Accurate Model Research Articles

Carbapenem-resistant Enterobacterales sepsis following endoscopic retrograde cholangiopancreatography: risk factors for 30-day all-cause mortality and the development of a nomogram based on a retrospective cohort

BackgroundEndoscopic retrograde cholangiopancreatography (ERCP) has become a routine endoscopic procedure that is essential for diagnosing and managing various conditions, including gallstone extraction and the treatment of bile duct and pancreatic tumors. Despite its efficacy, post-ERCP infections – particularly those caused by carbapenem-resistant Enterobacterales (CRE) – present significant risks. These risks highlight the need for accurate predictive models to enhance postprocedural care, reduce the mortality risk associated with post-ERCP CRE sepsis, and improve patient outcomes in the context of increasing antibiotic resistance.ObjectiveThis study aimed to examine the risk factors for 30-day mortality in patients with CRE sepsis following ERCP and to develop a nomogram for accurately predicting 30-day mortality risk.MethodsData from 195 patients who experienced post-ERCP CRE sepsis between January 2010 and December 2022 were analyzed. Variable selection was optimized via the least absolute shrinkage and selection operator (LASSO) regression model. Multivariate logistic regression analysis was then employed to develop a predictive model, which was evaluated in terms of discrimination, calibration, and clinical utility. Internal validation was achieved through bootstrapping.ResultsThe nomogram included the following predictors: age > 80 years (hazard ratio [HR] 2.61), intensive care unit (ICU) admission within 90 days prior to ERCP (HR 2.64), hypoproteinemia (HR 4.55), quick Pitt bacteremia score ≥ 2 (HR 2.61), post-ERCP pancreatitis (HR 2.52), inappropriate empirical therapy (HR 3.48), delayed definitive therapy (HR 2.64), and short treatment duration (< 10 days) (HR 5.03). The model demonstrated strong discrimination and calibration.ConclusionsThis study identified significant risk factors associated with 30-day mortality in patients with post-ERCP CRE sepsis and developed a nomogram to accurately predict this risk. This tool enables healthcare practitioners to provide personalized risk assessments and promptly administer appropriate therapies against CRE, thereby reducing mortality rates.

A performance neural network model for conventional solar stills via transfer learning

Predictive solar-desalination models are becoming more widespread using ML and AI. However, forecasting solar still water productivity based on numerous designs still needs to be improved. Herein, we used transfer learning to create precise supervised predictive ANN regression models for water productivity (L/m2.day) predictions based on literature findings. Such observation datasets from single-basin solar stills were utilized to build the random initialization ANN model. The transfer learning method was applied to the latter model by taking the learned network (weights) for fine-tuning the hyperparameters from the earlier developed novel hybrid solar still known as the source (pre-trained) ANN model, to predict the target ANN model. Based on most minor statistical errors, the pre-trained model with 5–64–64-1 architecture and ReLU activation function was the most appropriate for water productivity prediction. All created ANN models were compared to the MLR model. The results revealed that the generated target ANN model outperformed the ANN RI and MLR with OI values of 0.872, 0.834, and 0.803, respectively, in all modeling stages. The target ANN model's accuracy and generalization were sufficient. The target ANN model had residuals of forecasted distillate values of around 1%. This work discusses the significance of transfer learning to generate accurate target ANN models for predicting freshwater outputs in single-slope solar stills, which can be integrated with established theoretically tuned parameters to enhance performance and maximize distillate water yields.

