High Predictive Performance Research Articles

Analysis of Influencing Factors and Construction of Predictive Model for Persistent Cough After Lung Cancer Resection Under Thoracoscopy.

This study aims to explore the influencing factors of cough after pulmonary resection (CAP) after thoracoscopic lung resection in lung cancer patients and to develop a predictive model. A total of 374 lung cancer patients who underwent lung resection in our hospital from March 2020 to October 2023 were randomly divided into a modeling group (n=262) and a validation group (n=112). Based on the occurrence of CAP in the modeling group, the patients were divided into a CAP group (n=85) and a non-CAP group (n=177). Multivariate Logistic regression analysis was used to identify the influencing factors of CAP in lung cancer patients. A nomogram model for predicting the risk of CAP was constructed using R4.3.1. The consistency of the model's predictions was evaluated, and a clinical decision curve (DCA) was drawn to assess the clinical utility of the nomogram. The predictive performance of the model was evaluated using ROC curves and the Hosmer-Lemeshow test. Multivariate Logistic regression analysis showed that smoking history (OR=6.285, 95% CI: 3.031-13.036), preoperative respiratory function training (OR=20.293, 95% CI: 7.518-54.779), surgical scope (OR=20.667, 95% CI: 7.734-55.228), and peribronchial lymph node dissection (OR=5.883, 95% CI: 2.829-12.235) were significant influencing factors of CAP in lung cancer patients (P<0.05). ROC curves indicated good discriminatory power of the model, and the Hosmer-Lemeshow test showed a high degree of agreement between predicted and actual probabilities. The DCA curve revealed that the nomogram model had high clinical value when the high-risk threshold was between 0.08 and 0.98. The nomogram model based on smoking history, preoperative respiratory function training, surgical scope, and peribronchial lymph node dissection has high predictive performance for CAP in lung cancer patients. It is useful for clinical prediction, guiding preoperative preparation, and postoperative care.

Interpretable analysis of public library service outcomes based on ensemble learning models: Data study from China (2007–2021)

Service outcome is a crucial component in the overall evaluation of public library service efficiency. Specifically, identifying and analyzing key factors that influence public library service output precisely can provide a significant theoretical basis for rational library resource allocation planning. Utilizing 15 years of data from the National Bureau of Statistics of China, the research predicted library service outcomes based on resource inputs. To achieve high predictive performance, six ensemble learning models were trained and evaluated, with CatBoost selected for its superior performance. Additionally, SHAP interpretability method was applied alongside CatBoost to offer nuanced insights into the influence of various factors, from both holistic and local perspectives. The research not only provided concrete suggestions for enhancing public library service outcomes but also introduced new approaches for processing and analyzing data in the field of library science.

Prediction of Neoadjuvant Chemoradiotherapy Sensitivity in Patients With Esophageal Squamous Cell Carcinoma Using CT-Based Radiomics Combined With Clinical Features.

Background: For patients with resectable locally advanced esophageal squamous cell carcinoma (ESCC), the current standard treatment is neoadjuvant chemoradiotherapy (nCRT) plus radical surgery. Objective: This study aimed to establish a predictive model, based on computed tomography (CT) radiomics features and clinical parameters, to predict sensitivity to nCRT in patients with ESCC pre-treatment. The goal was to provide risk stratification and decision-making recommendations for clinical treatments and offer more valuable information for developing personalized therapies. Methods: This retrospective study involved 102 patients diagnosed with ESCC through biopsy who underwent nCRT. To select radiomics features, we used the least absolute shrinkage and selection operator (LASSO) algorithm. A combined model was constructed, integrating the selected clinically relevant parameters with the Rad-Score. To assess the performance of this combined model, we utilized calibration curves and receiver operating characteristic (ROC) curves. Results: Nine optimal radiomics features were selected using the LASSO algorithm. The support vector machine (SVM) classifier was identified as having the best predictive performance. The area under the curve (AUC) of the SVM training group was 0.937 (95% CI: 0.856-1.000), and of the validation group was 0.831 (95% CI: 0.679-0.983). Smoking and alcohol history, neutrophil to lymphocyte ratio, serum aspartate aminotransferase to alanine aminotransferase ratio, and carcinoembryonic antigen and fibrinogen levels were independent predictors of sensitivity to nCRT in patients with ESCC. The AUCs of the combined model for the training and validation groups were 0.870 (95% CI: 0.774-0.964) and 0.821 (95% CI: 0.669-0.972), respectively. The calibration curve showed that the nomogram's predictions were close to the actual clinical observations, indicating that the model exhibited good predictive performance. Conclusion: Our combined model based on Rad-Score and clinical characteristics showed high predictive performance for predicting sensitivity to nCRT in patients with ESCC. It may be useful for predicting treatment effects in clinical practice and demonstrates the significant potential of radiomics in predicting and optimizing treatment decisions.

