed a prediction model for SSI/SSO using ML methods. It holds the potential to facilitate the selection of appropriate treatment options following elective open inguinal hernia surgery.

Multiple elite strategy enhanced RIME algorithm for 3D UAV path planning

With the wave of artificial intelligence sweeping the world in recent years, UAVs is widely used in various fields. UAV path planning has attracted much attention from scientists as an essential part of UAV work. In order to design an efficient and reasonable 3D UAV path planning program, recent researchers have invented and improved many algorithms. This paper proposes an elite RIME algorithm for 3D UAV path planning. First, we propose an elite reverse learning population selection strategy based on piecewise mapping to enhance the population diversity of the algorithm for better exploration. Second, this paper proposes a stochastic factor-controlled elite pool exploration strategy so that the algorithm is difficult to enter the local optimum and can better explore the global optimum. Then, this paper proposes a hard frost puncture exploitation strategy based on the sine–cosine function so that the algorithm can find the global optimum faster during the exploitation process. Meanwhile, in order to test the performance of the algorithm proposed in this paper, we compare it with 13 other intelligent optimization algorithms that are classical and popular nowadays on 52 test functions in three test sets, CEC2017, CEC2020, and CEC2022, and obtain competitive results. Finally, we applied it to the 3D UAV path planning problem in three different terrain scenarios, and the ELRIME algorithm achieved good results in all of them. Especially in the 7-peak model, the ELRIME algorithm improves the performance of the RIME algorithm by a factor of two. In the 9-peak model, the average value aspect also reduce the cost by 91 compared to the RIME algorithm, and more importantly, it has the smallest fluctuation in 30 runs, which is among the most stable of all the compared algorithms. In the 12-peak model, its stability is also significantly enhanced, and in terms of worst-case cost, it improves the cost by 340 compared to RIME.

Construction of an artificial neural network diagnostic model and investigation of immune cell infiltration characteristics for idiopathic pulmonary fibrosis

BackgroundIdiopathic pulmonary fibrosis (IPF) is a severe lung condition, and finding better ways to diagnose and treat the disease is crucial for improving patient outcomes. Our study sought to develop an artificial neural network (ANN) model for IPF and determine the immune cell types that differed between the IPF and control groups.MethodsFrom the Gene Expression Omnibus (GEO) database, we first obtained IPF microarray datasets. To conduct protein-protein interaction (PPI) networks and enrichment analyses, differentially expressed genes (DEGs) were screened between tissues of patients with IPF and tissues of controls. Afterward, we identified the important feature genes associated with IPF using random forest (RF) analysis, and then constructed and validated a prediction ANN mode. In addition, the proportions of immune cells were quantified using cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT) analysis, which was performed on microarray datasets based on gene expression profiling.ResultsA total of 11 downregulated and 36 upregulated DEGs were identified. PPI networks and enrichment analyses were carried out; the immune system and extracellular matrix were the subjects of the enrichments. Using RF analysis, the significant feature genes LRRC17, COMP, ASPN, CRTAC1, POSTN, COL3A1, PEBP4, IL13RA2, and CA4 were identified. The nine feature gene scores were integrated into the ANN to develop a diagnostic prediction model. The receiver operating characteristic (ROC) curves demonstrated the strong diagnostic ability of the ANN in predicting IPF in the training and testing sets. An analysis of IPF tissues in comparison to normal tissues revealed a reduction in the infiltration of natural killer cells resting, monocytes, macrophages M0, and neutrophils; conversely, the infiltration of T cells CD4 memory resting, mast cells, and macrophages M0 increased.ConclusionLRRC17, COMP, ASPN, CRTAC1, POSTN, COL3A1, PEBP4, IL13RA2, and CA4 were determined as key feature genes for IPF. The nine feature genes in the ANN model will be extremely important for diagnosing IPF. It may be possible to use differentiated immune cells from IPF samples in comparison to normal samples as targets for immunotherapy in patients with IPF.

