10-fold Cross-validation Research Articles

CT assessment of liver fat fraction and abdominal fat composition can predict postoperative liver metastasis of colorectal cancer

ObjectiveThe aim of this study is to investigate the clinical value of liver fat fraction assessed by CT(CT-LFF) and abdominal fat components. We focus on predicting liver metastasis (LM) after colorectal cancer (CRC) surgery. MethodsClinical and imaging data from 79 patients who underwent radical CRC surgery between January 2019 and December 2021 were retrospectively collected. Semi-automatic software was used to quantify the area of different body tissues at the level of the third lumbar vertebra, and liver fat fraction was calculated based on the CT values. Patients were grouped according to BMI, tumor grade, T stage, N stage, vascular invasion (VI), perineural invasion (PNI), and preoperative levels of CEA and CA199. A multivariate logistic regression model was used to identify independent risk factors for early LM after surgery. The diagnostic performance was assessed using the receiver operating characteristic analysis with 5-fold cross-validation. The Kaplan-Meier method was used to draw survival curves, and Log-Rank test was used for survival analysis. ResultsThe study found that the occurrence of LM after CRC surgery was significantly associated with CA199 positivity, VI, PNI, N1-2 stage, CT-LFF, VAT index (VATI). Multivariate logistic regression analysis showed that CA199 positivity (OR = 7.659), N1-2 stage (OR = 6.394), CT-LFF (OR = 1.271), VATI (OR = 1.043) were independent risk factors for predicting LM after CRC surgery. The multivariate logistic regression model, constructed using these independent risk factors, demonstrated robust predictive performance across 5-fold cross-validations, with an average AUC of 0.898 (95 % CI: 0.828–0.969). Survival analysis showed a significant difference in liver metastasis-free survival rates between the high-risk and low-risk groups (P < 0.001). ConclusionCT-LFF and VATI assessed by CT are independent risk factors for predicting LM after CRC surgery. The multivariate prediction model combining CA199 and N stage shows high predictive performance.

AB-SEL model for the prediction of coronary heart disease

Coronary heart disease (CHD) stands as the leading cause of silent and noncommunicable deaths. Early detection is essential for slowing the progression of death and saving lives. Machine learning is of interest to medical researchers and has been used to predict heart disease. This article proposes an Accuracy-Based Stacked Ensemble Learning (AB-SEL) Model to predict coronary heart disease while minimizing computational time. The dataset undergoes the Logistic Regression Recursive Feature Elimination (LR-RFE) method to identify the important features. LR, RF and AdaBoost classifiers are chosen to build Ensemble machine-learning models including techniques like bagging, majority voting, and stacking. Random search and grid search techniques have also been employed to optimize the hyperparameters. The authors applied the Cleveland dataset accessible on Kaggle and data scaling was performed using the standard scalar method. Performance measures were used to assess effectiveness, including accuracy, precision, recall, F1 score, and computational time, and were validated through 5-Fold cross-validation. The suggested approach achieved a 90.16% accuracy rate, requiring only 0.2 seconds of computational time, and yielded an AUC of 0.892.

Post-earthquake functionality and resilience prediction of bridge networks based on data-driven machine learning method

Earthquake-induced bridge damage can disrupt transportation networks, potentially hindering emergency response and post-disaster recovery efforts, and posing public safety risks in affected areas. Rapid and accurate assessment of post-earthquake resilience of bridge networks is crucial for evaluating urban seismic performance. Traditional resilience assessment methods, constrained by complex traffic distribution processes, struggle to quickly evaluate the traffic performance of bridge networks during the post-earthquake recovery period. This paper presents a two-layer stacking ensemble model for predicting the functionality and resilience of bridge networks. The first layer integrates advantages of four base learners, including random forest (RF), artificial neural network (ANN), convolutional neural network (CNN), and extreme gradient boosting (XGBoost). The second layer completes regression of functionality based on a support vector machine (SVM). Bayesian optimization and 5-fold cross-validation are employed for hyperparameter tuning of the ensemble model. Finally, the proposed model is validated using the Sioux-Falls bridge network. Results demonstrate that the developed model provides rapid predictions of post-earthquake network functionality and resilience. Additionally, this model can guide post-earthquake repair decisions and assist in optimizing the allocation of regional repair resources.

