Binary Model Research Articles

NO classifier prediction of anti neuroinflammatory agents using text mining of 3D molecular fingerprints.

CNS Drug discovery has been challenging due to the lack of clarity on CNS diseases' basic biological and pathological mechanisms. Despite the difficulty, some CNS drugs have been developed based on phenotypic effects. Herein, we propose a phenotype-structure relationship model, which predicts an anti-neuroinflammatory potency based on 3D molecular structures of the phenotype-active or inactive compounds without specifying targets. For this chemo-centric study, a predictive model of the nitric oxide (NO) inhibitory potency in hyper-activated microglia is built from the 548 agents, which were collected from 95 research articles (28 substructures consisting of natural products and synthetic scaffolds) and doubly externally validated by the agents of 9 research articles as third set. 3D Structures (multi-conformer ensemble) of every agent were encoded into the E3FP molecular fingerprint of the Keiser group as a 3D molecular representation. The location information of the molecular fingerprints could be learned and validated to classify the inhibitory potency of compounds (IC50 cut-off between the active and inactive: 37.1 µM): (1) multi-layer perceptron (MLP) (AUC-CV: 0.997, AUC-Test: 0.992), (2) recurrent neural network (RNN) (AUC-CV: 0.999, AUC-Test: 0.995), and (3) convolutional neural network (CNN) (AUC-CV: 0.998, AUC-Test: 0.994). The high performance of these models was compared with that of four classical machine classification models (Logistic, Ridge, Lasso, and Naïve Bayes). We named the binary classification models NO-Classifier. Independent test set validation and decision region analysis of the independent test set doubly demonstrated NO-Classifier effectively discerned the anti-inflammatory potency of testing compounds in inflammatory cell phenotype with the webserver in https://no-classifier.onrender.com.

Exploring the Motives Behind the Adoption of Climate Change Adaptation Strategies among Farmers in the Czech Republic

AbstractClimate change threatens agriculture in the EU and is a primary issue discussed in the European Green Deal within the Common Agricultural Policy. Central and Eastern European countries are particularly prone to climate change effects, such as droughts and extreme weather. Therefore, agriculture in Central and Eastern Europe is expected to be increasingly affected by shifting climatic patterns. This study examines the motivation for adopting adaptation strategies derived from climate-smart agriculture among farmers in the Czech Republic. We drew particular attention to analyzing the influence of farm-level and information source variables on the adaptation behavior of Czech farmers. The dataset comprises 358 respondents who were asked about climate change adaptation through a quantitative survey. We analyzed the collected data via descriptive statistics and binary logit regression models. The analysis results reveal a high degree of awareness and a diversified usage of climate change adaptation strategies among the respondents. The close linkage between perceived profitability and the willingness to adapt to climate change requires policymakers to communicate economic benefits within this context further. Information sources, such as topic-specific journals, research institutions, and field training, positively influenced the adaptation rates among the sample. Therefore, we recommend focusing on these media channels to communicate targets set within the European Green Deal.

Stellar expansion or inflation?

While stellar expansion after core-hydrogen exhaustion related to thermal imbalance has been documented for decades, the physical phenomenon of stellar inflation that occurs close to the Eddington limit has only come to the fore in recent years. We aim to elucidate the differences between these physical mechanisms for stellar radius enlargement, especially given that additional terms such as `bloated' and `puffed-up' stars have been introduced in the recent massive star literature. We employ single and binary star MESA structure and evolution models for constant mass, as well as models allowing the mass to change due to winds or binary interaction. We find cases that were previously attributed to stellar inflation in fact to be due to stellar expansion. We also highlight that while the opposite effect of expansion is contraction, the removal of an inflated zone should not be referred to as contraction but rather deflation as the star is still in thermal balance.

BCDPi: An Interpretable Multitask Deep Neural Network Model for Predicting Chemical Bioconcentration in Fish.

