Search

Our study delves into postpartum depression (PPD) extending observation up to six months postpartum, addressing the gap in long-term follow-ups and uncover critical intervention points. Through a continuous three-wave cohort study involving 3174 of 10,730 invited postpartum women, we utilized machine learning to predict PPD risk, incorporating self-reported surveys and health records from October 2021 to Jan 2023. PPD prevalence slightly decreased from 30.9 % to 29.1 % over six months. The Random Forest model emerged as the most effective, identifying key predictors of PPD at different stages. The top three factors at first month were newborn's birth weight, maternal weight before delivery and before pregnancy. The EPDS scores of last time, newborn's birth weight and maternal weight before pregnancy and before delivery were main predictors for EPDS scores at third and sixth months postpartum. The study faces limitations such as potential selection bias due to the convenience sampling method and the reliance on self-reported measures, which may introduce reporting bias. Furthermore, the high attrition rate could affect the representativeness of the sample and the generalizability of the findings. There is a slight decrease in PPD rates over six months, yet the prevalence remains high. This underscores the need for early and ongoing mental health support for new mothers. Our study highlights the efficacy of machine learning in enhancing PPD risk assessment and tailoring intervention strategies, paving the way for more personalized healthcare approaches in postpartum care. • Extensive follow-up reveals PPD trends up to six months postpartum, emphasizing continuous monitoring necessity. • Machine learning utilized in a three-wave cohort study identifies PPD risk predictors. • Key predictors for PPD include newborn's birth weight and maternal pre-delivery weight, highlighting intervention targets. • PPD prevalence demostrates a slight decline over six months, maintaining a significant impact. [ABSTRACT FROM AUTHOR]

Ceria‐supported precious metal catalysts have undergone extensive investigation for the catalytic methane combustion. However, it remains a significant challenge to achieve both highly synergistic oxidation activity and efficient atom utilization remains a challenge for commonly used supported nanoparticles and single‐atom catalysts. Dual‐atom catalysts (DACs) emerges as a frontier of advanced catalysts, presenting unique catalytic properties that benefit from the synergy of neighboring metal sites. In this study, 361 ceria‐supported DACs (M1M2/CeO2) encompassing combinations of 19 transition metals are systematically explored. Using high‐throughput density functional theory calculations, the structures, stability as well as activity of M1M2/CeO2 are assessed. Notably, Au1Ga1/CeO2 is identified as a promising DAC exhibiting high activity for methane total oxidation, substantiated by comprehensive DFT‐calculated reaction pathways. Furthermore, employing six machine‐learning algorithms, the structure‐properties relationship is explored within ceria‐based DACs and highlight the importance of oxidation states and atomic radii of doped metals as the descriptors. The trained model by computational dataset exhibits high accuracy and predict a more active Mn1Au1/CeO2 than those screened using only DFT datasets. The high‐throughput strategy demonstrated in this work not only provides insights into the rational design of methane oxidation catalysts, but also paves the way for exploring DACs for diverse applications. [ABSTRACT FROM AUTHOR]

River plumes are complex physical phenomena that occur at the interface between riverine and marine systems. The lack of direct measurements of sediment concentration complicates the study of these geomorphological features, since the boundaries of river plumes are often gradual and unclear. Therefore, the identification and digitalization of river plumes is not simple and the methods applied in different study areas are not always objective and replicable. The aim of this work is to provide a valid approach based on a deep-learning model that uses Convolution Neural Network (CNN) layers for the digitalization of river plumes. We describe the methodology applied to implement the input dataset used for training the model, the errors obtained, and an application for a study area of about 300 km located in the Mediterranean. The model uses Sentinel-2 Level-1C images. The application of the model to a specific study area allowed us to understand the possibility of investigating these geomorphological features to obtain results in agreement with previous works. As a matter of fact, by using the red band as a proxy of sediment concentration, we were able to investigate the average behaviours of sediment dispersion along the coast and to extract innovative data related to specific events for the study of morphological characteristics such as dimension and direction. [ABSTRACT FROM AUTHOR]

Background: Lung adenocarcinoma (LUAD) represents a significant global health burden, necessitating advanced prognostic tools for improved patient management. RNA modifications (m6A, m1A, m5C, m7G), and disulfidptosis, a novel cell death mechanism, have emerged as promising biomarkers and therapeutic targets in cancer. Methods: We systematically compiled disulfidptosis-correlated genes and RNA modification-related genes from existing literature. A novel disulfidptosis-correlated m6A/m1A/m5C/m7G riskscore was computed using integrated machine-learning algorithms. Transcriptomic data from TCGA and GEO databases were downloaded analyzed. Single-cell RNA-sequencing data from the TISCH database was processed using the Seurat package. Genes' protein–protein interaction network was constructed using the String database. Functional phenotype analysis was performed using GSVA, ClusterProfiler, and IOBR packages. Consensus clustering divided patients into two distinct groups. Drug sensitivity predictions were obtained from the GDSC1 database and predicted using the Oncopredict package. Results: The disulfidptosis-correlated m6A/m1A/m5C/m7G risk score effectively stratified LUAD patients into prognostically distinct groups, demonstrating superior predictive accuracy compared to conventional clinical parameters. Patients in different risk groups exhibited significant molecular and clinical differences. Subsequent analyses identified two molecular subtypes associated with RNA modification and disulfidptosis, revealing differences in immune infiltration and prognosis. Functional enrichment analyses highlighted pathways involving RNA modification and disulfidptosis, underscoring their roles in LUAD pathogenesis. Single-cell analysis revealed distinct features between high- and low-risk status cells. Conclusion: This study introduces a novel disulfidptosis-correlated m6A/m1A/m5C/m7G risk score as a robust prognostic tool for LUAD, integrating insights from RNA modifications and cell death mechanisms. The risk score enhances prognostic stratification and identifies potential targets for personalized therapeutic strategies in LUAD. This comprehensive approach emphasizes the critical roles of RNA modifications and disulfidptosis in LUAD biology, paving the way for future research and clinical applications aimed at improving patient outcomes. [ABSTRACT FROM AUTHOR]

Precursors are evoked upstream of the Capgras' syndrome. Then, an analogy is suggested between the need for prognostic classification linked to the saturation of the asylum population at the dawn of the 20th century, and the current overflow of the psychiatric healthcare system. The contemporary situation justifies the search for information useful to mitigate ill mental health in at-risk adolescents. The article presents recent research reports on adolescents at-risk of emotional dysregulation, stemming from a longitudinal cohort database of European adolescents. The database analyses have revealed new brain and psychometric predictors of emotional dysregulation in adolescents. New early indicators were derived from easy-to-administer questionnaires, exploring emotions, affective symptoms and traits, sleep, early adversity and stress, puberty. Findings suggest that the physiology and stages of brain development could be taken into account for decisions regarding Mental Health. Studies on adolescent brain development have implications for public health, in terms of the age of protection for adolescents, and targeted prevention upstream of care. [ABSTRACT FROM AUTHOR]

Worldwide communication bandwidth growth has largely been driven by (1) multimedia demands, (2) multicommunication-point demands and (3) multicommunication-rate demands, and has increased dramatically over the last two decades due to e-commerce, internet communication and the explosion of cell-phone use, in particular for in-flight services, all of which necessitate broadband use and low latency. In order to accommodate this huge surge in demand, next generation "mega-constellations" of satellites are being proposed combining a mix of heterogeneous unit types in LEO, MEO and GEO orbital shells, in order to provide continuous lower-latency and high-bandwidth service which exploits a wide-range of frequencies for fast internet connections (broadband, which is not possible with single satellite-type orbital shell systems). Accordingly, in this work, we develop a computationally-efficient digital-twin framework for a constellation of satellites around an arbitrary planet ("Planet-X"). The rapid speed of these simulations enables the ability to explore satellite infrastructure parameter combinations, represented by a multicomponent satellite constellation design vector Λ = def (number of satellites, satellite orbital radii, satellite orbital speeds, satellite types), that can deliver desired communication signal or camera coverage on "Planet-X", while simultaneously incorporating satellite infrastructural resource constraints. In order to cast the objective mathematically, we set up the system design as an inverse problem to minimize a cost function via a Genetic Machine Learning Algorithm (G-MLA), which is well-suited for nonconvex optimization. Numerical examples are provided to illustrate the framework. [ABSTRACT FROM AUTHOR]

