Leave-one-out Cross-validation Research Articles

Exploring low- and high-order functional connectivity in chronic ankle instability through resting-state fMRI.

The functional connectivity (FC) has emerged as a valuable tool for comprehending the cerebral operational mechanism. Understanding the FC changes in patients with chronic ankle instability (CAI) helps reveal the underlying central nervous system mechanisms of the disease and provides clues for developing personalized treatment plans. To explore differences between low- and high-order FC in patients with CAI and healthy controls, as well as the correlation among the feature connections and clinical data. In our study, we recruited 40 patients with CAI and 42 healthy individuals who had not experienced ankle injuries. All participants underwent clinical assessments of ankle joints, collected the number of ankle sprains within the past 6 months, and performed resting-state functional magnetic resonance imaging (rs-fMRI) scans. Pearson correlation and matrix variate normal distribution (MVND) were used to construct low-order and high-order FC networks, respectively. Feature selections between groups were performed by two-sample t-tests, and a multi-kernel support vector machine (MK-SVM) was subsequently applied to combine the multiple connection patterns for the classification. Using leave-one-out cross-validation (LOOCV) to assess classification performance and identify the consensus connections contributing most to classification. FC was reduced in certain brain regions of CAI patients. More consensus connections were recognized in low-order FC network than in high-order FC network. The highest classification accuracy of 91.30% was achieved by combining three connection patterns. The most discriminating functional connections were primarily centered on the default mode network and spanned the visual network, sensorimotor network, ventral attention network, and central executive network. In addition, FC strength in the left cingulate and paracingulate gyrus (DCG.L) and right superior temporal gyrus (STG.R) was negatively correlated with the number of ankle sprains in the past 6 months in all FC networks (p<0.05). Abnormalities in connectivity in patients with CAI were observed in both low- and high-order FC networks. The adaptive changes in the brain related to CAI may extend beyond the sensorimotor networks, primarily involving higher-level default mode networks associated with attention. Moreover, the FC strength between DCG.L and STG.R may predict the risk of ankle re-sprains and help clinicians develop personalized treatment plans.

Exploring Nonlinear Correlations Among Transition Metal Nanocluster Properties Using Deep Learning: A Comparative Analysis with LOO-CV Method and Cosine Similarity.

A novel approach is introduced for the rapid and accurate correlation analysis of nonlinear properties in Transition Metal (TM) clusters utilizing the Deep Leave-One-Out Cross-Validation (LOO-CV) echnique.This investigation demonstrates that the Deep Neural Network (DNN)-based approach offers a more efficient predictive method for various properties of fourth-row TM nanoclusters compared to conventional Density Functional Theory (DFT) methods, which are computationally intensive and time-consuming.The feature space, also known as descriptors, is established based on a broad spectrum of electronic and physical characteristics. Leveraging the similarities among these clusters, the DNN-based model is employed to explore the correlations among TM cluster properties.The proposed method, in conjunction with cosine similarity, achieves remarkable accuracy up to 10-9 for predicting total energy, lowest vibrational mode, binding energy, and HOMO-LUMO energy gap of TM2, TM3, and TM4 nanoclusters. By analyzing corre lation errors, the most closely coupled TM clusters are identified. Notably, Mn and Ni clusters exhibit the highest and lowest levels of energy coupling with other transition metals, respectively. Generally, energy prediction for TM2, TM3, and TM4 clusters exhibit similar trends, while an alternating behavior is observed for vibrational modes and binding energies. Furthermore, Ti, V, and Co demonstrate the highest binding energy correlations with TM2, TM3, and TM4 sets, respectively. Regarding energy gap predictions, Ni ex hibits the strongest correlation in the smallest TM2 clusters, while Cr shows the highest dependence in TM3 and TM4 sets. Lastly, Zn displays the largest error in HOMO-LUMO energy gap across all sets, indicating distinctive independent energy gap characteristics.