Predicting the bioconcentration of chemical compounds plays a crucial role in assessing environmental risks and toxicological impacts. This study presents a robust multitask deep learning model for predicting the bioconcentration potential. The model can predict the bioconcentration of compounds in multiple categories, including non-bioconcentrative (non-BC), weakly bioconcentrative (weak-BC), and strongly bioconcentrative (strong-BC). We also employed the SHapley Additive exPlanations (SHAP) technology for the model interpretation. The binary classification models (non-BC vs BC and weak-BC vs strong-BC) showed good predictive performance, which achieved accuracy values over 90% and area under the curve (AUC) values with 0.95. The final ternary classification model provided an overall accuracy with 91.11%. Comparative analysis of molecular physicochemical properties showed that the importance of molecular weight, polar surface area, solubility, and hydrogen bonding are important for chemical bioconcentration. Besides, we identified eight structural alerts responsible for chemical bioconcentration. We made the model available as an online tool named BCdpi-predictor, which is accessible at http://bcdpi.sapredictor.cn/. Users can predict the bioconcentration potential of chemical compounds freely. The model has significant implications for environmental policy and regulatory frameworks, such as REACH, by providing a more accurate and interpretable method for assessing chemical risks. We hope that the results of this study can provide helpful tools and meaningful information for chemical bioconcentration prediction in environmental risk assessment.

Survival models and longitudinal medical events for hospital readmission forecasting.

The rate of 30-day all-cause hospital readmissions can affect the funding a hospital receives. An accurate and reliable readmission prediction model could save money and increase quality-of-care. Few projects have explored formulating this task as a survival prediction problem, where models can exploit a real-valued time-to-readmission target. This paper demonstrates the effectiveness of a survival-inspired readmission model, especially when paired with a longitudinal patient representation that is agnostic to disease-cohort and predictive task. We forecast readmissions for a population-level cohort of 421,088 patients discharged in 2015 and 2016 from hospitals in Alberta, Canada. Clinical features and sequences of historical medical codes (calculated from at least four full years prior to discharge) from linked administrative sources serve as model inputs. We trained binary 30-day readmission models (XGBoost and a Deep Neural Network) and time-to-event readmission models (CoxPH and N-MTLR) with and without machine-learned medical knowledge at initialization, then compared against the popular LACE-based model using the AUROC score at 30 days (AUROC@30). Survival models are additionally evaluated using concordance, Integrated Brier, and L1-loss scores. All models that utilize sequence features markedly out-perform even the best models trained on only clinical features. Further, a time-to-event target improves predictive performance at 30 days, given the same model inputs and architecture. N-MTLR, using solely sequence inputs and initialized with pre-learned medical knowledge, achieves an average AUROC@30 of 0.8460 over five folds with a standard deviation of 0.003. All trained models match or out-perform the LACE baseline of 0.6587±0.003. Sequences of administrative medical codes contain rich predictive information for forecasting readmissions, and embedding medical knowledge a priori using machine learning provides readmission models an advantageous foundation for training. When combined with a model that can leverage a time-to-event target, excellent performance is possible on the 30-day all-cause readmission task using only administrative data.

Abstract B065: FabricaTM: A large-scale data simulation platform isolates tumor signal from cell-free DNA and improves tissue of origin prediction accuracy

