High Predictive Ability Research Articles

Anemia Risk Prediction Model for Osteosarcoma Patients Post‐Chemotherapy Using Artificial Intelligence

ABSTRACTObjectiveThis study aimed to develop a machine learning model for predicting anemia post‐chemotherapy in osteosarcoma patients.MethodsClinical data from 631 osteosarcoma patients were collected, and after data filtering, a training set and validation set were created. Various statistical tests were conducted on the data, and single‐factor and multiple‐factor logistic regression analysis, random forest (RF), support vector machine (SVM), and least absolute shrinkage and selection operator (LASSO) were used to construct risk prediction models. A new model was created by intersecting the above models to identify common risk factors, and a nomogram was developed to display the new model. The model's performance was validated using the validation set.ResultsTwenty‐five risk factors were identified in the anemia group compared to the non‐anemia group (p < 0.05). Single‐factor logistic regression analysis identified 22 risk factors (AUC 0.895), whereas multiple‐factor logistic regression analysis identified 8 risk factors (AUC 0.872), RF identified 7 risk factors (AUC 0.851), SVM identified 16 risk factors (AUC 0.851), and LASSO identified 19 risk factors (AUC 0.902). Five common risk factors (ALB, Ca, CREA, D‐dimer, and ESR) were identified through model intersection, yielding a new model with an AUC of 0.85. Internal validation of the new model showed an AUC of 0.802, indicating high predictive ability. A web model application was created (https://anemic‐prediction‐of‐osteosarcoma.shinyapps.io/DynNomapp/).ConclusionThe developed risk prediction model based on clinical and laboratory data can aid in individualized diagnosis and treatment of anemia in osteosarcoma patients post‐chemotherapy.

A novel structure adaptive new information priority grey Bernoulli model and its application in China's renewable energy production

At present, the global energy structure is undergoing major changes. China is in the transition period of energy structure. Accurately anticipating future energy trends is critical for China's energy structure and modernization. Considering the uncertainty and sparsity characteristics of China's energy system sequence, this study examines China's renewable energy scenario using the grey model with limited sample and uncertain system modelling features. Renewable energy is affected by a variety of uncertain factors, exhibiting a range of complicated traits including nonlinearity, periodicity and random volatility. The traditional grey model has been difficult to appropriately predict its future evolution. This paper focuses on the adaptability of the model, optimizes and improves the accumulation operator and model structure, and establishes a fractional-order structural self-adaptation grey Bernoulli model based on new information priority. Firstly, based on the new information priority accumulation operator, it is extended to the fractional order. In terms of model structure, combined with NGBM(1,1) model, SADGM(1,1) model and FPGM(1,1) model, periodic fluctuation term and nonlinear power term are included to improve the model's capacity to capture nonlinear, fluctuating and periodic features, and enhance the adaptability and flexibility of the model. The backward difference technique yields the model's parameter estimation and temporal response sequence. Based on the results of the algorithm comparison experiment, the Improved Grey Wolf Optimization Algorithm is chosen to optimize the structural parameters of the model in an effort to enhance its performance. The performance comparison experiment of the model was designed, and three cases of China's hydropower generation, China's renewable energy power generation installed capacity and China's solar energy quarterly power generation were selected to compare the performance with a variety of grey prediction models. Monte-Carlo simulation and probability density analysis were utilized to confirm the stability and accuracy of the proposed model. The results show that the proposed FSANGBM(1,1) model can handle data series of renewable energy with nonlinear, volatile, and periodic features with high prediction ability. Finally, the model is applied to forecast three cases' future development trends.

Low Apgar Score and Risk of Neonatal Mortality among Infants with Birth Defects.

