RF Algorithm Research Articles

Identification of synthetic cathinone positional isomers using electron activated dissociation mass spectrometry

BackgroundSynthetic cathinones (SCs) are a large category of new psychoactive substances (NPS), which pose a serious threat to public health due to limited information about their toxicology and pharmacology. Many SCs are closely related in their chemical structures, with some substances being positional isomers. In this study, we propose a new workflow for the identification of SC isomers using liquid chromatography-high-resolution tandem mass spectrometry (LC-HRMS2) combined with electron activated dissociation (EAD) and chemometrics. Differentiation between isomeric SCs is essential for both legislative and public safety reasons, since minor differences in their molecular structures may change their legal status and pharmacological profiles. ResultsThe workflow was optimized using ring-substituted isomers of methylmethcathinones, methylethcathinones, and chloromethcathinones. The kinetic energy in the EAD cell was investigated at three levels (i.e., 15, 18, and 20 eV) for each group. Two data analysis methods (i.e., t-distributed stochastic neighbor embedding [t-SNE] and a Random Forest [RF] algorithm) were applied using the obtained EAD mass spectral data. The three sets of ring-substituted SCs were clearly distinguished using t-SNE and an RF algorithm. Moreover, the RF approach resulted in a 97 % classification accuracy for isomer identification using various combinations of compounds, isomers, and electron kinetic energies. This workflow was subsequentially applied to the analysis of 26 blind street samples, resulting in a 92 % classification accuracy for isomer identification. However, the accuracy varied based on the kinetic electron energy. A subset of the original data set, focusing on 15-eV data only, was used, resulting in a classification accuracy of 100 %. SignificanceThis study presents the first LC-HRMS2 workflow based on EAD and chemometrics, which resulted in a classification accuracy of 100 % of authentic street samples. The developed LC-HRMS2 workflow demonstrates that EAD product ions and their characteristic ion ratios can be successfully used to identify ring-substituted positional isomers of SCs.

Combustion condition predictions for C2-C4 alkane and alkene fuels via machine learning methods

The accurate and rapid prediction of hydrocarbon type was a precondition for the utilization of fossil fuels with high efficiency and safety. In this study, machine learning based techniques were used to predict the type and equivalence ratio of flames of C2-C4 alkane and alkene fuels based on the differences in flame morphology between various combustion conditions. The test results of different machine learning algorithms, including ANN, SVM, SVR, KNN, MLR, and RF were compared in detail using statistical methods. Results indicated that ANN, SVM, KNN, and RF all exhibited an outstanding performance in predicting the types of C2-C4 alkane and alkene flames, achieving accuracies of 95.7 %, 96.3 %, 93.8 %, and 96.5 %, respectively. For the prediction of the equivalence ratio among these fuels, the mean absolute percentage errors of the ANN, SVR, MLR, and RF were only 5.6 %, 3.8 %, 8.2 %, and 3.8 %, respectively. The performance of SVM, SVR, and RF algorithms was significantly superior to that of ANN, MLR, and KNN algorithms for flame prediction. Moreover, the data of feature analysis revealed that the importance level of designed features exhibited a significant distinction between different prediction targets. For predicting the type of C2-C4 alkane and alkene fuels, the features associated with blue region showed a stronger importance level. However, the yellow region related features played a more significant role for the prediction of the equivalence ratio.

Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment

Flooding is a major natural hazard worldwide, causing catastrophic damage to communities and infrastructure. Due to climate change exacerbating extreme weather events robust flood hazard modeling is crucial to support disaster resilience and adaptation. This study uses multi-sourced geospatial datasets to develop an advanced machine learning framework for flood hazard assessment in the Arambag region of West Bengal, India. The flood inventory was constructed through Sentinel-1 SAR analysis and global flood databases. Fifteen flood conditioning factors related to topography, land cover, soil, rainfall, proximity, and demographics were incorporated. Rigorous training and testing of diverse machine learning models, including RF, AdaBoost, rFerns, XGB, DeepBoost, GBM, SDA, BAM, monmlp, and MARS algorithms, were undertaken for categorical flood hazard mapping. Model optimization was achieved through statistical feature selection techniques. Accuracy metrics and advanced model interpretability methods like SHAP and Boruta were implemented to evaluate predictive performance. According to the area under the receiver operating characteristic curve (AUC), the prediction accuracy of the models performed was around > 80%. RF achieves an AUC of 0.847 at resampling factor 5, indicating strong discriminative performance. AdaBoost also consistently exhibits good discriminative ability, with AUC values of 0.839 at resampling factor 10. Boruta and SHAP analysis indicated precipitation and elevation as factors most significantly contributing to flood hazard assessment in the study area. Most of the machine learning models pointed out southern portions of the study area as highly susceptible areas. On average, from 17.2 to 18.6% of the study area is highly susceptible to flood hazards. In the feature selection analysis, various nature-inspired algorithms identified the selected input parameters for flood hazard assessment, i.e., elevation, precipitation, distance to rivers, TWI, geomorphology, lithology, TRI, slope, soil type, curvature, NDVI, distance to roads, and gMIS. As per the Boruta and SHAP analyses, it was found that elevation, precipitation, and distance to rivers play the most crucial roles in the decision-making process for flood hazard assessment. The results indicated that the majority of the building footprints (15.27%) are at high and very high risk, followed by those at very low risk (43.80%), low risk (24.30%), and moderate risk (16.63%). Similarly, the cropland area affected by flooding in this region is categorized into five risk classes: very high (16.85%), high (17.28%), moderate (16.07%), low (16.51%), and very low (33.29%). However, this interdisciplinary study contributes significantly towards hydraulic and hydrological modeling for flood hazard management.

Sex and age estimation with corneal topography parameters by using machine learning algorithms and artificial neural networks

BackgroundThe aim of this study, which was based on this hypothesis, was to estimate sex and age by using a machine learning algorithm (ML) and artificial neural networks (ANN) with parameters obtained from the eyeball. The study was conducted on corneal topography images of 155 women and 155 men aged between 6 and 87 who did not have surgical intervention or pathology in their eyeballs. In the study, the individuals were divided into four different age groups 6–17, 18–34, 35–55, and 56–87. Sex and age estimation was carried out by using the numerical data of parameters obtained as a result of corneal topography imaging in ML and ANN inputs.ResultsAs a result of our study, in sex determination, a 0.98 accuracy rate (Acc) was obtained with the logistic regression algorithm, one of the ML algorithms, and 0.94 Acc was obtained with the MLCP model, one of the ANN algorithms; in age estimation, 0.84 Acc was obtained with RF algorithm, one of the ML algorithms. With the SHAP analyzer of the Random Forest algorithm, through which the effects of parameters on the overall result are evaluated, the parameter that made the highest contribution to sex estimation was found to be corneal volume, and the parameter that made the highest contribution to age estimation was found to be pupil Q parameter.ConclusionAs a result of our study, it was found that parameters obtained from the eyeball showed a high accuracy in sex and age estimation.

Understanding sexual homicide in Korea using machine learning algorithms.

The current study was conducted to confirm the characteristics in sexual homicide and to explore variables that effectively differentiate sexual homicide and nonsexual homicide. Further, newer methods that have received attention in criminology, such as the machine learning method, were used to explore the ideal algorithm for classifying sexual homicide and patterns for sexual homicide in Korea. To do this, 542 homicide cases were analyzed utilizing eight algorithms, and the classification performance of each algorithm was analyzed along with the importance of variables. The results of the analysis revealed that the Naive Bayes, K-Nearest Neighbors, and RF algorithms demonstrate good classification accuracy, and generally, factors such as relationships, marriage, planning, personal weapons, and overkill were identified as crucial variables that distinguish sexual homicide in Korea. In addition, the crime scene information of the crime occurring in the dark (at night) and body disposal were found to have high importance. The current study proposes ways to enhance the efficacy of crime investigation and advance the research on sexual homicides in Korea through a more scientific understanding of sexual homicide that has not been thoroughly explored domestically.

