Construction Of Prediction Model Research Articles

Construction of ferroptosis-related prediction model for pathogenesis, diagnosis and treatment of ruptured abdominal aortic aneurysm.

Abdominal aortic aneurysm (AAA) is a dangerous cardiovascular disease, which often brings great psychological burden and economic pressure to patients. If AAA rupture occurs, it is a serious threat to patients' lives. Therefore, it is of clinical value to actively explore the pathogenesis of ruptured AAA and prevent its occurrence. Ferroptosis is a new type of cell death dependent on lipid peroxidation, which plays an important role in many cardiovascular diseases. In this study, we used online data and analysis of ferroptosis-related genes to uncover the formation of ruptured AAA and potential therapeutic targets. We obtained ferroptosis-related differentially expressed genes (Fe-DEGs) from GSE98278 dataset and 259 known ferroptosis-related genes from FerrDb website. Enrichment analysis of differentially expressed genes (DEGs) was performed by gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG). Receiver Operating characteristic (ROC) curve was employed to evaluate the diagnostic abilities of Fe-DEGs. Transcription factors and miRNAs of Fe-DEGs were identified through PASTAA and miRDB, miRWalk, TargetScan respectively. Single-sample gene set enrichment analysis (ssGSEA) was used to observe immune infiltration between the stable group and the rupture group. DGIdb database was performed to find potential targeted drugs of DEGs. GO and KEGG enrichment analysis found that DEGs mainly enriched in "cellular divalent inorganic cation homeostasis," "cellular zinc ion homeostasis," "divalent inorganic cation homeostasis," "Mineral absorption," "Cytokine - cytokine receptor interaction," "Coronavirus disease - COVID-19." Two up-regulated Fe-DEGs MT1G and DDIT4 were found to further analysis. Both single and combined applications of MT1G and DDIT4 showed good diagnostic efficacy (AUC = 0.8254, 0.8548, 0.8577, respectively). Transcription factors STAT1 and PU1 of MT1G and ARNT and MAX of DDIT4 were identified. Meanwhile, has_miR-548p-MT1G pairs, has_miR-53-3p/has_miR-181b-5p/ has_miR-664a-3p-DDIT4 pairs were found. B cells, NK cells, Th2 cells were high expression in the rupture group compared with the stable group, while DCs, Th1 cells were low expression in the rupture group. Targeted drugs against immunity, GEMCITABINE and INDOMETHACIN were discovered. We preliminarily explored the clinical significance of Fe-DEGs MT1G and DDIT4 in the diagnosis of ruptured AAA, and proposed possible upstream regulatory transcription factors and miRNAs. In addition, we also analyzed the immune infiltration of stable and rupture groups, and found possible targeted drugs for immunotherapy.

MDs-NP: a property prediction model construction procedure for naphtha based on molecular dynamics simulation

In the context of carbon neutrality and carbon peaking, molecular management has become a focus of the petrochemical industry. The key to achieving molecular management is molecular reconstruction, which relies on rapid and accurate calculation of oil properties. Focusing on naphtha, we proposed a novel property prediction model construction procedure (MDs-NP) employing molecular dynamics simulations for property collections and gamma distribution from real analytical data for calculating mole fractions of simulation mixtures. We calculated 348 sets of mixture properties data in the range of 273 K–300 K by molecular dynamics simulations. Molecular feature extraction was based on molecular descriptors. In addition to descriptors based on open-source toolkits (RDKit and Mordred), we designed 12 naphtha knowledge (NK) descriptors with a focus on naphtha. Three machine learning algorithms (support vector regression, extreme gradient boosting and artificial neural network) were applied and compared to establish models for the prediction of the density and viscosity of naphtha. Mordred and NK descriptors + support vector regression algorithm achieved the best performance for density. The selected RDKFp and NK descriptors + artificial neural network algorithm achieved the best performance for viscosity. Using ablation studies, T, P_w and CC(C)C are three effective descriptors in NK that can improve the performance of the property prediction models. MDs-NP has the potential to be extended to more properties as well as more-complex petroleum systems. The models from MDs-NP can be used for rapid molecular reconstruction to facilitate construction of data-driven models and intelligent transformation of petrochemical processes.