Development of a COVID-19 early risk assessment system based on multiple machine learning algorithms and routine blood tests: a real-world study.

During the Coronavirus Disease 2019 (COVID-19) epidemic, the massive spread of the disease has placed an enormous burden on the world's healthcare and economy. The early risk assessment system based on a variety of machine learning (ML) algorithms may be able to provide more accurate advice on the classification of COVID-19 patients, offering predictive, preventive, and personalized medicine (PPPM) solutions in the future. In this retrospective study, we divided a portion of the data into training and validation cohorts in a 7:3 ratio and established a model based on a combination of two ML algorithms first. Then, we used another portion of the data as an independent testing cohort to determine the most accurate and stable model and compared it with other scoring systems. Finally, patients were categorized according to risk scores and then the correlation between their clinical data and risk scores was studied. The elderly accounted for the majority of hospitalized patients with COVID-19. The C-index of the model constructed by combining the stepcox[both] and survivalSVM algorithms was 0.840 in the training cohort and 0.815 in the validation cohort, which was calculated to have the highest C-index in the testing cohort compared to the other 119 ML model combinations. Compared with current scoring systems, including the CURB-65 and several reported prognosis models previously, our model had the highest AUC value of 0.778, representing an even higher predictive performance. In addition, the model's AUC values for specific time intervals, including days 7,14 and 28, demonstrate excellent predictive performance. Most importantly, we stratified patients according to the model's risk score and demonstrated a difference in survival status between the high-risk, median-risk, and low-risk groups, which means a new and stable risk assessment system was built. Finally, we found that COVID-19 patients with a history of cerebral infarction had a significantly higher risk of death. This novel risk assessment system is highly accurate in predicting the prognosis of patients with COVID-19, especially elderly patients with COVID-19, and can be well applied within the PPPM framework. Our ML model facilitates stratified patient management, meanwhile promoting the optimal use of healthcare resources.

Modeling the Time Evolution of Compact Binary Systems with Machine Learning

This work introduces advanced computational techniques for modeling the time evolution of compact binary systems using machine learning. The dynamics of compact binary systems, such as black holes and neutron stars, present significant nonlinear challenges due to the strong gravitational interactions and the requirement for precise numerical simulations. Traditional methods, like the post-Newtonian approximation, often require significant computational resources and face challenges in accuracy and efficiency. Here, we employed machine learning algorithms, including deep learning models like long short-term memory (LSTM) and temporal convolutional network (TCN), to predict the future evolution of these systems based on extensive simulation data. Our results demonstrate that employing both LSTM and TCN even as black-box predictors for sequence prediction can also significantly improve the prediction accuracy without physics-informed neural networks (as partial differential equation solvers with prior knowledge or inductive bias. By employing LSTM and TCN, we obtained R 2 values of 99.74% and 99.19% for the evolutionary orbits of the compact binaries data set, respectively. Our models demonstrate the ability to effectively capture the dynamics of the binaries, achieving high prediction performance with significantly reduced computational overhead by a factor of 40, compared to conventional numerical methods. This study paves the way for more effective and computationally scalable approaches to the understanding of gravitational phenomena and predictive modeling in gravitational-wave astronomy.

