Specific Prediction Model Research Articles

Multi-Model Gait-Based KAM Prediction System Using LSTM-RNN and Wearable Devices

The purpose of this study is to develop an optimized system for predicting Knee Adduction Moment (KAM) using wearable Inertial Measurement Unit (IMU) sensors and Long Short-Term Memory (LSTM) RNN. Traditional KAM measurement methods are limited by the need for complex laboratory equipment and significant time and cost investments. This study proposes two systems for predicting Knee Adduction Moment based on wearable IMU sensor data and gait patterns: the Multi-model Gait-based KAM Prediction System and the Single-model KAM Prediction System. The Multi-model system pre-classifies different gait patterns and uses specific prediction models tailored for each pattern, while the Single-model system handles all gait patterns with one unified model. Both systems were evaluated using IMU sensor data and GRF data collected from participants in a controlled laboratory environment. The overall performance of the Multi-model Gait-based KAM Prediction System showed an approximately 20% improvement over the Single-model KAM Prediction System. Specifically, the RMSE for the Multi-model system was 6.84 N·m, which is lower than the 8.82 N·m of the Single-model system, indicating a better predictive accuracy. The Multi-model system also achieved a MAPE of 8.47%, compared with 12.95% for the Single-model system, further demonstrating its superior performance.

Prediction models for ischemic stroke and bleeding in dialysis patients: a systematic review and meta-analysis

Abstract Background Patients with kidney failure on maintenance dialysis have a high stroke and bleeding risk. Multivariable prediction models can be used to estimate the risk of ischemic stroke and bleeding. A systematic review and meta-analysis was performed to determine the performance of the existing models in patients on dialysis. Methods MEDLINE and Embase databases were searched, from inception through January 12, 2024, for studies of prediction models for stroke or bleeding, derived or validated in dialysis cohorts. Discrimination measures for models with c-statistic data from ≥ 3 cohorts were pooled by random effects meta-analysis and a 95% prediction interval (PI) was calculated. Risk of bias was assessed using PROBAST. The review was conducted according to the PRISMA statement and the CHARMS checklist. Results Eight studies were included in this systematic review. All the included studies validated pre-existing models that were derived in cohorts from the general population. None of the identified studies reported the development of a new dialysis specific prediction model for stroke, while dialysis specific risk scores for bleeding were proposed by two studies. In meta-analysis of c-statistics, the CHA2DS2-VASc, CHADS2, ATRIA, HEMORR(2)HAGES and HAS-BLED scores showed very poor discriminative ability in the dialysis population. Six of the eight included studies were at low or unclear risk of bias and certainty of evidence was moderate. Conclusions The existing prediction models for stroke and bleeding have very poor performance in the dialysis population. New dialysis-specific risk scores should be developed to guide clinical decision making in these patients.

Comparison of mortality scores performance in transcatheter aortic valve replacement: suiting up to percutaneous intervention

Abstract Introduction As transcatheter aortic valve replacement (TAVR) is increasingly relevant for patients with severe symptomatic aortic stenosis, having a reliable procedure specific risk-prediction tool is paramount to provide high-quality care. Surgical scores as the EuroScore II and the Society of Thoracic Surgeons (STS) score II have been widely used to identify patients with high surgical risk in whom percutaneous treatment might be more favorable. However, current literature lacks a consensual specific predictive model for short-term and mid-term prognosis in patients undergoing transcatheter aortic valve implantation (TAVI). Purpose We aimed to access short and midterm (30 days and one year) mortality and to access the ability of a directly adapted score in estimating mortality in a real-world population. Methods We conducted a retrospective observational study in patients who implanted TAVR in a single center. Surgical mortality scores – EUROSCORE II and STS score II – and adapted score Society of Thoracic Surgeons (STS)/American College of Cardiology (ACC) transcatheter valve therapy (TVT) score were used to estimate mortality. Predictive abilities of these three scores were compared using area under the receiver operating characteristics (ROC) curve for 30-day and one year mortality. Results From January 2018 to December 2021, 416 patients were submitted to TAVR procedure in our center. The mean age was 83+-6 years old and 229 (55%) were female. 94% had hypertension, 80% dyslipidemia, 40% diabetes mellitus, 35% coronary artery disease, 32% chronic kidney disease. Mean ejection fraction was 56%. During a mean follow-up (FUP) of 816 ± 492 days, 30-day mortality was 1,7% and after 1 year mortality rate was 12,2% (higher than reported in PARTNER 3 trial, 8,5%). The Mean EuroSCORE was 3,4±3,2, mean STS-II 3,9±1,8 and mean value for STS/ACC-TVT score was 3,55±1,34. ROC curve analysis showed a significantly higher discriminative power of STS/ACC-TVT (AUC 0,749, 95% CI 0,681-0,818) compared with surgical scores (p=0,001) – figure 1. We also divided population into quartiles and compared the mortality rate at 30 days and 1 year in each quartile using either STSII or STS/ACC-TVT; As can be seen in figure 2, mortality rates correlated better with the STS/ACC-TVT score than with the STS score. Conclusion A score adapted to a TAVI population showed better predictive capacity than traditional surgical scores. Less preponderance of previous surgical status, relevance of access site and more adapted weight of age might explain the best performance of STS/ACC-TVT score. Surgical scores are helpful in choosing treatment option, but adapted scores are better to predict pos-TAVR mortality.