Unraveling the genetic and molecular landscape of sepsis and acute kidney injury: A comprehensive GWAS and machine learning approach

ObjectivesThis study aimed to explore the underlying mechanisms of sepsis and acute kidney injury (AKI), including sepsis-associated AKI (SA-AKI), a frequent complication in critically ill sepsis patients. MethodsGWAS data was analyzed for genetic association between AKI and sepsis. Then, we systematically applied three distinct machine learning algorithms (LASSO, SVM-RFE, RF) to rigorously identify and validate signature genes of SA-AKI, assessing their diagnostic and prognostic value through ROC curves and survival analysis. The study also examined the functional and immunological aspects of these genes, potential drug targets, and ceRNA networks. A mouse model of sepsis was created to test the reliability of these signature genes. ResultsLDSC confirmed a positive genetic correlation between AKI and sepsis, although no significant shared loci were found. Bidirectional MR analysis indicated mutual increased risks of AKI and sepsis. Then, 311 key genes common to sepsis and AKI were identified, with 42 significantly linked to sepsis prognosis. Six genes, selected through LASSO, SVM-RFE, and RF algorithms, showed excellent predictive performance for sepsis, AKI, and SA-AKI. The models demonstrated near-perfect AUCs in both training and testing datasets, and a perfect AUC in a sepsis mouse model. Significant differences in immune cells, immune-related pathways, HLA, and checkpoint genes were found between high- and low-risk groups. The study identified 62 potential drug treatments for sepsis and AKI and constructed a ceRNA network. ConclusionsThe identified signature genes hold potential clinical applications, including prognostic evaluation and targeted therapeutic strategies for sepsis and AKI. However, further research is needed to confirm these findings.

Using a Logistic Regression Model to Examine the Variables Influencing Changes in Northern Thailand’s Forest Cover and Comparing Machine Learning Algorithms

Protecting biodiversity and keeping the Earth’s temperature stable are both very important jobs performed by tropical forests. In the last few decades, remote sensing has given us new tools and ways to track changes in land cover. To understand what causes changes in forest cover, it is important to look at the things that affect those changes. However, there is not enough research that uses a logistic regression model (LRM) and compares the results with machine learning (ML) techniques to investigate the specific factors that cause forest cover change in remote mountainous areas like Thailand’s Mae Hong Son and Chiang Mai Provinces. Following a comparison of an LRM, a random forest, and an SVM, this study of the causes of changes in forest cover in Mae Hong Son found six important factors: soil series, rock types, slope, the NDVI, the NDWI, and the distances to city areas. Compared to the LRM, both the RF and SVM machine learning algorithms had higher values for the kappa coefficient, sensitivity, specificity, accuracy, positive and negative predictions, and sensitivity, especially the RF. Following what was found in Mae Hong Son, when the important factors were examined in Chiang Mai, the RF came out on top. It is believed that these results can be used in more situations to help make plans for restoring ecosystems and to promote long-lasting methods of managing land use.

Thrombomodulin as a potential diagnostic marker of acute myocardial infarction and correlation with immune infiltration: Comprehensive analysis based on multiple machine learning