A longstanding project of the chemical kinetics community is to predict reaction rates and the behavior of reacting systems, even for systems where there are no experimental data. Many important reacting systems (atmosphere, combustion, pyrolysis, partial oxidations) involve a large number of reactions occurring simultaneously, and reaction intermediates that have never been observed, making this goal even more challenging. Improvements in our ability to compute rate coefficients and other important parameters accurately from first principles, and improvements in automated kinetic modeling software, have partially overcome many challenges. Indeed, in some cases quite complicated kinetic models have been constructed which accurately predicted the results of independent experiments. However, the process of constructing the models, and deciding which reactions to measure or compute ab initio, relies on accurate estimates (and indeed most of the numerical rate parameters in most large kinetic models are estimates.) Machine‐learned models trained on large datasets can improve the accuracy of these estimates, and allow a better integration of quantum chemistry and experimental data. The need for continued development of shared (perhaps open‐source) software and databases, and some directions for improvement, are highlighted. As we model more complicated systems, many of the weaknesses of the traditional ways of doing chemical kinetic modeling, and of testing kinetic models, have been exposed, identifying several challenges for future research by the community. [ABSTRACT FROM AUTHOR]

Food sustainability is crucial aspect in achieving several United Nations (UN) Sustainable Development Goals (SDGs). By integrating advanced technologies for reliable and accurate decision-making, we can advance food sustainability and, consequently, make significant advances toward achieving the UN SDGs. Rice, a staple crop in many Asian and some African nations, is crucial to Sri Lanka as well. Serving as the primary food for most Sri Lankans, it plays a vital role in sustaining the livelihoods of over 1.8 million farmers. In Sri Lanka, rice is grown during two distinct seasons of the year (Yala and Maha). This study focuses on ML with feature engineering for rice yield prediction using weather data: Rainfall, Maximum temperature, Minimum temperature, and Radiation. The data from two districts in Yala and Maha seasons collected from 1982 to 2019 were used for evaluating two sets of models respectively. Data were pre-processed to handle the outliers and missing values and scaled using normalization. The machine learning models considered are Linear Regression (LR), Support Vector Machine (SVM), k-Nearest Neighbour (KNN), and Random Forest (RF). The performance of these models was evaluated using metrics: Root Mean Squared Error (RMSE), Relative Root Mean Squared Error (RRMSE), and Mean Absolute Error (MAE). The results demonstrate that Random Forest Regression with less number of features can yield comparable results compared to the original set of features.Article Highlights: Rice is a staple food and vital to the livelihoods of millions of people worldwide. Therefore, accurate and timely prediction of rice yield is essential for global food security. The study integrates machine learning techniques and feature engineering on weather data (including rainfall and temperature) to improve rice yield predictions, thus contributing to food sustainability and progress toward the UN Sustainable Development Goals (SDGs). Among the machine learning models evaluated (Linear Regression, Support Vector Machine, k-Nearest Neighbour, and Random Forest), Random Forest Regression demonstrated that fewer features could produce results comparable to those using a full set of features, highlighting its efficiency in rice yield prediction. [ABSTRACT FROM AUTHOR]

To improve the abrasive waterjet drilling procedure for yttrium-stabilized zirconia-coated Inconel 718 superalloy, this study suggests an integrated approach using machine learning and an evolutionary algorithm. The objective is to simultaneously minimize the erosion diameter and taper angle of the drilled holes by identifying the best combination of drilling parameters such as stand-off distance, abrasive flow rate, waterjet pressure, and angle of impact. The machine learning models are developed using the random forest algorithm after tuning its hyperparameters to predict the erosion diameter and taper angle. The multi-verse optimization (MVO) algorithm is used to identify the best combination of drilling parameters. The comparison of results proved the efficacy of MVO over other algorithms. Confirmation experiment results are also in line with the results of MVO, since the percentage of deviation is meager. This integrative approach has the capability of significantly improving aerospace and industrial abrasive waterjet drilling operations. [ABSTRACT FROM AUTHOR]

Background: Breast cancer (BC) constitutes a significant peril to global women's health. Contemporary research progressively suggests that mitochondrial dysfunction plays a pivotal role in both the inception and advancement of BC. However, investigations delving into the correlation between mitochondrialrelated genes (MRGs) and the prognosis and metastasis of BC are still infrequent. Methods: Utilizing data from the TCGA database, we employed the "limma" R package for differential expression analysis. Subsequently, both univariate and multivariate Cox regression analyses were executed, alongside LASSO Cox regression analysis, to pinpoint prognostic MRGs and to further develop the prognostic model. External validation (GSE88770 merged GSE425680) and internal validation were further conducted. Our investigation delved into a broad spectrum of analyses that included functional enrichment, metabolic and immune characteristics, immunotherapy response prediction, intratumor heterogeneity (ITH), mutation, tumor mutational burden (TMB), microsatellite instability (MSI), cellular stemness, single-cell, and drug sensitivity analysis. We validated the protein and mRNA expressions of prognostic MRGs in tissues and cell lines through immunohistochemistry and qRT-PCR. Moreover, leveraging the GSE102484 dataset, we conducted differential gene expression analysis to identify MRGs related to metastasis, subsequently developing metastasis models via 10 distinct machine-learning algorithms and then selecting the bestperforming model. The division between training and validation cohorts was set at 70% and 30%, respectively. Results: A prognostic model was constructed by 9 prognostic MRGs, which were DCTPP1, FEZ1, KMO, NME3, CCR7, ISOC2, STAR, COMTD1, and ESR2. Patients within the high-risk group experienced more adverse outcomes than their counterparts in the low-risk group. The ROC curves and constructed nomogram showed that the model exhibited an excellent ability to predict overall survival (OS) for patients and the risk score was identified as an independent prognostic factor. The functional enrichment analysis showed a strong correlation between metabolic progression and MRGs. Additional research revealed that the discrepancies in outcomes between the two risk categories may be attributed to a variety of metabolic and immune characteristics, as well as differences in intratumor heterogeneity (ITH), tumor mutational burden (TMB), and cancer stemness indices. ITH, TIDE, and IPS analyses suggested that patients possessing a low-risk score may exhibit enhanced responsiveness to immunotherapy. Additionally, distant metastasis models were established by PDK4, NRF1, DCAF8, CHPT1, MARS2 and NAMPT. Among these, the XGBoost model showed the best predicting ability. Conclusion: In conclusion, MRGs significantly influence the prognosis and metastasis of BC. The development of dual clinical prediction models offers crucial insights for tailored and precise therapeutic strategies, and paves the way for exploring new avenues in understanding the pathogenesis of BC. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to develop and evaluate machine-learning models for predicting the onset of overweight in adolescents aged 14‒17, utilizing easily collectible personal information. Methods: This study was a one-year prospective cohort study. Baseline data were collected through anthropometric measurements and questionnaires, and the incidence of overweight was calculated one year later via anthropometric measurements. Predictive factors were selected through univariate analysis. Six machine-learning models were developed for predicting the onset of overweight. The SHapley Additive exPlanations (SHAP) was used for global and local interpretation of the models. Results: Out of 1,241 adolescents, 204 (16.4%) were identified as overweight after one year. Nineteen features were associated with the overweight incidence in univariable analysis. Participants were randomly divided into a training group and a testing group in a 7:3 ratio. The Light Gradient Boosting Machine (LGBM) algorithm achieved outperformed other models, achieving the following metrics: Accuracy (0.956), Recall (0.812), Specificity (0.983), F1-score (0.855), AUC (0.961). Importance ranking revealed that the top 11 minimal feature set can maintain the stability of model performance. Conclusions: The onset of overweight in adolescents was accurately predicted using easily collectible personal information. The LGBM-based model exhibited superior performance. Oversampling technique notably improved model performance. The model interpretation technique provided innovative strategies for managing adolescent overweight/obesity. [ABSTRACT FROM AUTHOR]

The rapid depletion of fossil fuel resources and their detrimental impact on the environment necessitates the exploration of renewable energy alternatives. Biomass stands out as a reliable renewable source, especially in multigeneration systems. This study suggests a biomass-driven multigeneration configuration for the production of electricity, heating, hydrogen, and freshwater. The configuration is evaluated from thermodynamic and economic perspectives, utilizing an Artificial Neural Network to predict key outcomes. The system optimization process integrates Machine Learning with decision-making methods to achieve optimal conditions. The findings highlight that an anode-cathode gas recycling design is the most effective configuration for the Solid Oxide Fuel Cell unit, achieving a cycle efficiency of 67.68% and a product cost of $11.41/GJ. Municipal Solid Waste biomass and CO 2 were identified as the most efficient fuel and gasification agents, respectively. The evaluations also determined that the integration of the multi-objective grey wolf optimizer and the CatBoost method is the most reliable machine learning model for optimization. Furthermore, by combining the Multi-Objective Harris Hawks Optimization algorithm with TOPSIS, LINMAP, and Fuzzy decision-making approaches, the system achieves optimal performance across multiple scenarios. In one scenario, the system reached an exergy efficiency of 67.68% and a hydrogen production rate of 22.34 kg/h. The optimum recycling ratios for the anode and cathode were determined to be 0.16 and 0.38, respectively. The study demonstrates the feasibility of the proposed configuration, offering significant potential for sustainable and cost-effective energy generation. • Biomass multigeneration system for power, hydrogen, and freshwater generation. • System optimized via MOGWO-CatBoost and multi-objective techniques. • Achieveing 67.68% efficiency with a product cost of $11.41/GJ. • MSW and CO 2 selection as the most efficient biomass and gasification agents. • Producing 22.34 kg/h hydrogen with integrated freshwater production. [ABSTRACT FROM AUTHOR]