Innovative machine learning approaches for prediction of hypoglycemia in patients with type 2 Diabetes

Medical data science advances using machine learning, which predicts glucose levels. A supervised machine learning technique is employed in which regression and classification methods are used to check the prediction performance. The unsupervised machine learning technique makes clusters based on variables' similarities. Furthermore, the prediction accuracy of conventional machine learning techniques is improved by proposing a transfer learning technique. Based on a median value of 67 mg/dL, the data set is divided into two groups: group 1 (BSL 57 mg/dL to 67 mg/dL) has 50.67% of the samples, and group 2 (with BSL 68 mg/dL to 79 mg/dL) has 49.33% of the samples. In regression analysis, 5-fold cross-validation is performed. The decision tree (DT) and gradient boosting (GB) individually provide a prediction accuracy of 18.2%. Regarding classification analysis, a 10-fold cross-validation configuration is used for training and testing the model. AdaBoost, GB, random forest, and neural network achieve an accuracy rate of 66.3% and an area under curve (AUC) score of 0.731. In unsupervised learning, the datasets are divided into three clusters. The clustering result is used in regression and classification models using transfer learning. The accuracy and precision of the AdaBoost and GB are as follows: 69.6%, 0.696 with f1 0.661 and 69.6%, 0.708 with f1 0.708, respectively.

Multi-headed Ensemble Residual CNN: A Powerful Tool for Fibroblast Growth Factor Prediction

Fibroblast Growth Factor (FGF) performs a significant role in the repair, nervous system, development, and maintenance, making it a promising target for treating neurological diseases such as Parkinson's, stroke, Alzheimer's, and Huntington's disorders. However, the detection of FGF remains challenging due to the high cost and time required by traditional methods. To address this issue, we propose the first sequence-based computational method, FGF-MERCNN, for identifying FGFs using deep learning. Novel datasets were constructed by converting primary sequences into numerical representations through Enhanced Group Amino Acid Composition (EGAAC), Dipeptide Deviation from Expected Mean (DDE), and Group Tripeptide Composition (GTPC). These features were combined and analyzed using several deep learning models, including Convolutional Neural Networks (CNN), Multilayer Perceptrons (MLP), Gated Recurrent Units (GRU), and Multiheaded Ensemble Residual CNN (MERCNN). Among these, the MERCNN model achieved superior performance with accuracies of 88.60% on the training set and 83.68% on the test set, as validated by 5-fold cross-validation. The results of this study represent a significant advancement in FGF detection, offering a faster, cost-effective solution with the potential to improve diagnostic and therapeutic strategies for neurological diseases.

Prediction of Perceived Exertion Ratings in National Level Soccer Players Using Wearable Sensor Data and Machine Learning Techniques

This study aimed to identify relationships between external and internal load parameters with subjective ratings of perceived exertion (RPE). Consecutively, these relationships shall be used to evaluate different machine learning models and design a deep learning architecture to predict RPE in highly trained/national level soccer players. From a dataset comprising 5402 training sessions and 732 match observations, we gathered data on 174 distinct parameters, encompassing heart rate, GPS, accelerometer data and RPE (Borg’s 0-10 scale) of 26 professional male professional soccer players. Nine machine learning algorithms and one deep learning architecture was employed. Rigorous preprocessing protocols were employed to ensure dataset equilibrium and minimize bias. The efficacy and generalizability of these models were evaluated through a systematic 5-fold cross-validation approach. The deep learning model exhibited highest predictive power for RPE (Mean Absolute Error: 1.08 ± 0.07). Tree-based machine learning models demonstrated high-quality predictions (Mean Absolute Error: 1.15 ± 0.03) and a higher robustness against outliers. The strongest contribution to reducing the uncertainty of RPE with the tree-based machine learning models was maximal heart rate (determining 1.81% of RPE), followed by maximal acceleration (determining 1.48%) and total distance covered in speed zone 10-13 km/h (determining 1.44%). A multitude of external and internal parameters rather than a single variable are relevant for RPE prediction in highly trained/national level soccer players, with maximum heart rate having the strongest influence on RPE. The ExtraTree Machine Learning model exhibits the lowest error rates for RPE predictions, demonstrates applicability to players not specifically considered in this investigation, and can be run on nearly any modern computer platform.