Integrating anoikis and ErbB signaling insights with machine learning and single-cell analysis for predicting prognosis and immune-targeted therapy outcomes in hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) poses a significant global health challenge due to its poor prognosis and limited therapeutic modalities. Anoikis and ErbB signaling pathways are pivotal in cancer cell proliferation and metastasis, but their relevance in HCC remains insufficiently explored. This study evaluates the prognostic significance of anoikis and ErbB signaling pathways in HCC by utilizing data from The Cancer Genome Atlas (TCGA), the International Cancer Genome Consortium (ICGC), three additional independent validation cohorts, and an in-house cohort. Advanced bioinformatics analyses and 167 machine learning models based on leave-one-out cross-validation (LOOCV) were used to predict HCC prognosis and assess outcomes of immune-targeted therapies. Additionally, key biological processes of the anoikis and ErbB signaling pathways in HCC were further investigated. The single sample Gene Set Enrichment Analysis revealed a strong correlation between upregulated ErbB signaling in high anoikis-expressing tumors and poor clinical outcomes. The development of the Anoikis-ErbB Related Signature (AERS) using the LASSO + RSF model demonstrated robust predictive capabilities, as validated across multiple patient cohorts, and proved effective in predicting responses to immune-targeted therapies. Further investigation highlighted activated NOTCH signaling pathways and decreased macrophage infiltration was associated with resistance to sorafenib and immune checkpoint inhibitors, as evidenced by bulk and single-cell RNA sequencing (scRNA-seq). AERS provides a novel tool for clinical prognosis and paves the way for immune-targeted therapeutic approaches, underscoring the potential of integrated molecular profiling in enhancing treatment strategies for HCC.

Comparative Analysis of Cross-Validation Techniques: LOOCV, K-folds Cross-Validation, and Repeated K-folds Cross-Validation in Machine Learning Models

Effective model evaluation is crucial for robust machine learning, and cross-validation techniques play a significant role. This study compares Repeated k-folds Cross Validation, k-folds Cross Validation, and Leave-One-Out Cross Validation (LOOCV) on imbalanced and balanced datasets across four models: Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Random Forest (RF), and Bagging, both with and without parameter tuning. On imbalanced data without parameter tuning, Repeated k-folds cross-validation demonstrated strong performance for SVM with a sensitivity of 0.541 and balanced accuracy of 0.764. K-folds Cross Validation showed a higher sensitivity of 0.784 for RF and a balanced accuracy of 0.884. In contrast, LOOCV achieved notable sensitivity for RF and Bagging at 0.787 and 0.784, respectively, but at the cost of lower precision and higher variance, as detailed in Table 1. When parameter tuning was applied to balanced data, the performance metrics improved. Sensitivity for SVM reached 0.893 with LOOCV and balanced accuracy for Bagging increased to 0.895. Stratified k-folds provided enhanced precision and F1-Score for SVM and RF. Notably, processing times varied significantly, with k-folds being the most efficient with SVM taking 21.480 seconds and Repeated k-folds showing higher computational demands where RF took approximately 1986.570 seconds in model processing, as shown in Table 4. This analysis underscores that while k-folds and repeated k-folds are generally efficient, LOOCV and balanced approaches offer enhanced accuracy for specific models but require greater computational resources. The choice of cross-validation technique should thus be tailored to the dataset characteristics and computational constraints to ensure optimal model evaluation.

GCNPMDA: Human microbe-disease association prediction by hierarchical graph convolutional network with layer attention

