Superior Predictive Performance Research Articles

Early prediction of long-term survival of patients with nasopharyngeal carcinoma by multi-parameter MRI radiomics

The objective is to create a comprehensive model that integrates clinical, semantic, and radiomics features to forecast the 5-year progression-free survival (PFS) of individuals diagnosed with non-distant metastatic Nasopharyngeal Carcinoma (NPC). In a retrospective analysis, we included clinical and MRI data from 313 patients diagnosed with primary NPC. Patient classification into progressive and non-progressive categories relied on the occurrence of recurrence or distant metastasis within a 5-year timeframe. Initial screening comprised clinical features and statistically significant image semantic features. Subsequently, MRI radiomics features were extracted from all patients, and optimal features were selected to formulate the Rad-Score.Combining Rad-Score, image semantic features, and clinical features to establish a combined model Evaluation of predictive efficacy was conducted using ROC curves and nomogram specific to NPC progression. Lastly, employing the optimal ROC cutoff value from the combined model, patients were dichotomized into high-risk and low-risk groups, facilitating a comparison of 10-year overall survival (OS) between the groups. The combined model showcased superior predictive performance for NPC progression, reflected by AUC values of 0.84, an accuracy rate of 81.60%, sensitivity at 0.77, and specificity at 0.81 within the training group. In the test set, the AUC value reached 0.81, with an accuracy of 74.6%, sensitivity at 0.82, and specificity at 0.66. The amalgamation of Rad-Score, clinical, and imaging semantic features from multi-parameter MRI exhibited significant promise in prognosticating 5-year PFS for non-distant metastatic NPC patients. The combined model provided quantifiable data for informed and personalized diagnosis and treatment planning.

Decision tree-based approach to extrapolate life cycle inventory data of manufacturing processes

Life cycle assessment (LCA) plays a crucial role in green manufacturing to uncover the critical aspects for alleviating the environmental burdens due to manufacturing processes. However, the scarcity of life cycle inventory (LCI) data for the manufacturing processes is a considerable challenge. This paper proposes a novel approach to extrapolate LCI data of manufacturing processes. Taking advantage of LCI data in the Ecoinvent datasets, decision tree-based supervised machine learning models, namely decision tree, random forest, gradient boosting, and adaptive boosting, have been developed to extrapolate the data of GHG emissions, i.e., carbon dioxide, nitrous oxide, methane, and water vapor. Initially, a correlation analysis was conducted to derive the most influential factors on GHG quantities resulting from manufacturing activities. First, the collected data have been preprocessed and split into train and test sets (70% and 30%, respectively). Second, a five-fold cross-validation method was applied to tune the hyperparameters of the models. Then, the models were re-trained using the best hyperparameters and evaluated using the test set. The results reveal that the Gradient Boosting model has a superior predictive performance for extrapolating the GHG emission data, with average coefficients of determination (R2) on the test set <0.95. Moreover, the model predictions involve relatively low values of the average root mean squared error and an average mean percentage of error on the test set. The correlation and feature importance analyses emphasized that the workpiece material and manufacturing technology have a considerable effect on natural resource consumption, i.e., energy, material, and water inflows into the process. Meanwhile, energy consumption, water usage, and raw aluminum depletion were the most influential factors in GHG emissions. Eventually, a case study to extrapolate the inflows and the outflows for new manufacturing activities has been conducted using the validated models. The proposed GraBoost model provides a computational supplementary approach to estimate and extrapolate the GHG emissions for different manufacturing processes when LCI data are incomplete or don't exist within LCI databases.

Machine learning assisted improved desalination pilot system design and experimentation for the circular economy