Background: Lung cancer is the leading cause of cancer-related mortality worldwide. Lung cancer screening and early detection resulted in a decrease in cancer-specific mortality; however, it introduced additional dilemmas and adherence barriers for patients and providers. Methods: Innovations such as biomolecular diagnosis and biosensor-based technology improve the detection and stratification of high-risk patients and might assist in overcoming adherence barriers, hence providing new horizons for better selection of screened populations. Conclusions: In the present manuscript, we discuss some of the dilemmas clinicians are currently facing during the diagnosis and treatment processes. We further highlight the potential benefits of a novel biosensor platform for lung cancer detection during the decision making process surrounding lung cancer. [ABSTRACT FROM AUTHOR]

This review highlights the critical role of software sensors in advancing biosystem monitoring and control by addressing the unique challenges biological systems pose. Biosystems—from cellular interactions to ecological dynamics—are characterized by intrinsic nonlinearity, temporal variability, and uncertainty, posing significant challenges for traditional monitoring approaches. A critical challenge highlighted is that what is typically measurable may not align with what needs to be monitored. Software sensors offer a transformative approach by integrating hardware sensor data with advanced computational models, enabling the indirect estimation of hard-to-measure variables, such as stress indicators, health metrics in animals and humans, and key soil properties. This article outlines advancements in sensor technologies and their integration into model-based monitoring and control systems, leveraging the capabilities of Internet of Things (IoT) devices, wearables, remote sensing, and smart sensors. It provides an overview of common methodologies for designing software sensors, focusing on the modelling process. The discussion contrasts hypothetico-deductive (mechanistic) models with inductive (data-driven) models, illustrating the trade-offs between model accuracy and interpretability. Specific case studies are presented, showcasing software sensor applications such as the use of a Kalman filter in greenhouse control, the remote detection of soil organic matter, and sound recognition algorithms for the early detection of respiratory infections in animals. Key challenges in designing software sensors, including the complexity of biological systems, inherent temporal and individual variabilities, and the trade-offs between model simplicity and predictive performance, are also discussed. This review emphasizes the potential of software sensors to enhance decision-making and promote sustainability in agriculture, healthcare, and environmental monitoring. [ABSTRACT FROM AUTHOR]

The properties and relative stability of different structures of iron at the extreme conditions of pressure and temperature of relevance for the Earth's core were determined with ab‐initio atomistic simulations aided by a machine‐learning force‐field. We find that the body‐centered cubic (bcc) structure is mechanically stable at core temperatures, but its free energy is marginally higher than those of the hexagonal close‐packed and face‐centered cubic structures. The bcc structure is the only structure whose shear sound velocity matches seismic data. The small free‐energy difference between competing structures suggests that the role of impurities could be crucial in stabilizing the bcc structure in the inner core. Plain Language Summary: Determining the crystal structure and the elastic properties of the compound that forms the Earth's solid inner core is crucial to interpret seismic data. We know that the inner core is predominantly composed of iron, but laboratory‐based experiments and theoretical modeling haven't yet been able to constrain the crystal structure and the properties of pure Fe at the conditions of pressure and temperature found in the inner core. We have recently developed a deep‐learning‐aided atomistic simulation method that is able to determine Gibbs free energies of solids with quantum‐chemical accuracy (a few meV/atom). We find that although body‐centered cubic Fe is energetically slightly less favored than the hexagonal close‐packed form, the shear wave velocity of bcc Fe matches seismic data much better than all other crystal structures, suggesting that bcc is a strong candidate for the crystal structure of Fe in the Earth's inner core and could be stabilized by the presence of light elements in the core. Key Points: The body‐centered cubic structure of iron is mechanically stable at inner core conditionsThe hexagonal close‐packed structure is more stable, but small free energy differences could allow impurities to reverse this stabilityThe observed low shear velocity in the Earth's inner core is likely to be caused by the presence of the body‐centered cubic phase [ABSTRACT FROM AUTHOR]

Providing an appropriate difficulty level in a game is critical for keeping players engaged. Dynamic Difficulty Adjustment (DDA) is a common approach for optimizing player experience by automatically modifying game aspects. This paper reviews literature addressing mechanisms for adjusting video game difficulties in response to players' performance, emotions, or personality. For this purpose, we examined DDA studies using employed machine-learning techniques, player modeling approaches, data types used to assess players' states, testbed game genre, and application. Journal and conference articles published up to September 2022 served as the data sources in this review. The findings reveal that most studies have shown significant effects of DDA on parameters such as enjoyment, flow, motivation, engagement, and immersion. In addition, machine-learning and player modeling techniques have recently received more attention in the DDA design. However, given the ever-increasing use of games in various domains, more research is needed to understand player preferences better to adjust game parameters efficiently. By conducting further research into players' cognitive characteristics, such as visual attention, working memory, and response time, it will be possible to understand players' preferences better. [ABSTRACT FROM AUTHOR]

Introduction: Predicting which species are susceptible to viruses (i.e., host range) is important for understanding and developing effective strategies to control viral outbreaks in both humans and animals. The use of machine learning and bioinformatic approaches to predict viral hosts has been expanded with advancements in in-silico techniques. We conducted a scoping review to identify the breadth of machine learning methods applied to influenza and coronavirus genome data for the identification of susceptible host species. Methods: The protocol for this scoping review is available at https://hdl.handle.net/10214/26112. Five online databases were searched, and 1,217 citations, published between January 2000 and May 2022, were obtained, and screened in duplicate for English language and in-silico research, covering the use of machine learning to identify susceptible species to viruses. Results: Fifty-three relevant publications were identified for data charting. The breadth of research was extensive including 32 different machine learning algorithms used in combination with 29 different feature selection methods and 43 different genome data input formats. There were 20 different methods used by authors to assess accuracy. Authors mostly used influenza viruses (n = 31/53 publications, 58.5%), however, more recent publications focused on coronaviruses and other viruses in combination with influenza viruses (n = 22/53, 41.5%). The susceptible animal groups authors most used were humans (n = 57/77 analyses, 74.0%), avian (n = 35/77 45.4%), and swine (n = 28/77, 36.4%). In total, 53 different hosts were used and, in most publications, data from multiple hosts was used. Discussion: The main gaps in research were a lack of standardized reporting of methodology and the use of broad host categories for classification. Overall, approaches to viral host identification using machine learning were diverse and extensive. [ABSTRACT FROM AUTHOR]

To convert lightning indices generated by numerical weather prediction experiments into binary lightning hazard, a machine-learning tool was developed. This tool, consisting of parallel multilayer perceptron classifiers, was trained on an ensemble of planetary boundary layer schemes and microphysics parameterizations that generated four different lightning indices over 1 week. In a subsequent week, the multi-physics ensemble was applied and the machinelearning tool was used to evaluate the accuracy. Unintuitively, the machinelearning tool performed better on the testing dataset than the training dataset. Much of the error may be attributed to mischaracterizing the convection. The combination of the machine learning model and simulations could not differentiate between cloud-to-cloud lightning and cloud-to-ground lightning, despite being trained on cloud-to-ground lightning. It was found that the simulation most representative of the local operational model was the most accurate simulation tested. [ABSTRACT FROM AUTHOR]