Abstract Cell-free DNA (cfDNA) liquid biopsy is a promising non-invasive method for disease detection, but data availability and the complexity of cfDNA composition pose barriers to model development. Cancer prediction models trained on cfDNA data from clinically collected blood samples often struggle to isolate tumor-derived signals from confounding factors, and tissue of origin (TOO) models suffer from small sample sizes of rarer tumor types. To address these challenges, we developed FabricaTM, a platform to generate diverse, large-scale, high-fidelity simulated cfDNA datasets for robust and accurate machine learning (ML) model training. A key advantage of FabricaTM is its ability to enhance ML models by matching confounding variables between non-cancer and cancer samples. We first synthesized age-balanced non-cancer samples, then simulated tumor DNA shedding into circulation from 502 reference biopsy samples across 16 indications, optimizing for final tumor content distributions ranging from 0.001 to 14.2%. All reference non-cancer and biopsy samples consisted of aligned bisulfite sequencing reads from a custom target hybrid capture panel. This approach expanded a non-cancer dataset of 177 samples to 1,212 simulated samples and generated 6,400 simulated cancer cfDNA samples matching the non-cancers in age distribution. We then assessed this dataset for equivalence with clinical data and ability to improve cancer prediction. Non-linear dimensionality reduction and clustering of methylation signal showed simulated samples cluster indistinguishably from 2,290 samples (1,149 non-cancer, 1,141 treatment-naïve cancer) from the CORE-HH clinical study (NCT05435066). A binary cancer prediction model trained on the FabricaTM-generated dataset and evaluated on the CORE-HH dataset showed reduced reliance on age-associated signal (R2=0.15) and increased tuning towards tumor content, with minor cost to sensitivity (<4% at 95% specificity), relative to a model trained and cross-validated on the CORE-HH data (R2=0.60). To evaluate the benefit of these data for TOO prediction, we trained multiclass TOO models using FabricaTM's tumor biopsy reference data with and without the addition of our simulated data for 10 target indication groupings and benchmarked their performance on our clinical dataset. Training with both data types yielded a 10% increase in balanced accuracy. Moreover, peak performance was achieved at different training sample numbers per indication, illustrating FabricaTM's potential to estimate sample size requirements during study design. Our findings suggest FabricaTM-generated data can augment limited datasets to train ML models to identify tumor-specific biomarkers obscured by technical and demographic biases in real-world data. The age-balancing approach is readily applied to other confounders to help models learn true disease signatures. The platform is also adaptable to other diseases and biofluids (e.g., Alzheimer's disease, urine), allowing for extension to diagnostic and screening development beyond cancer and blood across the care spectrum. Citation Format: Kade Pettie, Shiva Farashahi, Jackson Killian, Dorna Kashef, Josh Hubbell, Feras Hantash, Jocelyn Charlton, Kieran Chacko. FabricaTM: A large-scale data simulation platform isolates tumor signal from cell-free DNA and improves tissue of origin prediction accuracy [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr B065.

Origin of the black hole spin in lower-mass-gap black hole-neutron star binaries

During the fourth observing run, the LIGO-Virgo-KAGRA Collaboration reported the detection of a coalescing compact binary (GW230529$_ $181500) with component masses estimated at $2.5-4.5\, M_ and $1.2-2.0\, M_ with 90<!PCT!> credibility. Given the current constraints on the maximum neutron star (NS) mass, this event is most likely a lower-mass-gap (LMG) black hole-neutron star (BHNS) binary. The spin magnitude of the BH, especially when aligned with the orbital angular momentum, is critical in determining whether the NS is tidally disrupted. An LMG BHNS merger with a rapidly spinning BH is an ideal candidate for producing electromagnetic counterparts. However, no such signals have been detected. In this study, we employ a detailed binary evolution model that incorporates new dynamical tide implementations to explore the origin of BH spin in an LMG BHNS binary. If the NS forms first, the BH progenitor (He-rich star) must begin in orbit shorter than 0.35 days to spin up efficiently, potentially achieving a spin magnitude of $ BH > 0.3$. Alternatively, if a nonspinning BH (e.g., $M_ BH = 3.6\, M_ forms first, it can accrete up to $ 0.2\, M_ via case BA mass transfer (MT), reaching a spin magnitude of $ BH 0.18$ under Eddington-limited accretion. With a higher Eddington accretion limit (i.e., 10.0 $ M Edd $), the BH can attain a significantly higher spin magnitude of $ BH by accreting approximately $1.0\, M_ during case BA MT phase.

The Impact of Astrophysical Priors on Parameter Inference for GW230529

Abstract We investigate the effects of prior selection on the inferred mass and spin parameters of the neutron star-black hole merger GW230529_181500. Specifically, we explore models motivated by astrophysical considerations, including massive binary and pulsar evolution. We examine mass and spin distributions of neutron stars constrained by radio pulsar observations, alongside black hole spin observations from previous gravitational wave detections. We show that the inferred mass distribution highly depends upon the spin prior. Specifically, under the most restrictive, binary stellar evolution models, we obtain narrower distributions of masses with a black hole mass of $4.3^{+0.1}_{-0.1}\, {\rm M}_{\odot }$and neutron star mass of $1.3^{+0.03}_{-0.03}\, {\rm M}_{\odot }$ where, somewhat surprisingly, it is the prior on component spins which has the greatest impact on the inferred mass distributions. Re-weighting using neutron star mass and spin priors from observations of radio pulsars, with black hole spins from observations of gravitational waves, yields the black hole and the neutron star masses to be $3.8^{+0.5}_{-0.6} \, M_\odot$ and $1.4^{+0.2}_{-0.1} \, M_\odot$ respectively. The sequence of compact object formation — whether the neutron star or the black hole formed first — cannot be determined at the observed signal-to-noise ratio. However, there is no evidence that the black hole was tidally spun up.