Desalination is among the most feasible solutions to supply sustainable and clean drinking water in water scarcity areas. In this regard, Multi-Effect Desalination (MED) systems are particularly preferred for harsh feeds (high temperature and salinity) because of their robust mode of operation for water production. However, maintaining the efficient operation of the MED systems is challenging because of the large system design and variables' interdependencies that are sensitive to the distillate production. Therefore, this research leverages the power of machine learning and optimization to estimate the optimal operating conditions for the maximum distillate production from the MED system. In the first step, detailed experimentation is conducted for distillate production against hot water temperature (HWT) varying from 38 to 70 °C, and feed water temperature (FWT) is changed from 34 to 42 °C. Whereas, the feed flow rate (FFR) is investigated to be varied nearly from 3.6 to 8.7 LPM in the three stages, i.e., FFR-S1, FFR-S2 and FFR-S3. The compiled dataset is used to make the process models of the MED system by three ML-based algorithms, i.e., Artificial Neural Network (ANN), Support Vector Machine (SVM), and Gaussian Process Regression (GPR) under rigorous hyperparameters optimization. GPR exhibited superior predictive performance than those of ANN and SVM on R2 value of 0.99 and RMSE of 0.026 LPM. Monte Carlo technique-based variable significance analysis revealed that the HWT has the highest effect on distillate production with a percentage significance of 95.6 %. Then Genetic Algorithm is used to maximize the distillate production with the GPR model embedded in the optimization problem. The GPR-GA driven maximum distillate production is estimated on HWT = 70 ± 0.5 °C, FWT = 40 ± 2.5 °C, FFR-S1 = 6 ± 2.6 LPM, FFR-S2 = 7 ± 1 LPM and FFR-S3 = 7 ± 1. The ML-GA-based system analysis and optimization of the MED system can boost the distillate production that promotes operation excellence and circular economy from the desalination sector.

Vancomycin: An analysis and evaluation of eight population pharmacokinetic models for clinical application in general adult population.

Based on the recent guidelines for vancomycin therapeutic drug monitoring (TDM), the area under the curve to minimum inhibitory concentration ratio was to be employed combined with the usage of population pharmacokinetic (popPK) model for dosing adaptation. Yet, deploying these models in a clinical setting requires an external evaluation of their performance. This study aimed to evaluate existing vancomycin popPK models from the literature for the use in TDM within the general patient population in a clinical setting. The models under external evaluation were chosen based on a review of literature covering vancomycin popPK models developed in general adult populations. Patients' data were collected from Charles-Le Moyne Hospital (CLMH). The external evaluation was performed with NONMEM® (v7.5). Additional analyses such as evaluating the impact of number of samples on external evaluation, Bayesian forecasting, and a priori dosing regimen simulations were performed on the best performing model. Eight popPK models were evaluated with an independent dataset that included 40 patients and 252 samples. The model developed by Goti and colleagues demonstrated superior performance in diagnostic plots and population predictive performance, with bias and inaccuracy values of 0.251% and 22.7%, respectively, and for individual predictive performance, bias and inaccuracy were -4.90% and 12.1%, respectively. When limiting the independent dataset to one or two samples per patient, the Goti model exhibited inadequate predictive performance for inaccuracy, with values exceeding 30%. Moreover, the Goti model is suitable for Bayesian forecasting with at least two samples as prior for the prediction of the next trough concentration. Furthermore, the vancomycin dosing regimen that would maximize therapeutic targets of area under the curve to minimum inhibitory concentration ratio (AUC24/MIC) and trough concentrations (Ctrough) for the Goti model was 20 mg/kg/dose twice daily. Considering the superior predictive performance and potential for Bayesian forecasting in the Goti model, future research aims to test its applicability in clinical settings at CLMH, both in a priori and a posteriori scenario.

The Relationship Between Cardiac CT-based Left Atrial Structure and Epicardial Adipose Tissue and Postablation Atrial Fibrillation Recurrence Within 2 Years.

The aim of this study was to explore the association of cardiac CT-based left atrium (LA) structural and functional parameters and left atrial epicardial adipose tissue (LA-EAT) parameters with postablation atrial fibrillation (AF) recurrence within 2 years. Contrast-enhanced cardiac CT images of 286 consecutive AF patients (median age: 65 y; 97 females) who underwent initial ablation between June 2018 and June 2020 were retrospectively analyzed. Structural and functional parameters of LA, including maximum and minimum volume and ejection fraction of LA and left atrial appendage (LAA), and LA-EAT volume, were measured. The body surface area indexed maximum and minimum volume of LA (LAVImax, LAVImin) and LAA (LAAVImax, LAAVImin), and LA-EAT volume index (LA-EATVI) were calculated. Independent predictors of AF recurrence were determined using Cox regression analysis. The clinical predictors were added to the imaging predictors to build a combined model (clinical+imaging). The predictive performance of the clinical, imaging, and combined models was assessed using the area under the receiver operating characteristics curve (AUC). A total of 108 (37.8%) patients recurred AF within 2 years after ablation at a median follow-up of 24 months (IQR=11, 32). LA and LAA size and LA-EAT volume were significantly increased in patients with AF recurrence (P<0.05). After the multivariable regression analysis, LA-EATVI, LAAVImax, female sex, AF duration, and stroke history were independent predictors for AF recurrence. The combined model exhibited superior predictive performance compare to the clinical model (AUC=0.712 vs. 0.641, P=0.023) and the imaging model (AUC=0.712 vs. 0.663, P=0.018). Cardiac CT-based LA-EATVI and LAAVImax are independent predictors for postablation AF recurrence within 2 years and may provide a complementary value for AF recurrence risk assessment.