Construction of a machine learning-based risk prediction model for depression in middle-aged and elderly hypertensive people in China: a longitudinal study

BackgroundHypertension is a common chronic disease that can trigger symptoms such as anxiety and depression. Therefore, it is essential to predict their risk of depression. The aim of this study is to find the best prediction model and provide effective intervention strategies for health professionals.MethodsThe study subjects were 2733 middle-aged and older adults who participated in the China Health and Retirement Longitudinal Study (CHARLS) between 2018 and 2020. R software was used for Lasso regression analysis to screen the best predictor variables, and logistic regression, random forest and XGBoost models were constructed. Finally, the prediction efficiency of the three models was compared.ResultsIn this study, 18 variables were included, and LASSO regression screened out 10 variables that were important for the establishment of the model. Among the three models, Logistic Regression model showed the best performance in various evaluation indicators.ConclusionThe prediction model based on machine learning can accurately assess the likelihood of depression in middle-aged and elderly patients with hypertension in the next three years. And by combining Logistic regression and nomograms, we were able to provide a clear interpretation of personalized risk predictions.

Conditional survival of patients with primary bone lymphoma of the spine: how survival changes after initial diagnosis

BackgroundThe current survival prediction methodologies for primary bone lymphoma (PBL) of the spine are deficient. This study represents the inaugural utilization of conditional survival (CS) to assess the outcome of this disease. Moreover, our objective was to devise a CS-based nomogram for predicting overall survival (OS) in real-time for spinal PBL.MethodsPatients with PBL of the spine diagnosed between January 2000 and December 2015 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. The OS was determined through the Kaplan–Meier method. The CS characteristic of patients with spinal PBL was delineated, with the CS being estimated utilizing the formula: CS(α|β) = OS(α+β)/OS(β). CS(α|β) denotes the probability of additional α-year survivorship, assuming the patient has already survived β years after the time of observation. Three methods including univariate Cox regression, best subset regression (BSR) and the least absolute shrinkage and selection operator (LASSO) regression were used to identify predictors for CS-based nomogram construction.ResultsKaplan-Meier analysis was executed to determine the OS rate for these patients, revealing a survival rate of 68% and subsequently 63% at the 3-year and 5-year mark respectively. We then investigated the CS patterning exhibited by these patients and discovered the survival of PBL in the spine progressively improved with time. Meanwhile, through three different prognostic factor selection methods, we identified the best predicter subset including age, tumor histology, tumor stage, chemotherapy and marital status, for survival prediction model construction. Finally, we successfully established and validated a novel CS-based nomogram model for real-time and dynamic survival estimation. Moreover, we further designed a risk stratification system to facilitate the identification of high-risk patients.ConclusionsThis is the first study to analyze the CS pattern of PBL of the spine. And we have also developed a CS-based nomogram that provide dynamic prognostic data in real-time, thereby aiding in the formulation of personalized treatment strategies in clinical practice.

Construction of Risk Prediction Model of Type 2 Diabetic Kidney Disease Based on Deep Learning.

This study aimed to develop a diabetic kidney disease (DKD) prediction model using long short term memory (LSTM) neural network and evaluate its performance using accuracy, precision, recall, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve. The study identified DKD risk factors through literature review and physician focus group, and collected 7 years of data from 6,040 type 2 diabetes mellitus patients based on the risk factors. Pytorch was used to build the LSTM neural network, with 70% of the data used for training and the other 30% for testing. Three models were established to examine the impact of glycosylated hemoglobin (HbA1c), systolic blood pressure (SBP), and pulse pressure (PP) variabilities on the model's performance. The developed model achieved an accuracy of 83% and an AUC of 0.83. When the risk factor of HbA1c variability, SBP variability, or PP variability was removed one by one, the accuracy of each model was significantly lower than that of the optimal model, with an accuracy of 78% (P<0.001), 79% (P<0.001), and 81% (P<0.001), respectively. The AUC of ROC was also significantly lower for each model, with values of 0.72 (P<0.001), 0.75 (P<0.001), and 0.77 (P<0.05). The developed DKD risk predictive model using LSTM neural networks demonstrated high accuracy and AUC value. When HbA1c, SBP, and PP variabilities were added to the model as featured characteristics, the model's performance was greatly improved.