A new extension of the Gumbel distribution with biomedical data analysis

In the field of biomedical research, data characteristics often exhibit significant variability, challenging the applicability of classical Gumbel distribution for biomedical data modeling. To address this, this paper introduces a novel extension of the Gumbel model known as the odd beta prime Gumbel (OBP-Gum) model. Derived from the odd beta prime family, the new distribution exhibits greater kurtosis compared to the traditional Gumbel distribution. Importantly, the proposed distribution is designed to capture right-skewed, left-skewed, and nearly symmetric density functions, as well as increasing, decreasing, constant, and upside-down bathtub shapes for its hazard rate function, providing excellent curvature features for creating flexible statistical models for biomedical research. We derive the fundamental features of the OBP-Gum model, such as the quantile function, linear representations, moment generating function, moments, skewness, kurtosis, incomplete moments, and Rényi and Tsallis entropies. Parameter estimation for this new model is conducted using the maximum likelihood estimation method. A simulation study demonstrates the performance of the model parameters. The empirical findings, based on applications to two biomedical datasets, suggest that the OBP-Gum distribution outperforms existing models, particularly in handling extreme observations. Instead of relying on conventional models for decision-making, this research provides relevant stakeholders with an improved statistical distribution for more accurate biomedical data modeling.

New Insights into the ORR Catalysis on Pt Alloy Nanoparticles from an Element Specific d-Band Analysis.

Bolstered by their unique atomic structures and tailored compositions, nanoalloys exhibit extraordinary properties making them ideal materials to solve challenges in energy storage and conversion catalysis. However, a quantitative description of the structure-property relationships using an accurate descriptor-based model for nanoalloys, ranging from bimetallic to multimetallic compositions, is needed to drive efficient material design toward high-performance catalysis. In this work, we highlight the electronic property and catalytic activity relationship from an element specific d-band analysis of Pt-based alloy catalysts using X-ray absorption near-edge spectroscopy (XANES). Using a series of L10-MPt/Pt (M = Fe, Co, Ni) core/shell alloy catalysts with well-defined atomic structures, we quantified subtle differences in the Pt d-electron states and correlated the Pt d-band structure to their superior catalytic activity toward the oxygen reduction reaction (ORR). Our analysis used the upper d-band edge position as a predictive descriptor for the mass activity toward the ORR instead of the commonly used d-band center position. Together with density functional theory calculations and Nørskov d-band theory, the upper d-band edge position for the Pt states, derived from experimental measurements, elucidates new physical insights into the ORR performance of the L10-MPt/Pt core/shell catalysts. An element specific Pt d-band analysis using XANES overcomes challenges in traditional X-ray photoelectron spectroscopy-based valence d-band analysis, which cannot distinguish signals from independent elements in nanoalloys. Thus, the insights from the element specific d-band analysis presented in this work are a promising approach to determine structure-property relationships in a variety of transition metal nanoalloys and will be useful in the design of future high-performance catalysts.

Sulfotransferase-mediated phase II drug metabolism prediction of substrates and sites using accessibility and reactivity-based algorithms.

Sulphotransferases (SULTs) are a major phase II metabolic enzyme class contributing ~20 % to the Phase II metabolism of FDA-approved drugs. Ignoring the potential for SULT-mediated metabolism leaves a strong potential for drug-drug interactions, often causing late-stage drug discovery failures or black-boxed warnings on FDA labels. The existing models use only accessibility descriptors and machine learning (ML) methods for class and site of sulfonation (SOS) predictions for SULT. In this study, a variety of accessibility, reactivity, and hybrid models and algorithms have been developed to make accurate substrate and SOS predictions. Unlike the literature models, reactivity parameters for the aliphatic or aromatic hydroxyl groups (R/Ar-O-H), the Bond Dissociation Energy (BDE) gave accurate models with a True Positive Rate (TPR)=0.84 for SOS predictions. We offer mechanistic insights to explain these novel findings that are not recognized in the literature. The accessibility parameters like the ratio of Chemgauss4 Score (CGS) and Molecular Weight (MW) CGS/MW and distance from cofactor (Dis) were essential for class predictions and showed TPR=0.72. Substrates consistently had lower BDE, Dis, and CGS/MW than non-substrates. Hybrid models also performed acceptablely for SOS predictions. Using the best models, Algorithms gave an acceptable performance in class prediction: TPR=0.62, False Positive Rate (FPR)=0.24, Balanced accuracy (BA)=0.69, and SOS prediction: TPR=0.98, FPR=0.60, and BA=0.69. A rule-based method was added to improve the predictive performance, which improved the algorithm TPR, FPR, and BA. Validation using an external dataset of drug-like compounds gave class prediction: TPR=0.67, FPR=0.00, and SOS prediction: TPR=0.80 and FPR=0.44 for the best Algorithm. Comparisons with standard ML models also show that our algorithm shows higher predictive performance for classification on external datasets. Overall, these models and algorithms (SOS predictor) give accurate substrate class and site (SOS) predictions for SULT-mediated Phase II metabolism and will be valuable to the drug discovery community in academia and industry. The SOS predictor is freely available for academic/non-profit research via the GitHub link.