High-resolution full-coverage ozone (O3) estimates using a data-driven spatial random forest model in Beijing-Tianjin-Hebei region, China

The Beijing-Tianjin-Hebei (BTH) region is severely polluted by ozone (O3). Accurate O3 estimates are essential for identifying high-polluted zones and developing targeted interventions to relieve the burden of diseases. Although many studies have estimated high-resolution O3 concentrations in BTH, the estimation accuracies are still insufficient. In this study, we incorporated data-driven spatial weight matrices (DDWs) into a random forest (RF) model to fully utilize both the spatial homogeneity and heterogeneity of maximum daily 8-h ozone concentration (MDA8O3), and obtained full-coverage MDA8O3 concentrations at 1km×1km in BTH from 2014 to 2022. DDW-RF exhibited satisfactory accuracy (10-fold cross-validation R2=0.937, RMSE=13.919 μg/m3). Overall O3 level presented a spatial pattern of lower in the north and higher in the southeast and showed a distinct temporal trend, i.e., first increasing and then decreasing during 2014-2021 and increasing slightly in 2022. The accurate MDA8O3 estimates indicates that more attention and resources should be poured into the areas adjacent to Bohai Rim, Shandong and Henan. Regulated operation of factories under specific meteorological conditions and upgrading industrial structure and production modes are recommended to mitigate the formation of O3 precursors and reduce O3 generation. Our findings provide evidence and reference for environmental cleaning policies and targeted interventions.

Transcriptome signature for multiple biotic and abiotic stress in barley (Hordeum vulgare L.) identifies using machine learning approach

Barley (Hordeum vulgare L.) is exposed to various biotic and abiotic stresses, making it crucial to fully understand the gene signatures that respond to stress. This study utilizes machine learning to analyze transcriptomic data from 515 RNA-seq profiles across 18 independent studies, covering eleven abiotic and three biotic stress types. Through meticulous data preprocessing, including quality assessment and batch effect correction, we have identified 4,311 genes for further analysis. Feature selection was performed using five weighting algorithms, resulting in the prioritization of 400 core genes. Machine learning models, specifically Random Forest and C4.5, were optimized and evaluated using a 10-fold cross-validation approach. The C4.5 algorithm demonstrated superior accuracy in predicting stress-responsive signatures. Key genes, such as bHLH119 and E3 ubiquitin protein ligase DRIP2, were identified as potential biomarkers. Functional enrichment analysis, conducted through protein-protein interaction networks and Gene Ontology/KEGG pathway analysis, has revealed significant involvement in lipid biosynthesis, signal transduction, and defense response processes. These findings highlight the crucial roles of the identified biomarkers genes in barley's resilience to stress and provide potential targets for genetic improvement. Future research should focus on validating these biomarkers in different barley cultivars and under field conditions to enhance crop resilience against stressors.

STQD-Det: Spatio-Temporal Quantum Diffusion Model for Real-Time Coronary Stenosis Detection in X-Ray Angiography.

Detecting coronary stenosis accurately in X-ray angiography (XRA) is important for diagnosing and treating coronary artery disease (CAD). However, challenges arise from factors like breathing and heart motion, poor imaging quality, and the complex vascular structures, making it difficult to identify stenosis fast and precisely. In this study, we proposed a Quantum Diffusion Model with Spatio-Temporal Feature Sharing to Real-time detect Stenosis (STQD-Det). Our framework consists of two modules: Sequential Quantum Noise Boxes module and spatio-temporal feature module. To evaluate the effectiveness of the method, we conducted a 4-fold cross-validation using a dataset consisting of 233 XRA sequences. Our approach achieved the F1 score of 92.39% with a real-time processing speed of 25.08 frames per second. These results outperform 17 state-of-the-art methods. The experimental results show that the proposed method can accomplish the stenosis detection quickly and accurately.

Enhancing Cardiovascular Disease Prediction Accuracy through an Ensemble Machine Learning Approach

This study explores the efficacy of an ensemble machine learning approach, specifically a Voting Classifier combining Decision Tree, k-Nearest Neighbors, and Gaussian Naive Bayes classifiers, in predicting cardiovascular diseases (CVDs). Utilizing a dataset consisting of 70,000 clinical records, the model was rigorously tested through 5-fold cross-validation, achieving remarkable results with average accuracies, precision, recall, and F1-scores all exceeding 99%. The findings validate the hypothesis that ensemble models, due to their capacity to leverage multiple learning algorithms, provide superior prediction accuracy and reliability compared to single predictor models. This research not only confirms the effectiveness of ensemble methods in medical diagnostics but also highlights their potential to enhance decision-making in clinical settings. Given the model's success in identifying various stages of cardiovascular conditions with high accuracy, it offers significant implications for early intervention and personalized patient management. Future research should aim to validate these results across more diverse populations and explore the integration of additional predictive factors that could refine the model's applicability. This study contributes to the computational health field by demonstrating how advanced machine learning techniques can be effectively applied in predicting health outcomes.