Construction of a Cutting-Tool Wear Prediction Model through Ensemble Learning

This study begins by conducting side milling experiments on SKD11 using tungsten carbide TiAlN-coated end mills to compare the surface roughness performance between two combinations of milling process parameters (feed rate and radial depth of cut), along with three ultrasonic-assisted methods (rotary, dual-axis, and rotary combined with dual-axis). The results suggest that the rotary (z-axis oscillation) ultrasonic-assisted method may provide better performance. Subsequently, this superior ultrasonic-assisted method was applied both with and without laser locally preheating assistance, respectively. Using a Taguchi orthogonal array, milling process parameters (spindle speed, feed rate, and radial depth of cut) were planned for experiments with the same cutting tool and the workpiece just mentioned above. The surface roughness serves as the objective function while being constrained by cutting-tool life. The characteristics of the smaller-the-better in the Taguchi method were applied to determine the optimal combination of process parameters. Based on the optimal milling process parameters obtained and the superior hybrid-assisted method adopted, milling experiments were repeatedly performed to collect the data on cutting force and cutting-tool wear. Feature engineering was performed on the cutting force signals, and different domain characteristics from both the time and frequency domains were extracted. Hereafter, feature selection by random forest and data standardization were further applied to feature extractions, and the data processing was thus completed. For the processed data, a cutting-tool wear prediction model was constructed by ensemble learning. This method leverages various machine learning regression models, including decision tree, random forest, extremely randomized tree, light gradient boosting machine, extreme gradient boosting, AdaBoost, stochastic gradient descent, support vector regression, linear support vector regression, and multilayer perceptron. After hyper-parameter tuning, the ensemble voting regression prediction was performed based on these ten mentioned models. The experimental results demonstrate that the ensemble voting regression model surpasses the performance of each individual machine learning regression model. In addition, this regression model achieves a coefficient of determination (R2) of 0.94576, a root mean square error (RMSE) of 0.24348, a mean squared error (MSE) of 0.05928, and a mean absolute error (MAE) of 0.18182. Therefore, the ensemble learning approach has been proven to be a feasible and effective method for monitoring cutting-tool wear.

Identification of Potential Injury Risk Factors and Prediction Model Construction of Athletes using Data Mining Algorithm

Identification of potential injury risk factors and construction of prediction models for athletes using data mining algorithms involve analyzing various factors such as biomechanical, physiological, and environmental variables to determine their correlation with injury occurrences. Data mining techniques, such as decision trees, logistic regression, or neural networks, are then applied to identify patterns and relationships within the data. By integrating this information, predictive models can be developed to forecast the likelihood of athletes sustaining injuries based on their individual characteristics and training conditions. This paper introduces a novel approach for athlete injury risk prediction using the Noninvasive Data Mining Model with Multi-relational and Multi-dimensional Clustering (Ni-DMMMC) algorithm. By leveraging advanced data mining techniques, Ni-DMMMC aims to identify hidden relationships between various athlete characteristics, including biomechanical risk, training load, physiological markers, and environmental factors, to predict injury susceptibility accurately. Through multi-relational and multi-dimensional clustering, the algorithm effectively categorizes athletes into distinct clusters based on their unique risk profiles. These clusters provide valuable insights into the diverse injury risk profiles present within athlete populations, enabling targeted intervention strategies and personalized athlete management approaches. The proposed approach holds significant promise for enhancing injury prevention efforts, optimizing athlete performance, and improving overall well-being in sports medicine practice. athletes in Cluster 1 exhibit high biomechanical risk (0.85), moderate training load (0.60), low physiological markers (0.25), and moderate environmental risk (0.45), while athletes in Cluster 2 display moderate biomechanical risk (0.70), high training load (0.90), high physiological markers (0.80), and low environmental risk (0.30). These numerical values serve as indicators for assessing an athlete's injury risk profile comprehensively.