Frequency-Dependent Bouc–Wen Modeling of Magnetorheological Damper Using Harmonic Balance Approach

Magnetorheological dampers (MRDs) are of great interest in engineering due to their continuously adjustable damping characteristics. Accurate models are essential for optimizing MRDs and analyzing system dynamics. However, conventional methods widely overlook the impact of excitation frequency and amplitude. To address this issue, this work proposes a modified Bouc–Wen model that can be adapted to various excitation conditions. The model’s parameters depend on the current, excitation frequency, and amplitude. The mechanical characteristics of the MRD were analyzed by the tests. The parameters in the Bouc–Wen model were identified by combining the harmonic balance method and the genetic algorithm. The modified Bouc–Wen model was established by analyzing the variation of each parameter with current, excitation frequency, and amplitude. Finally, the agreement between the modified prediction model and the test results was verified under sinusoidal excitation of 80 mm and 1 Hz. The average relative errors were 3.87%, 2.82%, 2.45%, 2.19%, and 3.27% for current excitations of 0 A, 0.5 A, 1 A, 1.5 A, and 2.0 A, respectively. Since the MRD in this paper operates from 0.5 Hz to 2 Hz, the modified model was validated in the same range. Experiments demonstrate that the modified Bouc–Wen model efficiently and accurately describes the mechanical properties of the MRD under various excitation conditions.

PSA-FL-CDM: A Novel Federated Learning-Based Consensus Model for Post-Stroke Assessment

The rapid development of Internet of Things (IoT) technologies and the potential benefits of employing the vast datasets generated by IoT devices, including wearable sensors and camera systems, has ushered in a new era of opportunities for enhancing smart rehabilitation in various healthcare systems. Maintaining patient privacy is paramount in healthcare while providing smart insights and recommendations. This study proposed the adoption of federated learning to develop a scalable AI model for post-stroke assessment while protecting patients’ privacy. This research compares the centralized (PSA-MNMF) model performance with the proposed scalable federated PSA-FL-CDM model for sensor- and camera-based datasets. The computational time indicates that the federated PSA-FL-CDM model significantly reduces the execution time and attains comparable performance while preserving the patient’s privacy. Impact Statement—This research introduces groundbreaking contributions to stroke assessment by successfully implementing federated learning for the first time in this domain and applying consensus models in each node. It enables collaborative model training among multiple nodes or clients while ensuring the privacy of raw data. The study explores eight different clustering methods independently on each node, revolutionizing data organization based on similarities in stroke assessment. Additionally, the research applies the centralized PSA-MNMF consensus clustering technique to each client, resulting in more accurate and robust clustering solutions. By utilizing the FedAvg federated learning algorithm strategy, locally trained models are combined to create a global model that captures the collective knowledge of all participants. Comparative performance measurements and computational time analyses are conducted, facilitating a fair evaluation between centralized and federated learning models in stroke assessment. Moreover, the research extends beyond a single type of database by conducting experiments on two distinct datasets, wearable and camera-based, broadening the understanding of the proposed methods across different data modalities. These contributions develop stroke assessment methodologies, enabling efficient collaboration and accurate consensus clustering models and maintaining data privacy.