BackgroundAcute myocardial infarction (AMI) is a global health problem with high mortality. Early diagnosis can prevent the development of AMI and provide valuable information for subsequent treatment. Angiogenesis has been shown to be a critical factor in the development of infarction and targeting this process may be a potential protective strategy for preventing myocardial injury and improving the prognosis of AMI patients. This study aimed to screen and verify diagnostic markers related to angiogenesis in AMI and to investigate the molecular mechanisms of action associated with AMI in terms of immune cell infiltration. MethodsThe GSE66360 and the GSE60993 datasets were both downloaded from the GEO database and were used as the training cohort and the external validation cohort, respectively. Angiogenesis-related genes (ARGs) were downloaded from the MSigDB database. The hub ARGs were identified via LASSO, RF, and SVM-RFE algorithms. ROC curves were used to assess the accuracy of the hub ARGs. The potential mechanisms of the hub ARGs were analyzed by GSEA. The ssGSEA algorithm was used to determine differences in immune cell infiltration and immune function. The CIBERSORT algorithm was used for immune cell infiltration analysis. In addition, we constructed a ceRNA network map of differentially expressed ARGs. ResultsWe identified the thrombomodulin (THBD) gene from ARGs as a potential diagnostic marker for AMI based on the LASSO, SVM-RFE, and RF algorithms. THBD was differentially expressed and had a potential diagnostic value (area under the curve [AUC] = 0.931 and 0.765 in the training and testing datasets, respectively). GSEA showed that the MAPK signaling pathway was more enriched in the high-expression group of THBD (P < 0.05). Immune cell infiltration analysis demonstrated that THBD was mainly positively correlated with monocytes (R = 0.48, P = 0.00055) and neutrophils (R = 0.36, P = 0.013). Finally, in the ceRNA regulatory network, THBD was closely associated with 9 miRNAs and 42 lncRNAs involved in AMI. ConclusionTHBD can be used as a potential diagnostic marker for AMI. This study provides new insights for future AMI diagnosis and molecular mechanism research. Moreover, immune cell infiltration plays an essential role in the occurrence and development of AMI.

Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases.

With the advent of artificial intelligence technology, machine learning algorithms have been widely used in the area of disease prediction. Cardiovascular disease (CVD) seriously jeopardizes human health worldwide, thereby needing the establishment of an effective CVD prediction model that can be of great significance for controlling the risk of the disease and safeguarding the physical and mental health of the population. Considering the UCI heart disease dataset as an example, initially, a single machine learning prediction model was constructed. Subsequently, six methods such as Pearson, chi-squared, RFE and LightGBM were comprehensively used for the feature screening. On the basis of the base classifiers, Soft Voting fusion and Stacking fusion was carried out to build a prediction model for cardiovascular diseases, in order to realize an early warning and disease intervention for high-risk populations. To address the data imbalance problem, the SMOTE method was adopted to process the data set, and the prediction effect of the model was analyzed using multi-dimensional and multi-indicators. In the single classifier model, the MLP algorithm performed optimally on the preprocessed heart disease dataset. After feature selection, five features eliminated. The ENSEM_SV algorithm that combines the base classifiers to determine the prediction results by soft voting on the results of the classifiers achieved the optimal value on five metrics such as Accuracy, Jaccard_Score, Hamm_Loss, AUC, etc., and the AUC value reached 0.951. The RF, ET, GBDT, and LGB algorithms were employed in the first stage sub-model composed of base classifiers. The AB algorithm was selected as the second stage model, and the ensemble algorithm ENSEM_ST, obtained by Stacking fusion of the two stages exhibited the best performance on 7 indicators such as Accuracy, Sensitivity, F1_Score, Mathew_Corrcoef, etc., and the AUC reached 0.952. Furthermore, a comparison of the algorithms' classification effects based on different training set occupancy was carried out. The results indicated that the prediction performance of both the fusion models was better than the single models, and the overall effect of ENSEM_ST fusion was stronger than the ENSEM_SV fusion. The fusion model established in this study improved the overall classification accuracy and stability of the model to a significant extent. It has a good application value in the predictive analysis of CVD diagnosis, and can provide a valuable reference in the disease diagnosis and intervention strategies.

Ensemble Learning for Pea Yield Estimation Using Unmanned Aerial Vehicles, Red Green Blue, and Multispectral Imagery

Peas are one of the most important cultivated legumes worldwide, for which early yield estimations are helpful for agricultural planning. The unmanned aerial vehicles (UAVs) have become widely used for crop yield estimations, owing to their operational convenience. In this study, three types of sensor data (red green blue [RGB], multispectral [MS], and a fusion of RGB and MS) across five growth stages were applied to estimate pea yield using ensemble learning (EL) and four base learners (Cubist, elastic net [EN], K nearest neighbor [KNN], and random forest [RF]). The results showed the following: (1) the use of fusion data effectively improved the estimation accuracy in all five growth stages compared to the estimations obtained using a single sensor; (2) the mid filling growth stage provided the highest estimation accuracy, with coefficients of determination (R2) reaching up to 0.81, 0.8, 0.58, and 0.77 for the Cubist, EN, KNN, and RF algorithms, respectively; (3) the EL algorithm achieved the best performance in estimating pea yield than base learners; and (4) the different models were satisfactory and applicable for both investigated pea types. These results indicated that the combination of dual-sensor data (RGB + MS) from UAVs and appropriate algorithms can be used to obtain sufficiently accurate pea yield estimations, which could provide valuable insights for agricultural remote sensing research.