Background: Infertility affects one in six couples worldwide, with advanced maternal age (AMA) posing unique challenges due to diminished ovarian reserve and reduced oocyte quality. Single vitrified-warmed blastocyst transfer (SVBT) has shown promise in assisted reproductive technology (ART), but success rates in AMA patients remain suboptimal. This study aimed to identify and refine predictive factors for live birth following SVBT in AMA patients, with the goal of enhancing clinical decision-making and enabling personalized treatment strategies. Methods: This retrospective cohort study analyzed 1,168 SVBT cycles conducted between June 2016 and December 2022 at the First Affiliated Hospital of Guangxi Medical University and Nanning Maternity and Child Health Hospital. Nineteen machine-learning models were applied to identify key predictive factors for live birth. Feature selection and 10-fold cross-validation were employed to validate the models. Results: The most significant predictors of live birth included inner cell mass quality, trophectoderm quality, number of oocytes retrieved, endometrial thickness, and the presence of 8-cell blastomeres on day 3. The stacking model demonstrated the best predictive performance (AUC: 0.791), followed by Extra Trees (AUC: 0.784) and Random Forest (AUC: 0.768). These models outperformed traditional methods, achieving superior accuracy, sensitivity, and specificity. Conclusion: Leveraging advanced machine-learning models and identifying critical predictive factors can improve the accuracy of live birth outcome predictions for AMA patients undergoing SVBT. These findings offer valuable insights for enhancing clinical decision-making and managing patient expectations. Further research is needed to validate these results in larger, multi-center cohorts and to explore additional factors, including fresh embryo transfers, to broaden the applicability of these models in clinical practice. [ABSTRACT FROM AUTHOR]

Remote sensing is now a valued solution for more accurately budgeting water supply by identifying spectral and spatial information. A study was put in place in a Vitis vinifera L. cv. Cabernet-Sauvignon vineyard in the San Joaquin Valley, CA, USA, where a variable rate automated irrigation system was installed to irrigate vines with twelve different water regimes in four randomized replicates, totaling 48 experimental zones. The purpose of this experimental design was to create variability in grapevine water status, in order to produce a robust dataset for modeling purposes. Throughout the growing season, spectral data within these zones was gathered using a Near InfraRed (NIR) - Short Wavelength Infrared (SWIR) hyperspectral camera (900 to 1700 nm) mounted on an Unmanned Aircraft Vehicle (UAV). Given the high water-absorption in this spectral domain, this sensor was deployed to assess grapevine stem water potential, Ψstem, a standard reference for water status assessment in plants, from pure grapevine pixels in hyperspectral images. The Ψstem was acquired simultaneously in the field from bunch closure to harvest and modeled via machine-learning methods using the remotely sensed NIR-SWIR data as predictors in regression and classification modes (classes consisted of physiologically different water stress levels). Hyperspectral images were converted to bottom of atmosphere reflectance using standard panels on the ground and through the Quick Atmospheric Correction Method (QUAC) and the results were compared. The best models used data obtained with standard panels on the ground and allowed predicting Ψstem values with an R2 of 0.54 and an RMSE of 0.11 MPa as estimated in cross-validation, and the best classification reached an accuracy of 74%. This project aims to develop new methods for precisely monitoring and managing irrigation in vineyards while providing useful information about plant physiology response to deficit irrigation. [ABSTRACT FROM AUTHOR]

Current research on game difficulty prediction mainly uses heuristic functions or physiological signals. The former does not consider user data, while the latter easily causes interference to the user. This paper proposes a difficulty prediction method based on multiple facial cues and game performance. Specifically, we first utilize various computer vision methods to detect players' facial expressions, gaze directions, and head poses. Then, we build a dataset by combining these three kinds of data and game performance as inputs, with the subjective difficulty ratings as labels. Finally, we compare the performance of several machine learning methods on this dataset using two classification tasks. The experimental results showed that the multilayer perceptron classifier (abbreviated as MLP) achieved the highest performance on these tasks, and its accuracy increased with the increase in input feature dimensions. These results demonstrate the effectiveness of our method. The proposed method could assist in improving game design and user experience. [ABSTRACT FROM AUTHOR]

In the realm of cybersecurity, spyware has emerged as a formidable adversary due to its persistent and stealthy nature. This study delves deeply into the multifaceted impact of spyware, meticulously examining its implications for individuals and organizations. This work introduces a systematic approach to spyware detection, leveraging decision trees (DT), a machine-learning classifier renowned for its analytical prowess. A pivotal aspect of this research involves the meticulous optimization of DT's hyperparameters, a critical operation for enhancing the precision of spyware threat identification. To evaluate the efficacy of the proposed methodology, the study employs the Obfuscated-MalMem2022 dataset, well-regarded for its comprehensive and detailed spyware-related data. The model is implemented using the Python programming language. Significantly, the findings of this study consistently demonstrate the superiority of the DT classifier over other methods. With an accuracy rate of 99.97%, the DT proves its exceptional effectiveness in detecting spyware, particularly in the face of more intricate threats. By advancing our understanding of spyware and providing a potent detection mechanism, this research equips cybersecurity professionals with a valuable tool to combat this persistent online menace. [ABSTRACT FROM AUTHOR]

Importance Firearm injuries constitute a public health crisis. At the healthcare encounter level, they are, however, rare events. Objective To develop a predictive model to identify healthcare encounters of adult patients at increased risk of firearm injury to target screening and prevention efforts. Materials and Methods Electronic health records data from Kaiser Permanente Southern California (KPSC) were used to identify healthcare encounters of patients with fatal and non-fatal firearm injuries, as well as healthcare visits of a sample of matched controls during 2010-2018. More than 170 predictors, including diagnoses, healthcare utilization, and neighborhood characteristics were identified. Extreme gradient boosting (XGBoost) and a split sample design were used to train and test a model that predicted risk of firearm injury within the next 3 years at the encounter level. Results A total of 3879 firearm injuries were identified among 5 288 529 KPSC adult members. Prevalence at the healthcare encounter level was 0.01%. The 15 most important predictors included demographics, healthcare utilization, and neighborhood-level socio-economic factors. The sensitivity and specificity of the final model were 0.83 and 0.56, respectively. A very high-risk group (top 1% of predicted risk) yielded a positive predictive value of 0.14% and sensitivity of 13%. This high-risk group potentially reduces screening burden by a factor of 11.7, compared to universal screening. Results for alternative probability cutoffs are presented. Discussion Our model can support more targeted screening in healthcare settings, resulting in improved efficiency of firearm injury risk assessment and prevention efforts. [ABSTRACT FROM AUTHOR]

The enormous amount of solar power and its state-of-the-art capturing technology that produces electricity, increases the grid interconnection rate of photovoltaic (PV) plants. Prior knowledge of the aperiodic characteristics of solar energy received by the Earth’s surface is essential for PV plants to ensure reliable operation and stable, secure grid connections. Power generation under diffused sunlight by PV plants with the most widely used first-generation solar cells has significant limitations. A dye-sensitized solar plant (DSSP), utilizes dye-sensitized solar cell (DSSC) technology, remains active in low light conditions. Though the activeness enables such plants to generate electricity throughout the year while receiving diffuse sunlight, unlike conventional solar technologies the plants have a requirement of knowledge of future power generation. This could be the first paper to report on the generated power forecast for such plants. The study has utilized a machine learning approach with a proposed DSSP model for the forecast. Spyder, an open-source integrated development environment, is the test workbench for the experimentation. The results show the robustness and reliability of the method, regardless of the weather conditions in the test area. The DSSP, along with the prediction model, will moderately overcome the shortcomings of power generation under diffuse daylight with intermittent solar radiation and grid connections. [ABSTRACT FROM AUTHOR]

Continuous renal replacement therapy (CRRT) is a life-saving procedure for sepsis but the benefit of CRRT varies and prediction of clinical outcomes is valuable in efficient treatment planning. This study aimed to use machine learning (ML) models trained using MIMIC III data for identifying sepsis patients who would benefit from CRRT. We first selected patients with sepsis and CRRT in the ICU setting and their gender, and an array of routine lab results were included as features to train machine learning models using 30-day mortality as the primary outcome. A total of 4161 patients were included for analysis, among whom there were 1342 deaths within 30 days. Without data augmentation, extreme gradient boosting (XGBoost) showed an accuracy of 64.2% with AUC-ROC of 0.61. Data augmentation using a conditional generative adversarial neural network (c-GAN) resulted in a significantly improved accuracy (82%) and ROC-AUC (0.78%). To enable prediction on pediatric patients, we adopted transfer learning approaches, where the weights of all but the last hidden layer were fixed, followed by fine-tuning of the weights of the last hidden layer using pediatric data of 200 patients as the inputs. A significant improvement was observed using the transfer learning approach (AUCROC = 0.76) compared to direct training on the pediatric cohort (AUCROC = 0.62). Through this transfer-learning-facilitated patient outcome prediction, our study showed that ML can aid in clinical decision-making by predicting patient responses to CRRT for managing pediatric sepsis. [ABSTRACT FROM AUTHOR]