Evaluating the student performance prediction and action framework through a learning analytics intervention study

AbstractLearning analytics intervention (LAI) studies aim to identify at-risk students early during an academic term using predictive models and facilitate educators to provide effective interventions to improve educational outcomes. A major impediment to the uptake of LAI is the lack of access to LAI infrastructure by educators to pilot LAI, which typically requires substantial institution-wide efforts and investment to collect related data sets and develop accurate predictive models that identify at-risk students and also provide tools to facilitate interventions. This paper presents a novel LAI framework, termed Student Performance Prediction and Action (SPPA), that facilitates educators to seamlessly provide LAIs in their courses avoiding the need for large-scale institution-wide efforts and investments. Educators develop course-specific predictive models using historical course assessment data. In learning analytics, providing effective interventions is a challenge. SPPA utilises pedagogy principles in course design and interventions to facilitate effective interventions by providing insights into students’ risk levels, gaps in students’ knowledge, and personalised study/revision plans addressing knowledge gaps. SPPA was evaluated in a large undergraduate course on its ability to predict at-risk students and facilitate effective interventions as well as its ease of use by academics. The results are encouraging with high performance of predictive models, facilitating effective interventions leading to significant improved educational outcomes with positive feedback and uptake by academics. With its advantages, SPPA has the potential to catalyse and influence wide-scale adoption in LAIs.

PRF: A Program Reuse Framework for Automated Programming by Learning from Existing Robot Programs

This paper explores the problem of automated robot program generation from limited historical data when neither accurate geometric environmental models nor online vision feedback are available. The Program Reuse Framework (PRF) is developed, which uses expert-defined motion classes, a novel data structure introduced in this work, to learn affordances, workspaces, and skills from historical data. Historical data comprise raw robot joint trajectories and descriptions of the robot task being completed. Given new tasks, motion classes are then used again to formulate an optimization problem capable of generating new open-loop, skill-based programs to complete the tasks. To cope with a lack of geometric models, a technique to learn safe workspaces from demonstrations is developed, allowing the risk of new programs to be estimated before execution. A new learnable motion primitive for redundant manipulators is introduced, called a redundancy dynamical movement primitive, which enables new end-effector goals to be reached while mimicking the whole-arm behavior of a demonstration. A mobile manipulator part transportation task is used throughout to illustrate each step of the framework.

An Optimization Method for Stiffness and Damping Mistuning Identification From Blade Tip Timing Data

Abstract System identification of dynamic properties is of large interest in the turbomachinery industry to create more accurate computational models and more effective designs. Previous identification techniques were able to accurately capture the blade variability, known as mistuning, in the stiffness as well as the average damping of all the blades. Mistuning is vital to accurately identify and study because the symmetry of the system is broken and can lead to vibration localization and high amplitudes. In this work, a new method is proposed to not only capture the stiffness mistuning values, but also the blade-to-blade variability in damping. These damping mistuning values have been shown to have a significant effect on the dynamics of bladed disk systems. Incorporation of the damping mistuning into the computational model can be done utilizing an augmented component mode mistuning method with either structural or proportional damping. The mistuning values for this new identification method were compared to a well-established direct method and a previously studied optimization method. Blade responses were then found using a harmonic analysis and the newly identified mistuning values. These blade responses were then compared to experimental tip timing data from full scale rotating experiments. These comparisons show that the new model is able to better reproduce experimental data using computational models that incorporate both stiffness and damping mistuning values.

Mapping the neurodevelopmental predictors of psychopathology.

Neuroimaging research has uncovered a multitude of neural abnormalities associated with psychopathology, but few prediction-based studies have been conducted during adolescence, and even fewer used neurobiological features that were extracted across multiple neuroimaging modalities. This gap in the literature is critical, as deriving accurate brain-based models of psychopathology is anessential steptowards understanding key neural mechanisms and identifying high-risk individuals. As such, we trained adaptive tree-boosting algorithms on multimodal neuroimaging features from the Lifespan Human Connectome Developmental (HCP-D) sample that contained 956 participants between the ages of 8 to 22 years old. Our feature space consisted of 1037 anatomical, 1090 functional, and 192 diffusion MRI features, which were used to derive models that separately predicted internalizing symptoms, externalizing symptoms, and the general psychopathology factor. We found that multimodal models were the most accurate, but all brain-based models of psychopathology yielded out-of-sample predictions that were weakly correlated with actual symptoms (r2 < 0.15). White matter microstructural properties, including orientation dispersion indices and intracellular volume fractions, were the most predictive of general psychopathology, followed by cortical thickness and functional connectivity. Spatially, the most predictive features of general psychopathology were primarily localized within the default mode and dorsal attention networks. These results were mostly consistent across all dimensions of psychopathology, except orientation dispersion indices and the default mode network were not as heavily weighted in the prediction of internalizing and externalizing symptoms. Taken with prior literature, it appears that neurobiological features are an important part of the equation for predicting psychopathology but relying exclusively on neural markers is clearly not sufficient, especially among adolescent samples with subclinical symptoms. Consequently, risk factor models of psychopathology may benefit from incorporating additional sources of information that have also been shown to explain individual differences, such as psychosocial factors, environmental stressors, and genetic vulnerabilities.