A study of impulsivity as a predictor of problematic internet use in university students with disabilities.

The role played by impulsivity in problematic internet use (PIU) is the object of much debate among researchers. Some studies emphasize its importance, while others suggest mental distress or personality traits may be more crucial. More research into the issue is clearly needed-especially in at-risk populations like people with disabilities. The objectives of this study were therefore to investigate the relationship between PIU and impulsivity among university students with disabilities, and to develop a specific predictive model for this group that would include psychological and life-functioning variables. A cross-sectional design was used with a sample of 240 Spanish university students with disabilities from seven universities. Several instruments were used for data collection: a sociodemographic questionnaire, the Internet Addiction Test (IAT), the Clinical Outcomes in Routine Evaluation-Outcome Measure (CORE-OM), and NEO-FFI-R. The results indicated that impulsivity is significantly correlated with PIU, as indeed it also is with other factors like conscientiousness and social functioning problems. The study's regression model explained nearly 50% of PIU variance, with impulsivity, personality traits, wellness and health indicators, and social media usage as predictive variables. This suggests that interventions should consider these psychological and lifestyle variables as a means of mitigating PIU risks in students with disabilities. The findings identify a need for further longitudinal studies to understand the causality and develop targeted prevention strategies.

Predicting the Recurrence of Ovarian Cancer Based on Machine Learning.

Recurrence is the main factor for poor prognosis in ovarian cancer, but few prognostic biomarkers were reported. In this study, we used machine learning methods based on multiple biomarkers to develop a specific prediction model for the recurrence of ovarian cancer. A total of 277 ovarian cancer patients were enrolled in this study and randomly classified into training and testing cohorts. The prediction information was obtained through 47 clinical parameters using six supervised clustering machine learning algorithms, including K-Nearest Neighbor (K-NN), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), and Extreme Gradient Boosting (XGBoost). In predicting the recurrence of ovarian cancer, machine learning algorithm was superior to conventional logistic regression analysis. In this study, XGBoost showed the best performance in predicting the recurrence of ovarian cancer, with an accuracy of 0.95. In addition, neoadjuvant chemotherapy, Monocyte ratio (MONO%), Hematocrit (HCT), Prealbumin (PAB), Aspartate aminotransferase (AST), and carbohydrate antigen 125 (CA125) are the most important biomarkers to predict the recurrence of ovarian cancer. The machine learning techniques can achieve a more accurate assessment of the recurrence of ovarian cancer, which can help clinicians make decisions, and develop personalized treatment strategies.

Using Natural Language Processing to develop risk-tier specific suicide prediction models for Veterans Affairs patients

