Comprehensive Prediction Model Research Articles

Using a comprehensive atlas and predictive models to reveal the complexity and evolution of brain-active regulatory elements.

Most genetic variants associated with psychiatric disorders are located in noncoding regions of the genome. To investigate their functional implications, we integrate epigenetic data from the PsychENCODE Consortium and other published sources to construct a comprehensive atlas of candidate brain cis-regulatory elements. Using deep learning, we model these elements' sequence syntax and predict how binding sites for lineage-specific transcription factors contribute to cell type-specific gene regulation in various types of glia and neurons. The elements' evolutionary history suggests that new regulatory information in the brain emerges primarily via smaller sequence mutations within conserved mammalian elements rather than entirely new human- or primate-specific sequences. However, primate-specific candidate elements, particularly those active during fetal brain development and in excitatory neurons and astrocytes, are implicated in the heritability of brain-related human traits. Additionally, we introduce PsychSCREEN, a web-based platform offering interactive visualization of PsychENCODE-generated genetic and epigenetic data from diverse brain cell types in individuals with psychiatric disorders and healthy controls.

Construction of a prognostic model for extensive-stage small cell lung cancer patients undergoing immune therapy in northernmost China and prediction of treatment efficacy based on response status at different time points

Background and purposeRecently, the emergence of immune checkpoint inhibitors has significantly improved the survival of patients with extensive-stage small cell lung cancer. However, not all patients can benefit from immunotherapy; therefore, there is an urgent need for precise predictive markers to screen the population for the benefit of immunotherapy. However, single markers have limited predictive accuracy, so a comprehensive predictive model is needed to better enable precision immunotherapy. The aim of this study was to establish a prognostic model for immunotherapy in ES-SCLC patients using basic clinical characteristics and peripheral hematological indices of the patients, which would provide a strategy for the clinical realization of precision immunotherapy and improve the prognosis of small cell lung cancer patients.MethodsThis research retrospectively collected data from ES-SCLC patients treated with PD-1/PD-L1 inhibitors between March 1, 2019, and October 31, 2022, at Harbin Medical University Cancer Hospital. The study data was randomly split into training and validation sets in a 7:3 ratio. Variables associated with patients’ overall survival were screened and modeled by univariate and multivariate Cox regression analyses. Models were presented visually via Nomogram plots. Model discrimination was evaluated by Harrell’s C index, tROC, and tAUC. The calibration of the model was assessed by calibration curves. In addition, the clinical utility of the model was assessed using a DCA curve. After calculating the total risk score of patients in the training set, patients were stratified by risk using percentile partitioning. The Kaplan–Meier method was used to plot OS and PFS survival curves for different risk groups and response statuses at different milestone time points. Differences in survival time groups were compared using the chi-square test. Statistical analysis software included R 4.1.2 and SPSS 26.ResultsThis study included a total of 113 ES-SCLC patients who received immunotherapy, including 79 in the training set and 34 in the validation set. Six variables associated with poorer OS in patients were screened by Cox regression analysis: liver metastasis (P = 0.001), bone metastasis (P = 0.013), NLR < 2.14 (P = 0.005), LIPI assessed as poor (P < 0.001), PNI < 51.03 (P = 0.002), and LDH ≥ 146.5 (P = 0.037). A prognostic model for immunotherapy in ES-SCLC patients was constructed based on the above variables. The Harrell’s C-index in the training and validation sets of the model was 0.85 (95% CI 0.76–0.93) and 0.88 (95% CI 0.76–0.99), respectively; the AUC values corresponding to 12, 18, and 24 months in the tROC curves of the training set were 0.745, 0.848, and 0.819 in the training set and 0.858, 0.904 and 0.828 in the validation set; the tAUC curves show that the overall tAUC is > 0.7 and does not fluctuate much over time in both the training and validation sets. The calibration plot demonstrated the good calibration of the model, and the DCA curve indicated that the model had practical clinical applications. Patients in the training set were categorized into low, intermediate, and high risk groups based on their predicted risk scores in the Nomogram graphs. In the training set, 52 patients (66%) died with a median OS of 15.0 months and a median PFS of 7.8 months. Compared with the high-risk group (median OS: 12.3 months), the median OS was significantly longer in the intermediate-risk group (median OS: 24.5 months, HR = 0.47, P = 0.038) and the low-risk group (median OS not reached, HR = 0.14, P = 0.007). And, the median PFS was also significantly prolonged in the intermediate-risk group (median PFS: 12.7 months, HR = 0.45, P = 0.026) and low-risk group (median PFS not reached, HR = 0.12, P = 0.004) compared with the high-risk group (median PFS: 6.2 months). Similar results were obtained in the validation set. In addition, we observed that in real-world ES-SCLC patients, at 6 weeks after immunotherapy, the median OS was significantly longer in responders than in non-responders (median OS: 19.5 months vs. 11.9 months, P = 0.033). Similar results were obtained at 12 weeks (median OS: 20.7 months vs 11.9 months, P = 0.044) and 20 weeks (median OS: 20.7 months vs 11.7 months, P = 0.015). Finally, we found that in the real world, ES-SCLC patients without liver metastasis (P = 0.002), bone metastasis (P = 0.001) and a total number of metastatic organs < 2 (P = 0.002) are more likely to become long-term survivors after receiving immunotherapy.ConclusionThis study constructed a new prognostic model based on basic patient clinical characteristics and peripheral blood indices, which can be a good predictor of the prognosis of immunotherapy in ES-SCLC patients; in the real world, the response status at milestone time points (6, 12, and 20 weeks) can be a good indicator of long-term survival in ES-SCLC patients receiving immunotherapy.