Enhanced 2D Hand Pose Estimation for Gloved Medical Applications: A Preliminary Model

(1) Background: As digital health technology evolves, the role of accurate medical-gloved hand tracking is becoming more important for the assessment and training of practitioners to reduce procedural errors in clinical settings. (2) Method: This study utilized computer vision for hand pose estimation to model skeletal hand movements during in situ aseptic drug compounding procedures. High-definition video cameras recorded hand movements while practitioners wore medical gloves of different colors. Hand poses were manually annotated, and machine learning models were developed and trained using the DeepLabCut interface via an 80/20 training/testing split. (3) Results: The developed model achieved an average root mean square error (RMSE) of 5.89 pixels across the training data set and 10.06 pixels across the test set. When excluding keypoints with a confidence value below 60%, the test set RMSE improved to 7.48 pixels, reflecting high accuracy in hand pose tracking. (4) Conclusions: The developed hand pose estimation model effectively tracks hand movements across both controlled and in situ drug compounding contexts, offering a first-of-its-kind medical glove hand tracking method. This model holds potential for enhancing clinical training and ensuring procedural safety, particularly in tasks requiring high precision such as drug compounding.

Machine-Learning Predictions of Critical Temperatures from Chemical Compositions of Superconductors.

In the quest for advanced superconducting materials, the accurate prediction of critical temperatures (Tc) poses a formidable challenge, largely due to the complex interdependencies between superconducting properties and the chemical and structural characteristics of a given material. To address this challenges, we have developed a machine-learning framework that aims to elucidate these complicated and hitherto poorly understood structure-property and property-property relationships. This study introduces a novel machine-learning-based workflow, termed the Gradient Boosted Feature Selection (GBFS), which has been tailored to predict Tc for superconductors by employing a distributed gradient-boosting framework. This approach integrates exploratory data analyses, statistical evaluations, and multicollinearity reduction techniques to select highly relevant features from a high-dimensional feature space, derived solely from the chemical composition of materials. Our methodology was rigorously tested on a data set comprising approximately 16,400 chemical compounds with around 12,000 unique chemical compositions. The GBFS workflow enabled the development of a classification model that distinguishes compositions likely to exhibit Tc values greater than 10 K. This model achieved a weighted average F1-score of 0.912, an AUC-ROC of 0.986, and an average precision score of 0.919. Additionally, the GBFS workflow underpinned a regression model that predicted Tc values with an R2 of 0.945, an MAE of 3.54 K, and an RMSE of 6.57 K on a test set obtained via random splitting. Further exploration was conducted through out-of-sample Tc predictions, particularly those exceeding the liquid nitrogen temperature, and out-of-distribution predictions for (Ca1-xLax)FeAs2 based on varying lanthanum content. The outcome of our study underscores the significance of systematic feature analysis and selection in enhancing predictive model performance, offering various advantages over models that rely primarily on algorithmic complexity. This research not only advances the field of superconductivity but also sets a precedent for the application of machine learning in materials science.

Global optimization for large‐scale water network synthesis based on dynamic partition and adaptive bound tightening

AbstractThe synthesis of large‐scale integrated water networks is typically formulated as nonconvex mixed‐integer quadratic constrained programming (MIQCP) or QCP problems. With the complexity arising from bilinear terms in modeling mass flows of contaminants and binary variables representing the presence of units or streams, numerous local optima exist, thus presenting a significant optimization challenge. This study introduces a deterministic global optimization algorithm based on mixed‐integer programming (MIP) to tackle such problems. The approach involves dynamically strengthening the relaxed problems to converge towards the original problems. A simultaneous partition strategy is proposed combining locally uniform division with dynamic partitioned variables choosing. Furthermore, several adaptive bound contraction schemes are introduced to efficiently manage the size of the relaxed problems, assisting in accelerating the solution process. The algorithm's effectiveness and robustness are demonstrated with a large test set, showing superior performance compared to commercial solvers specifically on MIQCP problems.

Automated ASPECTS Segmentation and Scoring Tool: a Method Tailored for a Colombian TelestrokeNetwork.

To evaluate our two non-machine learning (non-ML)-based algorithmic approaches for detecting early ischemic infarcts on brain CT images of patients with acute ischemic stroke symptoms, tailored to our local population, to be incorporated in our telestroke software. One-hundred and thirteen acute stroke patients, excluding hemorrhagic, subacute, and chronic patients, with accessible brain CT images were divided into calibration and test sets. The gold standard was determined through consensus among three neuroradiologist. Four neuroradiologist independently reported Alberta Stroke Program Early CT Scores (ASPECTSs). ASPECTSs were also obtained using a commercial ML solution (CMLS), and our two methods, namely the Mean Hounsfield Unit (HU) relative difference (RELDIF) and the density distribution equivalence test (DDET), which used statistical analyze the of the HUs of each region and its contralateral side. Automated segmentation was perfect for cortical regions, while minimal adjustment was required for basal ganglia regions. For dichotomized-ASPECTSs (ASPECTS < 6) in the test set, the area under the receiver operating characteristic curve (AUC) was 0.85 for the DDET method, 0.84 for the RELDIF approach, 0.64 for the CMLS, and ranged from 0.71-0.89 for the neuroradiologist. The accuracy was 0.85 for the DDET method, 0.88 for the RELDIF approach, and was ranged from 0.83 - 0.96 for the neuroradiologist. Equivalence at a margin of 5% was documented among the DDET, RELDIF, and gold standard on mean ASPECTSs. Noninferiority tests of the AUC and accuracy of infarct detection revealed similarities between both DDET and RELDIF, and the CMLS, and with at least one neuroradiologist. The alignment of our methods with the evaluations of neuroradiologist and the CMLS indicates the potential of our methods to serve as supportive tools in clinical settings, facilitating prompt and accurate stroke diagnosis, especially in health care settings, such as Colombia, where neuroradiologist are limited.