The Apgar score is a clinical tool to assess newborn health at delivery and has shown utility in predicting neonatal mortality in the general population, but its predictive ability in neonates with birth defects remains unexplored. As such, we aimed to investigate the performance of the 5-minute Apgar score in predicting neonatal mortality among neonates with a spectrum of major birth defects. Data for neonates with birth defects born between 1999 and 2017 were obtained from the Texas Birth Defect Registry. We generated receiver operating characteristic curves and corresponding area under the curve (AUC) values for neonatal mortality (death within the first 28 days of life) by 5-minute Apgar score (<7 vs. ≥7) to measure discrimination capacity. We performed secondary analyses to determine the predictive ability of the Apgar score: (1) among infants with an isolated birth defect and (2) separately in preterm and term neonates. Low Apgar score yielded substantial predictive ability for neonatal mortality, with 25 out of 26 AUC values > 0.70 across a spectrum of defect categories. High predictive ability was consistent among neonates with isolated defects, and preterm and term neonates. The Apgar score is likely useful for predicting neonatal mortality among most neonates with birth defects. Despite small sample sizes limiting some secondary analyses, the findings emphasize the potential continued use of the Apgar score as a rapid clinical assessment tool for newborns with birth defects. Continued research may refine the Apgar score's application in this important population, both in clinical practice and population health research. · Predictive models suggest the 5-minute Apgar score (<7) is predictive of neonatal mortality.. · Consistent results were observed across spectrum of birth defect categories.. · Secondary analyses (e.g., preterm infants) yielded similarly consistent results..

Identification of optimal cutting parameters regarding lacquer wettability of CNC processed MDF panels by artificial neural network

ABSTRACT The primary objective of this study was to evaluate the surface roughness and lacquer wettability of medium-density fiberboard (MDF) panels processed on computer numerical control (CNC) machine. Then, it is aimed to determine the optimal CNC cutting parameters by modeling the data obtained from the experiments with ANN. For these purposes, two cutting tool types, two toolpath strategies, three spindle speed and four cutting depth values were used as CNC cutting parameters. The roughness and lacquer wettability tests were performed on the surfaces of MDF specimens after CNC machining. Using the obtained experimental data, the ANN models with the highest predictive ability were determined and the optimum CNC cutting parameters were defined according to surface roughness and lacquer wettability. The smoothest surfaces were obtained for the spiral router bit with offset toolpath strategy, 22,500 rpm spindle speed and 1.6 mm cutting depth, and for the straight router bit with raster toolpath strategy, 21,500 rpm spindle speed and 1.7 mm cutting depth. The optimal cutting parameters that gave the best lacquer wettability were an offset toolpath strategy, 20,500 rpm spindle speed and 1.5 mm cutting depth for spiral router, and a raster toolpath strategy, 20,500 rpm spindle speed and 3.1 mm cutting depth for straight router.

Association mapping and genomic prediction for processing and end-use quality traits in wheat (Triticum aestivum L.).

End-use and processing traits in wheat (Triticum aestivum L.) are crucial for varietal development but are often evaluated only in the advanced stages of the breeding program due to the amount of grain needed and the labor-intensive phenotyping assays. Advances in genomic resources have provided new tools to address the selection for these complex traits earlier in the breeding process. We used association mapping to identify key variants underlying various end-use quality traits and evaluate the usefulness of genomic prediction for these traits in hard red spring wheat from the Northern United States. A panel of 383 advanced breeding lines and cultivars representing the diversity of the University of Minnesota wheat breeding program was genotyped using the Illumina 90K single nucleotide polymorphism array and evaluated in multilocation trials using standard assessments of end-use quality. Sixty-three associations for grain or flour characteristics, mixograph, farinograph, and baking traits were identified. The majority of these associations were mapped in the vicinity of glutenin/gliadin or other known loci. In addition, a putative novel multi-trait association was identified on chromosome 6AL, and candidate gene analysis revealed eight genes of interest. Further, genomic prediction had a high predictive ability (PA) for mixograph and farinograph traits, with PA up to 0.62 and 0.50 in cross-validation and forward prediction, respectively. The deployment of 46 markers from GWAS to predict dough-rheology traits yielded low to moderate PA for various traits. The results of this study suggest that genomic prediction for end-use traits in early generations can be effective for mixograph and farinograph assays but not baking assays.