Classification of Quality Defects using Multivariate Control Chart with Ensemble Machine Learning Model

Multivariate control charts enable to monitor processes affected by more than one variable. But, when the process is out of control, it cannot detect which variable is causing it. It is an important requirement to know which variables in the process need corrective actions. In this study, a machine learning-based model is proposed to predict the variable/s that make the process out of control. For this purpose, ensemble algorithms, which are known to have higher prediction performance than single algorithms, were preferred. Because it is aimed to determine the variable(s) that cause the process to be out of control in the most accurate way. It is thought that a classification model in which ensemble algorithms are used together can increase the prediction accuracy. The model, which has not been encountered before in a quality control problem, was applied to a real problem and 98.06% classification accuracy was achieved. Another benefit is that it can predict the variable/variables that make the process uncontrolled without the need for multivariate control charts.

Structural and functional design of CTAB-geopolymer adsorbents for rapid removal of tetracycline: A comparative study

A powder, inorganic membrane and 3D printing cetyltrimethylammonium bromide (CTAB)-geopolymer adsorbents system for adsorbing tetracycline (TC) was developed. And the adsorption properties, adsorption mechanism, adsorption cycle application based on the dynamic pH of adsorption system were systematically investigated by experiment, characterization and density functional theory (DFT) calculation. The introduction of CTAB significantly increased the adsorption response to TC in the high alkaline environment caused by spontaneous alkali release of geopolymer. The adsorption of CTAB-geopolymer for TC was most efficient in the dynamic pH range corresponding to TC- species. The predominant influencing mechanism between CTAB-geopolymer with TC was electrostatic interaction assisted by the hydrogen bonding and n-π interaction. The powder adsorbent with 11 wt% CTAB can capture 92.38 % TC at 2 min and fitted the pseudo-second-order model, and was also suitable for adsorption of trace TC. Although the extension of the diffusion path of the monolithic adsorbents limited the adsorption rate, the 3D printed adsorbent showed an adsorption efficiency of 84.20 % at 302 min. The outstanding adsorption (4 times)-desorption (3 times) cycle properties of 11 %CT-GA (81.15 % at 24 min, 4th adsorption) and cycle cumulative adsorption efficiency of 11 %CT-3DP (59.23 % at 120 min, 4th adsorption) adsorbent were exhibited. Furthermore, a high accuracy performance prediction model with the mean R2 value tended to 1 and the low root mean square error (0.0747) was provided, which can provide theoretical and technical reference for the subsequent industrial application of CTAB-geopolymer adsorbents.

AI-enabled CT-guided end-to-end quantification of total cardiac activity in 18FDG cardiac PET/CT for detection of cardiac sarcoidosis.

[18F]-fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) plays a central role in diagnosing and managing cardiac sarcoidosis. We propose a fully automated pipeline for quantification of [18F]FDG PET activity using deep learning (DL) segmentation of cardiac chambers on computed tomography (CT) attenuation maps and evaluate several quantitative approaches based on this framework. We included consecutive patients undergoing [18F]FDG PET/CT for suspected cardiac sarcoidosis. DL segmented left atrium, left ventricular(LV), right atrium, right ventricle, aorta, LV myocardium, and lungs from CT attenuation scans. CT-defined anatomical regions were applied to [18F]FDG PET images automatically to target to background ratio (TBR), volume of inflammation (VOI) and cardiometabolic activity (CMA) using full sized and shrunk segmentations. A total of 69 patients were included, with mean age of 56.1 ± 13.4 and cardiac sarcoidosis present in 29 (42%). CMA had the highest prediction performance (area under the receiver operating characteristic curve [AUC] 0.919, 95% confidence interval [CI] 0.858 - 0.980) followed by VOI (AUC 0.903, 95% CI 0.834 - 0.971), TBR (AUC 0.891, 95% CI 0.819 - 0.964), and maximum standardized uptake value (AUC 0.812, 95% CI 0.701 - 0.923). Abnormal CMA (≥1) had a sensitivity of 100% and specificity 65% for cardiac sarcoidosis. Lung quantification was able to identify patients with pulmonary abnormalities. We demonstrate that fully automated volumetric quantification of [18F]FDG PET for cardiac sarcoidosis based on CT attenuation map-derived volumetry is feasible, rapid, and has high prediction performance. This approach provides objective measurements of cardiac inflammation with consistent definition of myocardium and background region.

The study on the high cycle fatigue performance and life prediction of Ti–6Al–4V alloy fabricated by laser engineered net shaping

The study on the high cycle fatigue performance and life prediction of Ti–6Al–4V alloy fabricated by laser engineered net shaping

Shrinking suitable habitat of a sub-Arctic foundation kelp under future climate scenarios.