Suicide is a leading cause of death. Suicide rates are particularly elevated among Department of Veterans Affairs (VA) patients. While VA has made impactful suicide prevention advances, efforts primarily target high-risk patients with documented suicide risk. This high-risk population accounts for less than 10% of VA patient suicide deaths. We previously evaluated epidemiological patterns among VA patients that had lower classified suicide risk and derived moderate- and low-risk groupings. Expanding upon VA's leading suicide prediction model, this study uses national VA data to refine high-, moderate-, and low-risk specific suicide prediction methods. We selected all VA patients who died by suicide in 2017 or 2018 (n = 4584), matching each case with five controls who remained alive during treatment year and shared suicide risk percentiles. We extracted all sample unstructured electronic health record notes, analyzed them using natural language processing, and applied machine-learning classification algorithms to develop risk-tier-specific predictive models. We calculated area under the curve (AUC) and suicide risk concentration to evaluate predictive accuracy and analyzed derived words. ResultsOur high-risk model (AUC = 0.621 (95% CI: 0.55–0.68)), moderate-risk (AUC = 0.669 (95% CI: 0.64–0.71)), and low-risk (AUC = 0.673 (95% CI: 0.63–0.72)) models offered significant predictive accuracy over VA's leading suicide prediction algorithm. Derived words varied considerably, the high-risk model including chronic condition service words, moderate-risk model including outpatient care, and low-risk model including acute condition care.Study suggests benefit of leveraging unstructured electronic health records and expands prediction resources for non-high-risk suicide decedents, an historically underserved population.

Predicting Ozone Concentration in Hangzhou with the Fusion Class Stacking Algorithm

Aiming at the problem that the single machine learning model has low prediction accuracy of daily average ozone concentration, an ozone concentration prediction method based on the fusion class Stacking algorithm （FSOP） was proposed, which combined the statistical method ordinary least squares （OLS） with machine learning algorithms and improved the prediction accuracy of the ozone concentration prediction model by integrating the advantages of different learners. Based on the principle of the Stacking algorithm, the observation data of the daily maximum 8h ozone average concentration and meteorological reanalysis data in Hangzhou from January 2017 to December 2022 were used. Firstly, the specific ozone concentration prediction models based on the light gradient boosting machine （LightGBM） algorithm, long short-term memory model （LSTM）, and Informer model were established, respectively. Then, the prediction results of the above models were used as meta-features, and the OLS algorithm was used to obtain the prediction expression of ozone concentration to fit the observed ozone concentration. The results showed that the prediction accuracy of the model combined with the class Stacking algorithm was improved, and the fitting effect of ozone concentration was better. Among them, R2, RMSE, and MAE were 0.84, 19.65 μg·m-3, and 15.50 μg·m-3, respectively, which improved the prediction accuracy by approximately 8% compared with that of the single machine learning model.

Regression trees for fast and adaptive prediction intervals

In predictive modeling, quantifying prediction uncertainty is crucial for reliable decision-making. Traditional conformal inference methods provide marginally valid predictive regions but often produce non-adaptive intervals when naively applied to regression, potentially biasing applications. Recent advances using quantile regressors or conditional density estimators improve adaptability but are typically tied to specific prediction models, limiting their ability to quantify uncertainty around arbitrary models. Similarly, methods based on partitioning the feature space adopt sub-optimal strategies, failing to consistently measure predictive uncertainty across the feature space, especially in adversarial examples. This paper introduces a model-agnostic family of methods to calibrate prediction intervals for regression with local coverage guarantees. By leveraging regression trees and Random Forests, our approach constructs data-adaptive partitions of the feature space to approximate conditional coverage, enhancing the accuracy and scalability of prediction intervals. Our methods outperform established benchmarks on simulated and real-world datasets. They are implemented in the Python package clover, which integrates seamlessly with the scikit-learn interface for practical application.

Drug-Drug Interactions and Synergy: From Pharmacological Models to Clinical Application.

This review explores the concept of synergy in pharmacology, emphasizing its importance in optimizing treatment outcomes through the combination of drugs with different mechanisms of action. Synergy, defined as an effect greater than the expected additive effect elicited by individual agents according to specific predictive models, offers a promising approach to enhance therapeutic efficacy while minimizing adverse events. The historical evolution of synergy research, from ancient civilizations to modern pharmacology, highlights the ongoing quest to understand and harness synergistic interactions. Key concepts, such as concentration-response curves, additive effects, and predictive models, are discussed in detail, emphasizing the need for accurate assessment methods throughout translational drug development. Although various mathematical models exist for synergy analysis, selecting the appropriate model and software tools remains a challenge, necessitating careful consideration of experimental design and data interpretation. Furthermore, this review addresses practical considerations in synergy assessment, including preclinical and clinical approaches, mechanism of action, and statistical analysis. Optimizing synergy requires attention to concentration/dose ratios, target site localization, and timing of drug administration, ensuring that the benefits of combination therapy detected bench-side are translatable into clinical practice. Overall, the review advocates for a systematic approach to synergy assessment, incorporating robust statistical analysis, effective and simplified predictive models, and collaborative efforts across pivotal sectors, such as academic institutions, pharmaceutical companies, and regulatory agencies. By overcoming critical challenges and maximizing therapeutic potential, effective synergy assessment in drug development holds promise for advancing patient care. SIGNIFICANCE STATEMENT: Combining drugs with different mechanisms of action for synergistic interactions optimizes treatment efficacy and safety. Accurate interpretation of synergy requires the identification of the expected additive effect. Despite innovative models to predict the additive effect, consensus in drug-drug interactions research is lacking, hindering the bench-to-bedside development of combination therapies. Collaboration among science, industry, and regulation is crucial for advancing combination therapy development, ensuring rigorous application of predictive models in clinical settings.

