Explore the vast range of titles available.

Oral microbiota is related to the severity and recovery of SARS-CoV-2 infection. This study aims to predict clinical classification after SARS-CoV-2 infection using oral microbiota before infection. Herein, we collected tongue-coating samples before infection and then monitored clinical information after infection. Oral microbiota was detected by MiSeq sequencing. We randomly assigned participants from Zhengzhou into discovery and validation cohorts to develop a predictive model and conducted cross-region verification using Xinyang and Hangzhou cohorts. Sixteen asymptomatic patients (AP), 257 mild patients (MP), 106 common patients (CP), and 7 severe patients (SP) were enrolled. Oral microbiota diversity was decreased in CP versus MP. At genus level, 11 microorganisms, including Rothia and Gemella , were increased, while 5 microorganisms, including Selenomonas and Lachnoanaerobaculum , were decreased in CP versus MP. Moreover, the classifier based on 15 optimal markers showed high prediction efficiency in discovery cohort (area under the curve [AUC]: 98.35%), validation cohort (AUC: 81.91%), Xinyang cohort (AUC: 74.34%), and Hangzhou cohort (AUC: 94.44%). Interestingly, a higher abundance of Selenomonas was associated with milder clinical symptoms. In conclusion, our study established a good model to predict clinical classification after SARS-CoV-2 infection using oral microbiota before infection, providing a novel strategy for precise prevention and treatment.

Background and aim Ovarian cancer (OC) is a prevalent and aggressive malignancy that poses a significant public health challenge. The lack of preventive strategies for OC increases morbidity, mortality, and other negative consequences. Screening OC through risk prediction could be leveraged as a powerful strategy for preventive purposes that have not received much attention. So, this study aimed to leverage machine learning approaches as predictive assistance solutions to screen high-risk groups of OC and achieve practical preventive purposes. Materials and methods As this study is data-driven and retrospective in nature, we leveraged 1516 suspicious OC women data from one concentrated database belonging to six clinical settings in Sari City from 2015 to 2019. Six machine learning (ML) algorithms, including XG-Boost, Random Forest (RF), J-48, support vector machine (SVM), K-nearest neighbor (KNN), and artificial neural network (ANN) were leveraged to construct prediction models for OC. To choose the best model for predicting OC, we compared various prediction models built using the area under the receiver characteristic operator curve (AU-ROC). Results Current experimental results revealed that the XG-Boost with AU-ROC = 0.93 (0.95 CI = [0.91–0.95]) was recognized as the best-performing model for predicting OC. Conclusions ML approaches possess significant predictive efficiency and interoperability to achieve powerful preventive strategies leveraging OC screening high-risk groups.

Background Colorectal cancer (CRC) ranks among the most prevalent cancers globally. Some studies have found that arthritis could reduce the risk of CRC through inflammatory immune mediation. However, there have been no reports on whether arthritis is related to CRC. Therefore, the correlation between arthritis and CRC was investigated to provide some theoretical support for understanding the prevention and diagnosis of CRC. Methods This study utilized data from the National Health and Nutrition Examination Survey (NHANES) to investigate the relationship between arthritis and CRC among Americans. A total of 300,106 adults participated in the study, and through a questionnaire survey, they were categorized into the control group and the CRC group. In this study, arthritis was considered the exposure variable, and 17 covariates were included. The relationship between the variables and CRC was then revealed through baseline characteristic analysis, association analysis, and stratified analysis. The predictive efficiency of arthritis for the CRC was assessed using the receiver operating characteristic curve (ROC) analysis. Finally, nomogram was created to evaluate the predictive capacity. Results A total of 297,681 control subjects and 2,425 CRC subjects within this survey. Significant disparities were observed between the two groups for all variables except for drink and poverty income ratio (PIR). Three models demonstrated a clear association between arthritis and CRC (model 1: odds ratio (OR) = 3.57, 95% confidence interval (CI) = 2.5–5.1, P  = 0.00000000025; model 2: OR = 1.71, 95% CI = 1.15–2.53, P  = 0.008; model 3: OR = 1.56, 95% CI = 1.03–2.38, P  = 0.0369), indicating that the effect of arthritis on CRC was not significantly confounded by other covariates across the three models. Stratified analysis showed that arthritis was positively associated with CRC, and the area under the curve (AUC) was 0.818, indicating that arthritis was more effective in the prognosis of CRC. Finally, the decision curve and calibration curve indicated that the nomogram could effectively predict CRC. Conclusion This study found that arthritis had a strong association with the occurrence of CRC, providing ideas and strategies for its early detection.