Climate change has profound effects on the distribution of kelp forests in the Arctic and sub-Arctic. However, studies on the responses of kelps to climate change, particularly along the sub-Arctic regions of the Alaska coast, are limited. Eualaria fistulosa is a foundational kelp species in the Aleutian Islands, with an east-west distribution that extends from Japan to southern southwest Alaska. In this study, we utilized a species distribution model (SDM) to explore changes in the future habitat suitability of E. fistulosa under contrasting Shared Socioeconomic Pathway (SSP) scenarios. Our model exhibited relatively high predictive performance, validating our SDM predictions. Notably, the SDM results indicate that minimum sea surface temperature, annual range in sea surface temperatures, and annual mean current velocities are the three most important predictor variables determining E. fistulosa's distribution. Furthermore, the projected geographic distribution of Eualaria is generally consistent with its observed occurrence records. However, under high emission scenarios (SSP5-8.5), E. fistulosa is predicted to contract its distribution range by 9.0% by 2100, with widespread disappearance along the southeast Alaskan coast and limited northward migration to Kamchatka Krai in Russia and Bristol Bay in Alaska. These findings contribute valuable insights for conservation strategies via addressing climate-induced alterations in sub-Arctic kelp distribution.

A deep learning approach to prediction of blood group antigens from genomic data.

Deep learning methods are revolutionizing natural science. In this study, we aim to apply such techniques to develop blood type prediction models based on cheap to analyze and easily scalable screening array genotyping platforms. Combining existing blood types from blood banks and imputed screening array genotypes for ~111,000 Danish and 1168 Finnish blood donors, we used deep learning techniques to train and validate blood type prediction models for 36 antigens in 15 blood group systems. To account for missing genotypes a denoising autoencoder initial step was utilized, followed by a convolutional neural network blood type classifier. Two thirds of the trained blood type prediction models demonstrated an F1-accuracy above 99%. Models for antigens with low or high frequencies like, for example, Cw, low training cohorts like, for example, Cob, or very complicated genetic underpinning like, for example, RhD, proved to be more challenging for high accuracy (>99%) DL modeling. However, in the Danish cohort only 4 out of 36 models (Cob, Cw, D-weak, Kpa) failed to achieve a prediction F1-accuracy above 97%. This high predictive performance was replicated in the Finnish cohort. High accuracy in a variety of blood groups proves viability of deep learning-based blood type prediction using array chip genotypes, even in blood groups with nontrivial genetic underpinnings. These techniques are suitable for aiding in identifying blood donors with rare blood types by greatly narrowing down the potential pool of candidate donors before clinical grade confirmation.

Appraising machine learning algorithms in predicting noise level and emissions from gasoline-powered household backup generators

AbstractMachine learning is presently receiving great attention. However, machine learning applications to gasoline engine research are limited. This paper investigated the implementation of various machine learning models in predicting the emissions (CO2, CO, and PM2.5) and noise levels of gasoline-powered household generators for the first time. Data of operating and installed capacity, efficiency (input) and emissions, and noise level (output) obtained from 166 generators were used in extreme gradient boosting, artificial neural network (ANN), decision tree (DT), random forest (RF), and polynomial regression (PNR) algorithms to develop predictive models. Results revealed high prediction performance (R2 = 0.9377–1.0000) of these algorithms marked with very low errors. The implementation of PNR followed by the RF exhibited the best models for predicting CO2, CO, PM2.5, and the noise level of generators. R2 of 1.000 and 0.9979–0.9994, mean squared error of &lt; 10−6 and 2 × 10−5–8.6 × 10−5, mean absolute percentage error of 9.15 × 10−16–1.3 × 10−15 and 7.1 × 10−3–8.1 × 10−2, and root mean squared error of 3.3 × 10−16–5.4 × 10−16 and 4.4 × 10−3–9.3 × 10−2 were recorded for all the output parameters using PNR and RF respectively. DT models had the least prediction capacity for CO, CO2, and noise levels (R2 = 0.9493–0.9592) while ANN produced the least performance for PM2.5 (R2 = 0.9377). This study further strengthens machine learning applications in engine research for the prediction of various output parameters.