A Terminal Residual Vibration Suppression Method of a Robot Based on Joint Trajectory Optimization

Vibration problems have become one of the most important factors affecting robot performance. To this end, a terminal residual vibration suppression method based on joint trajectory optimization is proposed to improve the accuracy and stability of robot motion. Firstly, based on the characteristics of the friction nonlinearity due to joint coupling and physical feasibility of dynamic parameters, a semidefinite programming method is used to identify dynamic parameters with actual physical meaning, thereby obtaining an accurate dynamic model. Then, based on the result of the residual vibration time domain analysis, a joint trajectory optimization model with the goal of minimizing joint tracking error is established. The Chebyshev collocation method is used to discretize the optimization model. The dynamic model is used as the optimization constraint, and barycentric interpolation is used to obtain the optimized joint motion trajectory. Finally, industrial robot experiments prove that the vibration suppression method proposed in this article can reduce the maximum acceleration amplitude of residual vibration by 62% and the vibration duration by 71%. Compared with the input shaping method, the method proposed in this paper can reduce the terminal residual vibration more effectively and ensure the consistency of running time and trajectory.

Research on Hydrodynamics of Trans-Media Vehicles Considering Underwater Time-Varying Attitudes

A trans-media vehicle is a new type of equipment that can adapt to two environments, water and air, to maintain optimal hydrodynamic and aerodynamic performance. However, no matter what kind of trans-media vehicle, its dynamics are much more complicated when traversing the interface of the medium, as the parameters are time-varying due to the change in ambient medium and vehicle attitudes. In order to improve the stability and performance of the trans-media vehicle in complex environments, an accurate mathematical model is established to characterize the dynamics of the trans-media vehicle in this process in this study. The time-varying hydrodynamic coefficients with different attitudes or depths are obtained using computational fluid dynamics software. The mathematical model is solved iteratively using a Runge–Kutta solver to calculate the dynamic response. A prototype of trans-media vehicle is fabricated, and motion experiments are performed in the pool. The experimental results confirm the effectiveness of the established model and lay the foundation for further controller design, providing a reference for the dynamic modeling of other similar equipment operating in complex environments. The primary novelty of this study lies in the fact that the established dynamic model considers the complex interaction between the attitude of the trans-media vehicle and the inherent different properties of water and air and utilizes computational fluid dynamics software to accurately obtain time-varying coefficients under different attitudes and depths. This approach not only recognizes the criticality of orientation-dependent hydrodynamic coefficients but also incorporates their temporal variations, which were often overlooked in previous studies.

Quantum modeling simulates nutrient effect of bioplastic polyhydroxyalkanoate (PHA) production in Pseudomonas putida

