Ten-fold Cross-validation Research Articles

Explainable machine learning model for predicting the risk of significant liver fibrosis in patients with diabetic retinopathy

Abstract Background Diabetic retinopathy (DR), a prevalent complication in patients with type 2 diabetes, has attracted increasing attention. Recent studies have explored a plausible association between retinopathy and significant liver fibrosis. The aim of this investigation was to develop a sophisticated machine learning (ML) model, leveraging comprehensive clinical datasets, to forecast the likelihood of significant liver fibrosis in patients with retinopathy and to interpret the ML model by applying the SHapley Additive exPlanations (SHAP) method. Methods This inquiry was based on data from the National Health and Nutrition Examination Survey 2005–2008 cohort. Utilizing the Fibrosis-4 index (FIB-4), liver fibrosis was stratified across a spectrum of grades (F0-F4). The severity of retinopathy was determined using retinal imaging and segmented into four discrete gradations. A ten-fold cross-validation approach was used to gauge the propensity towards liver fibrosis. Eight ML methodologies were used: Extreme Gradient Boosting, Random Forest, multilayer perceptron, Support Vector Machines, Logistic Regression (LR), Plain Bayes, Decision Tree, and k-nearest neighbors. The efficacy of these models was gauged using metrics, such as the area under the curve (AUC). The SHAP method was deployed to unravel the intricacies of feature importance and explicate the inner workings of the ML model. Results The analysis included 5,364 participants, of whom 2,116 (39.45%) exhibited notable liver fibrosis. Following random allocation, 3,754 individuals were assigned to the training set and 1,610 were allocated to the validation cohort. Nine variables were curated for integration into the ML model. Among the eight ML models scrutinized, the LR model attained zenith in both AUC (0.867, 95% CI: 0.855–0.878) and F1 score (0.749, 95% CI: 0.732–0.767). In internal validation, this model sustained its superiority, with an AUC of 0.850 and an F1 score of 0.736, surpassing all other ML models. The SHAP methodology unveils the foremost factors through importance ranking. Conclusion Sophisticated ML models were crafted using clinical data to discern the propensity for significant liver fibrosis in patients with retinopathy and to intervene early. Practice implications Improved early detection of liver fibrosis risk in retinopathy patients enhances clinical intervention outcomes.

Predicting viral proteins that evade the innate immune system: a machine learning-based immunoinformatics tool

Viral proteins that evade the host’s innate immune response play a crucial role in pathogenesis, significantly impacting viral infections and potential therapeutic strategies. Identifying these proteins through traditional methods is challenging and time-consuming due to the complexity of virus-host interactions. Leveraging advancements in computational biology, we present VirusHound-II, a novel tool that utilizes machine learning techniques to predict viral proteins evading the innate immune response with high accuracy. We evaluated a comprehensive range of machine learning models, including ensemble methods, neural networks, and support vector machines. Using a dataset of 1337 viral proteins known to evade the innate immune response (VPEINRs) and an equal number of non-VPEINRs, we employed pseudo amino acid composition as the molecular descriptor. Our methodology involved a tenfold cross-validation strategy on 80% of the data for training, followed by testing on an independent dataset comprising the remaining 20%. The random forest model demonstrated superior performance metrics, achieving 0.9290 accuracy, 0.9283 F1 score, 0.9354 precision, and 0.9213 sensitivity in the independent testing phase. These results establish VirusHound-II as an advancement in computational virology, accessible via a user-friendly web application. We anticipate that VirusHound-II will be a crucial resource for researchers, enabling the rapid and reliable prediction of viral proteins evading the innate immune response. This tool has the potential to accelerate the identification of therapeutic targets and enhance our understanding of viral evasion mechanisms, contributing to the development of more effective antiviral strategies and advancing our knowledge of virus-host interactions.