Uncertainty Quantification of Data-driven Quality Prediction Model For Realizing the Active Sampling Inspection of Mechanical Properties in Steel Production

Pre-production quality defect inspection is a crucial step in industrial manufacturing, and many traditional inspection strategies suffer from inefficiency issues. This is especially true for tasks such as mechanical performance testing of steel products, which involve time-consuming processes like offline sampling, specimen preparation, and testing. The inspection volume significantly impacts the production cycle, inventory, yield, and labor costs. Constructing a data-driven model for predicting product quality and implementing proactive sampling inspection based on the prediction results is an appealing solution. However, the prediction uncertainty of data-driven models poses a challenging problem that needs to be addressed. This paper proposes an active quality inspection approach for steel products based on the uncertainty quantification in the predictive model for mechanical performance. The objective is to reduce both the sampling frequency and the omission rate on the production site. First, an ensemble model based on improved lower and upper bound estimation is established for interval prediction of mechanical performance. The uncertainty of the specific value prediction model is quantitatively estimated using interval probability distributions. Then, a predictive model for the mechanical performance failure probability is built based on the prediction interval size and probability distribution. By determining an appropriate probability threshold, the trade-off between prediction accuracy and defect detection accuracy (recall rate) is balanced, enabling the establishment of an active sampling strategy. Finally, this functionality is integrated into the manufacturing execution system of a steel factory, realizing a mechanical performance inspection approach based on proactive sampling. The proposed approach is validated using real production datasets. When the probability threshold is set to 30%, the prediction accuracy and recall rate for failure mechanical performance samples are 75% and 100%, respectively. Meanwhile, the sampling rate is only 5.33%, while controlling the risk of omission. This represents a 50% reduction in sampling rate compared to the inspection rules commonly used in actual production. The overall efficiency of product quality inspection is improved, and inspection costs are reduced.

A predictive model for premature atherosclerosis in systemic lupus erythematosus based on clinical characteristics.

Systemic lupus erythematosus (SLE) is associated with a significant risk of atherosclerotic cardiovascular disease, especially in the development of premature atherosclerosis. Specific prediction models for premature atherosclerosis in SLE patients are still limited. The objective of this study was to establish a predictive model for premature atherosclerosis in SLE. The study collected clinical and laboratory data from 148 SLE patients under the age of 55, between January 2021 and June 2023. The least absolute shrinkage and selection operator logistic regression model was utilized to identify potentially relevant features. Subsequently, a nomogram was developed using multivariable logistic analysis. The performance of the nomogram was evaluated through a receiver-operating characteristic curve, calibration curve, and decision curve analysis (DCA). A total of 148 SLE patients who fulfilled the inclusion criteria were enrolled in the study, of whom 53 patients (35.81%) met the definition of premature atherosclerosis. Hypertension, antiphospholipid syndrome, azathioprine use, duration of glucocorticoid, and age of patients were included in the multivariable regression. The nomogram, based on the non-overfitting multivariable model, was internally validated and demonstrated sufficient clinical utility for assessing the risk of premature atherosclerosis (area under curve: 0.867). The comprehensive nomogram constructed in this study serves as a useful and convenient tool for evaluating the risk of premature atherosclerosis in SLE patients. It is helpful for clinicians to early identify SLE patients with premature atherosclerosis and facilitates the implementation of more effective preventive measures. Key Points • SLE patients are at a significantly higher risk of developing premature atherosclerosis compared to the general population, and this risk persists even in cases with low disease activity. Traditional models used to evaluate and predict premature atherosclerosis in SLE patients often underestimate the risk. • This study establishes a comprehensive and visually orientated predictive model of premature atherosclerosis in SLE patients, based on clinical characteristics. • The scoring system allows for convenient and effective prediction of individual incidence of premature atherosclerosis, and could provide valuable information for identification and making further intervention decision.