Polyhydroxyalkanoates (PHAs) could be used to make sustainable, biodegradable plastics. However, the precise and accurate mechanistic modeling of PHA biosynthesis, especially medium-chain-length PHA (mcl-PHA), for yield improvement remains a challenge to biology. PHA biosynthesis is typically triggered by nitrogen limitation and tends to peak at an optimal carbon-to-nitrogen (C/N) ratio. Specifically, simulation of the underlying dynamic regulation mechanisms for PHA bioprocess is a bottleneck owing to surfeit model complexity and current modeling philosophies for uncertainty. To address this issue, we proposed a quantum-like decision-making model to encode gene expression and regulation events as hidden layers by the general transformation of a density matrix, which uses the interference of probability amplitudes to provide an empirical-level description for PHA biosynthesis. We implemented our framework modeling the biosynthesis of mcl-PHA in Pseudomonas putida with respect to external C/N ratios, showing its optimization production at maximum PHA production of 13.81% cell dry mass (CDM) at the C/N ratio of 40:1. The results also suggest the degree of P. putida’s preference in channeling carbon towards PHA production as part of the bacterium’s adaptative behavior to nutrient stress using quantum formalism. Generic parameters (kD, kN and theta θ) obtained based on such quantum formulation, representing P. putida’s PHA biosynthesis with respect to external C/N ratios, was discussed. This work offers a new perspective on the use of quantum theory for PHA production, demonstrating its application potential for other bioprocesses.

Constructing and Validating Estimation Models for Individual-Tree Aboveground Biomass of Salix suchowensis in China

Biomass serves as a crucial indicator of plant productivity, and the development of biomass models has become an efficient way for estimating tree biomass production rapidly and accurately. This study aimed to develop a rapid and accurate model to estimate the individual aboveground biomass of Salix suchowensis. Growth parameters, including plant height (PH), ground diameter (GD), number of first branches (NFB), number of second branches (NSB) and aboveground fresh biomass weight (FW), were measured from 892 destructive sample trees. Correlation analysis indicated that GD had higher positive correlations with FW than PH, NFB and NSB. According to the biological features and field observations of S. suchowensis, the samples were classified into three categories: single-stemmed type, first-branched type and second-branched type. Based on the field measurement data, regression models were constructed separately between FW and each growth trait (PH, GD, NFB and NSB) using linear and nonlinear regression functions (linear, exponential and power). Then, multiple power regression and multiple linear regression were conducted to estimate the fresh biomass of three types of S. suchowensis. For the single-stemmed plant type, model M1 with GD as the single parameter had the highest adj R2, outperforming the other models. Among the 16 constructed biomass-estimating equations for the first-branched plant type, model M32 FW = 0.010371 × PH1.15862 × GD1.250581 × NFB0.190707 was found to have the best fit, with the highest coefficient of determination (adj R2 = 0.6627) and lowest Akaike Information Criterion (AIC = 5997.3081). When it comes to the second-branched plant type, the best-fitting equation was proved to be the multiple power model M43 with PH, GD, NFB and NSB as parameters, which had the highest adj R2 value and best-fitting effect. The stability and reliability of the models were confirmed by the F-test, repeated k-fold cross-validation and paired-sample t-tests. The models developed in this study could provide efficient tools for accurately estimating the total aboveground biomass for S. suchowensis at individual tree levels. The results of this study could also be useful for optimizing the economic productivity of shrub willow plantations.

A dependent circular-linear model for multivariate biomechanical data: Ilizarov ring fixator study.

Biomechanical and orthopaedic studies frequently encounter complex datasets that encompass both circular and linear variables. In most cases (i) the circular and linear variables are considered in isolation with dependency between variables neglected and (ii) the cyclicity of the circular variables is disregarded resulting in erroneous decision making. Given the inherent characteristics of circular variables, it is imperative to adopt methods that integrate directional statistics to achieve precise modelling. This paper is motivated by the modelling of biomechanical data, that is, the fracture displacements, that is used as a measure in external fixator comparisons. We focus on a dataset, based on an Ilizarov ring fixator, comprising of six variables. A modelling framework applicable to the six-dimensional joint distribution of circular-linear data based on vine copulas is proposed. The pair-copula decomposition concept of vine copulas represents the dependence structure as a combination of circular-linear, circular-circular and linear-linear pairs modelled by their respective copulas. This framework allows us to assess the dependencies in the joint distribution as well as account for the cyclicity of the circular variables. Thus, a new approach for accurate modelling of mechanical behaviour for Ilizarov ring fixators and other data of this nature is imparted.