A prediction model of rubber content in the dried root of Taraxacum kok-saghyz Rodin based on near-infrared spectroscopy

BackgroundTaraxacum kok-saghyz Rodin (TKS) is a highly potential source of natural rubber (NR) due to its wide range of suitable planting areas, strong adaptability, and suitability for mechanized planting and harvesting. However, current methods for detecting NR content are relatively cumbersome, necessitating the development of a rapid detection model. This study used near-infrared spectroscopy technology to establish a rapid detection model for NR content in TKS root segments and powder samples. The K445 strain at different growth stages within a year and 129 TKS samples hybridized with dandelion were used to obtain their near-infrared spectral data. The rubber content in the root of the samples was detected using the alkaline boiling method. The Monte Carlo sampling method (MCS) was used to filter abnormal data from the root segments of TKS and powder samples, respectively. The SPXY algorithm was used to divide the training set and validation set in a 3:1 ratio. The original spectrum was preprocessed using moving window smoothing (MWS), standard normalized variate (SNV), multiplicative scatter correction (MSC), and first derivative (FD) algorithms. The competitive adaptive reweighted sampling (CARS) algorithm and the corresponding chemical characteristic bands of NR were used to screen the bands. Partial least squares (PLS), random forest (RF), Lightweight gradient augmentation machine (LightGBM), and convolutional neural network (CNN) algorithms were employed to establish a model using the optimal spectral processing method for three different bands: full band, CARS algorithm, and chemical characteristic bands corresponding to NR. The model with the best predictive performance for high rubber content intervals (rubber content > 15%) was identified.ResultThe results indicated that the optimal rubber content prediction models for TKS root segments and powder samples were MWS–FD CASR–RF and MWS–FD chemical characteristic band RF, respectively. Their respective RP2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ ext{R}}_{{\ ext{P}}}^{2}$$\\end{document}, RMSEP, and RPDP values were 0.951, 0.979, 1.814, 1.133, 4.498, and 6.845. In the high rubber content range, the model based on the LightGBM algorithm had the best prediction performance, with the RMSEP of the root segments and powder samples being 0.752 and 0.918, respectively.ConclusionsThis research indicates that dried TKS root powder samples are more appropriate for constructing a rubber content prediction model than segmented samples, and the predictive capability of root powder samples is superior to that of root segmented samples. Especially in the elevated rubber content range, the model formulated using the LightGBM algorithm has superior predictive performance, which could offer a theoretical basis for the rapid detection technology of TKS content in the future.

PCDHGC3 hypermethylation as a potential biomarker of intestinal neuroendocrine carcinomas.