Machine learning algorithms using the inflammatory prognostic index for contrast-induced nephropathy in NSTEMI patients.

Aim: Inflammatory prognostic index (IPI), has been shown to be related with poor outcomes in cancer patients. We aimed to investigate the predictive role of IPI for contrast-induced nephropathy (CIN) development in non-ST segment elevation myocardial infarction patients using a nomogram and performing machine learning (ML) algorithms.Materials & methods: A total of 178 patients with CIN (+) and 1511 with CIN (-) were included.Results: CIN (+) patients had higher IPI levels, and IPI was independently associated with CIN. A risk prediction nomogram including IPI had a higher predictive ability and good calibration. Naive Bayes and k-nearest neighbors were the best ML algorithms for the prediction of CIN patients.Conclusion: IPI might be used as an easily obtainable marker for CIN prediction using ML algorithms.

Prospectively predicting 6-month risk for non-suicidal self-injury among adolescents after psychiatric hospitalization based on a predictive model.

It is challenging to predict the occurrence of non-suicidal self-injury (NSSI) among adolescents over short periods. Moreover, the predictive value of indices for NSSI remains elusive. Thus, this study aimed to identify predictors of NSSI within 6 months among adolescents after psychiatric hospitalization by establishing a risk assessment model. A total of 632 high-risk participants were included in this study. The distribution characteristics of adolescent NSSI were initially assessed through a cross-sectional survey, following which risk factors were identified using logistic regression analysis. The risk score method was then used to construct a 6-month risk assessment model for NSSI. Lastly, the predictive effect of the model was evaluated by indicators such as the area under the receiver operating characteristic (ROC) curve and the positive predictive value. After 6 months, 412 cases of NSSI were identified. According to the logistic regression model, the frequency of relapses, medication status, and NSSI history were identified as influencing factors. Higher scores on the Impulsive Behavior Scale and Pittsburgh Sleep Quality Index were associated with a higher risk of NSSI. Conversely, higher scores on the Pain and Belief Perception Scale were correlated with a lower risk of NSSI. Moreover, the area under the ROC curve for the predictive model was 0.9989, with a 95% confidence interval of (0.9979, 0.9999), highlighting its high predictive ability and accuracy. The predictive model was validated using 78 patients, yielding an area under the ROC curve of 0.9703 and a 95% confidence interval of (0.9167, 0.9999), demonstrating outstanding predictability. These results collectively showed that the predictive model could accurately predict adolescent NSSI. Thus, the model's primary variables may be applied to predict the risk of NSSI in the clinical setting.

Leveraging large-scale Mycobacterium tuberculosis whole genome sequence data to characterise drug-resistant mutations using machine learning and statistical approaches

Tuberculosis disease (TB), caused by Mycobacterium tuberculosis (Mtb), is a major global public health problem, resulting in > 1 million deaths each year. Drug resistance (DR), including the multi-drug form (MDR-TB), is challenging control of the disease. Whilst many DR mutations in the Mtb genome are known, analysis of large datasets generated using whole genome sequencing (WGS) platforms can reveal new variants through the assessment of genotype-phenotype associations. Here, we apply tree-based ensemble methods to a dataset comprised of 35,777 Mtb WGS and phenotypic drug-susceptibility test data across first- and second-line drugs. We compare model performance across models trained using mutations in drug-specific regions and genome-wide variants, and find high predictive ability for both first-line (area under ROC curve (AUC); range 88.3–96.5) and second-line (AUC range 84.1–95.4) drugs. To aggregate information from low-frequency variants, we pool mutations by functional impact and observe large improvements in predictive accuracy (e.g., sensitivity: pyrazinamide + 25%; ethionamide + 10%). We further characterise loss-of-function mutations observed in resistant phenotypes, uncovering putative markers of resistance (e.g., ndh 293dupG, Rv3861 78delC). Finally, we profile the distribution of known DR-associated single nucleotide polymorphisms across discretised minimum inhibitory concentration (MIC) data generated from phenotypic testing (n = 12,066), and identify mutations associated with highly resistant phenotypes (e.g., inhA − 779G > T and 62T > C). Overall, our work demonstrates that applying machine learning to large-scale WGS data is useful for providing insights into predicting Mtb binary drug resistance and MIC phenotypes, thereby potentially assisting diagnosis and treatment decision-making for infection control.