Development and validation of an artificial intelligence model for predicting de novo distant bone metastasis in breast cancer: a dual-center study

ObjectiveBreast cancer has become the most prevalent malignant tumor in women, and the occurrence of distant metastasis signifies a poor prognosis. Utilizing predictive models to forecast distant metastasis in breast cancer presents a novel approach. This study aims to utilize readily available clinical data and advanced machine learning algorithms to establish an accurate clinical prediction model. The overall objective is to provide effective decision support for clinicians.MethodsData from 239 patients from two centers were analyzed, focusing on clinical blood biomarkers (tumor markers, liver and kidney function, lipid profile, cardiovascular markers). Spearman correlation and the least absolute shrinkage and selection operator regression were employed for feature dimension reduction. A predictive model was built using LightGBM and validated in training, testing, and external validation cohorts. Feature importance correlation analysis was conducted on the clinical model and the comprehensive model, followed by univariate and multivariate regression analysis of these features.ResultsThrough internal and external validation, we constructed a LightGBM model to predict de novo bone metastasis in newly diagnosed breast cancer patients. The area under the receiver operating characteristic curve values of this model in the training, internal validation test, and external validation test1 cohorts were 0.945, 0.892, and 0.908, respectively. Our validation results indicate that the model exhibits high sensitivity, specificity, and accuracy, making it the most accurate model for predicting bone metastasis in breast cancer patients. Carcinoembryonic Antigen, creatine kinase, albumin-globulin ratio, Apolipoprotein B, and Cancer Antigen 153 (CA153) play crucial roles in the model’s predictions. Lipoprotein a, CA153, gamma-glutamyl transferase, α-Hydroxybutyrate dehydrogenase, alkaline phosphatase, and creatine kinase are positively correlated with breast cancer bone metastasis, while white blood cell ratio and total cholesterol are negatively correlated.ConclusionThis study successfully utilized clinical blood biomarkers to construct an artificial intelligence model for predicting distant metastasis in breast cancer, demonstrating high accuracy. This suggests potential clinical utility in predicting and identifying distant metastasis in breast cancer. These findings underscore the potential prospect of developing economically efficient and readily accessible predictive tools in clinical oncology.

Regional quality analysis of the hydrological environment with an improved random forest model based on the chimpanzee algorithm.

High-precision evaluations of water environment quality are highly important for improving the accuracy of early warning systems of regional water pollution risk and improving the regional water environment. This paper employs the chimp optimization algorithm (ChOA) to enhance the traditional random forest model, resulting in the chimp optimization algorithm-random forest (ChOA-RF) water quality assessment model for evaluating the Jiansanjiang area in Heilongjiang Province, China. The results show that the overall water environment in Jiansanjiang has the following characteristics: "The water quality of farms in the northwest is poor, and the quality of groundwater is better than that of surface water." Total nitrogen (TN) and total phosphorus (TP) in surface water and ammonium nitrogen (NH3-N), ferrum (Fe), and manganese (Mn) in groundwater are the main pollutants. The TP and TN in surface water and the NH3-N in groundwater exceeded the relevant standards, likely due to the excessive application of chemical fertilizers, especially nitrogen fertilizers. Additionally, Fe and Mn are harmful native substances. According to these findings, targeted improvement strategies, such as reducing nitrogen fertilizer application, plugging well, and increasing the surface water utilization rate, are proposed. Moreover, the ChOA-RF model is compared with the traditional empirical value model and the particle swarm optimization-random forest (PSO-RF) model. The results show that the ChOA-RF model can effectively reduce the root mean square error and mean absolute percentage error and improve the coefficient of determination. The running time and convergence ability are also better than those of the PSO-RF model, which is a more accurate and efficient machine learning model. The model can be used not only for high-precision evaluation of regional water environment quality but also for other machine learning fields.