Neuroendocrine neoplasms (NENs) encompass tumors arising from neuroendocrine cells in various organs, including the gastrointestinal tract, pancreas, adrenal gland, and paraganglia. Despite advancements, accurately predicting the aggressiveness of gastroenteropancreatic (GEP) NENs based solely on pathological data remains challenging, thereby limiting optimal clinical management. Our previous research unveiled a crucial link between hypermethylation of the protocadherin PCDHGC3 gene and neuroendocrine tumors originating from the paraganglia and adrenal medulla. This epigenetic alteration was associated with increased metastatic potential and succinate dehydrogenase complex (SDH) dysfunction. Expanding upon this discovery, the current study explored PCDHGC3 gene methylation within the context of GEP-NENs in a cohort comprising 34 cases. We uncovered promoter hypermethylation of PCDHGC3 in 29% of GEP-NENs, with a significantly higher prevalence in gastrointestinal (GI) neuroendocrine carcinomas (NECs) compared with both pancreatic (Pan) NECs and neuroendocrine tumors (NETs) of GI and Pan origin. Importantly, these findings were validated in one of the largest multi-center GEP-NEN cohorts. Mechanistic analysis revealed that PCDHGC3 hypermethylation was not associated with SDH mutations or protein loss, indicating an SDH-independent epigenetic mechanism. Clinically, PCDHGC3 hypermethylation emerged as a significant prognostic factor, correlating with reduced overall survival rates in both patient cohorts. Significantly, whereas PCDHGC3 hypermethylation exhibited a strong correlation with TP53 somatic mutations, a hallmark of NEC, its predictive value surpassed that of TP53 mutations, with an area under the curve (AUC) of 0.95 (95% CI 0.83-1.0) for discriminating GI-NECs from GI-NETs, highlighting its superior predictive performance. In conclusion, our findings position PCDHGC3 methylation status as a promising molecular biomarker for effectively stratifying patients with GI-NENs. This discovery has the potential to advance patient care by enabling more precise risk assessments and tailored treatment strategies. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Assessing heart rate fragmentation to predict atrial fibrillation in the general population aged 65

Abstract Rationale Screening the general population aged 65 for atrial fibrillation (AF) has been proposed as a preventive measure against potential complications. The dysfunction of the autonomic nervous system (ANS) plays an important role in atrial fibrillation (AF). Short-term HRV is conceptually attributed to physiologic vagal tone modulation. But recent data suggest that a component of short-term HRV, called heart rate fragmentation (HRF), is related to ANS breakdown and may be a predictor of AF occurrence. Metrics derived from heart rate variability (HRV) that depict heart rate fragmentation (HRF) have been suggested to reflect autonomic nervous system (ANS) dysfunction. Objectives To assess the predictive capacity of HRF markers for AF occurrence over an 18-year follow-up in individuals aged 65 at the study’s inspection and to develop a predictive score for AF onset. Methods A cohort study was designed to prospectively assess the predictive value of ANS activity level among general population regarding cardiovascular events and mortality. 1011 subjects aged 65 were enrolled in the study from September 2000 to December 2002. The study population had no history of AF and a low cardiovascular risk. A median follow-up of 17.8 years was managed. HRV data were acquired by 24-h Holter electrcardiogram (ECG) monitoring at baseline and assessed by frequency domain and time domain methods. Heart rate fragmentation using the percentage of inflection points (PIP) and alpha 1-index (using fractal evaluation of NN intervals) were then calculated. The study outcome was the development of AF during follow-up, defined as a standard 12-lead ECG recording or Holter recording with ≥ 30 s of AF. Results AF was diagnosed in 123 patients during the 18-year follow-up, representing a cumulative incidence of 13.4%. Using multivariate analysis, the occurrence of AF was independently predicted by the male gender (HR=1.74, 95%CI:1.16-2.63, p&amp;lt;0.01), a heart rate below 70bpm (HR=1.85, 95%CI:1.18-2.90, p&amp;lt;0.01), an increased percentage of NN intervals that differ by more than 50 ms from the previous interval (pnn50) (HR=1.69, 95%CI:1.06-2.70, p=0.03), an increased percentage of inflection points (HR=2.80, 95%CI:1.66-4.72,p&amp;lt;0.01), and a reduced alpha 1 index (HR=1.61, 95%CI:1.03-2.53, p=0.04). Given these results, a predictive score was built up based on the 4 independent predictors, ranging from 0 to 6 (Graphical Abstract). The high-risk group, defined as having a PROOF-AF score of 4 or higher, exhibited a 3.3-fold higher risk of developing AF (Figure). The PROOF-AF score demonstrated superior predictive performance compared to other available risk scores for incident AF such as CHARGE-AF score, C2HEST score, FHS score, and JMC score. Conclusion HRF parameters, included in the PROOF-AF score, may be used to identify individuals aged 65 without pre-existing health conditions who are at high-risk of developing AF and assist population screening.Graphical abstractFigure

#1465 Enhancing vascular access planning in CKD: validating the 40% KFRE threshold in a French retrospective cohort study