Background: Fetal growth restriction (FGR) occurs in 10% of pregnancies worldwide. Placenta dysfunction, as one of the most common causes of FGR, is associated with various poor perinatal outcomes. The main objectives of this study were to screen potential diagnostic biomarkers for FGR and to evaluate the function of immune cell infiltration in the process of FGR. Methods: Firstly, differential expression genes (DEGs) were identified in two Gene Expression Omnibus (GEO) datasets, and gene set enrichment analysis was performed. Diagnosis-related key genes were identified by using three machine learning algorithms (least absolute shrinkage and selection operator, random forest, and support vector machine model), and the nomogram was then developed. The receiver operating characteristic curve, calibration curve, and decision curve analysis curve were used to verify the validity of the diagnostic model. Using cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT), the characteristics of immune cell infiltration in placental tissue of FGR were evaluated and the candidate key immune cells of FGR were screened. In addition, this study also validated the diagnostic efficacy of TREM1 in the real world and explored associations between TREM1 and various clinical features. Results: By overlapping the genes selected by three machine learning algorithms, four key genes were identified from 290 DEGs, and the diagnostic model based on the key genes showed good predictive performance (AUC = 0.971). The analysis of immune cell infiltration indicated that a variety of immune cells may be involved in the development of FGR, and nine candidate key immune cells of FGR were screened. Results from real-world data further validated TREM1 as an effective diagnostic biomarker (AUC = 0.894) and TREM1 expression was associated with increased uterine artery PI (UtA-PI) (pvalue = 0.029). Conclusion: Four candidate hub genes (SCD, SPINK1, TREM1, and HIST1H2BB) were identified, and the nomogram was constructed for FGR diagnosis. TREM1 was not only associated with a variety of key immune cells but also correlated with increased UtA-PI. The results of this study could provide some new clues for future research on the prediction and treatment of FGR. [ABSTRACT FROM AUTHOR]

The use of autonomous recording units (ARUs) has become an increasingly popular and powerful method of data collection for biological monitoring in recent years. However, the large-scale recordings collected using these devices are often nearly impossible for human analysts to parse through, as they require copious amounts of time and resources. Automated recognition techniques have allowed for quick and efficient analysis of these recordings, and machine learning (ML) approaches, such as deep learning, have greatly improved recognition robustness and accuracy. We evaluated the performance of two deep-learning algorithms: 1. our own custom convolutional neural network (CNN) detector (specialist approach) and 2. BirdNET, a publicly available detector capable of identifying over 6,000 bird species (generalist approach). We used audio recordings of mountain chickadees (Poecile gambeli) collected from ARUs and directional microphones in the field as our test stimulus set, with our custom detector trained to identify mountain chickadee songs. Using confidence thresholds of 0.6 for both detectors, we found that our custom CNN detector yielded higher detection compared to BirdNET. Given both ML approaches are significantly faster than a human detector and the custom CNN detector is highly accurate, we hope that our findings encourage bioacoustics practitioners to develop custom solutions for targeted species identification, especially given the availability of open-source toolboxes such as Koogu. [ABSTRACT FROM AUTHOR]

Background: Axillary lymph node dissection (ALND) is a standard procedure for early-stage breast cancer (BC) patients with three or more positive sentinel lymph nodes (SLNs). However, ALND can lead to significant postoperative complications without always providing additional clinical benefits. This study aims to develop machine-learning (ML) models to predict non-sentinel lymph node (non-SLN) metastasis in Chinese BC patients with three or more positive SLNs, potentially allowing the omission of ALND. Methods: Data from 2217 BC patients who underwent SLN biopsy at Shantou University Medical College were analyzed, with 634 having positive SLNs. Patients were categorized into those with ≤ 2 positive SLNs and those with ≥ 3 positive SLNs. We applied nine ML algorithms to predict non-SLN metastasis. Model performance was evaluated using ROC curves, precision-recall curves, and calibration curves. Decision Curve Analysis (DCA) assessed the clinical utility of the models. Results: The RF model showed superior predictive performance, achieving an AUC of 0.987 in the training set and 0.828 in the validation set. Key predictive features included size of positive SLNs, tumor size, number of SLNs, and ER status. In external validation, the RF model achieved an AUC of 0.870, demonstrating robust predictive capabilities. Conclusion: The developed RF model accurately predicts non-SLN metastasis in BC patients with ≥ 3 positive SLNs, suggesting that ALND might be avoided in selected patients by applying additional axillary radiotherapy. This approach could reduce the incidence of postoperative complications and improve patient quality of life. Further validation in prospective clinical trials is warranted. [ABSTRACT FROM AUTHOR]

Background: Bladder cancer, a highly fatal disease, poses a significant threat to patients. Positioned at 19q13.2-13.3, LIG1, one of the four DNA ligases in mammalian cells, is frequently deleted in tumour cells of diverse origins. Despite this, the precise involvement of LIG1 in BLCA remains elusive. This pioneering investigation delves into the uncharted territory of LIG1's impact on BLCA. Our primary objective is to elucidate the intricate interplay between LIG1 and BLCA, alongside exploring its correlation with various clinicopathological factors. Methods: We retrieved gene expression data of para-carcinoma tissues and bladder cancer (BLCA) from the GEO repository. Single-cell sequencing data were processed using the "Seurat" package. Differential expression analysis was then performed with the "Limma" package. The construction of scale-free gene co-expression networks was achieved using the "WGCNA" package. Subsequently, a Venn diagram was utilized to extract genes from the positively correlated modules identified by WGCNA and intersect them with differentially expressed genes (DEGs), isolating the overlapping genes. The "STRINGdb" package was employed to establish the protein-protein interaction (PPI) network.Hub genes were identified through the PPI network using the Betweenness Centrality (BC) algorithm. We conducted KEGG and GO enrichment analyses to uncover the regulatory mechanisms and biological functions associated with the hub genes. A machine-learning diagnostic model was established using the R package "mlr3verse." Mutation profiles between the LIG1^high and LIG1^low groups were visualized using the BEST website. Survival analyses within the LIG1^high and LIG1^low groups were performed using the BEST website and the GENT2 website. Finally, a series of functional experiments were executed to validate the functional role of LIG1 in BLCA. Results: Our investigation revealed an upregulation of LIG1 in BLCA specimens, with heightened LIG1 levels correlating with unfavorable overall survival outcomes. Functional enrichment analysis of hub genes, as evidenced by GO and KEGG enrichment analyses, highlighted LIG1's involvement in critical function such as the DNA replication, cellular senescence, cell cycle and the p53 signalling pathway. Notably, the mutational landscape of BLCA varied significantly between LIG1high and LIG1low groups. Immune infiltrating analyses suggested a pivotal role for LIG1 in immune cell recruitment and immune regulation within the BLCA microenvironment, thereby impacting prognosis. Subsequent experimental validations further underscored the significance of LIG1 in BLCA pathogenesis, consolidating its functional relevance in BLCA samples. Conclusions: Our research demonstrates that LIG1 plays a crucial role in promoting bladder cancer malignant progression by heightening proliferation, invasion, EMT, and other key functions, thereby serving as a potential risk biomarker. [ABSTRACT FROM AUTHOR]

The present study analyzes and optimizes machining characteristics, including feed rate (fz), depth of cut (ap), cutting speed (Vc), cutter-coated material (Mtc) and cutting-edge radius (rt), impacting on surface roughness (Ra), material removal rate (MRR) and tool wear (VB) of 42CrMo4 steel during dry end-milling. A total of 108 experimental runs were conducted, focusing on Ra, VB and MRR as response parameters. The nano TiAlN PVD-coated tool yielded better results for Ra and VB than did the TiCN/Al2O3 MT-CVD-coated tool. Then, Ra, VB and MRR optimization was carried out simultaneously using a Non-Dominated Sorting Genetic Algorithm III (NSGA-III) and Machine Learning (ML) models. Pareto solutions were found to offer a range of values for the three performance objectives: Ra (0.315–0.556 µm), VB (12.33–32.48 µm) and MRR (0.44–3.58 cm3/min). A quantitative performance score (Ps) ranking index was calculated to rank Pareto solutions for practical case studies. Validation experiments were subsequently performed to affirm that the optimal solution fell within a reasonable error range, with MAPE of 9.58% for Ra, 9.25% for VB and 13.39% for MRR. The validation results underscore the versatility of this approach, suggesting its applicability to a wide array of machining optimization challenges. Highlights: 108 experiments were conducted considering cutting speed (Vc), axial depth of cut (ap), feed per tooth (fz), cutting-edge radius (rt) and cutting-coated material (Mtc); The effect of cutting characteristics on surface roughness (Ra), flank wear (VB) and material removal rate (MRR) of 42CrMo4 was revealed; Machine learning models were developed to predict Ra, VB and MRR accurately; The multiobjective NSGA-III technique was employed to optimize Ra, VB and MRR simultaneously; These Pareto solutions underwent meticulous evaluation using a quantitative ranking index—the performance score (PS)—which thoughtfully considered user preferences and reliability; Experiments were performed to validate the optimum solution within an acceptance range of errors; [ABSTRACT FROM AUTHOR]