Microorganisms play a crucial role in various physiological processes, including metabolism, immune defense, nutrition absorption, defense against cancer, and protection against pathogen colonization. Changes in microbial communities serve as potential biomarkers for diseases, offering significant insights into disease treatment and diagnosis. However, the association between microorganisms and diseases is still unclear, and more computational methods are needed to predict potential associations. In this paper, we introduce a novel computational model, the Graph Convolutional Network to Predict Microbe-Disease Associations (GCNPMDA), which employs layer attention mechanisms (see Figure 1). GCNPMDA integrates known microbe-disease associations, microbe–microbe similarities, and disease–disease similarities into a heterogeneous network. The model utilizes a Graph Convolutional Network (GCN) to learn embeddings for diseases and microbes. To enhance attribute information, microbe–microbe similarities are computed using Cosine similarity, Jaccard similarity, Gaussian kernel, and functional information, while disease–disease similarities are computed using Cosine similarity, Jaccard similarity, Gaussian kernel, and symptom information. Additionally, attention mechanisms are applied to combine embeddings from multiple graph convolution layers. The model’s predictive effectiveness is evaluated on Human Microbe-Disease Association Database (HMDAD). Leave-one-out cross-validation (LOOCV) was conducted. The Area Under ROC Curve (AUC) of LOOCV is 0.98. The 5-fold cross-validation (5-fold CV) on HMDAD yields average AUC of 0.98 ± 0.009. Furthermore, we carried out a case study of type 2 diabetes (T2D), inflammatory bowel disease (IBD), and rheumatoid arthritis. Based on existing literature evidence, it was confirmed that 6, 7, and 7 of the top-10 inferred microbes have established associations with T2D, IBD, and rheumatoid arthritis, respectively. GCNPMDA demonstrates potential efficacy in identifying disease-related microbes, offering a promising tool to uncover the intricate relationship between microorganisms and their human hosts.

Development of land use regression, dispersion, and hybrid models for prediction of outdoor air pollution exposure in Barcelona

BackgroundAir pollution is the leading environmental risk factor for health. Assessing outdoor air pollution exposure with detailed spatial and temporal variability in urban areas is crucial for evaluating its health effects. Aim: We developed and compared Land Use Regression (LUR), dispersion (DM), and hybrid (HM) models to estimate outdoor concentrations for NO2, PM2.5, black carbon (BC), and PM2.5-constituents (Fe, Cu, Zn) in Barcelona. MethodsTwo monitoring campaigns were conducted. In the first, NO2 concentrations were measured twice at 984 home addresses and in the second, NO2, PM2.5, and BC were measured four times at 34 points across Barcelona. LUR and DM were constructed using conventional techniques, while HM was developed using Random Forest (RF). Model performance was evaluated using leave-one-out cross-validation (LOOCV) and 10-fold cross-validation (10-CV) for LUR and HM, and by comparing DM and LUR estimates with routine monitoring stations. NO2 levels estimated by all models were externally validated using the home monitoring campaign. Agreement between models was assessed using Spearman correlation (rs) and Bland-Altman (BA) plots. ResultsModels showed moderate to good performance. LUR exhibited R2LOOCV of 0.62 (NO2), 0.45 (PM2.5), 0.83 (BC), and 0.85 to 0.89 (PM2.5-constituents). DM model comparison showed R2 values of 0.39 (NO2), 0.26 (PM2.5), and 0.65 (BC). HM models had higher R210-CV 0.64 (NO2), 0.66 (PM2.5), 0.86 (BC), and 0.44 to 0.70 (PM2.5-constituents). Validation for NO2 showed R2 values of 0.56 (LUR), 0.44 (DM), and 0.64 (HM). Correlations between models varied from −0.38 to 0.92 for long-term exposure, and − 0.23 to 0.94 for short-term exposure. BA plots showed good agreement between models, especially for NO2 and BC. ConclusionsOur models varied substantially, with some models performing better in validation samples (NO2 and BC). Future health studies should use the most accurate methods to minimize bias from exposure measurement error.

Predicting Disease Progression in Inoperable Localized NSCLC Patients Using ctDNA Machine Learning Model.