Quantification and prediction of furnace cylinder activity based on LASSO-GWO-CNN hybrid model

Blast furnace smelting environments are complex and characterised by multi-scale, non-linear and strong coupling, and it is often difficult for operators to detect changes in cylinder activity in a timely manner. Quantifying the cylinder activity is the basis for monitoring and improving the cylinder activity. Aiming at the traditional method of quantifying the cylinder activity, which relies heavily on a single empirical formula and is difficult to realise the prediction effect of the cylinder activity, this paper proposes a new method of quantitatively characterising the cylinder activity by combining the core dead material column temperature index and the dead material pile cleanliness index, which comprehensively takes into account the thermodynamic and kinetic characteristics of the cylinder, and is able to more accurately and comprehensively assess the state of the cylinder activity. Firstly, a new quantitative cylinder activity formula is set according to the combined index, in which the weights of the indexes will be gradually adjusted in the iterative process of the model, and the entropy weighting method is adopted for its operation; a hierarchical affiliation function is established, and the calculation of the affiliation is used to judge the degree of contribution of the new indexes to the active state of the furnace cylinder with different weights in order to assist in finalising the final weights of the indexes, and the final weights of the indexes are then validated through the analysis of the calculation examples. Afterwards, the rationality of the final weights and the effectiveness of the proposed quantisation method are verified through case analysis. Finally, the LASSO algorithm is used to filter the feature variables, and the Grey Wolf Optimisation (GWO) optimised Convolutional Neural Network (CNN) based cylinder activity prediction model is proposed. According to the results of the comparative validation between five different prediction models, the prediction accuracy of the GWO-CNN model reaches more than 90%, which indicates that the model has a higher prediction performance in predicting the furnace cylinder activity.

Prediction of Glioma enhancement pattern using a MRI radiomics-based model.

Contrast-MRI scans carry risks associated with the chemical contrast agents. Accurate prediction of enhancement pattern of gliomas has potential in avoiding contrast agent administration to patients. This study aimed to develop a machine learning radiomics model that can accurately predict enhancement pattern of gliomas based on T2 fluid attenuated inversion recovery images. A total of 385 cases of pathologically-proven glioma were retrospectively collected with preoperative magnetic resonance T2 fluid attenuated inversion recovery images, which were divided into enhancing and non-enhancing groups. Predictive radiomics models based on machine learning with 6 different classifiers were established in the training cohort (n = 201), and tested both in the internal validation cohort (n = 85) and the external validation cohort (n = 99). Receiver-operator characteristic curve was used to assess the predictive performance of these radiomics models. This study demonstrated that the radiomics model comprising of 15 features using the Gaussian process as a classifier had the highest predictive performance in both the training cohort and the internal validation cohort, with the area under the curve being 0.88 and 0.80, respectively. This model showed an area under the curve, sensitivity, specificity, positive predictive value and negative predictive value of 0.81, 0.98, 0.61, 0.82, 0.76 and 0.96, respectively, in the external validation cohort. This study suggests that the T2-FLAIR-based machine learning radiomics model can accurately predict enhancement pattern of glioma.

Short-term air quality prediction based on EMD-transformer-BiLSTM

Actual acquired air quality time series data are highly volatile and nonstationary, and accurately predicting nonlinear time series data containing complex noise is an ongoing challenge. This paper proposes an air quality prediction method based on empirical mode decomposition (EMD), a transformer and a bidirectional long short-term memory neural network (BiLSTM), which is good at addressing the ultrashort-term prediction of nonlinear time-series data and shows good performance for application to the air quality dataset of Patna, India (6:00 am on October 3, 2015–0:00 pm on July 1, 2020). The AQI sequence is first decomposed into intrinsic mode functions (IMFs) via EMD and subsequently predicted separately via the improved transformer algorithm based on BiLSTM, where linear prediction is performed for IMFs with simple trends. Finally, the predicted values of each IMF are integrated using BiLSTM to obtain the predicted AQI values. This paper predicts the AQI in Patna with a time window of 5 h, and the RMSE, MAE and MAPE are as low as 5.6853, 2.8230 and 2.23%, respectively. Moreover, the scalability of the proposed model is validated on air quality datasets from several other cities, and the results prove that the proposed hybrid model has high performance and broad application prospects in real-time air quality prediction.