In the engineering design process, design fixation significantly constrains the diversity of design solutions. Numerous studies have aimed to mitigate design fixation, yet determining its occurrence in real-time remains a challenge. This research seeks to systematically identify the emergence of fixation through the behavior of novice designers in the early stages of the design process. We conducted a laboratory study, involving 50 novice designers possessing engineering drafting skills. Their design processes were monitored via video cameras, with both their design solutions and physical behaviors recorded. Subsequently, expert evaluators categorized design solutions into three types: Fixation, Low-quality, and Innovative. We manually recorded the names and durations of 31 different physical behaviors observed in the videos, which were then coded and filtered. Meanwhile, we propose a filtering and calculation method for the behavior in the design process. From this, four fixation behaviors were identified using variance analysis (ANOVA): Touch Mouth (TM), Touch Head (TH), Rest Head in Hands (RH), and Hold Face in Hands (HF). Our findings suggest that continuous interaction between the hand and head, mouth, or face can be indicative of a fixation state. Finally, we developed a Behavior-Fixation model based on the Support Vector Machine (SVM) for stage fixation judgment tasks, achieving an accuracy rate of 85.6%. This machine-learning model outperforms manual assessment in speed and accuracy. Overall, our study offers promising prospects for assisting designers in recognizing and avoiding design fixation. These findings, coupled with our proposed computational techniques, provide valuable insights for the development of automated and intelligent design innovation systems. [ABSTRACT FROM AUTHOR]

[Display omitted] For landslide prevention and control, it is essential to establish a landslide susceptibility prediction framework that can explain the model's decision-making process. Wushan County, Chongqing was selected as the study area, and seventeen landslide conditioning factors were initially chosen for this investigation. GeoDetector was used to remove noise factors and reduce the latitude of the data. The research investigates the use of three machine learning methods for assessing landslide susceptibility: SVM, RF, and XGBoost, and finally explains the decision mechanism of the model by SHAP-PDP. The results indicate that XGBoost has better evaluation results than RF and SVM. And XGBoost uncertainty is lower. The integrated interpretation framework based on SHAP-PDP can evaluate and interpret landslide susceptibility models both globally and locally, which is of great practical significance for the application of machine learning in landslide prediction. [ABSTRACT FROM AUTHOR]

In the competitive landscape of Airbnb hosting, optimizing pricing strategies for properties is a complex challenge that requires revenue maximization with high occupancy rates. This research aimed to introduce a solution that leverages big data and machine learning techniques to help hosts improve their property's market performance. Our primary goal was to introduce a solution that can augment property owners' understanding of their property's market value within their urban context, thereby optimizing both the utilization and profitability of their listings. We employed a multi-faceted approach with diverse models, including support vector regression, XGBoost, and neural networks, to analyze the influence of factors such as location, host attributes, and guest reviews on a listing's financial performance. To further refine our predictive models, we integrated natural language processing techniques for in-depth listing review analysis, focusing on term frequency-inverse document frequency (TF-IDF), bag-of-words, and aspect-based sentiment analysis. Integrating such techniques allowed for in-depth listing review analysis, providing nuanced insights into guest preferences and satisfaction. Our findings demonstrated that AirBnB hosts can effectively utilize both state-of-the-art and traditional machine learning algorithms to better understand customer needs and preferences, more accurately assess their listings' market value, and focus on the importance of dynamic pricing strategies. By adopting this data-driven approach, hosts can achieve a balance between maintaining competitive pricing and ensuring high occupancy rates. This method not only enhances revenue potential but also contributes to improved guest satisfaction and the growing field of data-driven decisions in the sharing economy, specially tailored to the challenges of short-term rentals. [ABSTRACT FROM AUTHOR]

Physical reservoir computing (PRC) with visible-light signals was demonstrated using dye-sensitized solar cells. The short-term memory required for PRC was confirmed using light pulse inputs. Waveform learning was demonstrated for nonlinear autoregressive moving-average time series level 2 (NARMA2) signals with normalized mean square error of 0.027. The relatively slow (milliseconds to seconds) and complex charge transfer dynamics in the TiO2 porous layer with redox reactions in the solution phase provided the characteristics required for PRC. [ABSTRACT FROM AUTHOR]

Revolutions are invariably viewed as the violent replacement of an existing political order. However, many social innovations that result in fundamental institutional and cultural shifts do not occur via force nor have clear beginning and ending dates. Focusing on early-modern England, we provide the first-ever quantitative inquiry into such quiet revolutions. Using existing topic model estimates that leverage caselaw and print-culture corpora, we construct annual time series of attention to 100 legal and 110 cultural ideas between the mid-sixteenth and mid-eighteenth centuries. We estimate the timing of structural breaks in these series. Quiet revolutions begin when there are concurrent upturns in attention to several related topics. Early-modern England featured several quiet, but profound, revolutionary episodes. The financial revolution began by 1660. The Protectorate saw a revolution in land law. A revolution in caselaw relating to families was underway by the early eighteenth century. Elizabethan times saw an increased emphasis on basic skills and showed signs of a Puritan revolution affecting both theology and ideas on institutions. In the decade before the Civil War, a quiet revolution of dissent preceded the turmoil that led to a king's beheading. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of solving Fokker–Planck equations, which are prevalent mathematical models across a myriad of scientific fields. Due to factors like fractional-order derivatives and non-linearities, obtaining exact solutions to this problem can be complex. To overcome these challenges, our framework first discretizes the given equation using the Crank-Nicolson finite difference method, transforming it into a system of ordinary differential equations. Here, the approximation of time dynamics is done using forward difference or an L1 discretization technique for integer or fractional-order derivatives, respectively. Subsequently, these ordinary differential equations are solved using a novel strategy based on a kernel-based machine learning algorithm, named collocation least-squares support vector regression. The effectiveness of the proposed approach is demonstrated through multiple numerical experiments, highlighting its accuracy and efficiency. This performance establishes its potential as a valuable tool for tackling Fokker–Planck equations in diverse applications. [ABSTRACT FROM AUTHOR]

Chenchun Ding,1 Zhenzhen Guo,2 Quan Liao,1 Renjie Zuo,1 Junjie He,1 Ziwei Ye,2 Weibin Chen1 1Department of Thoracic Surgery, Zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, 361102, People’s Republic of China; 2School of Pharmaceutical Sciences, Xiamen University, Xiamen, Fujian, 361102, People’s Republic of ChinaCorrespondence: Weibin Chen, Department of Thoracic Surgery, Zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, 361102, People’s Republic of China, Email cwbxmu@163.comPurpose: Idiopathic pulmonary fibrosis (IPF) is an irreversible respiratory disease. In this study, we evaluated the efficacy of salidroside (SAL), the main component of Rhodiola rosea, in treating IPF.Methods: The pharmacological effects of SAL against epithelial-mesenchymal transition (EMT) and IPF were assessed through in vivo and in vitro experiments. Targets for SAL in treating IPF were identified from various databases and a PPI network was constructed. Functional analyses of target genes were performed using GO, KEGG, DO, and GSEA. Core target genes were identified using LASSO logistic regression and support vector machine (SVM) analysis, followed by molecular docking simulations. Predicted targets and pathways were validated through Western blotting, qRT-PCR, and IHC.Results: Our results demonstrated that SAL ameliorated alveolar epithelial cells (AECs) EMT and mitigated bleomycin -induced pulmonary fibrosis. Through network pharmacology, we identified 74 targets for SAL in the treatment of IPF (PFDR< 0.05) and analyzed their biological functions. Based on these findings, we further applied machine learning techniques to narrow down 9 core targets (PFDR< 0.05). Integrating the results from molecular docking, KEGG, and GSEA analyses, we selected three key targets—IGF1, hypoxia-inducible factor 1-alpha (HIF-1α), and MAPK (PFDR< 0.05)—for further investigation. Our study revealed that SAL inhibits the IGF1 signaling pathway, thereby improving AECs senescence and cell cycle arrest. By inhibiting the HIF-1α pathway, SAL alleviates endoplasmic reticulum stress and reduces intracellular ROS accumulation. Moreover, SAL suppresses the activation of the MAPK signaling pathway, leading to a decrease in inflammation markers in AECs and lung tissue.Conclusion: Experimental results suggest that SAL effectively ameliorates BLM-induced EMT and IPF, likely through the inhibition of IGF1, HIF-1α, and MAPK signaling pathways. This study holds potential translational prospects and may provide new perspectives and insights for the use of traditional Chinese medicine in the treatment of IPF.Keywords: salidroside, idiopathic pulmonary fibrosis, network pharmacology, machine-learning, molecular docking