Heat shock protein-related diagnostic signature and molecular subtypes in ankylosing spondylitis: new pathogenesis insights

Heat shock proteins (HSP) have been associated with a range of persistent inflammatory disorders; however, little research has been conducted on the involvement of HSP in the development of ankylosing spondylitis (AS). The research aims to identify a diagnostic signature based on HSP-related genes and determine the molecular subtypes of AS. We gathered the transcriptional data of patients with AS from the GSE73754 dataset and conducted a literature search for HSP-related genes (HRGs). The logistic regression model was utilized for the identification of hub HRGs associated with AS. Subsequently, these HRGs were employed in the construction of a nomogram prediction model. We employed a consensus clustering approach to identify novel molecular subgroups. Subsequently, we conducted functional analyses, encompassing GO, KEGG, and GSEA, to elucidate the underlying mechanisms between these subgroups. To assess the immunological landscape, we employed the xCell algorithm. Through logistic regression analysis, the four core HRGs (CCT2, HSPA6, DNAJB14, and DNAJC5) were confirmed as potential biomarkers for AS. Subsequent stratification revealed two distinct molecular phenotypes, designated as Cluster 1 and Cluster 2. Notably, Cluster 2 was characterized by the upregulation of pathways pertinent to immune response and inflammation. Our research suggests that the CCT2, HSPA6, DNAJB14, and DNAJC5 exhibit potential as effective blood-based diagnostic biomarkers for AS. These findings contribute to a deeper comprehension of the underlying mechanisms involved in the development of AS and offer potential targets for personalized therapeutic interventions.

Analysis of risk factors associated with diffuse alveolar haemorrhage in patients with ANCA-associated vasculitis and construction of a risk prediction model using line graph.

This study aims to analyse the risk factors associated with diffuse alveolar haemorrhage (DAH) in patients with ANCA-associated vasculitis (AAV) and construct a risk prediction model using line graph. A retrospective study was conducted from January 2012 to May 2023 at the First Clinical College of Three Gorges University, focusing on patients diagnosed with AAV. Clinical and laboratory data were collected from these patients. The potential predictors subsets of high-risk AAV combined with DAH were screened by LASSO regression and 10-fold cross-validation method, and determined by using multivariate Logistic regression analysis, then were used for developing a prediction nomogram for high-risk AAV combined with DAH using the R software. ROC curve analysis was used to validate the model's stability. Internal validation was performed using a bootstrap method. The discrimination of the nomogram was determined by calculating the average consistency index(C-index). The calibration curve was used to assess the calibration of the nomogram. A total of 234 patients with AAV were included, among whom 85 developed DAH, with an incidence rate of 36%, and the average age was 63±12. Multivariable logistic regression analysis showed that Age [OR=1.037 (95%CI: 1.006, 1.071), p=0.019], platelet count (PLT) [OR=0.996 (95%CI: 0.992, 0.999), p=0.029], ESR [OR=1.028 (95%CI: 1.015, 1.042), p<0.01], HB [OR=0.978 (95%CI: 0.959, 0.996), p=0.024], and haematuria [OR=3.77 (95%CI: 1.677, 8.976), p=0.001] were found to be independent predictors of AAV combined with DAH and were used to construct a nomogram. The AUCROC values of the nomogram for DAH in AAV patients was 0.852 (95%CI: 0.801, 0.903), and the C-index could reach 0.824 after internal verification, showing good differentiation and consistency. The new nomogram, which included age, Hb, ESR, PLT and haematuria as variables, had the potential to predict the risk of AAV patients complicated with DAH.