There is an urgent clinical need to accurately predict the risk for disease progression in post-treatment NSCLC patients, yet current ctDNA mutation profiling approaches are limited by low sensitivity. We represent a non-invasive liquid biopsy assay utilizing cfDNA neomer profiling for predicting disease progression in 44 inoperable localized NSCLC patients. A total of 97 plasma samples were collected at various time points during or post-treatments (TP1: 39, TP2: 33, TP3: 25). cfDNA neomer profiling, generated based on target sequencing data, was used to fit survival support vector machine models for each time point. Leave-one-out cross-validation (LOOCV) was performed to evaluate the models' predictive performances. Our cfDNA neomer profiling assay showed excellent performance in detecting patients with a high risk for disease progression. At TP1, the high-risk patients detected by our model showed an increased risk of 3.62 times (hazard ratio [HR] = 3.62, p = 0.0026) for disease progression, compared to 3.91 times (HR = 3.91, p = 0.0022) and 4.00 times (HR = 4.00, p = 0.019) for TP2 and TP3. These neomer profiling determined HRs were higher than the ctDNA mutation-based results (HR = 2.08, p = 0.074; HR = 1.49, p&amp;#x02009;=&amp;#x02009;0.61) at TP1 and TP3. At TP1, the predictive model reached 40% sensitivity at 92.9% specificity, outperforming the mutation-based method (40% sensitivity at 78.6% specificity), while the combination results reached a higher sensitivity (60%). Finally, the longitudinal analysis showed that the combination of neomer and ctDNA mutation-based results could predict disease progression with an excellent sensitivity of 88.9% at 80% specificity. In conclusion, we developed a cfDNA neomer profiling assay for predicting disease progression in inoperable NSCLC patients. This assay showed increased predicting power during and post-treatment compared to the ctDNA mutation-based method, thus illustrating a great clinical potential to guide treatment decisions in inoperable NSCLC patients. ClinicalTrials.gov: NCT04014465.

Comparison of feature learning methods for non-invasive interstitial glucose prediction using wearable sensors in healthy cohorts: a pilot study

BackgroundAlterations in glucose metabolism, especially the postprandial glucose response (PPGR), are crucial contributors to metabolic dysfunction, which underlies the pathogenesis of metabolic syndrome (MetSyn). Personalized low-glycemic diets (PLGD) have shown promise in reducing postprandial glucose spikes. However, current methods such as invasive continuous glucose monitoring (CGM) or multi-omics data integration to assess PPGR come with limitations, including cost and invasiveness, hindering widespread adoption in primary disease prevention. Our aim is to assess machine-learning algorithms for predicting individual PPGR using non-invasive wearable data, thereby circumventing the limitations associated with existing approaches. By identifying the most accurate model, we seek to provide a more accessible and efficient method for managing glucose metabolism. MethodsThis data-driven analysis utilized the experimental dataset from the SENSE (”Systemische Ernährungsmedizin”) study. Healthy participants used an Empatica E4 wristband and Abbott Freestyle Libre 3 CGM for ten days. Blood volume pulse (BVP), electrodermal activity (EDA), heart rate (HR), skin temperature (TEMP), and the corresponding CGM values were measured. Subsequently, four data-driven deep learning (DL) model-convolutional neural network (CNN), lightweight transformer (LTF), long short-term memory with attention (LSTM-A), and Bi-directional LSTM (BiLSTM)-were implemented and compared to determine the potential of DL in predicting interstitial glucose levels without involving food and activity logs. ResultsThe proposed BiLSTM achieved the best interstitial glucose prediction performance, with an average root mean squared error (RMSE) of 13.42 mg/dL, an average mean absolute percentage error (MAPE) of 0.12, and only 3.01% values falling within area D in Clarke error grid analysis (CEGA), incorporating the leave-one-out cross-validation (LOOCV) strategy for a five-minute prediction horizon. ConclusionThe findings of this study may demonstrate the feasibility of transferring knowledge gained from invasive glucose monitoring devices to non-invasive approaches. Furthermore, it emphasizes the promising prospects of combining deep learning with wearable technologies to predict glucose levels in healthy individuals.