Understanding the Health Impacts of Vehicular Emissions in South Florida: A Comprehensive Analysis

South Florida is famous for its diverse cultural scene and year-round sunshine. This success, however, has not been without its consequences. While the region enjoys economic prosperity, the hidden cost of deteriorating air quality and adverse health effects from vehicle emissions necessitates urgent attention. Electric vehicles (EVs) have emerged as a potential solution, promising reduced emissions, and increased energy efficiency. However, the intricate life cycle emissions associated with EV energy production raise questions about their net benefits. Using predictive modeling and historical data, the study forecasts emissions trajectories and assesses their health implications. Results indicate a substantial reduction in pollutants like PM2.5 and NOx by 2050, particularly in counties with higher vehicle miles traveled (VMT). However, challenges remain, such as Broward County’s heightened dependence on polluting electricity sources for EV charging, leading to increased SO2 emissions and public health costs. The analysis underscores the importance of transitioning to cleaner energy sources, highlighting the potential benefits of renewable resources in reducing emissions and improving public health outcomes. By incorporating comprehensive data and predictive models, this study provides valuable insights for policymakers and communities, advocating for a concerted effort towards sustainable transportation solutions. Ultimately, the findings emphasize the necessity of proactive measures to mitigate the adverse effects of vehicle emissions and foster a healthier, more sustainable future for South Florida.

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

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

Risk Prediction of the Development of the Digital Economy Industry Based on a Machine Learning Model in the Context of Rural Revitalization

Risk Prediction of the Development of the Digital Economy Industry Based on a Machine Learning Model in the Context of Rural Revitalization

Data Mining Strategies for Gold Price Prediction Using Multi-Factorial Influences

The prediction of gold prices is a critical endeavor in the realm of financial markets, given the precious metal's significance as a store of value and its susceptibility to various economic, geopolitical, and market influences. This research focuses on the application of machine learning (ML) models to predict gold rates by incorporating factors such as the dollar exchange rate, crude oil prices, and element prices. The objective is to utilize advanced ML algorithms, including regression, decision trees, and ensemble methods, to analyze and interpret the complex relationships between these key factors and gold prices. Through the use of robust ML models and historical data, the study aims to improve the accuracy of gold rate predictions. Additionally, the research seeks to explore the importance of features and interactions among variables to develop comprehensive predictive models. The utilization of ML techniques in this context is expected to provide a deeper understanding of the dynamic influences of the dollar exchange rate, crude oil prices, and element prices on gold rates, offering valuable insights for investment and risk management strategies in financial markets.

New findings and new methods on macrophages in primary immune thrombocytopenia.

Primary immune thrombocytopenia (ITP) is an acquired autoimmune disease with multiple immune cells take part in the pathogenesis. Macrophages play multiple roles in both innate and adaptive immune system. The report by Jiani Mo and colleagues identified new biomarkers and explore the role of mitophagy and ferroptosis in ITP pathogenesis. Commentary on: Mo etal. Comprehensive analysis and prediction model of mitophagy and ferroptosis in primary immune thrombocytopenia. Br J Haematol 2024 (Online ahead of print). doi: 10.1111/bjh.19489.