Carbon Flow Allocation Patterns of CH4, CO2, and Biomass Production Vary with Sewage and Sediment Microbial and Biochemical Factors in the Anaerobic Sewer Environment.

Understanding the carbon (C) fate in municipal sewers is imperative for optimizing current sewer-C-degradation control and treatment efficiency, aligning with China's C-neutrality strategy in determining the exact C budget of the wastewater system. This study used laboratory batch tests mimicking the anaerobic sewer environment and sewage-sediment stratification to evaluate C flow allocation (CFA) patterns in response to biotic and abiotic variables. We quantified the C equivalent mass (CEM) and used absolute quantitative 16S rRNA gene amplicon sequencing to characterize the microbiome. The substantial methane production (CH4, 17.2%-18.8%) required both activated sediment and exogenous C, while biomass production (BP, 63.1%-74.9%) formed C sink predominated as the main CFA direction under the stratified state. This was supported by the high diversity, interspecific interactions, and metabolic capacity of the sediment microbiome. However, CH4 and BP patterns demonstrated non-synchronicity and opposite dynamic characteristics. Carbon dioxide (CO2, 64.0%-81.3%) production dominated the sewage CFA. The absolute abundance of the sediment microbiome, which was 5.6 times higher than that of the sewage, exhibited a strong increase in magnitude across the phases. It was primarily associated with biomass growth and N metabolism, whereas sewage showed differentiated and competing communities and appeared to act mainly as the exogenous C sources. We constructed a binary quadratic linear model revealing the non-linear relationship between ACK activity, DOC degradation rate, and CEMCH4 rate; the former maintained low CH4 production when the available substrate was insufficient. The influence of N and S factors on the CFA is complex and multi-faceted. These findings highlight the importance of further investigations into the process-based framework of the sewer C budget, focusing on the C source-emission-sink functions and mass balance.

Abstract 4138303: Stress Hyperglycemia Ratio Predicts MACE and All-cause Mortality in Acute Coronary Syndrome Patients: A Meta-Analysis Comparing Patient with Diabetes Mellitus and Non-Diabetes Mellitus

Background: A higher stress hyperglycemic ratio (SHR) has been reported to be associated with adverse cardiac outcomes. However, the role of SHR in predicting clinical outcomes by comparing patients with and without diabetes mellitus is yet to be explored. Objective: To evaluate the prognostic value of the SHR for predicting major adverse cardiovascular (MACE) and all-cause mortality in ACS patients with and without diabetes mellitus. Methods: Per PRISMA guidelines, we comprehensively reviewed PubMed, Google Scholar, and SCOPUS for eligible studies reporting on SHR and its association with MACE (8 studies) and all-cause mortality (7 studies) in ACS patients. Pooled odds ratios (ORs) and 95% confidence intervals (CIs) were calculated using a binary random-effects model, with results displayed as forest plots. Heterogeneity was assessed using I2 statistics, and a leave-one-out sensitivity analysis was performed. P<0.05 was considered significant. Results: A total of 15 studies with 45,774 patients with ACS were included in the analysis. The majority of patients were males (72.6%) with a mean age of 62.8 years. High SHR was associated with higher odds of MACE (1.93 [1.54–2.42]) and all-cause mortality (1.91 [1.58–2.31]) (Fig. 1). Subgroup analysis revealed increased odds of all-cause mortality (1.69 [1.34–2.11] for patients with diabetes vs 2.12 [1.65–2.71] for patients without diabetes) and MACE (1.60 [1.30–1.97] for patients with diabetes vs 1.44 [1.28–1.62] for patients without diabetes), all p<0.01. (Fig. 2). Additionally, the leave-one-out sensitivity analysis demonstrated that excluding any particular study did not significantly affect outcomes (p<0.05). Conclusions: In patients with ACS, SHR is an independent predictor of MACE and all-cause mortality, irrespective of diabetes status. Strict glycemic control strategies may improve outcomes in this high-risk population. These findings underscore the importance of early recognition and management of stress hyperglycemia in ACS patients.