The aim of the current study is to estimate whether spatial data on place features from OpenStreetMap (OSM) produce results similar to those when employing register data to predict future violent crime in public across three Swedish cities of varying sizes. Using violent crime in public as an outcome, four models for each city are produced using a Risk Terrain Modeling approach. One using spatial data on place features from register data and one from OSM, one model with prior violent crime excluded and one with prior crime included. The results show that several place features are significantly associated with violent crime in public independent of using register or OSM data as input. While models using register data seem to produce more accurate and efficient predictions than OSM data for the two smaller cities, the difference for the largest city is negligible indicating that the models provide similar results. As such, OSM place feature data may be of value when predicting the spatial distribution of future violent crime in public and provide results similar to those when using register data, at least when employed in larger compared to smaller cities. Possibilities, limitations, and avenues for future research when using OSM data in place-based criminological research are discussed.

We study optimal conformity measures for various criteria of efficiency of set-valued classification in an idealised setting. This leads to an important class of criteria of efficiency that we call probabilistic and argue for; it turns out that the most standard criteria of efficiency used in literature on conformal prediction are not probabilistic unless the problem of classification is binary. We consider both unconditional and label-conditional conformal prediction.

In the contemporary digital era, cloud computing offers an ideal platform for artificial intelligence (AI) applications by providing the necessary computational power, memory, and scalability to handle the massive volumes of data required by intelligent algorithms. AI systems enable computing devices to make expert-level decisions by effectively leveraging information. However, challenges, related to adaptability, efficiency, privacy preservation, and the latent requirement for minimal user intervention remain critical. Notably, error detection efficiency can be improved by distributing data across multiple cloud storage services, akin to spreading data across physical disk drives. Nevertheless, continuously optimizing the performance and cost-efficiency of multiple cloud providers remains a complex task, due to varying pricing models and service quality levels. This paper aims to clarify how rule enforcement for distributed systems can be improved through the use of diverse cloud hosting services guided by authorization patterns. We propose an Effective AI Architecture for File Distribution Enhancement (EAIFDE), which aims to minimize costs and waiting times across various cloud platforms. The proposed architecture is validated using a cloud storage system simulator to evaluate the operational complexity and performance differences among multiple providers.

Objective To explore the predictive value of prepregnancy body mass index (pBMI) and early gestational fasting blood glucose (eFBG) in gestational diabetes mellitus (GDM). Methods This case–control study enrolled pregnant women at 6 to 16 weeks of gestation. The pBMI, eFBG and glycosylated haemoglobin (HbA1c) was recorded in the first trimester of pregnancy. Receiver-operating characteristic (ROC) curve analysis was used to measure the efficacy of factors that predict GDM. Results A total of 2119 pregnant women were enrolled in this study. Of these, 386 were diagnosed with GDM and 1733 did not have GDM. The age (odds ratio [OR] 1.16; 95% confidence interval [CI] 1.13, 1.20), pBMI (OR 1.12; 95% CI 1.07, 1.17) and eFBG (OR 5.37; 95% CI 3.93, 7.34) were independent risk factors for GDM occurrence. The areas under the ROC curve of eFBG, pBMI and eFBG + pBMI were 0.68 (95% credibility interval 0.65, 0.71), 0.66 (95% credibility interval 0.63, 0.69) and 0.71 (95% credibility interval 0.69, 0.74), respectively. The area under the curve of eFBG + pBMI was significantly higher than that of eFBG or pBMI alone. Conclusion The combination of eFBG and pBMI had a high predictive value for GDM.