Late-xerostomia prediction model based on 18F-FDG PET image biomarkers of the main salivary glands

Background and purposeRecently, a comprehensive xerostomia prediction model was published, based on baseline xerostomia, mean dose to parotid glands (PG) and submandibular glands (SMG). Previously, PET imaging biomarkers (IBMs) of PG were shown to improve xerostomia prediction. Therefore, this study aimed to explore the potential improvement of the additional PET-IBMs from both PG and SMG to the recent comprehensive xerostomia prediction model (i.e., the reference model). Materials and methodsTotally, 540 head and neck cancer patients were split into training and validation cohorts. PET-IBMs from the PG and SMG, were selected using bootstrapped forward selection based on the reference model. The IBMs from both the PG and SMG with the highest selection frequency were added to the reference model, resulting in a PG-IBM model and a SMG-IBM model which were combined into a composite model. Model performance was assessed using the area under the curve (AUC). Likelihood ratio test compared the predictive performance between the reference model and models including IBMs. ResultsThe final selected PET-IBMs were 90th percentile of the PG SUV and total energy of the SMG SUV. The additional two PET-IBMs in the composite model improved the predictive performance of the reference model significantly. The AUC of the reference model and the composite model were 0.67 and 0.69 in the training cohort, and 0.71 and 0.73 in the validation cohort, respectively. ConclusionThe composite model including two additional PET-IBMs from PG and SMG improved the predictive performance of the reference xerostomia model significantly, facilitating a more personalized prediction approach.

Anticipating the lifespan: Predicting the durability of an anode-supported solid oxide fuel cell short stack over 50,000 h

In the present study, the operational lifetime of a solid oxide fuel (SOFC) short stack is predicted by investigating the performance degradation of both the short stack and its cells throughout 1000 ​h at 800 ​°C. The short stack and integral cell voltages are continuously measured during the long-term test, with electrochemical impedance spectroscopy (EIS) conducted every 200 ​h. The short stack voltage decreased rapidly for the initial 200–300 ​h and afterwards, it decreased at a slow rate due to the increase in the Ohmic and polarization resistances in the same manner. Scanning electron microscopy results show that there is no delamination or cracking among constituent layers of the short-stack cells. The single degradation effects of the Ni coarsening in the anode, cation migration and surface segregation in cathode and oxide scale growth in metallic interconnect mesh are successfully integrated into a comprehensive lifetime prediction model. The experimentally measured voltage degradation data of the short stack fits well with the developed mathematical model and allows the successful prediction of the lifetime up to 50,000 ​h.

Proposal of a practical stability probability model for cut slopes reflecting characteristics of weathering and angle of stratification

This research evaluates the stability of cut slopes, considering the effects of weathering and the angle of stratification. Incorporating both a weathering degree index and a factor of safety, we developed a novel formula to assess the temporal deterioration of cut slopes. Utilizing this formula, logistic regression was conducted to ascertain cut slope stability. We used the Hierarchical Bayesian model to refine the parameters of the logistic regression function, culminating in the formulation of a comprehensive slope stability probability prediction model. The model’s predicted stability probabilities for diverse cut slopes exhibited a compelling congruence with empirical data upon validation. Importantly, this approach provides expressway management authorities with a tool to preliminarily assess whether longstanding in-service cut slopes require intervention or stabilization measures.

Structure-independent machine-learning predictions of the CDK12 interactome

Cyclin-dependent kinase 12 (CDK12) is a critical regulatory protein involved in transcription and DNA repair processes. Dysregulation of CDK12 has been implicated in various diseases, including cancer. Understanding the CDK12 interactome is pivotal for elucidating its functional roles and potential therapeutic targets. Traditional methods for interactome prediction often rely on protein structure information, limiting applicability to CDK12 characterized by partly disordered terminal C region. In this study, we present a structure-independent machine-learning model that utilizes proteins’ sequence and functional data to predict the CDK12 interactome. This approach is motivated by the disordered character of the CDK12 C-terminal region mitigating a structure-driven search for binding partners. Our approach incorporates multiple data sources, including protein-protein interaction networks, functional annotations, and sequence-based features, to construct a comprehensive CDK12 interactome prediction model. The ability to predict CDK12 interactions without relying on structural information is a significant advancement, as many potential interaction partners may lack crystallographic data. In conclusion, our structure-independent machine-learning model presents a powerful tool for predicting the CDK12 interactome and holds promise in advancing our understanding of CDK12 biology, identifying potential therapeutic targets, and facilitating precision-medicine approaches for CDK12-associated diseases.