Abstract Food sustainability is crucial aspect in achieving several United Nations (UN) Sustainable Development Goals (SDGs). By integrating advanced technologies for reliable and accurate decision-making, we can advance food sustainability and, consequently, make significant advances toward achieving the UN SDGs. Rice, a staple crop in many Asian and some African nations, is crucial to Sri Lanka as well. Serving as the primary food for most Sri Lankans, it plays a vital role in sustaining the livelihoods of over 1.8 million farmers. In Sri Lanka, rice is grown during two distinct seasons of the year (Yala and Maha). This study focuses on ML with feature engineering for rice yield prediction using weather data: Rainfall, Maximum temperature, Minimum temperature, and Radiation. The data from two districts in Yala and Maha seasons collected from 1982 to 2019 were used for evaluating two sets of models respectively. Data were pre-processed to handle the outliers and missing values and scaled using normalization. The machine learning models considered are Linear Regression (LR), Support Vector Machine (SVM), k-Nearest Neighbour (KNN), and Random Forest (RF). The performance of these models was evaluated using metrics: Root Mean Squared Error (RMSE), Relative Root Mean Squared Error (RRMSE), and Mean Absolute Error (MAE). The results demonstrate that Random Forest Regression with less number of features can yield comparable results compared to the original set of features.

Abstract Background Lung adenocarcinoma (LUAD) represents a significant global health burden, necessitating advanced prognostic tools for improved patient management. RNA modifications (m6A, m1A, m5C, m7G), and disulfidptosis, a novel cell death mechanism, have emerged as promising biomarkers and therapeutic targets in cancer. Methods We systematically compiled disulfidptosis-correlated genes and RNA modification-related genes from existing literature. A novel disulfidptosis-correlated m6A/m1A/m5C/m7G riskscore was computed using integrated machine-learning algorithms. Transcriptomic data from TCGA and GEO databases were downloaded analyzed. Single-cell RNA-sequencing data from the TISCH database was processed using the Seurat package. Genes’ protein–protein interaction network was constructed using the String database. Functional phenotype analysis was performed using GSVA, ClusterProfiler, and IOBR packages. Consensus clustering divided patients into two distinct groups. Drug sensitivity predictions were obtained from the GDSC1 database and predicted using the Oncopredict package. Results The disulfidptosis-correlated m6A/m1A/m5C/m7G risk score effectively stratified LUAD patients into prognostically distinct groups, demonstrating superior predictive accuracy compared to conventional clinical parameters. Patients in different risk groups exhibited significant molecular and clinical differences. Subsequent analyses identified two molecular subtypes associated with RNA modification and disulfidptosis, revealing differences in immune infiltration and prognosis. Functional enrichment analyses highlighted pathways involving RNA modification and disulfidptosis, underscoring their roles in LUAD pathogenesis. Single-cell analysis revealed distinct features between high- and low-risk status cells. Conclusion This study introduces a novel disulfidptosis-correlated m6A/m1A/m5C/m7G risk score as a robust prognostic tool for LUAD, integrating insights from RNA modifications and cell death mechanisms. The risk score enhances prognostic stratification and identifies potential targets for personalized therapeutic strategies in LUAD. This comprehensive approach emphasizes the critical roles of RNA modifications and disulfidptosis in LUAD biology, paving the way for future research and clinical applications aimed at improving patient outcomes.

Abstract Classifying individuals based on metabotypes and lifestyle phenotypes using exploratory factor analyses, cluster definition, and machine-learning algorithms is promising for precision chronic disease prevention and management. This study analyzed data from the NUTRiMDEA online cohort (baseline: n = 17332 and 62 questions) to develop a clustering tool based on 32 accessible questions using machine-learning strategies. Participants ranged from 18 to over 70 years old, with 64.1% female and 35.5% male. Five clusters were identified, combining metabolic, lifestyle, and personal data: Cluster 1 (“Westernized Millennial”, n = 967) included healthy young individuals with fair lifestyle habits; Cluster 2 (“Healthy”, n = 10616) consisted of healthy adults; Cluster 3 (“Mediterranean Young Adult”, n = 2013) represented healthy young adults with a healthy lifestyle and showed the highest adherence to the Mediterranean diet; Cluster 4 (“Pre-morbid”, n = 600) was characterized by healthy adults with declined mood; Cluster 5 (“Pro-morbid”, n = 312) comprised older individuals (47% >55 years) with poorer lifestyle habits, worse health, and a lower health-related quality of life. A computational algorithm was elicited, which allowed quick cluster assignment based on responses (“lifemetabotypes”). This machine-learning approach facilitates personalized interventions and precision lifestyle recommendations, supporting online methods for targeted health maintenance and chronic disease prevention.

Objectives: To explore the predictive performance on the need for surgical intervention in patients with adhesive small bowel obstruction (ASBO) using machine-learning (ML) algorithms and investigate the optimal timing for transition to surgery. Methods: One hundred and six patients with ASBO who initially underwent long transnasal intestinal tube (LT) decompression were enrolled in this retrospective study. Traditional logistic regression analysis and ML algorithms were used to evaluate the risk of need for surgical intervention. Results: Non-operative management (NOM) by LT decompression failed in 28 patients (26%). Multivariate logistic regression analysis identified a drainage volume 665 ml via LT on day 1, interval between ASBO diagnosis and LT intubation, and small bowel dilatation at 48 h after LT intubation to be independent predictors of transition to surgery (odds ratios 7.10, 1.42, and 19.81, respectively; 95% confidence intervals 1.63-30.94, 1.00-2.02, and 3.04-129.10; P-values 0.009, 0.047, and 0.002). The random forest algorithm showed the best predictive performance of five ML algorithms tested, with an area under the curve of 0.889, accuracy of 0.864, and precision of 0.667 in the test set. 97.4% of patients without transition to surgery (n=78) had passes of first flatus until three days. Conclusions: This is the first study to demonstrate that ML algorithm can predict the need for surgery in patients with ASBO. The guideline recommended period for initial NOM of 72 h seems to be reasonable. These findings can be used to develop a framework for earlier clinical decision-making in these patients.

Abstract Background Infertility affects one in six couples worldwide, with advanced maternal age (AMA) posing unique challenges due to diminished ovarian reserve and reduced oocyte quality. Single vitrified-warmed blastocyst transfer (SVBT) has shown promise in assisted reproductive technology (ART), but success rates in AMA patients remain suboptimal. This study aimed to identify and refine predictive factors for live birth following SVBT in AMA patients, with the goal of enhancing clinical decision-making and enabling personalized treatment strategies. Methods This retrospective cohort study analyzed 1,168 SVBT cycles conducted between June 2016 and December 2022 at the First Affiliated Hospital of Guangxi Medical University and Nanning Maternity and Child Health Hospital. Nineteen machine-learning models were applied to identify key predictive factors for live birth. Feature selection and 10-fold cross-validation were employed to validate the models. Results The most significant predictors of live birth included inner cell mass quality, trophectoderm quality, number of oocytes retrieved, endometrial thickness, and the presence of 8-cell blastomeres on day 3. The stacking model demonstrated the best predictive performance (AUC: 0.791), followed by Extra Trees (AUC: 0.784) and Random Forest (AUC: 0.768). These models outperformed traditional methods, achieving superior accuracy, sensitivity, and specificity. Conclusion Leveraging advanced machine-learning models and identifying critical predictive factors can improve the accuracy of live birth outcome predictions for AMA patients undergoing SVBT. These findings offer valuable insights for enhancing clinical decision-making and managing patient expectations. Further research is needed to validate these results in larger, multi-center cohorts and to explore additional factors, including fresh embryo transfers, to broaden the applicability of these models in clinical practice.

Abstract Continuous renal replacement therapy (CRRT) is a life-saving procedure for sepsis but the benefit of CRRT varies and prediction of clinical outcomes is valuable in efficient treatment planning. This study aimed to use machine learning (ML) models trained using MIMIC III data for identifying sepsis patients who would benefit from CRRT. We first selected patients with sepsis and CRRT in the ICU setting and their gender, and an array of routine lab results were included as features to train machine learning models using 30-day mortality as the primary outcome. A total of 4161 patients were included for analysis, among whom there were 1342 deaths within 30 days. Without data augmentation, extreme gradient boosting (XGBoost) showed an accuracy of 64.2% with AUC-ROC of 0.61. Data augmentation using a conditional generative adversarial neural network (c-GAN) resulted in a significantly improved accuracy (82%) and ROC-AUC (0.78%). To enable prediction on pediatric patients, we adopted transfer learning approaches, where the weights of all but the last hidden layer were fixed, followed by fine-tuning of the weights of the last hidden layer using pediatric data of 200 patients as the inputs. A significant improvement was observed using the transfer learning approach (AUCROC = 0.76) compared to direct training on the pediatric cohort (AUCROC = 0.62). Through this transfer-learning-facilitated patient outcome prediction, our study showed that ML can aid in clinical decision-making by predicting patient responses to CRRT for managing pediatric sepsis.