Abstract Background and Aims The optimal timing for dialysis vascular access creation remains a complex clinical decision, balancing the risk of early intervention against the prospect of starting dialysis with a central venous catheter. This study sought to compare the predictive capabilities of the Kidney Failure Risk Equation (KFRE) and estimated Glomerular Filtration Rate (eGFR) in determining the appropriate timing for arteriovenous fistula (AVF) creation in patients with advanced chronic kidney disease (CKD). Method A retrospective cohort of 238 patients referred for ultrasound vascular mapping from April 2013 to June 2023 was analyzed. Data on patient characteristics, laboratory results, and clinical outcomes were collected. The 4-variable and 8-variable KFRE and eGFR were assessed for their ability to predict end-stage kidney disease (ESKD) within a 2-year period. Discrimination was evaluated using receiver operating characteristic (ROC) curves, and calibration was assessed graphically. Net benefit decision curves were utilized to compare the net benefit of the KFRE models at various threshold probabilities. Results The cohort comprised 238 patients with an average age of 65.2 years and a mean eGFR of 13.3 mL/min/m²73. During the median 10.7-month follow-up, 178 patients (74.8%) progressed to ESKD, and 21 (9.2%) died prior to reaching ESKD. At the 1-year mark, the probability of progressing to ESKD was 77.6% (95% CI, 69.9-85.3%) when a 40% threshold for the 4-variable KFRE was applied, compared to 65.8% (95% CI, 58.3-73.3%) with an eGFR threshold of 15 mL/min/m²73. Discrimination analysis demonstrated a superior predictive performance for the 8-variable KFRE at 6 months, with a C-statistic of 0.82 (95% CI: 0.76-0.88). At 1 year, both KFRE models showed strong predictive abilities, with C-statistics of 0.835 (95% CI: 0.78-0.89) for the 4-variable KFRE and 0.82 (95% CI: 0.76-0.875) for the 8-variable KFRE. Sensitivity and specificity analyses underscored the benefits of utilizing the 40% KFRE threshold for predicting ESKD over the eGFR threshold. Conclusion The study demonstrates that both the 4-variable and 8-variable KFRE are valuable tools for predicting the need for vascular access in pre-dialysis patients, outperforming eGFR alone. The 8-variable KFRE, in particular, provides a significant improvement in 6-months ESKD prediction, with potential implications for clinical decision-making and patient management in advanced CKD. These findings advocate for the incorporation of KFRE in the clinical evaluation process for timely and appropriate vascular access planning.

Integrating IASLC grading and radiomics for predicting postoperative outcomes in stage IA invasive lung adenocarcinoma.

The International Association for the Study of Lung Cancer (IASLC) Pathology Committee introduced a histologic grading system for invasive lung adenocarcinoma (LUAD) in 2020. The IASLC grading system, hinging on the evaluation of predominant and high-grade histologic patterns, has proven to be practical and prognostic for invasive LUAD. However, there are still limitations in evaluating the prognosis of stage IA LUAD. Radiomics may serve as a valuable complement. To establish a model that integrates IASLC grading and radiomics, aimed at predicting the prognosis of stage IA LUAD. We conducted a retrospective analysis of 628 patients diagnosed with stage IA LUAD who underwent surgical resection between January 2015 and December 2018 at our institution. The patients were randomly divided into the training set (n=439) and testing set (n=189) at a ratio of 7:3. Overall survival (OS) and disease-free survival (DFS) were taken as the end points. Radiomics features were obtained by PyRadiomics. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO). The prediction models for OS and DFS were developed using multivariate Cox regression analysis, and the models were visualized through nomogram plots. The model's performance was evaluated using area under the curves (AUC), concordance index (C-index), calibration curves, and survival decision curve analysis (DCA). In total, nine radiomics features were selected for the OS prediction model, and 15 radiomics features were selected for the DFS prediction model. Patients with high radiomics scores were associated with a worse prognosis (p<0.001). We built separate prediction models using radiomics or IASLC alone, as well as a combined prediction model. In the prediction of OS, we observed that the combined model (C-index: 0.812±0.024, 3 years AUC: 0.692, 5 years AUC: 0.792) achieved superior predictive performance than the radiomics (C-index: 0.743±0.038, 3 years AUC: 0.633, 5 years AUC: 0.768) and IASLC grading (C-index: 0.765±0.042, 3 years AUC: 0.658, 5 years AUC: 0.743) models alone. Similar results were obtained in the models for DFS. The combination of radiomics and IASLC pathological grading proves to be an effective approach for predicting the prognosis of stage IA LUAD. This has substantial clinical relevance in guiding treatment decisions for early-stage LUAD.