Emergency Vehicle Classification Using Combined Temporal and Spectral Audio Features with Machine Learning Algorithms

This study presents a novel approach to emergency vehicle classification that leverages a comprehensive set of informative audio features to distinguish between ambulance sirens, fire truck sirens, and traffic noise. A unique contribution lies in combining time domain features, including root mean square (RMS) and zero-crossing rate, to capture the temporal characteristics, like signal energy changes, with frequency domain features derived from short-time Fourier transform (STFT). These include spectral centroid, spectral bandwidth, and spectral roll-off, providing insights into the sound’s frequency content for differentiating siren patterns from traffic noise. Additionally, Mel-frequency cepstral coefficients (MFCCs) are incorporated to capture the human-like auditory perception of the spectral information. This combination captures both temporal and spectral characteristics of the audio signals, enhancing the model’s ability to discriminate between emergency vehicles and traffic noise compared to using features from a single domain. A significant contribution of this study is the integration of data augmentation techniques that replicate real-world conditions, including the Doppler effect and noise environment considerations. This study further investigates the effectiveness of different machine learning algorithms applied to the extracted features, performing a comparative analysis to determine the most effective classifier for this task. This analysis reveals that the support vector machine (SVM) achieves the highest accuracy of 99.5%, followed by random forest (RF) and k-nearest neighbors (KNNs) at 98.5%, while AdaBoost lags at 96.0% and long short-term memory (LSTM) has an accuracy of 93%. We also demonstrate the effectiveness of a stacked ensemble classifier, and utilizing these base learners achieves an accuracy of 99.5%. Furthermore, this study conducted leave-one-out cross-validation (LOOCV) to validate the results, with SVM and RF achieving accuracies of 98.5%, followed by KNN and AdaBoost, which are 97.0% and 90.5%. These findings indicate the superior performance of advanced ML techniques in emergency vehicle classification.

CMFHMDA: a prediction framework for human disease-microbe associations based on cross-domain matrix factorization.

Predicting associations between microbes and diseases opens up new avenues for developing diagnostic, preventive, and therapeutic strategies. Given that laboratory-based biological tests to verify these associations are often time-consuming and expensive, there is a critical need for innovative computational frameworks to predict new microbe-disease associations. In this work, we introduce a novel prediction algorithm called Predicting Human Disease-Microbe Associations using Cross-Domain Matrix Factorization (CMFHMDA). Initially, we calculate the composite similarity of diseases and the Gaussian interaction profile similarity of microbes. We then apply the Weighted K Nearest Known Neighbors (WKNKN) algorithm to refine the microbe-disease association matrix. Our CMFHMDA model is subsequently developed by integrating the network data of both microbes and diseases to predict potential associations. The key innovations of this method include using the WKNKN algorithm to preprocess missing values in the association matrix and incorporating cross-domain information from microbes and diseases into the CMFHMDA model. To validate CMFHMDA, we employed three different cross-validation techniques to evaluate the model's accuracy. The results indicate that the CMFHMDA model achieved Area Under the Receiver Operating Characteristic Curve scores of 0.9172, 0.8551, and 0.9351$\pm $0.0052 in global Leave-One-Out Cross-Validation (LOOCV), local LOOCV, and five-fold CV, respectively. Furthermore, many predicted associations have been confirmed by published experimental studies, establishing CMFHMDA as an effective tool for predicting potential disease-associated microbes.

Prediction of Human Microbe-Drug Association based on Layer Attention Graph Convolutional Network.

In this paper, we have proposed a novel model of layer attention graph convolutional network for microbe-drug association prediction. First, multiple biological data have been integrated into a heterogeneous network. Then, the heterogeneous network has been incorporated into a graph convolutional network to determine the embedded microbe and drug. Finally, the microbe-drug association scores have been obtained by decoding the embedding of microbe and drug based on the layer attention mechanism. To evaluate the performance of our proposed model, leave-one-out crossvalidation (LOOCV) and 5-fold cross-validation have been implemented on the two datasets of aBiofilm and MDAD. As a result, based on the aBiofilm dataset, our proposed model has attained areas under the curve (AUC) of 0.9178 and 0.9022 on global LOOCV and local LOOCV, respectively. Based on aBiofilm dataset, the proposed model has attained an AUC value of 0.9018 and 0.8902 on global LOOCV and local LOOCV, respectively. In addition, the average AUC and standard deviation of the proposed model for 5- fold cross-validation on the aBiofilm and MDAD datasets were 0.9141±6.8556e-04 and 0.8982±7.5868e-04, respectively. Also, two kinds of case studies have been further conducted to evaluate the proposed models. Traditional methods for microbe-drug association prediction are timeconsuming and laborious. Therefore, the computational model proposed was used to predict new microbe-drug associations. Several evaluation results have shown the proposed model to achieve satisfactory results and that it can play a role in drug development and precision medicine.