Abstract Decades of research in exercise immunology have demonstrated the profound impact of exercise on the immune response, influencing an individual's disease susceptibility. Accurate prediction of white blood cells (WBCs) count during exercise can help to design effective training programs to maintain optimal the immune system function and prevent its suppression. In this regard, this study aimed to develop an easy-to-use and efficient modelling tool for predicting WBCs count during exercise. To achieve this goal, the predictive power of a range of machine-learning algorithms, including six standalone models (M5 prime (M5P), random forest (RF), alternating model trees (AMT), reduced error pruning tree (REPT), locally weighted learning (LWL), and support vector regression (SVR)) were assessed along with six types of hybrid models trained with a bagging (BA) algorithm (BA-M5P, BA-RF, BA-AMT, BA-REPT, BA-LWL, and BA- SVR). A comprehensive database was constructed from 200 eligible people. The models employed post-exercise training WBCs counts as the output parameter and seven WBCs-influencing factors, including intensity and duration of exercise, pre-exercise training WBCs counts, age, body fat percentage, maximal aerobic capacity, and muscle mass as input parameters. Comparing the prediction results of the models to the observed WBCs using standard statistics indicated that the BA-M5P model had the greatest potential to produce a robust prediction of the number of lymphocytes, neutrophils, monocytes, and WBC compared to other models. Moreover, pre-exercise training WBCs counts, intensity and duration of exercise and body fat percentage were the most important features in predicting WBCs counts. These findings hold significant implications for the advancement of exercise immunology and the promotion of public health.

Abstract Enhlink is a computational tool for scATAC-seq data analysis, facilitating precise interrogation of enhancer function at the single-cell level. It employs an ensemble approach incorporating technical and biological covariates to infer condition-specific regulatory DNA linkages. Enhlink can integrate multi-omic data for enhanced specificity, when available. Evaluation with simulated and real data, including multi-omic datasets from the mouse striatum and novel promoter capture Hi-C data, demonstrate that Enhlink outperfoms alternative methods. Coupled with eQTL analysis, it identified a putative super-enhancer in striatal neurons. Overall, Enhlink offers accuracy, power, and potential for revealing novel biological insights in gene regulation.

Abstract Background Axillary lymph node dissection (ALND) is a standard procedure for early-stage breast cancer (BC) patients with three or more positive sentinel lymph nodes (SLNs). However, ALND can lead to significant postoperative complications without always providing additional clinical benefits. This study aims to develop machine-learning (ML) models to predict non-sentinel lymph node (non-SLN) metastasis in Chinese BC patients with three or more positive SLNs, potentially allowing the omission of ALND. Methods Data from 2217 BC patients who underwent SLN biopsy at Shantou University Medical College were analyzed, with 634 having positive SLNs. Patients were categorized into those with ≤ 2 positive SLNs and those with ≥ 3 positive SLNs. We applied nine ML algorithms to predict non-SLN metastasis. Model performance was evaluated using ROC curves, precision-recall curves, and calibration curves. Decision Curve Analysis (DCA) assessed the clinical utility of the models. Results The RF model showed superior predictive performance, achieving an AUC of 0.987 in the training set and 0.828 in the validation set. Key predictive features included size of positive SLNs, tumor size, number of SLNs, and ER status. In external validation, the RF model achieved an AUC of 0.870, demonstrating robust predictive capabilities. Conclusion The developed RF model accurately predicts non-SLN metastasis in BC patients with ≥ 3 positive SLNs, suggesting that ALND might be avoided in selected patients by applying additional axillary radiotherapy. This approach could reduce the incidence of postoperative complications and improve patient quality of life. Further validation in prospective clinical trials is warranted.

For landslide prevention and control, it is essential to establish a landslide susceptibility prediction framework that can explain the model’s decision-making process. Wushan County, Chongqing was selected as the study area, and seventeen landslide conditioning factors were initially chosen for this investigation. GeoDetector was used to remove noise factors and reduce the latitude of the data. The research investigates the use of three machine learning methods for assessing landslide susceptibility: SVM, RF, and XGBoost, and finally explains the decision mechanism of the model by SHAP-PDP. The results indicate that XGBoost has better evaluation results than RF and SVM. And XGBoost uncertainty is lower. The integrated interpretation framework based on SHAP-PDP can evaluate and interpret landslide susceptibility models both globally and locally, which is of great practical significance for the application of machine learning in landslide prediction.

BACKGROUND: HIV subtype is associated with varied rates of disease progression. The HIV accessory protein, Nef, continues to be present during antiretroviral therapy (ART) where it has numerous immunoregulatory effects. In this study, we analyzed Nef sequences from HIV subtypes A1, B, C, and D using a machine learning approach that integrates functional amino acid information to identify if unique physicochemical features are associated with Nef functional/structural domains in a subtype-specific manner. METHODS: 2253 sequences representing subtypes A1, B, C, and D were aligned and domains with known functional properties were scored based on amino acid physicochemical properties. Following feature generation, we used statistical pruning and evolved neural networks (ENNs) to determine if we could successfully classify subtypes. Next, we used ENNs to identify the top five key Nef physicochemical features applied to specific immunoregulatory domains that differentiated subtypes. A signature pattern analysis was performed to the assess amino acid diversity in sub-domains that differentiated each subtype. RESULTS: In validation studies, ENNs successfully differentiated each subtype at A1 (87.2%), subtype B (89.5%), subtype C (91.7%), and subtype D (85.1%). Our feature-based domain scoring, followed by t-tests, and a similar ENN identified subtype-specific domain-associated features. Subtype A1 was associated with alterations in Nef CD4 binding domain; subtype B was associated with alterations with the AP-2 Binding domain; subtype C was associated with alterations in a structural Alpha Helix domain; and, subtype D was associated with alterations in a Beta-Sheet domain. CONCLUSIONS: Recent studies have focused on HIV Nef as a driver of immunoregulatory disease in those HIV infected and on ART. Nef acts through a complex mixture of interactions that are directly linked to the key features of the subtype-specific domains we identified with the ENN. The study supports the hypothesis that varied Nef subtypes contribute to subtype-specific disease progression.

Zimbabwe, located in Southern Africa, faces a significant public health challenge due to schistosomiasis. We investigated this issue with emphasis on risk prediction of schistosomiasis for the entire population. To this end, we reviewed available data on schistosomiasis in Zimbabwe from a literature search covering the 1980-2022 period considering the potential impact of 26 environmental and socioeconomic variables obtained from public sources. We studied the population requiring praziquantel with regard to whether or not mass drug administration (MDA) had been regularly applied. Three machine-learning algorithms were tested for their ability to predict the prevalence of schistosomiasis in Zimbabwe based on the mean absolute error (MAE), the root mean squared error (RMSE) and the coefficient of determination (R2). The findings revealed different roles of the 26 factors with respect to transmission and there were particular variations between Schistosoma haematobium and S. mansoni infections. We found that the top-five correlation factors, such as the past (rather than current) time, unsettled MDA implementation, constrained economy, high rainfall during the warmest season, and high annual precipitation were closely associated with higher S. haematobium prevalence, while lower elevation, high rainfall during the warmest season, steeper slope, past (rather than current) time, and higher minimum temperature in the coldest month were rather related to higher S. mansoni prevalence. The random forest (RF) algorithm was considered as the formal best model construction method, with MAE = 0.108; RMSE = 0.143; and R2 = 0.517 for S. haematobium, and with the corresponding figures for S. mansoni being 0.053; 0.082; and 0.458. Based on this optimal model, the current total schistosomiasis prevalence in Zimbabwe under MDA implementation was 19.8%, with that of S. haematobium at 13.8% and that of S. mansoni at 7.1%, requiring annual MDA based on a population of 3,003,928. Without MDA, the current total schistosomiasis prevalence would be 23.2%, that of S. haematobium 17.1% and that of S. mansoni prevalence at 7.4%, requiring annual MDA based on a population of 3,521,466. The study reveals that MDA alone is insufficient for schistosomiasis elimination, especially that due to S. mansoni. This study predicts a moderate prevalence of schistosomiasis in Zimbabwe, with its elimination requiring comprehensive control measures beyond the currently used strategies, including health education, snail control, population surveillance and environmental management.