Risk stratification of residual abscess after surgical treatment for gastroduodenal perforation

AbstractAimsResidual abscess is a major complication after emergency surgery for gastroduodenal (GD) perforation. However, there is little evidence regarding potential risk factors contributing to its development. Establishing a risk stratification strategy would be valuable for the entire management process.MethodsThis single‐center, retrospective study analyzed 115 consecutive patients who underwent surgery for GD perforation between 2010 and 2023 at a secondary emergency care hospital. Patients were divided into two groups based on the presence or absence of residual abscesses. Potential risk factors for abscess formation were evaluated from various aspects.ResultsThe incidence of residual abscesses was 19.1% (22 of 115). Multivariable analysis revealed that current use of nonsteroidal antiinflammatory drugs (odds ratio [OR] 3.76, p = 0.037), cancer chemotherapy (OR 13.56, p = 0.005), and preoperative renal dysfunction (OR 4.72, p = 0.018) were independent predictors. A potential scoring model could be created using these three parameters, and the number of risk factors correlated with the likelihood of developing a residual abscess (0 vs. 1 vs. ≥2; 6.2% vs. 29.4% vs. 50.0%, p &lt; 0.001). From a bacteriological point of view, the presence of Enterococcus in the ascites culture was closely related to its occurrence with 100% probability. Moreover, regarding early detection of this complication, C‐reactive protein on postoperative d 5 had the highest predictive ability with an area under the curve of 0.818.ConclusionThe risk of residual abscess formation after surgical treatment of GD perforation can be assessed utilizing both preoperative and postoperative information.

3D-QSAR and Molecular Docking Studies of Pyrimidine-based EGFR Inhibitors

Background: Epidermal growth factor tyrosine kinase receptor (EGFR) is expressed in a variety of tumors and has become a new target for anti-cancer drugs. In recent years, small molecule inhibitors targeting EGFR have been reported extensively. Objective: To investigate the quantitative structure-activity relationship (QSAR) of a set of EGFR inhibitors and design several new EGFR inhibitors with better efficiency and selectivity. Methods: The structure–activity relationship of 119 pyrimidine EGFR inhibitors were studied based on comparative field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMISA). Results: In this study, performance models with high prediction ability were constructed (CoMFA model: q2= 0.574, r2= 0.970, SEE= 0.163, F= 407.252; CoMSIA model: q2= 0.575, r2= 0.968, SEE= 0.171, F= 286.102), according to which 9 new EGFR inhibitors were designed. MD simulation (100 ns) on the docked complex of compound N7 (the most active compound) shows that the small molecule bindswith the protein stably. Conclusion: The newly designed compound N7 was considered to be a promising EGFR inhibitor with better activity than the best active compound 80, according to the results of molecular docking, molecular dynamics, and ADMET prediction. These results will provide valuable guidance for the design of novel EGFR inhibitors.