Genetic Susceptibility, Mendelian randomization and Nomogram Model Construction of Gestational Diabetes Mellitus

Abstract Context Gestational diabetes mellitus (GDM) is a pregnancy complicated disease that poses a risk to maternal and infant health. However, the etiology of the disease has been not yet elucidated. Objective To detect the genetic susceptibility and construct a nomogram model with significantly associated polymorphisms and key clinical indicators for early prediction of gestational diabetes mellitus (GDM). Methods 11 functional single nucleotide polymorphisms (SNPs) screened by genome-wide association study (GWAS) were genotyped in 554 GDM cases and 641 healthy controls. Functional analysis of GDM positively associated SNPs, Multivariate mendelian randomization (MVMR) and a GDM early predictive nomogram model construction were performed. Result rs1965211, rs3760675 and rs7814359 were significantly associated with genetic susceptibility to GDM after adjusting age and pre-pregnancy BMI (pre-BMI). It seems that GDM associated SNPs have effects on regulating target gene transcription factor binding, post transcriptional splicing, and translation product structure. Besides, rs3760675 can be expression quantitative trait locis (eQTLs) and increase the XAB2 mRNA expression level (P = 0.047). The MVMR analysis showed that the increase of clinical variables of BMI, HbA1c and FPG had significant causal effects on GDM (BMI-ORMVMR = 1.52, HbA1c-ORMVMR = 1.32, FPG-ORMVMR = 1.78), P &amp;lt;0.05. A nomogram model constructed with pre-BMI, FPG, HbA1c, and genotypes of rs1965211, rs3760675 and rs7814359 showed an area under the ROC curve of 0.824. Conclusion Functional polymorphisms can change women's susceptibility to GDM and the predictive nomogram model based on genetic and environmental factors can effectively distinguish individuals with different GDM risks in early stages of pregnancy.

Comprehensive analysis of immunogenic cell death-related gene and construction of prediction model based on WGCNA and multiple machine learning in severe COVID-19

The death of coronavirus disease 2019 (COVID-19) is primarily due to from critically ill patients, especially from ARDS complications caused by SARS-CoV-2. Therefore, it is essential to contribute an in-depth understanding of the pathogenesis of the disease and to identify biomarkers for predicting critically ill patients at the molecular level. Immunogenic cell death (ICD), as a specific variant of regulatory cell death driven by stress, can induce adaptive immune responses against cell death antigens in the host. Studies have confirmed that both innate and adaptive immune pathways are involved in the pathogenesis of SARS-CoV-2 infection. However, the role of ICD in the pathogenesis of severe COVID-19 has rarely been explored. In this study, we systematically evaluated the role of ICD-related genes in COVID-19. We conducted consensus clustering, immune infiltration analysis, and functional enrichment analysis based on ICD differentially expressed genes. The results showed that immune infiltration characteristics were altered in severe and non-severe COVID-19. In addition, we used multiple machine learning methods to screen for five risk genes (KLF5, NSUN7, APH1B, GRB10 and CD4), which are used to predict COVID-19 severity. Finally, we constructed a nomogram to predict the risk of severe COVID-19 based on the classification and recognition model, and validated the model with external data sets. This study provides a valuable direction for the exploration of the pathogenesis and progress of COVID-19, and helps in the early identification of severe cases of COVID-19 to reduce mortality.

Ultra-short-term multi-energy load forecasting for integrated energy systems based on multi-dimensional coupling characteristic mining and multi-task learning

To address the challenges posed by the randomness and volatility of multi-energy loads in integrated energy systems for ultra-short-term accurate load forecasting, this paper proposes an ultra-short-term multi-energy load forecasting method based on multi-dimensional coupling feature mining and multi-task learning. Firstly, a method for mining multi-dimensional coupling characteristics of multi-energy loads is proposed, integrating multiple correlation analysis methods. By constructing coupling features of multi-energy loads and using them as input features of the model, the complex coupling relationships between multi-energy loads are effectively quantified. Secondly, an ultra-short-term multi-energy load forecasting model based on multi-task learning and a temporal convolutional network is constructed. In the prediction model construction phase, the potential complex coupling characteristics between multiple loads can be fully explored, and the potential temporal associations and long-term dependencies within data can be extracted. Then, the multi-task learning loss function weight optimization method based on homoscedastic uncertainty is used to optimize the forecasting model, realizing automatic tuning of the loss function weight parameters and further improving the prediction performance of the model. Finally, an experimental analysis is conducted using the integrated energy system of Arizona State University in the United States as an example. The results show that the proposed forecasting method has higher prediction accuracy than other prediction methods.