The physical, social, and mental conditions of machine learning in student health evaluation

AbstractBackgroundThis study aims to assess how well several machine learning (ML) algorithms predict the physical, social, and mental health condition of university students.ObjectivesThe physical health measurements used in the study include BMI (Body Mass Index), %BF (percentage of Body Fat), BSC (Blood Serum Cholesterol), SBP (Systolic Blood Pressure), and DBP (Diastolic Blood Pressure).MethodsThe mental health evaluation relied on the following methods: PHQ‐9 (Patient Health Questionnaire‐9), ISI (Insomnia Severity Index), GAD‐7 (Generalized Anxiety Disorder Scale), and SBQ‐R (Suicidal Behaviors Questionnaire‐Revised). The study assessed KEYES, the comprehensive social health indicator. The study uses a famous methodology for training and testing four well‐known ML algorithms, namely the K‐nearest neighbors algorithm, decision trees, Naïve Bayes, and the random forest algorithm.Results and ConclusionsThe recall value of the RF algorithm is higher by 2.0%, 4.15%, and 11.25%, respectively. The F‐score value of the RF algorithm is also the highest. The differences amount to 4.56% (Naïve Bayes), 2.50% (DT), and 11.20% (K‐NN). Accuracy, Precision, Recall, and F‐score were used to assess the researched ML algorithms' prediction ability. With a 99.40% prediction accuracy, a 97.60% precision, a 99.30% recall, and an F‐score value of 98.70%, the Random Forest method performed the best. ML algorithms can serve as tools for the prediction of physical, mental, and social health state of patients, including students, but they have a rather narrow scope of application and do not cover all aspects of health.

Machine-learning models for diagnosis of rotator cuff tears in osteoporosis patients based on anteroposterior X-rays of the shoulder joint

ObjectiveThis study aims to diagnose Rotator Cuff Tears (RCT) and classify the severity of RCT in patients with Osteoporosis (OP) through the analysis of shoulder joint anteroposterior (AP) X-ray-based localized proximal humeral bone mineral density (BMD) measurements and clinical information based on machine learning (ML) models. MethodsA retrospective cohort of 89 patients was analyzed, including 63 with both OP and RCT (OPRCT) and 26 with OP only. The study analyzed a series of shoulder radiographs from April 2021 to April 2023. Grayscale values were measured after plotting ROIs based on AP X-rays of shoulder joint. Five kinds of ML models were developed and compared based on their performance in predicting the occurrence and severity of RCT from ROIs' greyscale values and clinical information (age, gender, advantage side, lumbar BMD, and acromion morphology (AM)). Further analysis using SHAP values illustrated the significant impact of selected features on model predictions. ResultsR1-6 had a positive correlation with BMD respectively. The nine variables, including greyscale R1-6, age, BMD, and AM, were used in the prediction models. The RF model was determined to be superior in effectively diagnosing RCT in OP patients, with high AUC scores of 0.998, 0.889, and 0.95 in the training, validation, and testing sets, respectively. SHAP values revealed that the most influential factors on the diagnostic outcomes were the grayscale values of all cancellous bones in ROIs. A column-line graph prediction model based on nine variables was constructed, and DCA curves indicated that RCT prediction in OP patients was favored based on this model. Furthermore, the RF model was also the most superior in predicting the types of RCT within the OPRCT group, with an accuracy of 86.364% and 73.684% in the training and test sets, respectively. SHAP values indicated that the most significant factor affecting the predictive outcomes was the AM, followed by the grayscale values of the greater tubercle, among others. ConclusionsML models, particularly the RF algorithm, show significant promise in diagnosing RCT occurrence and severity in OP patients using conventional shoulder X-rays based on the nine variables. This method presents a cost-effective, accessible, and non-invasive diagnostic strategy that has the potential to substantially enhance the early detection and management of RCT in OP patient population.