Prediction of hypoattenuating leaflet thickening in patients underwent transcatheter aortic valves replacement based on clinical factors and 4D-computed tomography morphological characteristics: A retrospective cross-sectional study

BackgroundThe rapid increase in the number of transcatheter aortic valve replacement (TAVR) procedures in China and worldwide has led to growing attention to hypoattenuating leaflet thickening (HALT) detected during follow-up by 4D-CT. It's reported that HALT may impact the durability of prosthetic valve. Early identification of these patients and timely deployment of anticoagulant therapy are therefore particularly important. MethodsWe retrospectively recruited 234 consecutive patients who underwent TAVR procedure in Fuwai Hospital. We collected clinical information and extracted morphological characteristics parameters of the transcatheter heart valve (THV) post TAVR procedure from 4D-CT. LASSO analysis was conducted to select important features. Three models were constructed, encapsulating clinical factors (Model 1), morphological characteristics parameters (Model 2), and all together (Model 3), to identify patients with HALT. Receiver operating characteristic (ROC) curves and decision curve analysis (DCA) were plotted to evaluate the discriminatory ability of models. A nomogram for HALT was developed and verified by bootstrap resampling. ResultsIn our study patients, Model 3 (AUC = 0.738) showed higher recognition effectiveness compared to Model 1 (AUC = 0.674, p = 0.032) and Model 2 (AUC = 0.675, p = 0.021). Internal bootstrap validation also showed that Model 3 had a statistical power similar to that of the initial stepwise model (AUC = 0.723 95%CI: 0.661–0.786). Overall, Model 3 was rated best for the identification of HALT in TAVR patients. ConclusionA comprehensive predictive model combining patient clinical factors with CT-based morphology parameters has superior efficacy in predicting the occurrence of HALT in TAVR patients.

Mapping the roles of scan strategy and build orientation in predicting the crystallographic texture and yield strength of 316L stainless steel produced by laser powder bed fusion

Laser Powder Bed Fusion (L-PBF) has emerged as a leading additive manufacturing (AM) technique for manufacturing complex metal parts, with 316L stainless steel being favored for its exceptional corrosion resistance and mechanical properties. While previous studies have explored the effects of different scan strategies and build orientations on the microstructure and room temperature tensile properties of L-PBF printed 316L stainless steel, there is still a lack of a comprehensive predictive model that accurately captures the combined effects of these process parameters on the final crystallographic texture and tensile properties. This study presents a novel approach that establishes a direct correlation between process parameters, microstructure, and mechanical behavior by modeling the influence of scan strategy rotation angles and build orientations on the crystallographic texture of L-PBF-manufactured 316L stainless steel. To validate the model, a series of samples were fabricated using various scan strategy rotation angles and build orientations, enabling detailed microstructural analysis and mechanical testing. The findings demonstrate a direct relationship between the selected process parameters and the resulting mechanical properties, underscoring the importance of scan strategy and build orientation selection on mechanical response. Furthermore, our calibrated model exhibits high predictive accuracy as validated through a comparison with experimental data.

Predictors of musculoskeletal disorders among special education teachers in Sabah, Malaysia

Special education teachers encounter considerable occupational challenges, yet there is limited information concerning musculoskeletal disorders (MSD) within this group. Therefore, this study aimed to address this gap by determining the prevalence of MSD, investigating associated factors of MSD, and identifying predictors of MSD among special education teachers. A cross-sectional study was conducted among special education teachers in Kota Kinabalu and Penampang, Sabah. Data were collected through self-administered questionnaires and musculoskeletal fitness assessments. Chi-square tests and independent t-tests were utilized to determine factors associated with MSD, while multiple logistic regression was performed to develop a comprehensive predictive model for MSD, which was then validated and tested for model fitness. A total of 122 individuals participated in the study, yielding a response rate of 95 %. The findings revealed a high prevalence of MSD (77.9 %) among special education teachers, with the lower back, shoulder, neck, knee, upper back, and foot being the most affected regions. The multivariable regression model identified several predictors of MSD, including marital status (adjusted odds ratio [aOR] = 4.78, 95 % confidence interval [CI] = 1.49–15.40), body fat percentage (aOR = 1.06, 95 % CI = 1.00–1.12), teaching in prolonged standing for few days a week (aOR = 3.20, 95 % CI = 0.99–10.29) or every day (aOR = 6.20, 95 % CI = 1.44–26.70), mindfulness (aOR = 0.47, 95 % CI = 0.22–0.98), and back extensor strength (aOR = 5.86, 95 % CI = 1.92–17.92). This study highlights the necessity of implementing interventions focusing on the ergonomic, psychological, and musculoskeletal fitness components to mitigate the prevalence of MSD and improve the overall well-being of special education teachers.