Deciphering the cytotoxicity of micro- and nanoplastics in Caco-2 cells through meta-analysis and machine learning

Plastic pollution, driven by micro- and nanoplastics (MNPs), poses a major environmental threat, exposing humans through various routes. Despite human colorectal adenocarcinoma Caco-2 cells being used as an in vitro model for studying the intestinal epithelium, uncertainties linger about MNPs harming these cells and the factors influencing adverse effects. Addressing this lacuna, our study aimed to elucidate the pivotal MNP parameters influencing cytotoxicity in Caco-2 cells, employing meta-analysis and machine learning techniques for quantitative assessment. Initial scrutiny of 95 publications yielded 17 that met the inclusion criteria, generating a dataset of 320 data points. This dataset underwent meticulous stratification based on polymer type, exposure time, polymer size, MNP concentration, and biological assays utilised. Subsequent dose-response curve analysis revealed moderate correlations for selected subgroups, such as the (3-[4,5-dimethylthiazol-2-yl]-2,5 diphenyl tetrazolium bromide) MTT biological assay and exposure time exceeding 24 hours, with coefficient of determination (R2) values of 0.50 (p-value: 0.0065) and 0.60 (p-value: 0.0018) respectively. For the aforementioned two subgroups, the MNP concentrations surpassing 10 μg/mL led to diminished viability of Caco-2 cells. Notably, we observed challenges in employing meta-analysis to navigate this multidimensional MNP dataset. Leveraging a random forest model, we achieved improved predictive performance, with R2 values of 0.79 and a root mean square error (RMSE) of 0.14 for the prediction of the Log Response Ratio on the test set. Model interpretation indicated that size and concentration are the principal drivers influencing Caco-2 cell cytotoxicity. Additionally, the partial dependence plot illustrating the relationship between the size of MNPs and predicted cytotoxicity reveals a complex pattern. Our study provides crucial insights into the health impacts of plastic pollution, informing policymakers for targeted interventions, thus contributing to a comprehensive understanding of its human health consequences.

Multimodal registration network with multi-scale feature-crossing.

A critical piece of information for prostate intervention and cancer treatment is provided by the complementary medical imaging modalities of ultrasound (US) and magnetic resonance imaging (MRI). Therefore, MRI-US image fusion is often required during prostate examination to provide contrast-enhanced TRUS, in which image registration is a key step in multimodal image fusion. We propose a novel multi-scale feature-crossing network for the prostate MRI-US image registration task. We designed a feature-crossing module to enhance information flow in the hidden layer by integrating intermediate features between adjacent scales. Additionally, an attention block utilizing three-dimensional convolution interacts information between channels, improving the correlation between different modal features. We used 100 cases randomly selected from The Cancer Imaging Archive (TCIA) for our experiments. A fivefold cross-validation method was applied, dividing the dataset into five subsets. Four subsets were used for training, and one for testing, repeating this process five times to ensure each subset served as the test set once. We test and evaluate our technique using fivefold cross-validation. The cross-validation trials result in a median target registration error of 2.20 mm on landmark centroids and a median Dice of 0.87 on prostate glands, both of which were better than the baseline model. In addition, the standard deviation of the dice similarity coefficient is 0.06, which suggests that the model is stable. We propose a novel multi-scale feature-crossing network for the prostate MRI-US image registration task. A random selection of 100 cases from The Cancer Imaging Archive (TCIA) was used to test and evaluate our approach using fivefold cross-validation. The experimental results showed that our method improves the registration accuracy. After registration, MRI and TURS images were more similar in structure and morphology, and the location and morphology of cancer were more accurately reflected in the images.