NIMG-76. INCORPORATING IMAGING FEATURES OF NORMAL BRAIN TO ENHANCE SPATIALLY DIFFERENTIATING TREATMENT-INDUCED EFFECTS FROM RECURRENT GLIOMA WITH AI

Abstract INTRODUCTION Although AI-based approaches have been applied to discriminate between tumor recurrence (rTumor) and treatment-induced effects (TxE) from chemoradiotherapy in patients with recurrent glioma, these models typically either do not account for within-lesion mixtures of rTumor and TxE or generalize to independent test-sets with >80% accuracy. We hypothesize that incorporating imaging features of normal-appearing brain (NAB) into existing AI-based models that leverage tissue-samples with known locations on MRI and physiological imaging will significantly improve performance for distinguishing regions of TxE from rTumor and allow for visualization of rTumor beyond the T2-lesion. METHODS Using 254 pathology-confirmed tissue-samples with coordinates on diffusion-weighted, perfusion-weighted, and anatomical MRI from 135 glioma suspected of progression, we modified previously-developed binary, AI-based prediction models to learn multi-class targets consisting of rTumor, TxE, and contralateral NAB-regions (3/patient) with imaging signatures of CSF, white-matter, and grey-matter (659 total 10mm-isotropic samples). The multi-class ensemble model was trained with 4 unique repeats of constrained-5-fold-cross-validation and evaluated on a held-out test set (30 patients). This process was repeated 20 times, and the performance was compared to corresponding binary AI-based models. RESULTS NAB was easiest to distinguish from individual and combined classes (AUC-ROCs>0.98). Multi-class model performance for predicting TxE increased by 27% to 0.93±0.03 (p<0.00001) when discriminating between NAB and rTumor as compared to just rTumor with the binary models. While TxE vs rTumor alone was most difficult to predict with the multi-class model (AUC-ROC=0.73) achieving equivalent performance to binary models, there was 67% less variance in test performance. This approach allowed for the quantification of whole-brain probability maps of rTumor, TxE, and NAB along with a combined 3-channel colormap, facilitating the visualization of rTumor predictions beyond the T2-lesion. CONCLUSIONS Including NAB imaging features improved performance of AI-based models of rTumor/TxE, while expanding the predicted area to produce more interpretable whole-brain probability maps. Current work is evaluating their utility in prospectively guiding sampling of rTumor tissue and predicting survival.

Investigating 39 Galactic Wolf-Rayet stars with VLTI/GRAVITY. Uncovering a long-period binary desert

Wolf-Rayet stars (WRs) represent one of the final evolutionary stages of massive stars and are thought to be the immediate progenitors of stellar-mass black holes. Their multiplicity characteristics form an important anchor point in single and binary population models for predicting gravitational-wave progenitors. Recent spectroscopic campaigns have suggested incompatible multiplicity fractions and period distributions for N- and C-rich Galactic WRs (WNs and WCs) at both short and long orbital periods, in contradiction with evolutionary model predictions. In this work, we employed long-baseline infrared interferometry to investigate the multiplicity of WRs at long periods and explored the nature of their companions. We present a magnitude-limited ($K<9$; $V<14$) survey of 39 Galactic WRs, including 11 WN, 15 WC, and 13 H-rich WN (WNh) stars. We used the $K$-band instrument GRAVITY at the Very Large Telescope Interferometer (VLTI) in Chile. The sensitivity of GRAVITY at spatial scales of sim 1--200 milliarcseconds and flux contrast of $1<!PCT!>$ allowed an exploration of periods in the range $10^ $ d and companions down to sim 5$\,M_ We carried out a companion search for all our targets, with the aim of either finding wide companions or calculating detection limits. We also explored the rich GRAVITY dataset beyond a multiplicity search to look for other interesting properties of the WR sample. We detected wide companions with VLTI/GRAVITY for only four stars in our sample: WR 48, WR 89, WR 93, and WR 115. Combining our results with spectroscopic studies, we arrived at observed multiplicity fractions of $f^ WN obs WC obs and WNh obs The multiplicity fractions and period distributions of WNs and WCs are consistent in our sample. For single WRs, we placed upper limits on the mass of potential companions down to sim 5$\,M_ for WNs and WCs, and sim 7$\,M_ for WNh stars. In addition, we also found other features in the GRAVITY dataset, such as (i) a diffuse extended component contributing significantly to the $K$-band flux in over half the WR sample; (ii) five known spectroscopic binaries resolved in differential phase data, which constitutes an alternative detection method for close binaries; and (iii) spatially resolved winds in four stars: WR 16, WR 31a, WR 78, and WR 110. Our survey reveals a lack of intermediate- (a few hundred days) and long- (a few years to decades) period WR systems. The 200d peak in the period distributions of WR+OB and BH+OB binaries predicted by Case B mass-transfer binary evolution models is not seen in our data. The rich companionship of their O-type progenitors in this separation range suggests that the WR progenitor stars expand and interact with their companions, most likely through unstable mass transfer, resulting in either a short-period system or a merger.