Assessment of gully erosion susceptibility using four data-driven models AHP, FR, RF and XGBoosting machine learning algorithms

Gully erosion is a significant global threat to socioeconomic and environmental sustainability, making it a widespread natural hazard. Developing spatial models for gully erosion is crucial for local governance to effectively implement mitigation measures and promote regional development. This study applied two machine learning (ML) models, RF and XGB, alongside an AHP-based multi-criteria decision method and FR bivariate statistics, to assess gully erosion susceptibility (GES) in the Kangsabati River basin in eastern India's Chotonagpur plateau fringe. A GIS database was created, incorporating recorded gully erosion incidents and 20 conditioning variables, which were evaluated for multicollinearity. These variables served as predictive factors for assessing gully erosion presence in the study area. The models' performance was evaluated using metrics such as RMSE, MAE, specificity, sensitivity, and accuracy. The XGB model outperformed the others, achieving a predictive accuracy of 90.22%. The study found that approximately 6.56% of the Kangsabati catchment is highly susceptible to gully erosion, with 12.39% moderately susceptible and 81.05% not susceptible. The XGB model had the highest ROC value of 85.5 during testing, indicating its superiority over the FR (ROC ​= ​81.7), AHP (ROC ​= ​79.8), and RF (ROC ​= ​83.8) models. These findings highlight the XGB model's efficacy and potential for large-scale GES mapping.

Intelligent prediction of 110kV insulator lightning flashover criteria based on random forest

The lightning flashover criteria of insulators vary significantly under different conditions, and it is impractical to exhaustively enumerate all the criteria through extensive tests. Therefore, this paper aims to explore the intelligent prediction of lightning flashover criteria for 110 kV insulators using a data-driven approach. Initially, a test database comprising 4,978 high- and low-altitude test data of 110 kV insulator lightning impulse flashover is established. Subsequently, relevant characteristic values are extracted from the database as inputs for the prediction model. Various machine learning algorithms, such as the BPNN, SVM and RF algorithms, are employed to construct prediction models for the U50% and volt-time characteristics of 110 kV insulators under lightning impulses. The results demonstrate that the RF algorithm yields an average absolute percentage error of merely 1.17 % for the U50% prediction model. Additionally, the RF and BP algorithms achieve the highest prediction accuracies of 10.7 % and 6.5 %, respectively, for the volt-time characteristics at high- and low-altitude. This validates the feasibility of substituting many traditional tests with more accurate flashover criteria predicted through a data-driven approach. This paper provides a novel concept for predicting the lightning impulse flashover criteria of insulators under different working conditions. Reducing the need for repetitive tests is expected to acquire the high-precision intelligent prediction of insulator lightning impulse flashover criteria.

Machine learning for predicting liver and/or lung metastasis in colorectal cancer: A retrospective study based on the SEER database

ObjectiveThis study aims to establish a machine learning (ML) model for predicting the risk of liver and/or lung metastasis in colorectal cancer (CRC). MethodsUsing the National Institutes of Health (NIH)'s Surveillance, Epidemiology, and End Results (SEER) database, a total of 51265 patients with pathological diagnosis of colorectal cancer from 2010 to 2015 were extracted for model development. On this basis, We have established 7 machine learning algorithm models. Evaluate the model based on accuracy, and AUC of receiver operating characteristics (ROC) and explain the relationship between clinical pathological features and target variables based on the best model. We validated the model among 196 colorectal cancer patients in Beijing Electric Power Hospital of Capital Medical University of China to evaluate its performance and universality. Finally, we have developed a network-based calculator using the best model to predict the risk of liver and/or lung metastasis in colorectal cancer patients. Results51265 patients were enrolled in the study, of which 7864 (15.3 %) had distant liver and/or lung metastasis. RF had the best predictive ability, In the internal test set, with an accuracy of 0.895, AUC of 0.956, and AUPR of 0.896. In addition, the RF model was evaluated in the external validation set with an accuracy of 0.913, AUC of 0.912, and AUPR of 0.611. ConclusionIn this study, we constructed an RF algorithm mode to predict the risk of colorectal liver and/or lung metastasis, to assist doctors in making clinical decisions.