Epileptic Seizure Prediction Using Spatiotemporal Feature Fusion on EEG.

Electroencephalography (EEG) plays a crucial role in epilepsy analysis, and epileptic seizure prediction has significant value for clinical treatment of epilepsy. Currently, prediction methods using Convolutional Neural Network (CNN) primarily focus on local features of EEG, making it challenging to simultaneously capture the spatial and temporal features from multi-channel EEGs to identify the preictal state effectively. In order to extract inherent spatial relationships among multi-channel EEGs while obtaining their temporal correlations, this study proposed an end-to-end model for the prediction of epileptic seizures by incorporating Graph Attention Network (GAT) and Temporal Convolutional Network (TCN). Low-pass filtered EEG signals were fed into the GAT module for EEG spatial feature extraction, and followed by TCN to capture temporal features, allowing the end-to-end model to acquire the spatiotemporal correlations of multi-channel EEGs. The system was evaluated on the publicly available CHB-MIT database, yielding segment-based accuracy of 98.71%, specificity of 98.35%, sensitivity of 99.07%, and F1-score of 98.71%, respectively. Event-based sensitivity of 97.03% and False Positive Rate (FPR) of 0.03/h was also achieved. Experimental results demonstrated this system can achieve superior performance for seizure prediction by leveraging the fusion of EEG spatiotemporal features without the need of feature engineering.

Towards Predicting the Quality of Red Wine Using Novel Machine Learning Methods for Classification, Data Visualization and Analysis

here is a growing concern among consumers and the wine industry regarding the quality of wine. Traditionally, wine experts determined its quality through tasting, which was time-consuming. Therefore, there is a need to predict wine quality based on specific key features to streamline these tasks. Technological developments like machine learning (ML) approaches have replaced human assessments with computational methods. However, some of these methods have faced criticism due to their low accuracy and lack of interpretability for humans. In this paper, a stacking ensemble method is introduced and demonstrates superior predictive performance when compared to other classification techniques like Logistic Regression (LR), Decision Trees (DT), Gradient Boosting (GB), Adaptive Boosting (AdaBoost), and Random Forest (RF). This evaluation is based on classification metrics such as accuracy, precision, recall, and F1-Score, all under the same conditions. Additionally, outlier detection algorithms were employed to identify exceptional or subpar wines, though their results did not match the accuracy of classification approaches. Lastly, a feature analysis study was conducted to assess the significance of each feature in the model's performance.

Terahertz Nondestructive Measurement of Heat Radiation Performance of Thermal Barrier Coatings Based on Hybrid Artificial Neural Network

Effective control of the micro- and nanostructure of thermal barrier coatings is essential to enhance the thermal radiation performance of the coating, which helps to determine the remaining service life of the coating. This paper proposed a method to measure the radiation properties of thermal barrier coatings by terahertz nondestructive testing technique, using APS-prepared thermal barrier coatings as the object of study. Radiative properties were a comprehensive set of properties characterized by the diffuse reflectance, transmittance, and absorptance of the thermal barrier coating. The coating data in actual service were obtained by scanning electron microscopy and metallographic experiments, and the data were used as the simulation model critical value. The terahertz time-domain simulation data of coatings with different microstructural features were obtained using the finite-different time-domain (FDTD) method. In simulating the real test signals, white noise with a signal-to-noise ratio of 20 dB was added, and fast Fourier transform (FFT), short-time Fourier transform (STFT), and wavelet transform (WT) were used to reduce the noise and compare their noise reduction effects. Different machine learning methods were used to build the model, including support vector machine algorithm (SVM) and k-nearest neighbor algorithm (KNN). The principal component algorithm (PCA) was used to reduce the dimensionality of terahertz time-domain data, and the SVM algorithm and KNN algorithm were optimized using the particle swarm optimization algorithm (PSO) and the ant colony optimization algorithm (ACO), respectively, to improve the robustness of the system. The K-fold cross-validation method was used to construct the model to improve the adaptability of the model. It could be clearly seen that the novel hybrid PCA-ACO-SVM model had superior prediction performance. Finally, this work proposed a novel, convenient, nondestructive, online, safe and highly accurate method for measuring the radiation performance of thermal barrier coatings, which could be used for the judgment of the service life of thermal barrier coatings.