Prediction of viral oncoproteins through the combination of generative adversarial networks and machine learning techniques

Viral oncoproteins play crucial roles in transforming normal cells into cancer cells, representing a significant factor in the etiology of various cancers. Traditionally, identifying these oncoproteins is both time-consuming and costly. With advancements in computational biology, bioinformatics tools based on machine learning have emerged as effective methods for predicting biological activities. Here, for the first time, we propose an innovative approach that combines Generative Adversarial Networks (GANs) with supervised learning methods to enhance the accuracy and generalizability of viral oncoprotein prediction. Our methodology evaluated multiple machine learning models, including Random Forest, Multilayer Perceptron, Light Gradient Boosting Machine, eXtreme Gradient Boosting, and Support Vector Machine. In ten-fold cross-validation on our training dataset, the GAN-enhanced Random Forest model demonstrated superior performance metrics: 0.976 accuracy, 0.976 F1 score, 0.977 precision, 0.976 sensitivity, and 1.0 AUC. During independent testing, this model achieved 0.982 accuracy, 0.982 F1 score, 0.982 precision, 0.982 sensitivity, and 1.0 AUC. These results establish our new tool, VirOncoTarget, accessible via a web application. We anticipate that VirOncoTarget will be a valuable resource for researchers, enabling rapid and reliable viral oncoprotein prediction and advancing our understanding of their role in cancer biology.

Maternal Nutritional Factors Enhance Birthweight Prediction: A Super Learner Ensemble Approach

Birthweight (BW) is a widely used indicator of neonatal health, with low birthweight (LBW) being linked to higher risks of morbidity and mortality. Timely and precise prediction of LBW is crucial for ensuring newborn health and well-being. Despite recent machine learning advancements in BW classification based on physiological traits in the mother and ultrasound outcomes, maternal status in essential micronutrients for fetal development is yet to be fully exploited for BW prediction. This study aims to evaluate the impact of maternal nutritional factors, specifically mid-pregnancy plasma concentrations of vitamin B12, folate, and anemia on BW prediction. This study analyzed data from 729 pregnant women in Tarragona, Spain, for early BW prediction and analyzed each factor’s impact and contribution using a partial dependency plot and feature importance. Using a super learner ensemble method with tenfold cross-validation, the model achieved a prediction accuracy of 96.19% and an AUC-ROC of 0.96, outperforming single-model approaches. Vitamin B12 and folate status were identified as significant predictors, underscoring their importance in reducing LBW risk. The findings highlight the critical role of maternal nutritional factors in BW prediction and suggest that monitoring vitamin B12 and folate levels during pregnancy could enhance prenatal care and mitigate neonatal complications associated with LBW.

Smart Health Monitoring Approach to Diagnose Attention-Deficit Hyperactivity Disorderbased on Real-Time Activity and Heart Rate Variability using Boosting Models

Introduction: Attention-Deficit Hyperactivity Disorder (ADHD) is a prevalent chronic mental health condition that significantly impacts the psychological and physical wellbeing of millions of adolescents. Early detection and accurate diagnosis are crucial for effective treatment and mitigating the disorder's adverse effects. Despite extensive research efforts, current methods often fall short in simultaneously accounting for daily motor activity and heart rate variability in ADHD detection. Method: Addressing these gaps, this paper introduces a histogram-based gradient-boosting classifier for analyzing real-time activity and heart-rate variability data to automate ADHD diagnosis. By extracting twelve key features from the data and selecting the most significant ones with the extra tree model, we evaluate these features using various classifiers, including histogram-based gradient boosting, light gradient boosting machine, extreme gradient boosting, gradient boosting, and adaptive boosting. Results: The histogram-based gradient-boosting model, validated through ten-fold crossvalidation, outperforms other classifiers with an accuracy of 99.12%, an F1 measure of 99.12%, and a sensitivity of 99.13%. Additionally, it achieves a specificity of 99.1%, an AUC of 0.9995, and a minimal FDR of 0.88%. These results demonstrate that the proposed approach offers a highly effective and precise solution for automated ADHD diagnosis. Conclusion: The implications of these findings suggest that integrating real-time activity and heart-rate variability data into diagnostic processes can significantly enhance the accuracy and efficiency of ADHD assessment, potentially leading to earlier and more reliable diagnoses, improved patient outcomes, and more tailored treatment strategies.

Predicting nodal response to neoadjuvant treatment in breast cancer with core biopsy biomarkers of tumor microenvironment using data mining.