Are all models wrong? Falsifying binary formation models in gravitational-wave astronomy using exceptional events

Abstract As the catalogue of gravitational-wave transients grows, several entries appear ‘exceptional’ within the population. Tipping the scales with a total mass of ∼150M⊙, GW190521 likely contained black holes in the pair-instability mass gap. The event GW190814, meanwhile, is unusual for its extreme mass ratio and the mass of its secondary component. A growing model-building industry has emerged to provide explanations for such exceptional events, and Bayesian model selection is frequently used to determine the most informative model. However, Bayesian methods can only take us so far. They provide no answer to the question: does our model provide an adequate explanation for exceptional events in the data? If none of the models we are testing provide an adequate explanation, then it is not enough to simply rank our existing models—we need new ones. In this paper, we introduce a method to answer this question with a frequentist p-value. We apply the method to different models that have been suggested to explain the unusually massive event GW190521: hierarchical mergers in active galactic nuclei and globular clusters. We show that some (but not all) of these models provide adequate explanations for exceptionally massive events like GW190521.

Prediction of dialysis adequacy using data-driven machine learning algorithms

Background Adequate delivery of hemodialysis (HD), measured by the spKt/V derived from urea reduction, is an important determinant of clinical outcomes in chronic hemodialysis patients. However, the need for pre- and postdialysis blood samples prevented the assessment of spKt/V in every session. Methods This retrospective single-center study was performed on end-stage renal disease (ESKD) patients aged ≥ 18 years who received standard thrice-weekly chronic HD therapy. Eighty-seven variables, including general, intradialytic, and laboratory variables, were collected from the medical records for analysis. Five steps of preprocessing procedure were deployed to select only the most relevant variables. Six binary classification models were developed to predict whether spKt/V was higher than 1.4. Results A total of 1869 HD sessions from 373 ESKD patients were included in this study. The Random Forest model showed the best prediction for dialysis adequacy, with AUROC scores of 0.860 in the validation dataset and 0.873 in the testing dataset. Notably, an accessible model that solely relied on noninvasively collected general and dialysis-related variables maintained high prediction accuracy, with AUROC scores of 0.854 and 0.868 in the validation and testing datasets, respectively. The five most significant predictive variables were vascular access, gender, body mass index, ultrafiltration volume, and dialysis duration. Conclusion The study results suggest that the development of ML models for accurately predicting dialysis adequacy based on general and intradialytic variables is feasible. These models have the potential to be utilized for noninvasive clinical assessments of dialysis adequacy.

RADT-11. FACTORS ASSOCIATED WITH LOCAL FAILURE AFTER STEREOTACTIC RADIATION TO THE SURGICAL BED OF BREAST CANCER PATIENTS WITH A SINGLE BRAIN METASTASIS