Development of a QSAR model to predict protein-flavor binding in protein-rich food systems

Protein-flavor binding is a common challenge in food formulation. Prediction models provide a time-, resource-, and cost-efficient way to investigate how the structural and physicochemical properties of flavor compounds affect this binding mechanism. This study presents a Quantitative Structure-Activity Relationship model derived from five commercial plant-based proteins and thirty-three flavor compounds. The results showed that protein-flavor binding is primarily influenced by the structure and physicochemical properties of the flavor compound, with the protein source having a minor contribution. In addition to hydrophobicity, topological, electronic, and geometrical descriptors significantly contribute to the observed protein-flavor binding. The Random Forest model demonstrated a strong correlation between predicted and experimental values (Q2 = 0.93) and a high predictive ability for a validation set of flavors and proteins not previously used (Q2 = 0.88). The prediction model developed holds promise for customizing flavor combinations and streamlining product design, thereby, optimizing efficiency while reducing the risk of flavor overdose.

Predictive analytics of student performance: Multi-method and code

The maintenance of a high level of education in universities can be a challenging task due to low academic performance. Despite the significant amount of collected diagnostic data, education managers underutilize machine learning methods to improve the accuracy of predicting academic performance. Authors apply a multi-method approach for data analysis using simple logistic and linear regressions, k-means clustering, that all together gave a synergetic effect. The proposed approach differs from known analogs in that, firstly, the dimensionality of the feature space increases due to the normalization of scores onto a single scale and the creation of new features: the index and rank of students, as well as the changes in performance across various activities for each student. Secondly, students at academic risk are forecasted, and the statistical significance of the features included in the model is evaluated. Thirdly, for each student, the final score for the semester is forecasted using an linear regressive model of academic performance. Fourthly, groups of students with similar learning trajectories are identified for customization of consultations. The authors managed to achieve a high predictive ability of models based on historical training data: binary prediction of exam passing in 90% of cases, prediction of individual assessment in 70% of cases.

Machine learning-aided enhancement of white tea extraction efficiency using hybridized GMDH models in microwave-assisted extraction

White tea is valuable for having a high antioxidant content, which is considered to possess numerous beneficial effects on health. This study investigated the application of microwave-assisted extraction (MAE) for the extraction of total phenolic compounds from white tea. The experimental setup included four independent variables: microwave power (ranging from 100 to 300 W), extraction time (ranging from 10 to 40 min), temperature (ranging from 35 to 50 °C), and the ratio of food to solvent (ranging from 0.25 to 0.5 g/10 mL). The responses that were evaluated were IC50 (ppm) and total phenolic content (mg/g). The experimental design consisted of thirty runs conducted within the MAE system. The group method of data handling (GMDH) models were used to predict important efficiency measures (IC50 and total phenol content) in the extraction process. The models were assessed based on their ability to capture the relationships between input conditions and efficiency outputs. Three GMDH variants were compared: baseline GMDH, GMDH optimized with a genetic algorithm (GMDH-GA), and GMDH optimized with a harmony search algorithm (GMDH-HS). While all models achieved high predictive ability on a test set, GMDH-HS emerged as the superior performer. It achieved near-perfect agreement with observations (d-index > 0.998), minimal errors (NRMSE < 0.02), and effectively captured data variance (NSE > 0.99) for both outputs. Correlation diagrams and Taylor diagrams confirmed the superior performance of GMDH-HS in terms of linearity, correlation, and error minimization. This study demonstrates the effectiveness of hybridizing GMDH with a harmony search algorithm for complex modeling tasks, paving the way for improved efficiency and yield optimization in extraction processes.

Predictive ability and prognostic correlation of global longitudinal strain in patients with negative dipyridamole stress echocardiography by wall motion criteria