Global Path Planning of Unmanned Surface Vehicle in Complex Sea Areas Based on Improved Streamline Method

In this paper, an innovative method is proposed to improve the global path planning of Unmanned Surface Vehicles (USV) in complex sea areas, combining fluid mechanic calculations with an improved A* algorithm. This method not only generates smooth paths but also ensures feasible global solutions, significantly enhancing the efficiency and safety of path planning. Firstly, in response to the water depths limitation, this study set up safe water depths, providing strong guarantees for the safe navigation of USVs in complex waters. Secondly, based on the hydrological and geographical characteristics of the study sea area, an accurate ocean environment model was constructed using Ansys Fluent software and computational fluid dynamics (CFD) technology, thus providing USVs with a feasible path solution on a global scale. Then, the local sea area with complex obstacles was converted into a grid map to facilitate detailed planning. Meanwhile, the improved A* algorithm was utilized for meticulous route optimization. Furthermore, by combining the results of local and global planning, the approach generated a comprehensive route that accounts for the complexities of the maritime environment while avoiding local optima. Finally, simulation results demonstrated that the algorithm proposed in this study shows faster pathfinding speed, shorter route distances, and higher route safety compared to other algorithms. Moreover, it remains stable and effective in real-world scenarios.

62 Prognostic biomarker development using deep learning and spatial proteomics in papillary renal cell carcinoma

Abstract Background Papillary renal cell carcinoma (pRCC) is a prevalent but understudied kidney cancer pathology, constituting 15-20% of cases. While many patients achieve curative therapy using nephrectomy, others go on to develop progressive, metastatic disease with poor overall prognosis. In order to improve the current standards of care for pRCC patients, it is critical to identify new methods to identify high-risk patients likely to require more intense and risk-modulated follow-up. Our goals in this project are two-fold: (1) to identify prognostic patient clusters based on spatial architecture of tumor tissue, and (2) to identify a minimal subset of markers to accurately predict the defined clusters for clinical translation. Methods A tissue microarray of 100 pRCC patients was assayed using multiplex immunofluorescence with a 31-antibody panel with immune- and cancer-related proteins. We have developed novel algorithms to identify spatial neighborhoods and features. These features are then used to identify unsupervised clusters of patients. This new approach to classifying patients allows for a more specific and comprehensive description of each patient tumor’s spatial composition and association with diverse clinical outcomes. Next, we developed attention-based deep learning models capable of predicting these spatially-defined clusters directly from the underlying immunofluorescence images and subsequently profiled these for interpretability by retraining based on individual channels. We assessed each model iteratively on a validation set and a held-out test set for final model selection. We focussed on developing an accurate model with the minimal number of channels to enable development of a cost-efficient biomarker assay for the clinic. Results We performed a systematic analysis of the cellular and spatial phenotypes for each patient in our cohort and identified six (6) major spatial clusters. These clusters are based on the spatial neighborhood composition of the tumors (Fig 1A) and describe the composite effects of cell-cell interactions within a patient tumor. We identified one cluster in particular (cluster #6, mainly associated with spatial interaction of CD163+ macrophages) with a significantly worse prognosis than the other clusters. Using our advanced deep learning models, we have been able to achieve excellent validation accuracy in predicting a variety of clinical phenotypes and spatial features, including patient clusters and histological grade. We wished to then reduce the set of required features and began our efforts in predicting tumor vs. normal based on individual immunofluorescence channels and identified 6 channels with &amp;gt;75% individual predictive accuracy (Fig. 1B). Compositing all 6 markers further improves our accuracy to 90%. This success paves the way for exciting future prospects as we work to extend these efforts to identify a minimal clinically-applicable subset of protein markers. Conclusions The combination of computational spatial proteomics and deep learning models has the potential to identify new biomarkers specific to the spatial organization of patient tumors. We have identified a particular patient cluster with multiple associations with CD163+ macrophages demonstrating poor prognosis; selecting these patients may allow for tailored and more informed patient care. We are also working to enhance our deep learning models to circumvent the need for stepwise spatial analysis and, instead, allow for direct-from-image assessment of patients for particular spatial features indicative of various prognostic indicators. Our identified set of 6 markers serves as a basis for further refinements as we work to identify a minimal set of relevant markers able to predict various clinical outcomes from immunofluorescence imaging, offering a promising new avenue in the field of cancer pathology and biomarker development. DOD CDMRP Funding: yes