An evolutionary deep learning model based on XGBoost feature selection and Gaussian data augmentation for AQI prediction

Accurate prediction of air quality is crucial for ensuring the scientific validity and effectiveness of air pollution control measures. This study proposes a combined deep learning (DL) model (XGBoost-GDA-TCN-IMRFO-GRU) for predicting hourly air quality index (AQI) data in four cities. The model integrates Extreme gradient boosting (XGBoost) for feature selection, Gaussian data augmentation (GDA), improved manta ray foraging optimization (IMRFO) algorithm, temporal convolutional network (TCN), and gated recurrent unit (GRU). XGBoost calculates the scores of pollutant gases affecting AQI, selecting the top four important pollutants (PM2.5, PM10, NO2, O3) based on their importance rankings. GDA enhances the robustness of the DL models and addresses the limitations of insufficient and overfitting training datasets. Additionally, the IMRFO algorithm, with two improved strategies, is applied to enhance the GRU model. TCN extracts spatiotemporal features of AQI, while GRU constructs a temporal model for efficient computations. Compared to eleven benchmark models, the proposed model demonstrates superior performance in terms of MAE, RMSE, MAPE, and NSE, achieving high accuracy and optimal prediction performance. Specifically, the XGBoost-GDA-TCN-IMRFO-GRU model reduces RMSE, MAE, and MAPE by 33–60 %, 39–68 %, and 39–66 %, respectively, compared to the TCN model. Therefore, the XGBoost-GDA-TCN-IMRFO-GRU model can provide reliable early warnings for air quality, which is of great significance for air pollution prevention and the sustainable development of society.

Predicting cerebellar mutism syndrome in children using lesion map combined with clinical features.

This study aimed to develop a predictive model for cerebellar mutism syndrome (CMS) in pediatric patients with posterior fossa tumors, integrating lesion-symptom mapping (LSM) data with clinical factors, and to assess the model's performance. A cohort of pediatric patients diagnosed with posterior fossa tumors and undergoing surgery at Beijing Children's Hospital from July 2013 to December 2023 was analyzed. Clinical variables gender, age at surgery, tumor characteristics, hydrocephalus, surgical route and pathology were collected. LSM was used to link tumor locations with CMS outcomes. Lasso regression and logistic regression were employed for feature selection and model construction, respectively. Model performance was assessed using area under the curve (AUC) and accuracy metrics. The study included 197 patients in total, with CMS rates consistent across training, validation, and prospective groups. Significant associations were found between CMS and gender, tumor type, hydrocephalus, paraventricular edema, surgical route, and pathology. A predictive model combining voxel location data from LSM with clinical factors achieved high predictive performance (C-index: training 0.956, validation 0.933, prospective 0.892). Gender, pathology, and voxel location were identified as key predictors for CMS. The study established an effective predictive model for CMS in pediatric posterior fossa tumor patients, leveraging LSM data and clinical factors. The model's accuracy and robustness suggest its potential utility in clinical practice for early CMS risk assessment and intervention planning.

Prediction of transfusion risk after total knee arthroplasty: use of a machine learning algorithm