To generate a model for predicting nodal response to neoadjuvant systemic treatment (NAST) in biopsy-proven node-positive breast cancer patients (cN+) that incorporates tumor microenvironment (TME) characteristics and could be used for planning the axillary surgical staging procedure. Clinical and pathologic features were retrospectively collected for 437 patients. Core biopsy (CB) samples were reviewed for stromal content and tumor-infiltrating lymphocytes (TIL). Orange Datamining Toolbox was used for model generation and assessment. 151/437 (34.6%) patients achieved nodal pCR (ypN0). The following 5 variables were included in the prediction model: ER, Her-2, grade, stroma content and TILs. After stratified tenfold cross-validation, the logistic regression algorithm achieved and area under the ROC curve (AUC) of 0.86 and F1 score of 0.72. Nomogram was used for visualization. We developed a clinical tool to predict nodal pCR for cN+ patients after NAST that includes biomarkers of TME and achieves an AUC of 0.86 after tenfold cross-validation.

Enhancing preoperative diagnosis of pancreatic ductal adenocarcinoma and mass-forming chronic pancreatitis: a study on normalized conventional MR imaging parameters.

To assess the utility of signal intensity ratio (SIR) in distinguishing between mass-forming chronic pancreatitis (MFCP) and pancreatic ductal adenocarcinoma (PDAC), thereby reducing unnecessary pancreatectomies or delayed diagnosis brought by misdiagnosis. This retrospective study included 170 participants (34 with MFCP and 136 with PDAC) who underwent radical pancreatic surgery and were diagnosed via specimen pathology. The study group was carefully selected with a 1:4 ratio matching for sex, age, and operation time between two entities. T1 SIR, T2 SIR, arterial phase (AP) SIR, portal venous phase (VP) SIR, delay phase (DP) SIR, DWI0-50 SIR, and DWI500-1000 SIR, were calculated by dividing the signal intensity of lesions by that of the paraspinal muscle, serving as a reference organ. Intraclass Correlation Coefficient (ICC) was estimated to evaluate the intraobserver and interobserver reliability. Wilcoxon tests were employed for univariate analysis, and receiver operating characteristic (ROC) curves were generated to determine optimal cutoff points and AUC values for selected predictors. A tenfold cross-validation method was applied to validate the robustness of the results. The ICC demonstrated excellent correlation for both intraobserver and interobserver(ICCs > 0.8). T1 SIR, AP SIR, VP SIR, and DP SIR were significantly lower in the PDAC group compared to the MFCP group, and exhibited good independent predictive properties with the sensitivities of 61.8, 61.8, 70.6, and 73.5%, specificities of 66.2, 68.4, 59.6, and 55.9%, and AUCs of 0.620, 0.659, 0.670, and 0.668, respectively, hovering around 0.7. The tenfold cross-validation confirmed the reliability and robustness of our findings, with consistent AUC, sensitivity, specificity, and 95% confidence intervals over 1000 iterations. T1 SIR, AP SIR, VP SIR, and DP SIR show promise as potential imaging biomarkers for distinguishing between MFCP and PDAC.

Multilevel hybrid handcrafted feature extraction based depression recognition method using speech

Background and purposeDiagnosis of depression is based on tests performed by psychiatrists and information provided by patients or their relatives. In the field of machine learning (ML), numerous models have been devised to detect depression automatically through the analysis of speech audio signals. While deep learning approaches often achieve superior classification accuracy, they are notably resource-intensive. This research introduces an innovative, multilevel hybrid feature extraction-based classification model, specifically designed for depression detection, which exhibits reduced time complexity. Materials and methodsMODMA dataset consisting of 29 healthy and 23 Major depressive disorder audio signals was used. The constructed model architecture integrates multilevel hybrid feature extraction, iterative feature selection, and classification processes. During the Hybrid Handcrafted Feature (HHF) generation stage, a combination of textural and statistical methods was employed to extract low-level features from speech audio signals. To enhance this process for high-level feature creation, a Multilevel Discrete Wavelet Transform (MDWT) was applied. This technique produced wavelet subbands, which were then input into the hybrid feature extractor, enabling the extraction of both high and low-level features. For the selection of the most pertinent features from these extracted vectors, Iterative Neighborhood Component Analysis (INCA) was utilized. Finally, in the classification phase, a one-dimensional nearest neighbor classifier, augmented with ten-fold cross-validation, was implemented to achieve detailed, results. ResultsThe HHF-based speech audio signal classification model attained excellent performance, with the 94.63 % classification accuracy. ConclusionsThe findings validate the remarkable proficiency of the introduced HHF-based model in depression classification, underscoring its computational efficiency.