In recent years, the numbers of battery electric vehicles and hybrid electric vehicles are strongly increasing in the European Union. For these vehicles dedicated thermal-management solutions have been developed. Since thermal-management has a high impact on these vehicles’ efficiencies and ranges, its improvement with new potentialities is of ongoing high importance to cope with the latest European carbon dioxide-reduction targets. For boosting the efficiency of an electric vehicle, two predictive thermal-management methods are presented in this work, which receive information on the upcoming route profile and powertrain heat release. Thermal and mechanical behavior for the projection duration of e.g., 5 minutes are prognosed, and optimized control parameters are calculated, that allow specific thermal and energetic optimisations of the vehicle, that help to reduce carbon dioxide emissions. The optimized control algorithm is tested in combination with a coolant temperature lift strategy, a complex integration of a phase change material storage as well as with an air-conditioning compressor control. The detailed methods as well as their dedicated benefits are described in this work. Additionally, hurdles and further challenges of such predictive control approaches are reported.

Procedures for prediction analysis in 2 x 2 contingency tables are illustrated by the analysis of successes to six types of problems associated with the acquisition of fractions. According to Hildebrand, Laing, and Rosenthal (1977), hypotheses such as \"success to problem type A implies in most cases success to problem type B\" can be evaluated from a numerical index. This index has been considered in various other frameworks and can be interpreted in terms of a measure of predictive efficiency of implication hypotheses. Confidence interval procedures previously proposed for this index are reviewed and extended. Then, under a multinomial model with a conjugate Dirichlet prior distribution, the Bayesian posterior distribution of this index is characterized, leading to straightforward numerical methods.1 The choices of \"noninformative\" priors for discrete data are shown to be no more arbitrary or subjective than the choices involved in the frequentist approach. Moreover, a simulation study of frequentist coverage probabilities favorably compares Bayesian credibility intervals with conditional confidence intervals.

Distortion product otoacoustic emissions (DPOEs) at the frequency of 2f1 — f2 (f1 < f2) were measured in 77 human adult ears with normal hearing or sensorineural hearing loss. The purpose of this study was to compare the performances of DPOE tests conducted with two sets of stimuli: 1) L1 = 65, L2 = 50 dB sound pressure level (SPL) re 20 μPa (“65/50”), and 2) L1 = L2 = 65 dB SPL (“65/65”). Half-octave DPOE root-mean-square levels at 1,000, 2,000,4,000, and 6,000 Hz were computed from the initial DPOEs measured at 0.25-octave intervals. Correlation coefficient and decision-theory analyses were applied to evaluate the DPOE test performance. For both stimuli, DPOE level exhibited significant correlation with pure tone hearing threshold. When the criterion DPOE level distinguishing normal from impaired hearing was adjusted, the curves of sensitivity and specificity crossed, and the values at the crossing were higher than 80% at frequencies of 2,000 to 6,000 Hz for both stimuli. The area under the receiver operating characteristic (ROC) curve, which provides an overall evaluation of the test performance independent of the criterion DPOE level, was .90 or higher at 2,000 to 6,000 Hz for both stimuli. At 2,000 and 4,000 Hz, all measures of test performance were higher for the 65/50 stimulus than the 65/65 stimulus: area under the ROC curve (.96 to .97 versus .90 to .91, statistically significant, p < .001, Wilcoxon test), sensitivity/specificity (90% to 93% versus 80% to 85%), and correlation coefficient (.78 to .87 versus .66 to .79). At 1,000 and 6,000 Hz, the performances of the DPOE tests were similar for the two stimuli. These results support the conclusion that a DPOE test with L1 = 65 and L2 = 50 dB SPL provides a better performance than that with L1 = L2 = 65 dB SPL and recommend the use of stimuli with L1 being higher than L2 by about 15 dB. These results also support a growing view that 2f1 — f2 DPOEs can be utilized clinically as a reliable method of testing human sensorineural hearing loss.