IntroductionTotal knee arthroplasty (TKA) carries a significant hemorrhagic risk, with a non-negligible rate of postoperative transfusions. The blood-sparing strategy has evolved to reduce blood loss after TKA by identifying the patient's risk factors preoperatively. In practice, a blood count is often performed postoperatively but rarely altering the patient's subsequent management. This study aimed to identify the preoperative variables associated with hemorrhagic risk, enabling the creation of a machine-learning model predictive of transfusion risk after total knee arthroplasty and the need for a complete blood count. HypothesisBased on preoperative data, a powerful machine learning predictive model can be constructed to estimate the risk of transfusion after total knee arthroplasty. Material and methodsThis retrospective single-centre study included 774 total knee arthroplasties (TKA) operated between January 2020 and March 2023. Twenty-five preoperative variables were integrated into the machine learning model and filtered by a recursive feature elimination algorithm. The most predictive variables were selected and used to construct a gradient-boosting machine algorithm to define the overall postoperative transfusion risk model. Two groups were formed of patients transfused and not transfused after TKA. Odds ratios were determined, and the area under the curve evaluated the model's performance. ResultsOf the 774 TKA surgery patients, 100 were transfused postoperatively (12.9%). The machine learning predictive model included five variables: age, body mass index, tranexamic acid administration, preoperative hemoglobin level, and platelet count. The overall performance was good with an area under the curve of 0.97 [95% CI 0.921–1], sensitivity of 94.4% [95% CI 91.2–97.6], and specificity of 85.4% [95% CI 80.6–90.2]. The tool developed to assess the risk of blood transfusion after TKA is available at https://arthrorisk.com. ConclusionThe risk of postoperative transfusion after total knee arthroplasty can be predicted by a model that identifies patients at low, moderate, or high risk based on five preoperative variables. This machine learning tool is available on a web platform that is accessible to all, easy to use, and has a high prediction performance. The model aims to limit the need for routine check-ups, depending on the risk presented by the patient. Level of evidenceII; diagnostic study

Metafeature Selection via Multivariate Sparse-Group Lasso Learning for Automatic Hyperparameter Configuration Recommendation.

The performance of classification algorithms is mainly governed by the hyperparameter settings deployed in applications, and the search for desirable hyperparameter configurations usually is quite challenging due to the complexity of datasets. Metafeatures are a group of measures that characterize the underlying dataset from various aspects, and the corresponding recommendation algorithm fully relies on the appropriate selection of metafeatures. Metalearning (MtL), aiming to improve the learning algorithm itself, requires development in integrating features, models, and algorithm learning to accomplish its goal. In this article, we develop a multivariate sparse-group Lasso (SGLasso) model embedded with MtL capacity in recommending suitable configurations via learning. The main idea is to select the principal metafeatures by removing those redundant or irregular ones, promoting both efficiency and performance in the hyperparameter configuration recommendation. To be specific, we first extract the metafeatures and classification performance of a set of configurations from the collection of historical datasets, and then, a metaregression task is established through SGLasso to capture the main characteristics of the underlying relationship between metafeatures and historical performance. For a new dataset, the classification performance of configurations can be estimated through the selected metafeatures so that the configuration with the highest predictive performance in terms of the new dataset can be generated. Furthermore, a general MtL architecture combined with our model is developed. Extensive experiments are conducted on 136 UCI datasets, demonstrating the effectiveness of the proposed approach. The empirical results on the well-known SVM show that our model can effectively recommend suitable configurations and outperform the existing MtL-based methods and the well-known search-based algorithms, such as random search, Bayesian optimization, and Hyperband.

Computational Studies of Novel Aniline Pyrimidine WDR5‐MLL1 Inhibitors: QSAR, Molecular Docking, and Molecular Dynamics Simulation

AbstractWD repeat‐containing protein 5 (WDR5) and mixed lineage leukemia (MLL) are critical for maintaining tumorigenesis in human cancers. Disruption of the MLL1–WDR5 interaction has been viewed as a promising therapeutic strategy for the treatment of leukemia. Here, we report a series of protein–protein binding interaction modes targeting MLL1‐WDR5 inhibitors using 3D‐QSAR, and molecular docking. CoMFA with q2 = 0.724, r2 = 0.957, rpred2 = 0.874 and CoMSIA with q2 = 0.826, r2 = 0.995, rpred2 = 0.827. Topomer CoMFA results show q2 = 0.807, r2 = 0.976, rpred2 = 0.789, and HQSAR results show q2 = 0.873, r2 = 0.982, rpred2 = 0.794. The 3D‐QSAR model with high validation and prediction performance is successfully constructed. Contour maps and molecular docking results according to the four models, 26 new compounds are finally designed on the computer after molecular screening. Further molecular dynamics simulations (MD) of compounds G01, G04, G09, G43, and G44 with high predicted activity are carried out to explore their possible binding modes. ILE305, PHE133, CYS261, and ALA176 are found to play crucial roles in stabilizing the inhibitor. ADMET predictions are also performed for these 26 new compounds. These results serve as references for the design of effective WDR5‐MLL1 inhibitors in the future.