Using Machine Learning Models to Identify Factors Associated With 30-Day Readmissions After Posterior Cervical Fusions: A Longitudinal Cohort Study.

Readmission rates after posterior cervical fusion (PCF) significantly impact patients and healthcare, with complication rates at 15%-5% and up to 12% 90-day readmission rates. In this study, we aim to test whether machine learning (ML) models that capture interfactorial interactions outperform traditional logistic regression (LR) in identifying readmission-associated factors. The Optum Clinformatics Data Mart database was used to identify patients who underwent PCF between 2004-2017. To determine factors associated with 30-day readmissions, 5 ML models were generated and evaluated, including a multivariate LR (MLR) model. Then, the best-performing model, Gradient Boosting Machine (GBM), was compared to the LACE (Length patient stay in the hospital, Acuity of admission of patient in the hospital, Comorbidity, and Emergency visit) index regarding potential cost savings from algorithm implementation. This study included 4,130 patients, 874 of which were readmitted within 30 days. When analyzed and scaled, we found that patient discharge status, comorbidities, and number of procedure codes were factors that influenced MLR, while patient discharge status, billed admission charge, and length of stay influenced the GBM model. The GBM model significantly outperformed MLR in predicting unplanned readmissions (mean area under the receiver operating characteristic curve, 0.846 vs. 0.829; p<0.001), while also projecting an average cost savings of 50% more than the LACE index. Five models (GBM, XGBoost [extreme gradient boosting], RF [random forest], LASSO [least absolute shrinkage and selection operator], and MLR) were evaluated, among which, the GBM model exhibited superior predictive performance, robustness, and accuracy. Factors associated with readmissions impact LR and GBM models differently, suggesting that these models can be used complementarily. When analyzing PCF procedures, the GBM model resulted in greater predictive performance and was associated with higher theoretical cost savings for readmissions associated with PCF complications.

Cost prediction for water reuse equipment using interpretable machine learning models

During the initial stages of engineering projects management, the accurate estimation of equipment costs plays a crucial role in determining project approval decisions. However, there is a significant research gap regarding the estimation of investment costs for water reuse equipment. Additionally, cost predictions for such construction projects often suffer from limitations, including low accuracy, limited generalizability, and inefficiency. Advanced machine learning (ML) methods, renowned for their ability to model complex decision-making processes, offer powerful solutions. In this study, four traditional models and four ensemble models were employed to predict the cost of water reuse equipment. The results demonstrated that the ensemble models exhibited significantly superior predictive performance to that of traditional models with the three boosting ensemble models achieving the best performance (traditional models: training R2 = 29.77 %–94.85 %, testing R2 = 30.62 %–71.72 %; boosting ensemble models: training R2 = 97.42 %, testing R2 = 82.16 %–93.79 %). Furthermore, this study simplified the features of predictive models and identified the key variables that influence the cost of water reuse equipment using Shapley additive explanations (SHAP) method. The retrained ensemble models re-constructed based on the selected variables achieved significant predictive performance, with the Gradient Boosting Decision Tree (GBDT) outperforming the other models (training set R2 = 97.37 %, testing set R2 = 93.86 %). The water quantity, inflow conductivity, outflow conductivity, and recovery rate emerged as critical factors affecting the cost of water reuse equipment. Overall, the methods proposed in this study can enhance the versatility of cost prediction processes in environmental engineering scenarios, particularly those concerning the construction costs of water treatment equipment.

Forecasting Next-Time-Step Forex Market Stock Prices Using Neural Networks

Purpose: This study aims to predict the closing price of the EUR/JPY currency pair in the forex market using recurrent neural network (RNN) architectures, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), with the incorporation of Bidirectional layers. Methods: The dataset comprises hourly price data obtained from Yahoo Finance and pre-processed accordingly. The data is divided into training and testing sets, and time series sequences are constructed for input into the models. The RNN, LSTM, and GRU models are trained using the Adam optimization algorithm with the mean squared error (MSE) loss metric. Results: Results indicate that the LSTM model, particularly when coupled with Bidirectional layers, exhibits superior predictive performance compared to the other models, as evidenced by lower MSE values. Conclusions: Therefore, the LSTM model with Bidirectional layers is the most effective in predicting the EUR/JPY currency pair's closing price in the forex market. These findings offer valuable insights for practitioners and researchers involved in financial market prediction and neural network modelling