Construction and Validation of a Clinical Prediction Model for Predicting Tubal Pregnancy Rupture Based on Nomogram

Construction and Validation of a Clinical Prediction Model for Predicting Tubal Pregnancy Rupture Based on Nomogram

Analysis of influencing factors and construction of prediction model for postoperative nausea and vomiting in patients undergoing laparoscopic sleeve gastrectomy: a single-center retrospective cohort study.

With the increasing number of bariatric surgeries, the high incidence of postoperative nausea and vomiting (PONV) associated with this surgery has also gradually attracted attention. Among the common bariatric surgery methods, patients undergoing sleeve gastrectomy (SG) have the highest incidence of nausea and vomiting. The mechanism of occurrence of PONV is very complex. This study aims to explore the influencing factors of PONV in patients undergoing laparoscopic sleeve gastrectomy (LSG) and construct a nomogram prediction model based on these factors. With the approval of the Ethics Committee, the electronic medical records of patients who underwent LSG from July 2022 to May 2023 were collected retrospectively. A total of 114 patients with complete medical records who underwent LSG from July 2022 to May 2023 were included in this study. Among them, 46 patients developed PONV, resulting in a PONV incidence rate of 40.4%. Multivariate logistic regression analysis revealed that female gender, the use of inhalation anesthesia, and operation time ≥ 120min were risk factors for PONV in LSG. Additionally, the use of more than two kinds of antiemetic drugs was identified as a protective factor. Based on these factors, a nomogram model was constructed. PONV in patients undergoing LSG is related to gender, type of anesthesia, duration of surgery, and combination therapy with antiemetic drugs. The nomogram prediction model constructed in this study demonstrates high accuracy and discrimination in predicting the occurrence of PONV in patients undergoing LSG.

Identification of KRAS mutation-associated gut microbiota in colorectal cancer and construction of predictive machine learning model.

Gut microbiota has demonstrated an increasingly important role in the onset and development of colorectal cancer (CRC). Nonetheless, the association between gut microbiota and KRAS mutation in CRC remains enigmatic. We conducted 16S rRNA sequencing on stool samples from 94 CRC patients and employed the linear discriminant analysis effect size algorithm to identify distinct gut microbiota between KRAS mutant and KRAS wild-type CRC patients. Transcriptome sequencing data from nine CRC patients were transformed into a matrix of immune infiltrating cells, which was then utilized to explore KRAS mutation-associated biological functions, including Gene Ontology items and Kyoto Encyclopedia of Genes and Genomes pathways. Subsequently, we analyzed the correlations among these KRAS mutation-associated gut microbiota, host immunity, and KRAS mutation-associated biological functions. At last, we developed a predictive random forest (RF) machine learning model to predict the KRAS mutation status in CRC patients, based on the gut microbiota associated with KRAS mutation. We identified a total of 26 differential gut microbiota between both groups. Intriguingly, a significant positive correlation was observed between Bifidobacterium spp. and mast cells, as well as between Bifidobacterium longum and chemokine receptor CX3CR1. Additionally, we also observed a notable negative correlation between Bifidobacterium and GOMF:proteasome binding. The RF model constructed using the KRAS mutation-associated gut microbiota demonstrated qualified efficacy in predicting the KRAS phenotype in CRC. Our study ascertained the presence of 26 KRAS mutation-associated gut microbiota in CRC and speculated that Bifidobacterium may exert an essential role in preventing CRC progression, which appeared to correlate with the upregulation of mast cells and CX3CR1 expression, as well as the downregulation of GOMF:proteasome binding. Furthermore, the RF model constructed on the basis of KRAS mutation-associated gut microbiota exhibited substantial potential in predicting KRAS mutation status in CRC patients.IMPORTANCEGut microbiota has emerged as an essential player in the onset and development of colorectal cancer (CRC). However, the relationship between gut microbiota and KRAS mutation in CRC remains elusive. Our study not only identified a total of 26 gut microbiota associated with KRAS mutation in CRC but also unveiled their significant correlations with tumor-infiltrating immune cells, immune-related genes, and biological pathways (Gene Ontology items and Kyoto Encyclopedia of Genes and Genomes pathways). We speculated that Bifidobacterium may play a crucial role in impeding CRC progression, potentially linked to the upregulation of mast cells and CX3CR1 expression, as well as the downregulation of GOMF:Proteasome binding. Furthermore, based on the KRAS mutation-associated gut microbiota, the RF model exhibited promising potential in the prediction of KRAS mutation status for CRC patients. Overall, the findings of our study offered fresh insights into microbiological research and clinical prediction of KRAS mutation status for CRC patients.