Classification of Skin Diseases using Decision Tree Algorithm on an Imbalanced Dataset

Skin infections caused by pathogens such as bacteria and fungi are common and can lead to serious health complications if not properly managed. Accurate classification of these infections is crucial for effective treatment and management. This study focuses on classifying two skin diseases, Chickenpox and Shingles, using a Decision Tree algorithm applied to an imbalanced dataset sourced from Kaggle. The dataset, which is imbalanced by nature, was split into training (80%) and testing (20%) subsets. Pre-processing involved segmentation using Thresholding to isolate regions of interest and feature extraction using Hu Moments to capture shape characteristics of the lesions. The dataset was scaled to ensure that all features had a mean of 0 and variance of 1. The classifier's performance was evaluated using 5-fold cross-validation, yielding a mean accuracy of 66.06%, with precision, recall, and F1-scores indicating moderate performance. The study highlights the challenges posed by imbalanced datasets and the limitations of the Decision Tree algorithm in this context. The results underscore the importance of proper pre-processing and feature extraction but also suggest the need for more advanced classification techniques and data balancing methods. This research contributes to the field by providing a detailed methodology and comprehensive evaluation metrics, offering insights into the application of machine learning for medical image classification. Future work should focus on improving classifier performance through data augmentation, advanced feature extraction, and exploring other machine learning models better suited for imbalanced datasets.

Feature Extraction and Classification of Retinal Images Using Sobel Segmentation and Linear SVC

Eye diseases such as Diabetic Retinopathy, Cataract, and Glaucoma are significant causes of visual impairment and blindness worldwide. Early detection and accurate diagnosis are crucial for effective treatment and management of these conditions. This study aimed to develop a machine learning model for the automated classification of retinal images into four categories: Normal, Diabetic Retinopathy, Cataract, and Glaucoma. The dataset, sourced from Kaggle, comprised approximately 1000 images per class, which were pre-processed using Sobel segmentation to enhance relevant features. Hu Moments were employed for feature extraction due to their invariance to scale, rotation, and translation. The classification was performed using a Linear Support Vector Classifier (SVC), and the model's performance was evaluated through 5-fold cross-validation. The average performance metrics were 44.34% for accuracy, 48.26% for precision, 44.34% for recall, and 41.76% for F1-score. These results indicate that while Sobel segmentation and Hu Moments effectively highlight and capture essential features of retinal images, the Linear SVC classifier's performance is moderate, suggesting the need for more advanced classifiers. The study's findings contribute to the ongoing research in automated eye disease diagnosis by demonstrating the strengths and limitations of classical image processing and machine learning techniques. Future research should focus on exploring more sophisticated models, such as convolutional neural networks, and addressing dataset imbalances to enhance classification accuracy and reliability. This study underscores the potential for automated diagnostic tools in clinical settings but also highlights the necessity for further optimization to achieve practical applicability.

Classification of Pseudopapilledema and Papilledema Using Decision Tree and Hu Moments

Pseudopapilledema, characterized by an anomalous elevation of the optic disc without retinal nerve fiber layer edema, often mimics the presentation of true papilledema caused by increased intracranial pressure. Accurate differentiation between these conditions is critical to avoid unnecessary invasive procedures. This study employs a Decision Tree classifier to classify optic disc images into three categories: normal, papilledema, and pseudopapilledema. The dataset, obtained from Kaggle, consists of imbalanced images segmented using the Canny edge detection method and features extracted using Hu Moments. The dataset was divided into 80% training and 20% testing sets. Performance was evaluated using 5-fold cross-validation, yielding an average accuracy of 53.61%, precision of 55.20%, recall of 54.12%, and F1-score of 55.17%. The study provides a comprehensive analysis of the classifier's performance, including visualizations such as segmentation results, scatter plots of Hu Moments, and confusion matrices. The results indicate that while the Decision Tree classifier demonstrates moderate effectiveness, there is significant room for improvement. The research highlights the potential of machine learning models in medical diagnostics but also underscores the need for more robust algorithms and diverse datasets. Future work should focus on incorporating more complex models and expanding the dataset to enhance diagnostic accuracy. These findings contribute to the field of medical image analysis and propose a non-invasive diagnostic tool that, when integrated with clinical expertise, could improve patient outcomes and reduce unnecessary procedures