Abstract Background Dipyridamole stress echocardiography (DSE) is an established technique to detect coronary artery disease (CAD) and for risk stratification. Speckle Tracking Echocardiography (STE), as an objective and quantitative evaluation of ventricular function, may add incremental value to conventional stress echo analysis. Purpose To assess the prognostic value of rest (Rest-GLS) and peak (Peak-GLS) stress global longitudinal strain (GLS) in patients with suspected CAD and negative DSE according to wall motion index (WMI) criteria. Methods We retrospectively enrolled patients who underwent DSE at our centre for suspected CAD, with normal WMI. Strain Reserve was calculated as Rest GLS – Peak-GLS (Delta-GLS). We also collected data regarding other conventional parameters such as coronary flow reserve (CFR) of left anterior descending (LAD), left ventricle contractile reserve (LVCR), delta left ventricular ejection fraction (Delta-LVEF), heart rate response (HRR). Our primary endpoint was a composite of all-cause death and coronary revascularization. Receiver operating characteristic (ROC) curves were used to compare the predictive ability of the parameters. Adjusted logistic regression analyses were used to assess associations, also modelled as a restricted cubic spline. Results A total of 355 patients were included in the analysis (median age 68.2, IQR 58.2-75.2, 38.0% female). At follow-up, 58 patients met the primary endpoint. Figure 1 shows the ROC curves of different DSE parameters. Delta-GLS and Peak-GLS showed high predictive ability of composite endpoint events (area under the curve [AUC] 0.87, 95% Confidence Interval [CI] 0.82-0.92, AUC, 0.85, 95% CI 0.79-0.91, respectively), which was significantly higher compared with other DSE parameters, included Basal-GLS (P for difference for all &amp;lt; 0.001). After adjustments for age, previous CAD, sex, and diabetes, reducing values of Rest-GLS, Peak-GLS and Delta-GLS were significantly associated with higher odds of experiencing composite endpoint events (Basal-GLS, odds ratio [OR] 1.13, 95% CI 1.04-1.24; Peak-GLS, OR 1.45, 95% CI 1.32-1.63; Delta-GLS, OR 1.73, 95% CI 1.50-2.04). Plotting the results of the logistic regression analysis on a restricted cubic spline, reducing values of Peak-GLS and Delta-GLS showed a linear increase for the risk of adverse events, while Rest-GLS showed a plateau for lower values. Conclusion The use of GLS parameters in DSE can help to better stratify the risk for the patients since they are associated with adverse cardiovascular events.Figure 1Figure 2

Estimating vegetation and litter biomass fractions in rangelands using structure-from-motion and LiDAR datasets from unmanned aerial vehicles

ContextThe invasion of annual grasses in western U.S. rangelands promotes high litter accumulation throughout the landscape that perpetuates a grass-fire cycle threatening biodiversity.ObjectivesTo provide novel evidence on the potential of fine spatial and structural resolution remote sensing data derived from Unmanned Aerial Vehicles (UAVs) to separately estimate the biomass of vegetation and litter fractions in sagebrush ecosystems.MethodsWe calculated several plot-level metrics with ecological relevance and representative of the biomass fraction distribution by strata from UAV Light Detection and Ranging (LiDAR) and Structure-from-Motion (SfM) datasets and regressed those predictors against vegetation, litter, and total biomass fractions harvested in the field. We also tested a hybrid approach in which we used digital terrain models (DTMs) computed from UAV LiDAR data to height-normalize SfM-derived point clouds (UAV SfM-LiDAR).ResultsThe metrics derived from UAV LiDAR data had the highest predictive ability in terms of total (R2 = 0.74) and litter (R2 = 0.59) biomass, while those from the UAV SfM-LiDAR provided the highest predictive performance for vegetation biomass (R2 = 0.77 versus R2 = 0.72 for UAV LiDAR). In turn, SfM and SfM-LiDAR point clouds indicated a pronounced decrease in the estimation performance of litter and total biomass.ConclusionsOur results demonstrate that high-density UAV LiDAR datasets are essential for consistently estimating all biomass fractions through more accurate characterization of (i) the vertical structure of the plant community beneath top-of-canopy surface and (ii) the terrain microtopography through thick and dense litter layers than achieved with SfM-derived products.

Severity Stratification of Coronary Artery Disease Using Novel Inner Ellipse-Based Foveal Avascular Zone Biomarkers.