Multi-scale reconstruction of rolling mill vibration signal based on fuzzy entropy clustering

The mill vibration signals collected during mill operation are often affected by complex working conditions and various disturbances, thus presenting strong non-stationary characteristics. After the vibration signal is processed by noise reduction, although the noise interference and modal aliasing phenomenon are solved, the extracted vibration signal of the rolling mill still has the problems of strong non-stationarity, high complexity, and great difficulty in analyzing, which largely affects the prediction model construction. To address the above problems, this study proposes a multi-scale signal reconstruction method based on Fuzzy Entropy and Gath-Geva fuzzy clustering algorithm, which effectively reduces the complexity of the original sequence, reduces the number of predictive modellings, and improves the signal predictability and prediction accuracy. The sequence reconstruction of such non-stationary vibration signals based on their internal characteristics has obvious advantages for the problem of mill vibration prediction and analysis.

Optimizing early neurological deterioration prediction in acute ischemic stroke patients following intravenous thrombolysis: a LASSO regression model approach.

Acute ischemic stroke (AIS) remains a leading cause of disability and mortality globally among adults. Despite Intravenous Thrombolysis (IVT) with recombinant tissue plasminogen activator (rt-PA) emerging as the standard treatment for AIS, approximately 6-40% of patients undergoing IVT experience Early Neurological Deterioration (END), significantly impacting treatment efficacy and patient prognosis. This study aimed to develop and validate a predictive model for END in AIS patients post rt-PA administration using the Least Absolute Shrinkage and Selection Operator (LASSO) regression approach. In this retrospective cohort study, data from 531 AIS patients treated with intravenous alteplase across two hospitals were analyzed. LASSO regression was employed to identify significant predictors of END, leading to the construction of a multivariate predictive model. Six key predictors significantly associated with END were identified through LASSO regression analysis: previous stroke history, Body Mass Index (BMI), age, Onset to Treatment Time (OTT), lymphocyte count, and glucose levels. A predictive nomogram incorporating these factors was developed, effectively estimating the probability of END post-IVT. The model demonstrated robust predictive performance, with an Area Under the Curve (AUC) of 0.867 in the training set and 0.880 in the validation set. The LASSO regression-based predictive model accurately identifies critical risk factors leading to END in AIS patients following IVT. This model facilitates timely identification of high-risk patients by clinicians, enabling more personalized treatment strategies and optimizing patient management and outcomes.

Construction and Optimization of Power Quality Risk Spillover Trend Prediction Model Based on Deep Learning

This study aims to establish and refine a deep learning-based predictive model for power quality risk spillover trends, thereby addressing the challenges posed by the escalating diversity and adaptability of power systems in the evolution of the renewable energy industry. Initially, the study introduces the concept of power quality risk spillover, referring to the influence exerted by power quality issues in one region on other regions. This influence initiates a chain reaction, ultimately leading to a more widespread deterioration in power quality. Then, the advantages and applications of the deep learning model in power quality risk spillover trend prediction are expounded. During the model development process, we employed deep learning algorithms such as the multilayer perceptron and extended short-term memory network, tailored specifically to the unique characteristics of power quality data. To enhance the model's predictive accuracy and stability, we implemented optimization strategies encompassing data preprocessing, feature engineering, and model integration. Our experimental findings demonstrate that the optimized model exhibits remarkable precision and stability in anticipating power quality risk spillover trends, thereby offering robust support for risk management and ensuring the stable operation of power systems. This study provides a valuable exploration and practice for the application and development of a power quality risk spillover trend prediction model based on deep learning.