Optimizing Cardiomegaly Detection: A Random Forest Approach to Processed Chest X-ray Imagery

This study explores the application of a Random Forest Classifier for the automated detection of Cardiomegaly from chest X-ray images, utilizing a dataset processed and derived from the NIH Chest X-ray Dataset. Given the crucial need for accurate and timely diagnosis of Cardiomegaly to inform appropriate treatment decisions, this research aims to determine the efficacy of machine learning models in augmenting diagnostic processes. Employing image pre-processing techniques such as Sobel filtering for edge detection and Hu Moments for feature extraction, the study enhances the input features for the model. The performance of the classifier was evaluated using a 5-fold cross-validation approach, yielding results with average accuracy, precision, recall, and F1-scores ranging approximately between 52% and 54%. These findings suggest a moderate level of reliability and consistency, indicating the potential utility of ensemble machine learning methods in medical imaging analysis. However, the variability in performance across different data subsets highlights the challenges and necessitates further optimization. This research contributes to the ongoing discourse on integrating machine learning into clinical settings, demonstrating the potential benefits and current limitations. Future research is recommended to expand the dataset variety, integrate advanced deep learning methodologies, and rigorously test these models in clinical environments. The findings hold significant implications for the development of automated diagnostic tools in healthcare, potentially leading to enhanced diagnostic accuracy and efficiency.

Retinal imaging based glaucoma detection using modified pelican optimization based extreme learning machine

Glaucoma is defined as progressive optic neuropathy that damages the structural appearance of the optic nerve head and is characterized by permanent blindness. For mass fundus image-based glaucoma classification, an improved automated computer-aided diagnosis (CAD) model performing binary classification (glaucoma or healthy), allowing ophthalmologists to detect glaucoma disease correctly in less computational time. We proposed learning technique called fast discrete curvelet transform with wrapping (FDCT-WRP) to create feature set. This method is entitled extracting curve-like features and creating a feature set. The combined feature reduction techniques named as principal component analysis and linear discriminant analysis, have been applied to generate prominent features and decrease the feature vector dimension. Lastly, a newly improved learning algorithm encompasses a modified pelican optimization algorithm (MOD-POA) and an extreme learning machine (ELM) for classification tasks. In this MOD-POA+ELM algorithm, the modified pelican optimization algorithm (MOD-POA) has been utilized to optimize the parameters of ELM’s hidden neurons. The effectiveness has been evaluated using two standard datasets called G1020 and ORIGA with the \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$10 \ imes 5$$\\end{document}-fold stratified cross-validation technique to ensure reliable evaluation. Our employed scheme achieved the best results for both datasets obtaining accuracy of 93.25% (G1020 dataset) and 96.75% (ORIGA dataset), respectively. Furthermore, we have utilized seven Explainable AI methodologies: Vanilla Gradients (VG), Guided Backpropagation (GBP ), Integrated Gradients ( IG), Guided Integrated Gradients (GIG), SmoothGrad, Gradient-weighted Class Activation Mapping (GCAM), and Guided Grad-CAM (GGCAM) for interpretability examination, aiding in the advancement of dependable and credible automation of healthcare detection of glaucoma.

AI-Driven Predictive Models for Sustainability

This research presents an AI-driven, explainable energy management model that aligns with Net Zero sustainability objectives by optimizing energy consumption, enhancing predictive accuracy, and ensuring transparency. The model integrates machine learning algorithms, including Gradient Boosting Machines and Random Forests, and utilizes techniques like SHAP and LIME for interpretability. Data was split 70/30 for training and validation, with 10-fold cross-validation to prevent overfitting, achieving a Mean Absolute Error (MAE) of 1.26-1.53 and Root Mean Squared Error (RMSE) of 1.97-2.06. The model's predictive accuracy reached an R2 of 0.92, with precision and recall scores of 85-90% and 80-88%, respectively, demonstrating significant improvements over traditional methods. Sensitivity analysis revealed high influence from temperature and historical consumption data, requiring careful monitoring. This model performed robustly across diverse scenarios, reducing CO₂ emissions by 30% and cutting costs by 18%, highlighting its adaptability in real-world applications. Conclusions affirm that the explainable AI model advances sustainable energy management by providing reliable, actionable insights, aligning with Net Zero goals, and supporting informed decision-making through enhanced transparency and accuracy.