Prediction of Drug Pathway-based Disease Classes using Multiple Properties of Drugs

Background: Drug repositioning now is an important research area in drug discovery as it can accelerate the procedures of discovering novel effects of existing drugs. However, it is challenging to screen out possible effects for given drugs. Designing computational methods are a quick and cheap way to complete this task. Most existing computational methods infer the relationships between drugs and diseases. The pathway-based disease classification reported in KEGG provides us a new way to investigate drug repositioning as such classification can be applied to drugs. A predicted class of a given drug suggests latent diseases it can treat. Objective: The purpose of this study is to set up efficient multi-label classifiers to predict the classes of drugs. Methods: We adopt three types of drug information to generate drug features, including drug pathway information, label information and drug network. For the first two types, drugs are first encoded into binary vectors, which are further processed by singular value decomposition. For the third type, the network embedding algorithm, Mashup, is employed to yield drug features. Above features are combined and fed into RAndom k-labELsets (RAKEL) to construct multi-label classifiers, where support vector machine is selected as the base classification algorithm. Results: The ten-fold cross-validation results show that the classifiers provide high performance with accuracy higher than 0.95 and absolute true higher than 0.92. The case study indicates the novel effects of three drugs, i.e., they may treat new diseases. Conclusion: The proposed classifiers have high performance and are superiority to the classifiers with other classic algorithms and drug information. Furthermore, they have the ability to discover new effects of drugs.

A Novel Liver Metastasis Score for Patients Undergoing Surgical Resection of Gastroenteropancreatic Neuroendocrine Tumors: A Multi-institutional Study.

Liver metastasis impacts survival in patients with gastroenteropancreatic neuroendocrine tumors (GEP-NETs); however, current guidelines lack consensus on post-resection surveillance and adjuvant therapy. A comprehensive risk stratification tool is needed to guide personalized management. We aimed to develop and validate a predictive model for liver metastasis risk after surgical resection of GEP-NETs that incorporates pathological factors and adjuvant therapy. Patients with GEP-NETs who underwent surgical resection with curative intent at three major Chinese hospitals (2010-2022) were identified. Univariable and multivariable Cox regression analysis identified independent risk factors of liver metastasis. The liver metastasis score (LMS) was developed using weighted risk factors and validated by tenfold cross-validation. Among the 724 patients included in the analytic cohort, liver metastasis occurred in 66 patients (9.1%) at a median of 36 months; patients with liver metastasis had a worse 5-year overall survival (no liver metastasis 63.6% vs. liver metastasis 95.8%; p<0.001). Independent predictors were Ki-67 index (hazard ratio [HR] 10.36 for Ki-67 3-20%, HR 18.30 for Ki-67 >20%, vs. <3%), vascular invasion (HR 5.03), lymph node metastases (HR 2.24), and lack of adjuvant therapy (HR 3.03). The LMS demonstrated excellent discrimination (C-index 0.888) and stratified patients into low, intermediate, and high-risk relative to 5-year risk of liver metastasis: 2.9%, 20.8%, and 49.7%, respectively (p<0.001). The novel LMS effectively predicted the risk of liver metastasis after surgical resection of GEP-NETs. This validated model can help guide personalized surveillance and adjuvant treatment strategies, potentially improving outcomes for high-risk patients.