Abstract BACKGROUND Metastatic breast cancer is the second most common cancer associated with brain metastases (BCBM). In our study we evaluated variables that influence local control in this breast cancer patients with a single BCBM who underwent surgical resection and stereotactic radiation to resection cavity. METHODS After ethics approval, we conducted a retrospective review of the medical records of BCBM patients treated with stereotactic radiation for BCBM between 2011 to 2022. Only breast cancer patients with a single BCBM who underwent surgical resection and stereotactic radiation to the surgical cavity were included. Clinical and dosimetric variables were analyzed to evaluate their impact on local control. Statistical analysis included descriptive analyses. X2 test was used for categorical variables. Total dose, dose per fraction, biologically effective dose (BED), and planning target volumes were analyzed as both continuous and categorical variables at different thresholds. A binary regression model was applied to study variables shown to impact local control. RESULTS A total of 62 patients included local control was 70.9% at 12 months. HER-2 disease, luminal-B, size of BCBM, time from craniotomy, total dose, inclusion of corridor, and non-cystic lesion were significant for local control. CONCLUSION Our data supports previous publications about the importance of tumor bed delineation, dose and fractionation, and time from craniotomy as factors associated with better local control. Our study shows that the role of BCBM subtype and new systemic therapies in contributing to local and intracranial control should be further explored.

Synergistic Effect of Influence Factors on Ammonia Volatilization in Fertilizer Solution: A Laboratory Experiment

Ammonia volatilization, which is one of the main ways that nitrogen gas is released from farmland, restricts promotion of the utilization of nitrogen fertilizer and contains some potential environmental risks. To investigate the general pattern of ammonia volatilization under actual paddy field conditions, we designed an indoor simulated system to measure the amount of ammonia volatilized within a single time period by controlling the pH and concentration of NH4+ (c(NH4+)) in the solution, the gas–liquid interfacial gas velocity, and the ambient temperature. In this paper, the influence of these factors, the synergistic effect on ammonia volatilization, and their quantitative relationship are discussed. We used solutions of ammonium bicarbonate (SAB) and diammonium phosphate (SDP) for the simulation experiments, and the results showed that there is a significant linear relationship between the amount of ammonia volatilization and c(NH4+). The correlation coefficients were between 0.9214 to 0.9897 and 0.8932 to 0.9904 for SAB and SDP, respectively. The quantitative relationship between temperature and pH and the influence factor (CIF) and the initial ammonia volatilization fluxes (IAVFs) was analyzed by the least-squares method, and the degrees of polynomial were one and two, respectively. The regression equations of the SAB and SDP among the amount of ammonia volatilization with the concentration of ammonium nitrogen, the temperature, and the pH were calculated by using MATLAB. Considering the effects of temperature and pH on the CIF and IAVFs under individual conditions, we used a binary cubic model to fit the relationship between temperature and pH to the CIF and IAVFs. The simulation results showed that the correlation coefficients between the CIF and IAVFs for SAB were 0.9980 and 0.9680, respectively, and the correlation coefficients were 0.9946 and 0.9708 for SDP, respectively. The quantitative equation took into account the coefficient of determination and degrees of polynomial, and the ammonia volatilization fluxes can be calculated by using these equations.

Stratified Care in Cognitive Behavioural Therapy: A Comparative Evaluation of Predictive Modelling Approaches for Individualized Treatment: La stratification des soins pour l'orientation vers une thérapie cognitivo-comportementale: une évaluation comparative des approches de modélisation prédictive pour un traitement individualisé.

In response to high demand and prolonged wait times for cognitive behavioural therapy (CBT) in Ontario, Canada, we developed predictive models to stratify patients into high- or low-intensity treatment, aiming to optimize limited healthcare resources. Using client records (n = 953) from Ontario Shores Centre for Mental Health Sciences (January 2017-2021), we estimated four binary outcome models to assign patients into complex and standard cases based on the probability of reliable improvement in Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) scores. We evaluated two choices of cut-offs for patient complexity assignment: models at an ROC (receiver operating characteristic)-derived cut-off and a 0.5 probability cut-off. Final model effectiveness was assessed by assigning treatment intensity (high-intensity or low-intensity CBT) based on the combined performance of both GAD-7 and PHQ-9 models. We compared the treatment assignment recommendations provided by the models to those assigned by clinical assessors. The predictive models demonstrated higher accuracy in selecting treatment modality compared to provider-assigned treatment selection. The ROC cut-off achieved the highest prediction accuracy of case complexity (0.749). The predictive models exhibited large sensitivity and specificity trade-offs (which influence the rates of patient assignment to high-intensity CBT) despite having similar accuracy statistics (ROC cut-off = 0.749, 0.5 cut-off = 0.690), emphasizing the impact of cut-off choices when implementing predictive models. Overall, our findings suggest that the predictive model has the potential to improve the allocation of CBT services by shifting incoming clients with milder symptoms of depression to low-intensity CBT, with those at highest risk of not improving beginning in high-intensity CBT. We have demonstrated that models can have significant sensitivity and specificity trade-offs depending on the chosen acceptable threshold for the model to make positive predictions of case complexity. Further research could assess the use of the predictive model in real-world clinical settings.