Study on meso-macroscopic ionic conductivity of hydrogels and construction of prediction model

The utilization of hydrogels in biological devices has seen a significant expansion, necessitating a thorough investigation into their conductivity. In this regard, we conducted a comprehensive examination of the impact of crosslinkers on pore radius and distribution. When the crosslinker proportion was augmented by a factor of 10, the pore radius exhibited a reduction of nearly 3.7 times, resulting in a more uniform pore distribution. Notably, our findings indicated a direct proportionality between conductivity and mesoscopic porosity, coupled with an inverse relationship with crosslinking density. To advance our understanding, we proposed an equivalent pore network model that omits considerations of curvature to predict the ionic conductivity of hydrogels. Intriguingly, as the proportion of crosslinker increased, the mesoscopic pores of hydrogels demonstrated a correlation with macroscopic features. Upon comparison with experimental data, the model exhibited a commendable alignment with the observed trends. Through mutual refinement with experimental results, a novel prediction equation emerged, yielding an average prediction error less than 2%. Beyond trend prediction, our model achieved relative quantitative predictions, providing valuable insights for the regulation of conductivity in electronic biological devices. This research contributes to the advancement of knowledge in the field, offering a nuanced perspective on the interplay between crosslinkers, pore characteristics, and the conductivity of hydrogels.

Identification of risk factors of EGFR-TKIs primary resistance in lung adenocarcinoma patients and construction of a risk predictive model: a case-control study.

Lung cancer is one of the malignancies with the highest incidence and mortality rates. Epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKIs) are recommended as the first-line treatment for patients with EGFR-mutated lung adenocarcinoma (LUAD). However, some patients with EGFR-sensitive mutations develop primary resistance to EGFR-TKIs. This study aims to analyze the clinical characteristics of LUAD patients with primary resistance to EGFR-TKIs, identify independent risk factors for primary resistance, and establish a risk predictive model to provide reference for clinical decision-making. We collected data from LUAD patients with EGFR-sensitive mutations (19del/21L858R) who were hospitalized in our institution between 2020 and 2022 and received first-generation EGFR-TKIs with follow-up exceeding 6 months. These patients were categorized into primary resistance and sensitive groups based on treatment outcomes. We compared general clinical data, laboratory tests, and tumor-related characteristics between the two groups, analyzed risk factors for primary resistance to EGFR-TKIs, and constructed a risk predictive model. The model's predictive value was comprehensively assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curves. Serum neuron-specific enolase (NSE) concentration (P=0.03), serum pro-gastrin-releasing peptide (ProGRP) concentration (P=0.01), and Ki67 expression (P<0.001) were identified as independent risk factors for primary resistance to EGFR-TKIs in LUAD. The combined presence of these three risk factors had the highest predictive value [area under the curve (AUC) =0.975, P<0.001]. We constructed a predictive model for the risk of primary resistance to EGFR-TKIs in LUAD patients, incorporating these three parameters, and represented it through a visually interpretable nomogram. The calibration curve of the nomogram demonstrated its strong predictive ability. Further decision curve analysis indicated the model's clinical utility. Based on a single-center retrospective case-control study, we identified serum NSE concentration, ProGRP concentration, and Ki67 expression as independent risk factors for primary resistance to EGFR-TKIs in LUAD patients. We constructed and validated a risk predictive model based on these findings. This predictive model holds promise for clinical application, aiding in the development of personalized treatment strategies and providing a scientific basis for early identification of primary resistance patients.