Predicting axillary lymph node metastasis in breast cancer based on ultrasound radiofrequency time-series analysis.

The status of axillary lymph nodes (ALN) plays a critical role in the management of patients with breast cancer. It is an urgent demand to develop highly accurate, non-invasive methods for predicting ALN status. To evaluate the efficacy of ultrasound radiofrequency (URF) time-series parameters, in combination with clinical data, in predicting ALN metastasis in patients with breast cancer. We prospectively gathered clinicopathologic and ultrasonic data from patients diagnosed with breast cancer. Various machine-learning (ML) models were developed using all available features to determine the most efficient diagnostic model. Subsequently, distinct prediction models were created using the optimal ML model, and their diagnostic performances were evaluated and compared. The study encompassed 240 patients, of whom 88 had lymph node metastases. A leave-one-out cross-validation (LOOCV) method was used to split the entire dataset into training and testing subsets. The random forest ML model outperformed the other algorithms, with an area under the curve (AUC) of 0.92. Prediction models based on clinical, ultrasonic, URF parameters, clinical + ultrasonic, clinical + URF, and ultrasonic + URF parameters had AUCs of 0.56, 0.79, 0.78, 0.90, 0.80, and 0.84, respectively, in the testing set. The comprehensive diagnostic model (clinical + ultrasonic + URF parameters) demonstrated strong diagnostic capability, with an AUC of 0.94 in the testing set, exceeding any single prediction model. The combined model (clinical + ultrasonic + URF parameters) could be used preoperatively to predict lymph node status, offering valuable input for the design of individualized surgical approaches.

Enhancing shear strength predictions of rocks using a hierarchical ensemble model

Shear strength (SS) parameters are essential for understanding the mechanical behavior of materials, particularly in geotechnical engineering and rock mechanics. This study proposes a novel hierarchical ensemble model (HEM) to predict SS parameters: cohesion (C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}) and angle of internal friction (φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document}). The HEM addresses the limitations of traditional machine learning models. Its performance was validated using leave-one-out cross-validation (LOOCV) and out-of-bag (OOB) evaluation methods. The model's accuracy was assessed with R-squared correlation (R2), absolute average relative error percentage (AAREP), Taylor diagrams, and quantile–quantile plots. The computational results demonstrated that the proposed HEM outperforms previous studies using the same database. The model predicted φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document} with R2 values of 0.93 and 0.979, respectively. The AAREP values were 1.96% for φ and 4.7% for C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}. These results indicate that the HEM significantly improves the prediction quality of φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}, and exhibits strong generalization capability. Sensitivity analysis revealed that σ_3maxσ3max (maximum principal stress) had the greatest impact on modeling both φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document}. According to uncertainty analysis, the LOOCV and OOB had the widest uncertainty bands for the φ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\varphi$$\\end{document} and C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C$$\\end{document} parameters, respectively.

Contrast-enhanced ultrasound image sequences based on radiomics analysis for diagnosis of metastatic cervical lymph nodes from thyroid cancer.