Correlation analysis and recurrence evaluation system for patients with recurrent hepatolithiasis: a multicentre retrospective study

BackgroundMethods for accurately predicting the prognosis of patients with recurrent hepatolithiasis (RH) after biliary surgery are lacking. This study aimed to develop a model that dynamically predicts the risk of hepatolithiasis recurrence using a machine-learning (ML) approach based on multiple clinical high-order correlation data.Materials and methodsData from patients with RH who underwent surgery at five centres between January 2015 and December 2020 were collected and divided into training and testing sets. Nine predictive models, which we named the Correlation Analysis and Recurrence Evaluation System (CARES), were developed and compared using machine learning (ML) methods to predict the patients’ dynamic recurrence risk within 5 post-operative years. We adopted a k-fold cross validation with k = 10 and tested model performance on a separate testing set. The area under the receiver operating characteristic curve was used to evaluate the performance of the models, and the significance and direction of each predictive variable were interpreted and justified based on Shapley Additive Explanations.ResultsModels based on ML methods outperformed those based on traditional regression analysis in predicting the recurrent risk of patients with RH, with Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) showing the best performance, both yielding an AUC (Area Under the receiver operating characteristic Curve) of∼0.9 or higher at predictions. These models were proved to have even better performance on testing sets than in a 10-fold cross validation, indicating that the model was not overfitted. The SHAP method revealed that immediate stone clearance, final stone clearance, number of previous surgeries, and preoperative CA19-9 index were the most important predictors of recurrence after reoperation in RH patients. An online version of the CARES model was implemented.ConclusionThe CARES model was firstly developed based on ML methods and further encapsulated into an online version for predicting the recurrence of patients with RH after hepatectomy, which can guide clinical decision-making and personalised postoperative surveillance.

Development and Validation of a Prediction Model Using Sella Magnetic Resonance Imaging–Based Radiomics and Clinical Parameters for the Diagnosis of Growth Hormone Deficiency and Idiopathic Short Stature: Cross-Sectional, Multicenter Study

Background Growth hormone deficiency (GHD) and idiopathic short stature (ISS) are the major etiologies of short stature in children. For the diagnosis of GHD and ISS, meticulous evaluations are required, including growth hormone provocation tests, which are invasive and burdensome for children. Additionally, sella magnetic resonance imaging (MRI) is necessary for assessing etiologies of GHD, which cannot evaluate hormonal secretion. Recently, radiomics has emerged as a revolutionary technique that uses mathematical algorithms to extract various features for the quantitative analysis of medical images. Objective This study aimed to develop a machine learning–based model using sella MRI–based radiomics and clinical parameters to diagnose GHD and ISS. Methods A total of 293 children with short stature who underwent sella MRI and growth hormone provocation tests were included in the training set, and 47 children who met the same inclusion criteria were enrolled in the test set from different hospitals for this study. A total of 186 radiomic features were extracted from the pituitary glands using a semiautomatic segmentation process for both the T2-weighted and contrast-enhanced T1-weighted image. The clinical parameters included auxological data, insulin-like growth factor-I, and bone age. The extreme gradient boosting algorithm was used to train the prediction models. Internal validation was conducted using 5-fold cross-validation on the training set, and external validation was conducted on the test set. Model performance was assessed by plotting the area under the receiver operating characteristic curve. The mean absolute Shapley values were computed to quantify the impact of each parameter. Results The area under the receiver operating characteristic curves (95% CIs) of the clinical, radiomics, and combined models were 0.684 (0.590-0.778), 0.691 (0.620-0.762), and 0.830 (0.741-0.919), respectively, in the external validation. Among the clinical parameters, the major contributing factors to prediction were BMI SD score (SDS), chronological age–bone age, weight SDS, growth velocity, and insulin-like growth factor-I SDS in the clinical model. In the combined model, radiomic features including maximum probability from a T2-weighted image and run length nonuniformity normalized from a T2-weighted image added incremental value to the prediction (combined model vs clinical model, P=.03; combined model vs radiomics model, P=.02). The code for our model is available in a public repository on GitHub. Conclusions Our model combining both radiomics and clinical parameters can accurately predict GHD from ISS, which was also proven in the external validation. These findings highlight the potential of machine learning–based models using radiomics and clinical parameters for diagnosing GHD and ISS.