Performance evaluation of 3D printed acoustic metamaterial using soft computing approach

This paper introduces a novel methodology for predicting the acoustic absorption coefficient of DENORMS cell based acoustic metamaterial. The samples were printed from resin using Digital Light Processing based 3D printing technique. The manufactured samples were tested in an Impedance tube using the two Microphone method. A virtual simulation test rig was used to generate data sets for geometrically distinct DENORMS cell based metamaterial. Four distinct soft computing techniques specifically the “Neural Networks (NN), Random Forests (RF), Decision Trees (Rpart) and Generalized Linear Model (GLM)”, were employed and compared to develop an accurate prediction model for forecasting the absorption coefficient of the developed metamaterial. The machine learning techniques were used due to their higher speed and lower computational power requirement compared to numerical simulations to determine the absorption coefficient. The input variables consist of the Spherical Diameter, Cylindrical Diameter, Cylinder Length of the DENORMS cell and Frequency of Incident noise. The performance of the four prediction models was evaluated based on criteria such as Root mean square error, Coefficient of determination, Correlation and Accuracy. Ten-Fold cross validation is performed to test the robustness of the model.

Innovative risk score to diagnose depression using data from the UAE Healthy Future Study

Abstract Introduction Depression has been recognized as a major mental health disorder. Diagnosing depression remains a challenge due to its complex multifactorial nature. The UAE Healthy Future Study is a long-term cohort study that focuses on understanding the factors that contribute to chronic disease among Emiratis. It involves answering a comprehensive questionnaire, undergoing physical measurements such as Body Mass Index (BMI), and biological samples for analysis. We analyized the eight-item depression screening instrument Patient Health Questionnaire (PHQ-8) for this project. Methods Out of 487 participants included in the PHQ-8, 205 participants (42.1%) were included in the statistical analysis after omitting missing values. A multivariate Least Absolute Selection Shrinkage Operator (LASSO) logistic regression model was performed using gender, age, BMI, waist circumference, hip circumference, body fat percentage, high-density lipoprotein (mg/dL), lowdensity lipoprotein (mg/dL), total cholesterol (mg/dL), diastolic blood pressure, systolic blood pressure, hemoglobin A1C, as predictors. The primary outcome was the binarized total PHQ-8 using a cutoff value of ten Tenfold cross-validation was applied. Results A cutoff value that yields an approximate sensitivity of 90% was selected to maximize the ability of the novel risk score to correctly identify subjects with depression symptoms. Sensitivity and specificity were estimated with a corresponding 95% confidence interval (95% CI). A novel depression risk score was computed as the linear predictor of the selected five variables in the LASSO regression analysis, as following: Risk score = -3.284 + 0.471*gender - 0.053*age + 0.049*BMI + 0.022*HDLmgdL - 0.072*HBA1c Conclusions We have shown that a novel depression risk score provides useful information for screening of depression. Further validation studies are needed to confirm the application of the risk score in daily practice. Key messages • A novel depression risk score provides useful information for screening of depression. • If the risk score can be verified in a different population, then it can improve the screening methods for depression.

Analyzing and forecasting air pollution concentration in the capital and Southern Thailand using a lag-dependent Gaussian process model.

The air pollution problem has now amassed worldwide attention due to its multifaceted harm to human health. Exploring the concentration of air pollution and improving forecast have important consideration worldwide. In this research, we analyze the air pollution concentration of Southern Thailand and compare it with the central region. Also, we proposed a methodology based on the lag-dependent Gaussian process (LDGP), a Bayesian non-parametric machine learning model, with a stable optimization approach, which is a cluster-based multi-starter technique based on the Nelder-Mead optimizer. This model also provides the confidence band for forecasted values. We also used autoregressive deep neural network (AR-DNN), autoregressive random forest (AR-RF), gradient boosting (GB), and K-nearest neighbors (KNN) models. A comparison of the proposed methodology was performed on the daily air pollution data collected from the southern provinces and also from the capital of Thailand from 1 January 2018 to 31 December 2022. We used well-established performance evaluation measures to compare the performance of the models. To evaluate the bias due to overfit, we performed a tenfold cross-validation for all the pollutants in each region and compared the models to choose the best one. Moreover, we explored the concentration of air pollution in these regions. Results of descriptive analysis revealed that Bangkok had a much higher concentration of air pollution as compared to the southern region. However, the southern region had higher exposure to PM air pollutants as per WHO recommendations and also had higher exposure to O3 and CO levels. The proposed LDGP model outperformed the other machine learning models for forecasting all air pollutants. Hence, it is recommended to be used by experts for further research and studies with different kernel functions. This research is also expected to contribute to local government planning and prevention and worldwide use of the same methodology for the sustainability of public health.