Comparison of Predictive Models for Prevention of Missed Endoscopy Appointments- failure of a Predictive Model to Outperform Overbooking Model.

Patient late cancelation and nonattendance for endoscopy appointments is an ongoing problem affecting the productivity and wait times of endoscopy units. Previous research evaluated a model for predictive overbooking and had promising results. All endoscopy visits at an outpatient endoscopy unit during 4 nonconsecutive months were included in the data analysis. Patients who did not attend their appointment, or canceled with 48 hours of their appointment were considered nonattendees. Demographic, health, and prior visit behavior data was collected and the groups compared. 1780 patients attended 2331 visits in the study period. Comparing the attendee versus non-attendees, there were significant differences in mean age, prior absenteeism, prior cancelations, and total number of hospital visits. No significant differences were seen between groups in winter versus non-winter months, the day of the week, sex distribution, type of procedure booked, or whether the referral was from specialist clinic or direct to procedure. The visit cancelation proportion (calculated excluding current visit) was substantially higher in the absentee group (P<0.0001). A predictive model was developed and compared to current booking as well as a straight overbooking of 7%. Both overbooking models performed better than the current practice, but the predictive overbooking model did not outperform straight overbooking. Developing an endoscopy unit specific predictive model may not be more beneficial than straight overbooking as calculated by missed appointment percentage.

Pyroptosis-related gene signature for predicting gastric cancer prognosis.

Gastric cancer (GC) is a prevalent form of malignancy characterized by significant heterogeneity. The development of a specific prediction model is of utmost importance to improve therapy alternatives. The presence of H. pylori can elicit pyroptosis, a notable carcinogenic process. Furthermore, the administration of chemotherapeutic drugs is often employed as a therapeutic approach to addressing this condition. In the present investigation, it was observed that there were variations in the production of 17 pyroptosis-regulating proteins between stomach tissue with tumor development and GC cells. The predictive relevance of each gene associated with pyroptosis was assessed using the cohort from the cancer genome atlas (TCGA). The least absolute shrinkage and selection operator (LASSO) was utilized to enhance the outcomes of the regression approach. Patients with gastric cancer GC in the cohort from the TCGA were categorized into low-risk or high-risk groups based on their gene expression profiles. Patients with a low risk of gastric cancer had a higher likelihood of survival compared to persons classified as high risk (P<0.0001). A subset of patients diagnosed with GC from a Genes Expression Omnibus (GEO) cohort was stratified according to their overall survival (OS) duration. The statistical analysis revealed a higher significance level (P=0.0063) regarding OS time among low-risk individuals. The study revealed that the GC risk score emerged as a significant independent prognostic factor for OS in patients diagnosed with GC. The results of Gene Ontology (GO) and Kyoto Encyclopaedia of Genes and Genomes (KEGG) research revealed that genes associated with a high-risk group had significantly elevated levels of immune system-related activity. Furthermore, it was found that the state of immunity was diminished within this particular group. The relationship between the immune response to cancer and pyroptosis genes is highly interconnected, suggesting that these genes have the potential to serve as prognostic indicators for GC.

Testing the diagnostic accuracy of common questions for seizure diagnosis: Challenges and future directions

ObjectiveThe aim of this study was to evaluate the diagnostic accuracy of common interview questions used to distinguish a diagnosis of epilepsy from seizure mimics including non-epileptic seizures (NES), migraine, and syncope. Methods200 outpatients were recruited with an established diagnosis of focal epilepsy (n = 50), NES (n = 50), migraine (n = 50), and syncope (n = 50). Patients completed an eight-item, yes-or-no online questionnaire about symptoms related to their events. Sensitivity and specificity were calculated. Using a weighted scoring for the questions alone with baseline characteristics, the overall questionnaire was tested for diagnostic accuracy. ResultsOf individual questions, the most sensitive one asked if events are sudden in onset (98 % sensitive for epilepsy (95 % CI: 89 %, 100 %)). The least sensitive question asked if events are stereotyped (46 % sensitive for epilepsy (95 % CI: 32 %, 60 %)). Overall, three of the eight questions showed an association with epilepsy as opposed to mimics. These included questions about “sudden onset” (OR 10.76, 95 % CI: (1.66, 449.21) p = 0.0047), “duration < 5 min” (OR 3.34, 95 % CI: (1.62, 6.89), p = 0.0008), and “duration not > 30 min” (OR 4.44, 95 % CI: (1.94, 11.05), p = <0.0001). When individual seizure mimics were compared to epilepsy, differences in responses were most notable between the epilepsy and migraine patients. Syncope and NES were most similar in responses to epilepsy. The overall weighted questionnaire incorporating patient age and sex produced an area under the ROC curve of 0.80 (95 % CI: 0.74, 0.87)). ConclusionIn this study, we examined the ability of common interview questions used by physicians to distinguish between epilepsy and prevalent epilepsy mimics, specifically NES, migraines, and syncope. Using a weighted scoring system for questions, and including age and sex, produced a sensitive and specific predictive model for the diagnosis of epilepsy. In contrast to many prior studies which evaluated either a large number of questions or used methods with difficult practical application, our study is unique in that we tested a small number of easy-to-understand “yes” or “no” questions that can be implemented in most clinical settings by non-specialists.