Models reveal shifting distribution of climatic suitability for pawpaw (Asimina triloba [L.] Dunal) cultivation under future climate change scenarios

The pawpaw (Asimina triloba [L.] Dunal) is a deciduous tree notable for its large edible fruit. Native to the eastern US and Canada, it has earned attention as a horticultural commodity and focus of scientific inquiry. However, few studies have modeled its potential future distribution under climate change. This study predicted the current and future potential distribution for pawpaw in North America and globally, with a focus on understanding future climatic suitability for fruit cultivation. This study first modeled suitability via the Maximum Entropy (MaxEnt) method by relating climate predictors with different datasets on pawpaw distribution, including nursery locations growing pawpaw. It also trained a boosted regression tree (BRT) model to estimate where sufficient heat accumulation for fruit ripening would occur. The models were applied to two future times (2041–2060 and 2081–2100), four emissions scenarios (SSP126, SSP245, SSP370, and SSP585), and climate projections from three climate models. Using nursery locations, the MaxEnt model yielded a mean area-under-the-curve statistic of 0.978 (standard deviation = 0.009) using 10-fold cross-validation, indicating strong predictive performance. The model suggested optimal conditions for pawpaw at these values: -4 °C for minimum temperature of coldest month, 26 °C for maximum temperature of warmest month, 88 cm for annual precipitation, and 0 % for precipitation seasonality. Models suggested shifting suitable climate conditions and accompanying increases in heat accumulation for fruit ripening. Northern America, Eastern Europe, and Northern Europe were predicted to have higher and increasing suitability; Western Europe, Southern Europe, and Eastern Asia were predicted to have higher but decreasing suitability. Little uncertainty existed due to collinearity shift or dissimilarity between current and future climate, but more uncertainty existed when predictions were based on differing climate model projections. This study provides insight into the pawpaw's potential response to climate change, and guidance on future locations for cultivation.

Machine learning models for coagulation dysfunction risk in inpatients administered β-lactam antibiotics

The β-Lactam antibiotics represent a widely used class of antibiotics, yet the latent and often overlooked risk of coagulation dysfunction associated with their use underscores the need for proactive assessment. Machine learning methodologies can offer valuable insights into evaluating the risk of coagulation dysfunction associated with β-lactam antibiotics. This study aims to identify the risk factors associated with coagulation dysfunction related to β-lactam antibiotics and to develop machine learning models for estimating the risk of coagulation dysfunction with real-world data. A retrospective study was performed using machine learning modeling analysis on electronic health record data, employing five distinct machine learning methods. The study focused on adult inpatients discharged from 1 January 2018, to 31 December 2021, at the First Affiliated Hospital of Shandong First Medical University. The models were developed for estimating the risk of coagulation dysfunction associated with various β-lactam antibiotics based on electronic health record feasibility. The dataset was divided into training and test sets to assess model performance using metrics such as total accuracy and area under the curve. The study encompassed risk-factor analysis and machine learning model development for coagulation dysfunction in inpatients administered different β-lactam antibiotics. A total of 45,179 participants were included in the study. The incidence of coagulation disorders related to cefazolin sodium, cefoperazone/sulbactam sodium, cefminol sodium, amoxicillin/sulbactam sodium, and piperacillin/tazobactam sodium was 2.4%, 5.4%, 1.5%, 5.5%, and 4.8%, respectively. Machine learning models for estimating coagulation dysfunction associated with each β-lactam antibiotic underwent validation with 5-fold cross-validation and test sets. On the test set, the optimal models for cefazolin sodium, cefoperazone/sulbactam sodium, cefminol sodium, amoxicillin/sulbactam sodium, and piperacillin/tazobactam sodium yielded AUC values of 0.798, 0.768, 0.919, 0.783, and 0.867, respectively. The study findings suggest that machine learning classifiers can serve as valuable tools for identifying patients at risk of coagulation dysfunction associated with β-lactam antibiotics and intervening based on high-risk predictions. Enhanced access to administrative and clinical data could further enhance the predictive performance of machine learning models, thereby expanding pharmacovigilance efforts.