Given the similarities between the retinal and coronary microvasculature, the retina holds promising potential to serve as a non-invasive screening tool for coronary artery disease (CAD). We aimed to develop novel inner ellipse-based metrics and discern whether foveal avascular zone (FAZ) alterations can serve as indicators for CAD presence and severity. Patients admitted to the Department of Cardiology who underwent coronary angiography were included. This resulted in an inclusion of 212 patients, of which 73 had no CAD. During the same visit, 6 × 6-mm (nominal size) fovea-centered optical coherence tomography angiography images of both eyes were acquired. The Gensini score (GS) was utilized to quantify CAD severity. Six known FAZ shape metrics were assessed and three novel biomarkers based on the inner ellipse were defined: absolute inner ellipse difference, Hausdorff distance, and Chamfer distance. Eight out of nine metrics showed significant associations with the GS in the left eye. However, significant differences across three CAD severity groups were only demonstrated by the novel metrics. Utilizing the Chamfer distance, age, and sex, patients with and without CAD could be distinguished with an average area under the curve (AUC) of 0.89 (95% confidence interval [CI], 0.84-0.95). Moreover, three CAD severity groups could be discerned with a macro average AUC of 0.77 (95% CI, 0.72-0.84). A comprehensive assessment of FAZ shape descriptors was performed, and a strong association with CAD was found. The inner ellipse-based biomarkers especially demonstrated high predictive abilities for CAD presence and severity.

Comparing AI/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction

BackgroundResearch comparing artificial intelligence and machine learning (AI/ML) methods with classical statistical methods applied to large population health databases is limited. ObjectivesThis retrospective cohort study aimed to compare the predictive performance of AI/ML algorithms against conventional multivariate logistic regression models using linked health administrative data. MethodsUsing Ontario's population health databases, we created a cohort of residents of the city of Ottawa, Ontario, who underwent a PCR test for COVID-19 between March 10, 2020, and May 13, 2021. Using demographic, socio-economic and health data (including COVID-19 PCR test results and available, symptom data), we developed predictive models for the purpose of COVID-19 case identification using the following approaches: classical multivariate logistic regression (LR); deep neural network (DNN); random forest (RF); and gradient boosting trees (GBT). Model performance comparisons were made using the area under the curve (AUC) swarm plot for 10-fold cross-validation. ResultsThe cohort consisted of n = 351,248 Ottawa residents tested for COVID-19 during the study period. Among whom, a total of n = 883,879 unique COVID-19 tests were performed (2.6 % positive test results). Inclusion of COVID-19 symptoms data in the analysis improved model performance and variable predictive value across all tested models (p < 0.0001), with the 10-fold cross-validation AUC increasing to near or over 0.7 in all models when symptoms data were included. In various pairwise comparisons, the GBT method had the highest predictive ability (AUC = 0.796 ± 0.017), significantly outperforming multivariate logistic regression and the other AI/ML approaches. ConclusionsConventional multivariate regression-based models are better than some and worse than other machine learning algorithms to provide good predictive accuracy in a moderate dataset with a reasonable number of features. However, whenever possible, the AI/ML GBT approach should be considered.

Development of hazard prediction test and interventions for two-wheeled electric vehicle riders in China

Objective This paper aimed to develop a hazard prediction test and enhance two-wheeled electric vehicle (TWEV) riders’ hazard perception and prediction capabilities via interventions by executing two distinct studies. Study 1 aimed to develop and validate a hazard prediction test. Study 2 evaluated the efficacy of two interventions, self-commentary and what happens next (WHN), integrating expert commentary. Method For Study 1, a video-based hazard prediction test was developed through video recording and clipping, with participants categorized into high and low prediction ability groups for experimentation. Data analysis employed the receiver operating characteristic (ROC) curve. Study 2 categorized participants into four groups: self-commentary with licenses (SCL), self-commentary without licenses (SCNL), WHN with licenses (WHNL), and WHN without licenses (WHNNL), for conducting a one-week intervention experiment. Data collected from participants’ pre-intervention, post-intervention, and aftereffect tests were subjected to repeated measures analysis of variance (ANOVA). Results Analysis of the ROC curve indicated the test can distinguish the riders with different hazard prediction levels. ANOVA results demonstrated that the measurement time had a significant positive effect on scores (p < 0.001). Both interventions significantly improved hazard prediction ability (p < 0.05), and the effect persisted one week after administration. The effect of the WHN intervention was significantly greater than the self-commentary method across all time points. Conclusion The hazard prediction test developed in this study could assess riders’ hazard prediction ability, with the identified interventions demonstrating effectiveness in enhancing this ability. These findings suggested potential application in future qualification tests for TWEV riders, contributing to enhanced traffic safety awareness among TWEV riders in China, thus advancing overall traffic safety.