Nomogram predicts cervical lymph node metastasis of pathological subtypes of papillary thyroid carcinoma.

Pathological subtypes of papillary thyroid carcinoma (PTC) are important factors in thyroid cancer. Some rare subtypes exhibit extensive lymph node metastasis. These pathological subtypes should receive more attention in clinical practice. Patients with different pathological subtypes of PTC were selected from the SEER database. Logistic regression, random forest, and bootstrap aggregating (bagging) methods were employed to screen for risk factors associated with cervical lymph node metastasis in the training cohort. A nomogram was established based on the model with the largest area under the curve (AUC) and evaluated using calibration curves. Decision curve analysis (DCA) was used to evaluate the clinical benefit to patients. The nomogram was validated in depth by 200 iterations of tenfold cross-validation. A total of 7,882 patients were included in the analysis, with 5,516 patients in the training group and 2,366 patients in the testing group. The logistic regression model achieved the highest AUC of 0.7396. Sex, age, race, extension (extrathyroidal extension), pathological type, and primary tumour size were identified as independent risk factors for cervical lymph node metastasis (p < 0.05). The calibration curve indicated that the model was well calibrated. DCA indicated that the nomogram model had good clinical practicability. In clinical practice, it is important to consider the pathological subtypes of PTC. The established nomogram can serve as a predictive tool for assessing cervical lymph node metastasis.

Development and construction of a cataract risk prediction model based on biochemical indices: the National Health and Nutrition Examination Survey, 2005-2008.

The aim of this study is to develop and validate a novel multivariable prediction model capable of accurately estimating the probability of cataract development, utilizing parameters such as blood biochemical markers and age. This population-based cross-sectional study comprised 9,566 participants drawn from the National Health and Nutrition Examination Survey (NHANES) across the 2005-2008 cycles. Demographic information and laboratory test results from the patients were collected and analyzed using LASSO regression and multivariate logistic regression to accurately capture the influence of biochemical indicators on the outcomes. The SHAP (Shapley Additive Explanations) scale was employed to assess the importance of each clinical feature, excluding age. A multivariate logistic regression model was then developed and visualized as a nomogram. To assess the model's performance, its discrimination, calibration, and clinical utility were evaluated using receiver operating characteristic (ROC) curves, 10-fold cross-validation, Hosmer-Lemeshow calibration curves, and decision curve analysis (DCA), respectively. Logistic regression analysis identified age, erythrocyte folate (nmol/L), blood glucose (mmol/L), and blood urea nitrogen (mmol/L) as independent risk factors for cataract, and these variables were incorporated into a multivariate logistic regression-based nomogram for cataract risk prediction. The area under the receiver operating characteristic (ROC) curve (AUC) for cataract risk prediction was 0.917 (95% CI: 0.9067-0.9273) in the training cohort, and 0.9148 (95% CI: 0.8979-0.9316) in the validation cohort. The Hosmer-Lemeshow calibration curve demonstrated a good fit, indicating strong model calibration. Ten-fold cross-validation confirmed the logistic regression model's robust predictive performance and stability during internal validation. Decision curve analysis (DCA) demonstrated that the nomogram prediction model provided greater clinical benefit for predicting cataract risk when the patient's threshold probability ranged from 0.10 to 0.90. This study identified blood urea nitrogen (mmol/L), serum glucose (mmol/L), and erythrocyte folate (mmol/L) as significant risk factors for cataract. A risk prediction model was developed, demonstrating strong predictive accuracy and clinical utility, offering clinicians a reliable tool for early and effective diagnosis. Cataract development may be delayed by reducing levels of blood urea nitrogen, serum glucose, and erythrocyte folate through lifestyle improvements and dietary modifications.