Multiple Disease Prediction System Using ML

Abstract: The increasing prevalence of diverse diseases presents a challenge to global healthcare systems, underscoring the need for innovative and efficient methods for early detection and preventive measures. This paper explores the application of machine learning algorithms in multiple disease prediction to enhance diagnostic accuracy and enable timely intervention. Leveraging diverse health-related data sources, including medical records and genomic information, comprehensive predictive models are developed. A multi-faceted machine learning approach integrates support vector machines, decision trees, neural networks, and ensemble learning methods to analyze complex data patterns. Feature selection and dimensionality reduction techniques optimize model performance and interpretability. The development of a predictive system involves essential steps such as data collection, preprocessing, and model training, followed by evaluation using metrics like accuracy and recall. Integration of Flask for web application development facilitates user interaction and prediction functionality. Deployment, testing, debugging, and ongoing maintenance ensure system efficiency and compliance with regulatory requirements for healthcare data security and privacy.

Comprehensive analysis and prediction model of mitophagy and ferroptosis in primary immune thrombocytopenia.

Primary immune thrombocytopenia (ITP) is linked to specific pathogenic mechanisms, yet its relationship with mitophagy and ferroptosis is poorly understood. This study aimed to identify new biomarkers and explore the role of mitophagy and ferroptosis in ITP pathogenesis. Techniques such as differential analysis, Mfuzz expression pattern clustering, machine learning, gene set enrichment analysis, single-cell RNA sequencing (scRNA-seq) and immune infiltration analysis were employed to investigate the molecular pathways of pivotal genes. Two-sample Mendelian randomization (TSMR) assessed the causal effects in ITP. Key genes identified in the training set included GABARAPL1, S100A8, LIN28A, and GDF9, which demonstrated diagnostic potential in validation sets. Functional analysis indicated these genes' involvement in ubiquitin phosphorylation, PPAR signalling pathway and T-cell differentiation. Immune infiltration analysis revealed increased macrophage presence in ITP, related to the critical genes. scRNA-seq indicated reduced GABARAPL1 expression in ITP bone marrow macrophages. TSMR linked S100A8 with ITP diagnosis, presenting an OR of 0.856 (95% CI = 0.736-0.997, p = 0.045). The study pinpointed four central genes, GABARAPL1, S100A8, LIN28A, and GDF9, tied to mitophagy and ferroptosis in ITP. It posits that diminished GABARAPL1 expression may disrupts ubiquitin phosphorylation and PPAR signalling, impairing mitophagy and inhibiting ferroptosis, leading to immune imbalance.

Effect Mechanism of Material Ratio on Ultrasonic P-wave Velocity in Coal Based Paste Fill Materials

This research is designed to investigate the variations in ultrasonic p-wave velocity in various coal based paste fill materials used for recovering standing pillars in closed/closing coal mines, with consideration given to the effects of numerous material-related factors. For this purpose, orthogonal tests were designed. The evaluation was performed on the effects of four variables on the ultrasonic p-wave velocities in samples, using coal grains as the primary material. These variables consisted of the coal grains’ particle size (PA), high-water material content (PB), cement content (PC), and water content (PD). The experimental results show the following: (1) Ultrasonic p-wave velocity of coal based paste fill materials are measured within the range of 1.596 to 2.357 km/s, and these are classified (in descending order) as PD, PB, PC, and then PA, based on their effects on ultrasonic p-wave velocity. (2) Ultrasonic p-wave velocity is positively correlated with compressive strength and shear strength; the correlation coefficients are 0.82 and 0.69, respectively. (3) Changes in the ultrasonic p-wave velocity of coal based paste fill materials, when exposed to various factors, have been characterized by fitted formulae. It was observed that the velocity maintained a quadratic polynomial correlation with factor PB and exponential correlations with factors PA, PC, and PD. The comprehensive predictive model, reflecting the characteristics of the ultrasonic p-wave velocity in response to the combined influence of these four factors, was developed through the utilization of fitted equations pertaining to individual factor variations. Subsequently, this model underwent verification.

A Comprehensive Prediction Model for Futile Recanalization in AIS Patients Post-Endovascular Therapy: Integrating Clinical, Imaging, and No-Reflow Biomarkers.