EFFECTS OF HEALTH EXPENDITURE ON FOOD SECURITY STATUS OF RURAL HOUSEHOLDS IN OGUN STATE, NIGERIA

The study assessed the effect of health expenditure on the food security status of rural households in Ogun State, Nigeria. Multistage sampling procedure was used to select 120 rural households in the study area. Data was collected from the respondents with the aid of a semi-structured questionnaire complemented with an interview guide. Descriptive statistics, food security index, cost of illness procedure and binary logit regression model were the analytical techniques used for data analysis. Findings from the study revealed that majority (79.2%) of the respondent were male, married (90.8%), with a mean household size of 5 persons. Also, the mean age of the respondents was found to be 54 years with most of them involved in farming as their major occupation. Findings also revealed that majority of the rural households suffered from various illnesses such as malaria, waist/back pain, fever, high blood pressure, rheumatism and other illnesses with an average estimated cost of illness (₦45, 973.68 per month). The results of the food security status of the rural households revealed that a higher percentage (53.3%) of the rural households were food insecure. Factors found to significantly affect the food security status of the rural households were cost of illness (p<0.1) and other socio-economic variables such as education (p<0.1), income (p<0.05) and sex of the household head (p<0.01). Therefore, this study recommends that government should subsidize the cost of drugs and other medical expenses for poor households particularly those in the rural areas in order to reduce their financial burden on health care and increase their economic access to food.

Processing and Comparison of GBoost, XGBoost, and Random Forest in Titanic Survival Prediction

Abstract. Contemporarily, the machine learning has evolved from its early concepts to a sophisticated field consisting of advanced algorithms and diverse applications. Tree-based classification models have become powerful tools for complex predictive challenges. In this study, the effectiveness of tree-based classification models, such as Random Forest, XGBoost, and Gradient Boosting, is examined on the Titanic survival prediction challenge, which originates from the 1912 Titanic disaster. Passengers survival and death were influenced by various factors in this disaster. By using features such as gender, age, and class, and the survival outcome as the target variable, a binary classification model is developed to predict each passenger's survival status. The study includes data preprocessing, feature selection based on a foundational model, and model training. After the construction, hyper-parameters tuning, and cross-validation of three classifiers, this research compares and analyzes the performance scores to evaluate the characteristics of these tree-based learning methods, aiming to provide a reference for the similar applications.

Peptipedia v2.0: a peptide sequence database and user-friendly web platform. A major update.

In recent years, peptides have gained significant relevance due to their therapeutic properties. The surge in peptide production and synthesis has generated vast amounts of data, enabling the creation of comprehensive databases and information repositories. Advances in sequencing techniques and artificial intelligence have further accelerated the design of tailor-made peptides. However, leveraging these techniques requires versatile and continuously updated storage systems, along with tools that facilitate peptide research and the implementation of machine learning for predictive systems. This work introduces Peptipedia v2.0, one of the most comprehensive public repositories of peptides, supporting biotechnological research by simplifying peptide study and annotation. Peptipedia v2.0 has expanded its collection by over 45% with peptide sequences that have reported biological activities. The functional biological activity tree has been revised and enhanced, incorporating new categories such as cosmetic and dermatological activities, molecular binding, and antiageing properties. Utilizing protein language models and machine learning, more than 90 binary classification models have been trained, validated, and incorporated into Peptipedia v2.0. These models exhibit average sensitivities and specificities of 0.877±0.0530 and 0.873±0.054, respectively, facilitating the annotation of more than 3.6 million peptide sequences with unknown biological activities, also registered in Peptipedia v2.0. Additionally, Peptipedia v2.0 introduces description tools based on structural and ontological properties and user-friendly machine learning tools to facilitate the application of machine learning strategies to study peptide sequences. Database URL: https://peptipedia.cl/.