Screening and validation of atherosclerosis PAN-apoptotic immune-related genes based on single-cell sequencing.

Carotid atherosclerosis (CAS) is a complication of atherosclerosis (AS). PAN-optosome is an inflammatory programmed cell death pathway event regulated by the PAN-optosome complex. CAS's PAN-optosome-related genes (PORGs) have yet to be studied. Hence, screening the PAN-optosome-related diagnostic genes for treating CAS was vital. We introduced transcriptome data to screen out differentially expressed genes (DEGs) in CAS. Subsequently, WGCNA analysis was utilized to mine module genes about PANoptosis score. We performed differential expression analysis (CAS samples vs. standard samples) to obtain CAS-related differentially expressed genes at the single-cell level. Venn diagram was executed to identify PAN-optosome-related differential genes (POR-DEGs) associated with CAS. Further, LASSO regression and RF algorithm were implemented to were executed to build a diagnostic model. We additionally performed immune infiltration and gene set enrichment analysis (GSEA) based on diagnostic genes. We verified the accuracy of the model genes by single-cell nuclear sequencing and RT-qPCR validation of clinical samples, as well as in vitro cellular experiments. We identified 785 DEGs associated with CAS. Then, 4296 module genes about PANoptosis score were obtained. We obtained the 7365 and 1631 CAS-related DEGs at the single-cell level, respectively. 67 POR-DEGs were retained Venn diagram. Subsequently, 4 PAN-optosome-related diagnostic genes (CNTN4, FILIP1, PHGDH, and TFPI2) were identified via machine learning. Cellular function tests on four genes showed that these genes have essential roles in maintaining arterial cell viability and resisting cellular senescence. We obtained four PANoptosis-related diagnostic genes (CNTN4, FILIP1, PHGDH, and TFPI2) associated with CAS, laying a theoretical foundation for treating CAS.

CARDIOVASCULAR DISEASES DETECTION IN ECG IMAGES USING DEEP LEARNING METHODS

Heart diseases are the leading cause of death world- wide. So,detecting and identifying them earlier can save many lives.Electrocardiogram (ECG) is a common and inexpensive tool for measuring the electrical activity of the heart and is used to detect cardiovascular disease.In this paper, the power of deep learning techniques was used to predict the four major cardiac abnormalities: abnormal heartbeat, myocardial infarction, his- tory of myocardial infarction, and normal person classes using the public ECG images dataset of cardiac patients. First, the preatrained models, namely SqueezeNet, AlexNet, proposed CNN and Xception were proposed for abnormality prediction.Second, these models were used as feature extraction tools for traditional machine learning algorithms, namely support vector machine, K- nearest neighbors, decision tree, random forest, and Na¨ıve Bayes. According to the experimental results, the performance metrics of the Xception model outperform the exciting works; it achieves 99.5% accuracy, 99.5% recall, 99.5% precision, and 99.5% F1 score. Moreover, when the Xception model is used for feature extraction, it achieves the best score of 99.8% using the RF and DT algorithms. Index Terms—Cardiovascular, deep learning, electrocardio- gram (ECG) images, feature extraction, machine learning, trans- fer learning.

BIT COIN PRICE PREDICTION USING RF ALGORITHM WITH SENTIMENT FACTORS.