Our study aimed to construct a predictive model for identifying instances of futile recanalization in patients with anterior circulation occlusion acute ischemic stroke (AIS) who achieved complete reperfusion following endovascular therapy. We included 173 AIS patients who attained complete reperfusion, as indicated by a Modified Thrombolysis in Cerebral Infarction (mTICI) scale score of 3. Our approach involved a thorough analysis of clinical factors, imaging biomarkers, and potential no-reflow biomarkers through both univariate and multivariate analyses to identify predictors of futile recanalization. The comprehensive model includes clinical factors such as age, presence of diabetes, admission NIHSS score, and the number of stent retriever passes; imaging biomarkers like poor collaterals; and potential no-reflow biomarkers, notably disrupted blood-brain barrier (OR 4.321, 95% CI 1.794-10.405; p = 0.001), neutrophil-to-lymphocyte ratio (NLR; OR 1.095, 95% CI 1.009-1.188; p = 0.030), and D-dimer (OR 1.134, 95% CI 1.017-1.266; p = 0.024). The model demonstrated high predictive accuracy, with a C-index of 0.901 (95% CI 0.855-0.947) and 0.911 (95% CI 0.863-0.954) in the original and bootstrapping validation samples, respectively. Notably, the comprehensive model showed significantly improved predictive performance over models that did not include no-reflow biomarkers, evidenced by an integrated discrimination improvement of 8.86% (95% CI 4.34%-13.39%; p < 0.001) and a categorized reclassification improvement of 18.38% (95% CI 3.53%-33.23%; p = 0.015). This model, which leverages the potential of no-reflow biomarkers, could be especially beneficial in healthcare settings with limited resources. It provides a valuable tool for predicting futile recanalization, thereby informing clinical decision-making. Future research could explore further refinements to this model and its application in diverse clinical settings.

Predicting Risk of Colorectal Cancer After Adenoma Removal in a Large Community-Based Setting.

Colonoscopy surveillance guidelines categorize individuals as high or low risk for future colorectal cancer (CRC) based primarily on their prior polyp characteristics, but this approach is imprecise, and consideration of other risk factors may improve postpolypectomy risk stratification. Among patients who underwent a baseline colonoscopy with removal of a conventional adenoma in 2004-2016, we compared the performance for postpolypectomy CRC risk prediction (through 2020) of a comprehensive model featuring patient age, diabetes diagnosis, and baseline colonoscopy indication and prior polyp findings (i.e., adenoma with advanced histology, polyp size ≥10 mm, and sessile serrated adenoma or traditional serrated adenoma) with a polyp model featuring only polyp findings. Models were developed using Cox regression. Performance was assessed using area under the receiver operating characteristic curve (AUC) and calibration by the Hosmer-Lemeshow goodness-of-fit test. Among 95,001 patients randomly divided 70:30 into model development (n = 66,500) and internal validation cohorts (n = 28,501), 495 CRC were subsequently diagnosed; 354 in the development cohort and 141 in the validation cohort. Models demonstrated adequate calibration, and the comprehensive model demonstrated superior predictive performance to the polyp model in the development cohort (AUC 0.71, 95% confidence interval [CI] 0.68-0.74 vs AUC 0.61, 95% CI 0.58-0.64, respectively) and validation cohort (AUC 0.70, 95% CI 0.65-0.75 vs AUC 0.62, 95% CI 0.57-0.67, respectively). A comprehensive CRC risk prediction model featuring patient age, diabetes diagnosis, and baseline colonoscopy indication and polyp findings was more accurate at predicting postpolypectomy CRC diagnosis than a model based on polyp findings alone.

Correlative Analysis and Prediction of Physical Education Data Via Machine Learning: A Case Study on Grade Evaluation Method in University

Physical education is an important way to strengthen the physical quality of students in the university. Sport performance is an important criterion for judging the physical fitness of college students. But during the process of calculating and collecting the comprehensive score for each student, teachers will use different equipment or various grading formulas to evaluate the grade for many years. Thus, referenced score will lose their values if the measurement data for each student in different years are not unified and sometimes with the subjective factor because of the manual calculations. This article analyzes the details of physical fitness test results and the relationship with the comprehensive score. It is discussed that the comprehensive score can provide serious help for teachers to know students’ physical quality level and make reasonable teaching program to each student according to their personal radar chat. Therefore, the artificial influence is excluded, and the prediction model is designed by using the principal component analysis method and the back propagation (BP) neural network technology. The predictive model allows students to evaluate their own physical test score in advance, get a preliminary understanding of their physical fitness. Comparisons are made between the applications of this model in different years and errors are discussed to verify the accuracy. The results indicate that the comprehensive score prediction model supplies one effective approach to unify the scoring standards and improve the computation efficiency in physical education.