Systematic development and validation of a predictive model for major postoperative complications in the Peri-operative Quality Improvement Project (PQIP) dataset.

Complications are common following major surgery and are associated with increased use of healthcare resources, disability and mortality. Continued reliance on mortality estimates risks harming patients and health systems, but existing tools for predicting complications are unwieldy and inaccurate. We aimed to systematically construct an accurate pre-operative model for predicting major postoperative complications; compare its performance against existing tools; and identify sources of inaccuracy in predictive models more generally. Complete patient records from the UK Peri-operative Quality Improvement Programme dataset were analysed. Major complications were defined as Clavien-Dindo grade ≥ 2 for novel models. In a 75% train:25% test split cohort, we developed a pipeline of increasingly complex models, prioritising pre-operative predictors using Least Absolute Shrinkage and Selection Operators (LASSO). We defined the best model in the training cohort by the lowest Akaike's information criterion, balancing accuracy and simplicity. Of the 24,983 included cases, 6389 (25.6%) patients developed major complications. Potentially modifiable risk factors (pain, reduced mobility and smoking) were retained. The best-performing model was highly complex, specifying individual hospital complication rates and 11 patient covariates. This novel model showed substantially superior performance over generic and specific prediction models and scores. We have developed a novel complications model with good internal accuracy, re-prioritised predictor variables and identified hospital-level variation as an important, but overlooked, source of inaccuracy in existing tools. The complexity of the best-performing model does, however, highlight the need for a step-change in clinical risk prediction to automate the delivery of informative risk estimates in clinical systems.

Patient-specific game-based transfer method for Parkinson's disease severity prediction

Dysphonia is one of the early symptoms of Parkinson's disease (PD). Most existing methods use feature selection methods to find the optimal subset of voice features for all PD patients. Few have considered the heterogeneity between patients, which implies the need to provide specific prediction models for different patients. However, building the specific model faces the challenge of small sample size, which makes it lack generalization ability. Instance transfer is an effective way to solve this problem. Therefore, this paper proposes a patient-specific game-based transfer (PSGT) method for PD severity prediction. First, a selection mechanism is used to select PD patients with similar disease trends to the target patient from the source domain, which reduces the risk of negative transfer. Then, the contribution of the transferred subjects and their instances to the disease estimation of the target subject is fairly evaluated by the Shapley value, which improves the interpretability of the method. Next, the proportion of valid instances in the transferred subjects is determined, and the instances with higher contribution are transferred to further reduce the difference between the transferred instance subset and the target subject. Finally, the selected subset of instances is added to the training set of the target subject, and the extended data is fed into the random forest to improve the performance of the method. Parkinson's telemonitoring dataset is used to evaluate the feasibility and effectiveness. The mean values of mean absolute error, root mean square error, and volatility obtained by predicting motor-UPDRS and total-UPDRS for target patients are 1.59, 1.95, 1.56 and 1.98, 2.54, 1.94, respectively. Experiment results show that the PSGT has better performance in both prediction error and stability over compared methods.

Performance of ASCVD Risk Prediction Models in Individuals With Inflammatory Bowel Disease: A UK Biobank Study.

Lay Summary This study suggests that the current atherosclerotic cardiovascular disease risk prediction models used in clinical practice performed better in the non–inflammatory bowel disease (IBD) cohort compared with IBD, highlighting the need for a more specific risk prediction model tailored to the IBD population.