Prediction of preterm birth in multiparous women using logistic regression and machine learning approaches

To predict preterm birth (PTB) in multiparous women, comparing machine learning approaches with traditional logistic regression. A population-based cohort study was conducted using data from the Ontario Better Outcomes Registry and Network (BORN). The cohort included all multiparous women who delivered a singleton birth at 20–42 weeks’ gestation in an Ontario hospital between April 1, 2012 and March 31, 2014. The primary outcome was PTB < 37 weeks, with spontaneous PTB analyzed as a secondary outcome. Stepwise logistic regression and the Boruta machine learning were used to select the important variables during the first and second trimester. For building prediction models, the whole data set were divided for the two independent parts: two-third for training the classifiers (Logistic regression, random forests, decision trees, and artificial neural networks) and one-third for model validation. Then, the training data set were balanced by random over sampling technique. The best hyper parameters were obtained by the tenfold cross validation. The performance of all models was evaluated by sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristics (AUC). The cohort included 145,846 births, of which 8125 (5.57%) were preterm. In first-trimester models, the strongest predictors of PTB were previous PTB, preexisting diabetes, and abnormal pregnancy‐associated plasma protein-A. In the testing data set, the highest predictive ability was seen for artificial neural networks, with an area under the receiver operating characteristic curve (AUC) of 68.8% (95% CI 67.6–70.1%). In second-trimester models, addition of infant sex, attendance at first-trimester appointment, medication exposure, and abnormal alpha-fetoprotein concentrations increased the AUC to 72.1% (95% CI 71.1–73.1%) with logistic regression. With the inclusion of the variable complications during pregnancy, the AUC increased to 80.5% (95% CI 79.6–81.5%) using logistic regression. For both overall and spontaneous PTB, during both the first and second trimesters, models yielded negative predictive values of 97%. Overall, machine learning and logistic regression produced similar performance for prediction of PTB. For overall and spontaneous PTB, both first- and second-trimester models provided negative predictive values of ~ 97%, higher than that of fetal fibronectin.

Experimental study and life prediction for aero-engine turbine blade considering creep-fatigue interaction effect

As an important failure form of the turbine blade, creep-fatigue interaction damage affects the safe operation and maintenance strategy of aero-engine, and has been the focus of scientific research and the academic community. Firstly, based on the Kachanov-Rabotnov-Lemaitre continuum damage mechanics theory and the nonlinear symmetry of creep damage and fatigue damage, a creep-fatigue life prediction model is constructed considering the interaction effect in this paper. Then, based on the thermal-fluid–solid multi-physical field coupling numerical simulation of the turbine blade, the equivalent method of creep-fatigue load spectrum was explored according to the equal damage criterion and linear damage rule, and the creep-fatigue interaction test of smooth samples of the blade material was conducted to analyze the creep-fatigue fracture morphology. Finally, the stress term in the creep-fatigue life prediction model of blade material is modified by the correction factor α, and the modified creep-fatigue life prediction model of the turbine blade is constructed considering the interaction effect. The results show that the modified creep-fatigue life prediction model considering the interaction effect has a high life prediction ability with an error of 3.9%. The above research has important scientific research value for the life extension design of turbine blades and the improvement of aero-engine maintenance strategy.