Mango leaf disease diagnosis using Total Variation Filter Based Variational Mode Decomposition

Mango leaf diseases significantly threaten mango cultivation, impacting both yield and quality. Accurate and early diagnosis is essential for effectively managing and controlling these diseases. This study introduces a novel approach for diagnosing mango leaf diseases, leveraging Total Variation Filter-based Variational Mode Decomposition. The proposed method enhances the extraction of disease-specific features from leaf images by decomposing them into intrinsic mode functions while simultaneously reducing noise and preserving important edge information. Experimental results demonstrate that the proposed method effectively isolates relevant patterns associated with various mango leaf diseases, improving diagnostic accuracy compared to traditional methods. Deep learning models, DenseNet121 and VGG-19, are used for feature extraction from sub-band images, and extracted features are concatenated and fed to Random Forest for classification. Utilizing tenfold cross-validation, our model demonstrated enhanced classification accuracy (98.85 %), specificity (99.37 %), and sensitivity (98.0 %) in detecting diseases from Mango leaf images. Feature maps and Gradient-weighted Class Activation Mapping analysis was conducted to visualize and scrutinize the essential regions crucial for accurate predictions. Statistical analysis indicates that our proposed architecture outperforms pre-trained models and existing mango leaf disease detection methods. This diagnostic approach can be a rapid disease detection tool for imaging specialists utilizing leaf images. The robustness and efficiency of the presented work in handling complex and noisy image data make it a promising tool for automated agricultural disease diagnosis systems, facilitating timely and precise interventions in mango orchards.

A Deep Learning Framework for Satellite-Derived Surface PM2.5 Estimation: Enhancing Spatial Analysis in the United States

Abstract Monitoring fine particulate matter (PM2.5) is crucial for evaluating air quality and its effects on public health. However, the limited distribution of monitoring stations presents a challenge in accurately assessing air pollution, especially in areas distant from these stations. To address this challenge, our study introduces a two-step deep learning approach for estimating daily gap-free surface PM2.5 concentrations across the contiguous United States (CONUS) from 2018 to 2022, with a spatial resolution of 4 km. In the first phase, we employ a Depthwise-Partial Convolutional Neural Network (DW-PCNN) to fill gaps between surface PM2.5 stations, utilizing Aerosol Optical Depth (AOD) data from the Moderate Resolution Imaging Spectroradiometer (MODIS). In the second phase, we integrate the PM2.5 grids imputed by the DW-PCNN with meteorological and anthropogenic variables into a Deep Convolutional Neural Network (Deep-CNN) to further enhance the accuracy of our estimation. This enables us to estimate gap-free surface PM2.5 concentrations accurately, evidenced by a Pearson’s correlation coefficient (R) of 0.92 and an Index of Agreement (IOA) of 0.96 in ten-fold cross-validation. We also introduce a grid-based method for calculating PM2.5 Design Values (DV), providing a continuous spatial representation of PM2.5 DV that enhances the traditional station-based approach. Our grid-based DV representations offer a comprehensive perspective on air quality, facilitating more detailed analysis. Furthermore, our model's ability to provide spatiotemporally consistent, gap-free PM2.5 data addresses the issue of missing values, supporting health impact research, policy formulation, and the accuracy of environmental assessments.

Computed tomography-based radiomics nomogram for prediction of lympho-vascular and perineural invasion in esophageal squamous cell cancer patients: a retrospective cohort study