Artificial Neural Network-Based Modelling for Yield Strength Prediction of Austenitic Stainless-Steel Welds

This study aimed to develop an artificial neural network (ANN) model for predicting the yield strength of a weld metal composed of austenitic stainless steel and compare its performance with that of conventional multiple regression and machine learning models. The input parameters included the chemical composition of the nine effective elements (C, Si, Mn, P, S, Ni, Cr, Mo, and Cu) and the heat input per unit length. The ANN model (comprising five nodes in one hidden layer), which was constructed and trained using 60 data points, yielded an R2 value of 0.94 and a mean average percent error (MAPE) of 2.29%. During model verification, the ANN model exhibited superior prediction performance compared with the multiple regression and machine learning models, achieving an R2 value of 0.8644 and a MAPE of 3.06%. Consequently, the ANN model effectively predicted the variation in the yield strength and microstructure resulting from the thermal history and dilution during the welding of 3.5–9% Ni steels with stainless steel-based welding consumables. Furthermore, the application of the prediction model was demonstrated in the design of welding consumables and heat input for 9% Ni steel.

DeepPepPI: A deep cross-dependent framework with information sharing mechanism for predicting plant peptide-protein interactions

Peptide-protein interactions (PepPIs) play a crucial role in various fundamental biological activities in plants. As traditional experimental technologies are usually time-consuming and labor-intensive, it is indispensable to develop computational methods for PepPI identification, which has potential applications across diverse fields including food safety and peptide drug discovery. However, existing methods have received relatively little attention in adequately representing the interaction information between peptides and proteins, consequently limiting the prediction performance. To this end, we present DeepPepPI, a novel deep cross-dependent framework for accurate prediction of plant PepPIs. Concretely, a data-driven context-embedded representation (DCR) module is developed as the peptide feature extractor that can capture rich contextual semantic information, even from short sequences. To fully characterize inherent properties of proteins, we propose a bi-level self-correlation search (BSS) module, which integrates the primary sequence and secondary structure into a unified space to learn their potential relationships. In addition, a cross-dependent feature integration (CFI) module with information sharing mechanism is introduced, aimed at providing a comprehensive feature representation to portray the intricate interaction patterns between peptides and proteins from a global perspective. Extensive experimental results conducted on the benchmark datasets show that DeepPepPI achieves superior prediction performance compared to other state-of-the-art methods.

Research on the application of deep learning techniques in stock market prediction and investment decision-making in financial management

Introduction: This paper introduces a deep learning approach based on Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory Networks (BiLSTM), and attention mechanism for stock market prediction and investment decision making in financial management. These methods leverage the advantages of deep learning to capture complex patterns and dependencies in financial time series data. Stock market prediction and investment decision-making have always been important issues in financial management.Methods: Traditional statistical models often struggle to handle nonlinear relationships and complex temporal dependencies, thus necessitating the use of deep learning methods to improve prediction accuracy and decision effectiveness. This paper adopts a hybrid deep learning model incorporating CNN, BiLSTM, and attention mechanism. CNN can extract meaningful features from historical price or trading volume data, while BiLSTM can capture dependencies between past and future sequences. The attention mechanism allows the model to focus on the most relevant parts of the data. These methods are integrated to create a comprehensive stock market prediction model. We validate the effectiveness of the proposed methods through experiments on real stock market data. Compared to traditional models, the deep learning model utilizing CNN, BiLSTM, and attention mechanism demonstrates superior performance in stock market prediction and investment decision-making.Results and Discussion: Through ablation experiments on the dataset, our deep learning model achieves the best performance across all metrics. For example, the Mean Absolute Error (MAE) is 15.20, the Mean Absolute Percentage Error (MAPE) is 4.12%, the Root Mean Square Error (RMSE) is 2.13, and the Mean Squared Error (MSE) is 4.56. This indicates that these methods can predict stock market trends and price fluctuations more accurately, providing financial managers with more reliable decision guidance. This research holds significant implications for the field of financial management. It offers investors and financial institutions an innovative approach to better understand and predict stock market behavior, enabling them to make wiser investment decisions.

DCGAN-DTA: Predicting drug-target binding affinity with deep convolutional generative adversarial networks

BackgroundIn recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications.ResultsTo mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index.ConclusionThe results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA. Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/.