Sentiment analysis was included into a predictive model that was created for this project in order to forecast bitcoin closing values. The dataset contains daily Bitcoin data for January 2024, including sentiment scores computed for each day as well as opening, high, low, and closing values. The study assesses the predictive ability of the Random Forest regression model by using metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R^2) score. The negative R^2 score indicates that, although the model may produce predictions, its overall fit to the data is still not ideal, implying that the model is unable to adequately represent the correlation between sentiment ratings and Bitcoin prices. Potential areas for development to increase the predicted accuracy of the model and gain a deeper understanding of how sentiment analysis affects Bitcoin prices include feature engineering, hyper parameter tuning, and model selection. Keywords: Cryptocurrency, Price Prediction, Machine learning, Random Forest

M6A-related bioinformatics analysis indicates that LRPPRC is an immune marker for ischemic stroke

Ischemic stroke (IS) is a common cerebrovascular disease whose pathogenesis involves a variety of immune molecules, immune channels and immune processes. 6-methyladenosine (m6A) modification regulates a variety of immune metabolic and immunopathological processes, but the role of m6A in IS is not yet understood. We downloaded the data set GSE58294 from the GEO database and screened for m6A-regulated differential expression genes. The RF algorithm was selected to screen the m6A key regulatory genes. Clinical prediction models were constructed and validated based on m6A key regulatory genes. IS patients were grouped according to the expression of m6A key regulatory genes, and immune markers of IS were identified based on immune infiltration characteristics and correlation. Finally, we performed functional enrichment, protein interaction network analysis and molecular prediction of the immune biomarkers. We identified a total of 7 differentially expressed genes in the dataset, namely METTL3, WTAP, YWHAG, TRA2A, YTHDF3, LRPPRC and HNRNPA2B1. The random forest algorithm indicated that all 7 genes were m6A key regulatory genes of IS, and the credibility of the above key regulatory genes was verified by constructing a clinical prediction model. Based on the expression of key regulatory genes, we divided IS patients into 2 groups. Based on the expression of the gene LRPPRC and the correlation of immune infiltration under different subgroups, LRPPRC was identified as an immune biomarker for IS. GO enrichment analyses indicate that LRPPRC is associated with a variety of cellular functions. Protein interaction network analysis and molecular prediction indicated that LRPPRC correlates with a variety of immune proteins, and LRPPRC may serve as a target for IS drug therapy. Our findings suggest that LRPPRC is an immune marker for IS. Further analysis based on LRPPRC could elucidate its role in the immune microenvironment of IS.

Inversion of Soil Moisture Content in Cotton Fields Using GBR-RF Algorithm Combined with Sentinel-2 Satellite Spectral Data

Soil moisture content plays a vital role in agricultural production, significantly influencing crop growth, development, and yield. Thoroughly understanding the specific soil moisture content in cotton fields is crucial for enhancing agricultural efficiency and driving sustainable agricultural development. This study utilized the gradient-boosting regression–random forest (GBR-RF) algorithm and the GBR and RF algorithms separately, in conjunction with Sentinel-2 satellite images, to estimate cotton soil moisture content, focusing on the B1–B8 bands and in particular the sensitive B6, B7, and B8 bands. The soil data in the jujube orchard of the study area were collected using soil augers at a depth of 30 cm, with soil data collected from a depth of 20 to 30 cm. The findings revealed that the integrated learning algorithm GBR-RF demonstrated high accuracy, with R2, MAE, and MSE results of 0.8838, 1.0121, and 1.6168, respectively. In comparison, the results using just the GBR algorithm yielded R2, MAE, and MSE values of 0.8158, 1.1327, and 1.9645, respectively, while those obtained from the RF algorithm were 0.8415, 1.0680, and 1.8331, respectively. These results indicate that the algorithms exhibited strong generalization, robustness, and accuracy, with GBR-RF outperforming GBR and RF by 8.34% and 5.03%, respectively, in combination with using the B1–B8 bands for inversion. Furthermore, utilizing the full-band data resulted in R2 values that were up to 24.27% higher than those of the individual bands, affirming the efficacy of band combinations for improved accuracy. This study’s demonstration of the positive impact of integrated learning algorithms on estimating cotton soil moisture content underscores the advantages of multi-band data combinations over single-band data, highlighting their ability to enhance accuracy without significantly impacting errors. Importantly, this study’s findings, while not limited to a single experimental field, have broad applicability in cotton precision agriculture, offering valuable insights for research on yield enhancement and agricultural efficiency.