PurposeLympho-vascular invasion (LVI) and perineural invasion (PNI) have been established as prognostic factors in various types of cancers. The preoperative prediction of LVI and PNI has the potential to guide personalized medicine strategies for patients with esophageal squamous cell cancer (ESCC). This study investigates whether radiomics features derived from preoperative contrast-enhanced CT could predict LVI and PNI in ESCC patients.Methods and materialsA retrospective cohort of 544 ESCC patients who underwent esophagectomy were included in this study. Preoperative contrast-enhanced CT images, pathological results of PNI and LVI, and clinical characteristics were collected. For each patient, the gross tumor volume (GTV-T) and lymph nodes volume (GTV-N) were delineated and four categories of radiomics features (first-order, shape, textural and wavelet) were extracted from GTV-T and GTV-N. The Mann–Whitney U test was used to select significant features associated with LVI and PNI in turn. Subsequently, radiomics signatures for LVI and PNI were constructed using LASSO regression with ten-fold cross-validation. Significant clinical characteristics were combined with radiomics signature to develop two nomogram models for predicting LVI and PNI, respectively. The area under the curve (AUC) and calibration curve were used to evaluate the predictive performance of the models.ResultsThe radiomics signature for LVI prediction consisted of 28 features, while the PNI radiomics signature comprised 14 features. The AUCs of the LVI radiomics signature were 0.77 and 0.74 in the training and validation groups, respectively, while the AUCs of the PNI radiomics signature were 0.69 and 0.68 in the training and validation groups. The nomograms incorporating radiomics signatures and significant clinical characteristics such as age, gender, thrombin time and D-Dimer showed improved predictive performance for both LVI (AUC: 0.82 and 0.80 in the training and validation group) and PNI (AUC: 0.75 and 0.72 in the training and validation groups) compared to the radiomics signature alone.ConclusionThe radiomics features extracted from preoperative contrast-enhanced CT of gross tumor and lymph nodes have demonstrated their potential in predicting LVI and PNI in ESCC patients. Furthermore, the incorporation of clinical characteristics has shown additional value, resulting in improved predictive performance.

The potential of decision trees as a tool to simplify broiler chicken welfare assessments

To simplify fast-growth broiler welfare assessments and use them as a benchmarking tool, decision trees were used to identify iceberg indicators discriminating flocks passing/failing welfare assessments as with the complete AWIN protocol. A dataset was constructed with data from 57 flocks and 3 previous projects. A final flock assessment score, previously not included in the dataset, was calculated and used as the benchmarking assessment classifier (pass/fail). A decision tree to classify flocks was built using the Chi-square Automatic Interaction Detection (CHAID) criterion. Cost-complexity pruning, and tenfold cross-validation were used. The final decision tree included cumulative mortality (%), immobile, lame birds (%), and birds with back wounds (%). Values were (mean ± se) 2.77 ± 0.14%, 0.16 ± 0.02%, 0.25 ± 0.02%, and 0.003 ± 0.001% for flocks passing the assessment; and 4.39 ± 0.49%, 0.24 ± 0.05%, 0.49 ± 0.09%, and 0.015 ± 0.006% for flocks failing. Cumulative mortality had the highest relative importance. The validated model correctly predicted 80.70% of benchmarking assessment outcomes. Model specificity was 0.8696; sensitivity was 0.5455. Decision trees can be useful to simplify welfare assessments. Model improvements will be possible as more information becomes available, and predictions are based on more samples.

Prediction of hemorrhage rate after tonsil surgery in children based on random forest model

Objective:Hemorrhage after tonsil surgery in children is a serious and potentially life-threatening complication. The purpose of this study was to establish a risk warning model for hemorrhage after tonsil surgery in children through a national multi-center retrospective study, providing a basis for hierarchical management after tonsil surgery in children. Methods:Stratified sampling was performed on 8 854 children who underwent tonsillectomy under general anesthesia from 15 research centers in different provinces from January 15, 2022 to May 15, 2023. The sample size of this study was 2 724 cases, including 1 096 males and 1 628 females. Children were divided into bleeding and non-bleeding groups according to whether or not they had bleeding after surgery. The random forest algorithm was used to build a risk warning model. By continuously exploring the optimized model, the accuracy of predicting the postoperative bleeding rate of tonsils in children was improved, and the prediction effectiveness of the model was verified by ten-fold cross-validation. Results:Among 2 724 children, 117 had postoperative bleeding after tonsillectomy, with a bleeding rate of 4.30%. The model constructed by the random forest algorithm for the training set was verified in the test set, and the obtained prediction accuracy was 98.72%, the recall rate was 78.95%, and the area under the ROC curve AUC was 0.96. Conclusion:Although the recall rate of the random forest model needs to be improved, the overall accuracy is quite excellent. It can effectively avoid misjudging positive cases as negative cases. It is a useful tool that can be used to predict the postoperative bleeding rate of tonsils and clinical medical decision-making, laying a good foundation for subsequent optimization and improvement.