Differential oral and gut microbial structure related to systemic metabolism in kidney stone patients.

To investigate the role of the oral and gut microbiome related to systemic metabolism and clinical parameters in various types of kidney stone disease. We conducted a case-control study by analyzing 16S rRNA and untargeted metabolomics profiling of 76 fecal, 68 saliva, 73 urine, and 43 serum samples from 76 participants aged 18-75years old. The participants included 15 patients with uric acid stones, 41 patients with calcium oxalate stones, and 20 healthy controls. Correlations among microbiome, metabolism, and clinical parameters were identified through Spearman's correlation analysis. (Clinical trial No. ChiCTR2200055316). Patients with uric acid stones exhibited reduced richness and diversity in their microbiome, as well as altered composition in both oral and gut microbiome. Furthermore, their fecal samples showed lower relative abundances of Bacteroides and Lachnospiraceae, while their saliva samples showed higher relative abundances of Porphyromonas and Neisseria. Predicted KEGG metabolism pathways, including amino acid and fatty acid metabolisms, were significantly altered in subjects with uric acid stones. Oral, gut microbiota, and metabolism were also associated with low water intake and urine pH. The area under the curve (AUC) of the specific microbiota and metabolite prediction models was over 0.85. The structure and composition of the oral and gut microbiome in different types of kidney stone disease, the correlations between oral and gut microbiome, and the associations among oral and gut microbiota, systemic metabolism and clinical parameters imply an important role that the oral and gut microbiome may play in kidney stone disease.

Construction of Intelligent Financial Supervision Mechanism for Colleges and Universities Based on RPA Technology

Abstract The RPA financial monitoring mechanism utilizes a predictive model to capture and store university data in preprocessing, and adopts a decision tree algorithm to construct a specific predictive model with good classification ability, and its logical structure is very similar to the decision-making ideas of human beings in the natural environment. CNN-LSTM financial risk assessment model is also utilized to carry out scientific risk assessment, the output of CNN is used as the input of LSTM, combining the advantages of the two to improve the learning ability of the financial fraud risk assessment model, and dynamic early warning can be accomplished beforehand for potential risk points. By analyzing the accuracy and coverage of the financial violation prediction model, 10.28% of violations were found with 96.7% accuracy. The accuracy is lower when the proportion of financial violations is higher. Risk assessment of fundraising activities and working capital of universities can be found that Z private universities have a relatively single source of income, tuition income is dominant, and in 2019, 2020 and 2022, the proportion of constructive expenditures of Z private universities reaches more than 20%, while the expenses of scientific research costs are less, however, the university’s comprehensive early warning status is relatively good. The financial risk is not significant and is in a safer range. In the university research fund violation supervision, the weight of researchers still have balance funds after two years after the completion of the project is 0.073, which indicates that the research project fund management supervision is not in place.

STATISTICAL ANALYSIS BY WAVELET LEADERS REVEALS DIFFERENCES IN MULTI-FRACTAL CHARACTERISTICS OF STOCK PRICE AND RETURN SERIES IN TURKISH HIGH FREQUENCY DATA

The price and return time series are two distinct features of any financial asset. Hence, examining the evolution of multiscale characteristics of price and returns sequential data in time domain would be helpful in gaining a better understanding of the dynamical evolution mechanism of the financial asset as a complex system. In fact, this is important to understand their respective dynamics and to design their appropriate predictive models. The main purpose of the current work is to investigate the multiscale fractals of price and return high frequency data in Turkish stock market. In this regard, the wavelet leaders computational method is applied to each high frequency data to reveal its multi-fractal behavior. In particular, the method is applied to a large set of Turkish stocks and statistical results are performed to check for (i) presence of multi-fractals in price and return series and (ii) differences between prices and returns in terms of multi-fractals. Our statistical results show strong evidence that high frequency price and return data exhibit multi-fractal dynamics. In addition, they show evidence of distinct fractal characteristics on different scales between price and return series. Furthermore, our statistical results show evidence of differences in local fluctuation characteristics of price and return time series. Therefore, differences in local characteristics are useful to build specific predictive models for each type of data for better modeling and prediction to generate profits. Besides, we found evidence that both long-range correlations and fat-tail distributions contribute to the multifractality in Turkish stocks. This finding can be attributed to the major role played by international investors in increasing the volatility of Turkish stocks.