Thyroid cancer (TC) prone to cervical lymph node (CLN) metastasis both before and after surgery. Ultrasonography (US) is the first-line imaging method for evaluating the thyroid gland and CLNs. However, this assessment relies mainly on the subjective judgment of the sonographer and is very much dependent on the sonographer's experience. This prospective study was designed to construct a machine learning model based on contrast-enhanced ultrasound (CEUS) videos of CLNs to predict the risk of CLN metastasis in patients with TC. Patients who were proposed for surgical treatment due to TC from August 2019 to May 2020 were prospectively included. All patients underwent US of CLNs suspected of metastasis, and a 2-minute imaging video was recorded. After target tracking, feature extraction, and feature selection through the lymph node imaging video, three machine learning models, namely, support vector machine, linear discriminant analysis (LDA), and decision tree (DT), were constructed, and the sensitivity, specificity, and accuracy of each model for diagnosing lymph nodes were calculated by leave-one-out cross-validation (LOOCV). A total of 75 lymph nodes were included in the study, with 42 benign cases and 33 malignant cases. Among the machine learning models constructed, the support vector machine had the best diagnostic efficacy, with a sensitivity of 93.0%, a specificity of 93.8%, and an accuracy of 93.3%. The machine learning model based on US video is helpful for the diagnosis of whether metastasis occurs in the CLNs of TC patients.

Detecting starch-adulterated turmeric using Vis-NIR spectroscopy and multispectral imaging with machine learning

Chemicals are often added to turmeric to increase profits, posing significant health risks to consumers. At the same time, traditional methods for detecting contaminants in turmeric are complicated and time-consuming. This study aimed to develop a more practical approach using visible-near infrared (Vis-NIR) and multispectral imaging (MSI) techniques to detect starch adulteration in turmeric. The turmeric powder was mixed with starch (0.1, 0.5, 1, 2.5, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, and 100 % (w/w)) to create spectral and MSI datasets within the 400–1050 nm wavelength range. Spectra were corrected using spectral preprocessing techniques such as Savitzky-Golay (SG), Multiplicative Scatter Correction (MSC), and Standard Normal Variate (SNV). Principal Component Analysis (PCA) applied to reduce the dimensions and various machine learning (ML) models for prediction. The Random Forest Regressor (RFR) achieved a coefficient of determination (R²) of 0.999, a root mean squared error (RMSE) of 0.391 mg (w/w), and a residual predictive deviation (RPD) of 92.3 % in regression analysis. For classification, the Random Forest Classifiers (RFC) achieved an F1 score of 96.0 % and a Matthews Correlation Coefficient (MCC) of 94.6 %. In MSI analysis, the DenseNet201 model obtained an F1 score of 92.9 % and an MCC of 91.9 %. Moreover, the robustness of these models was cross-validated using leave-one-out cross-validation (LOOCV) and K-fold methods. The significance of the study lies in several critical areas, such as public health, advancement in technology, etc. The study's findings reveal that Vis-NIR and MSI approaches are excellent in detecting starch adulteration in turmeric with reliability. It has important implications for public health and food safety by offering a reliable tool for verifying the purity of turmeric and other food items.

Pilot Study on the Use of Attenuated Total Reflectance-Fourier Transform Infrared Spectroscopy for Diagnosing and Characterizing Cardiac Amyloidosis.

Amyloidosis diagnosis relies on Congo red staining with immunohistochemistry and immunofluorescence for subtyping but lacks sensitivity and specificity. Laser-microdissection mass spectroscopy offers better accuracy but is complex and requires extensive sample preparation. Attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectroscopy offers a promising alternative for amyloidosis characterization. Cardiac tissue sections from nine patients with amyloidosis and 20 heart transplant recipients were analyzed using ATR-FTIR spectroscopy. Partial least squares discriminant analysis (PLS-DA), principal component analysis (PCA), and hierarchical cluster analysis (HCA) models were used to differentiate healthy post-transplant cardiac tissue from amyloidosis samples and identify amyloidosis subtypes [κ light chain (n = 1), λ light chain (n = 3), and transthyretin (n = 5)]. Leave-one-out cross-validation (LOOCV) was employed to assess the performance of the PLS-DA model. Significant spectral differences were found in the 1700-1500 cm-1 and 1300-1200 cm-1 regions, primarily related to proteins. The PLS-DA model explained 85.8% of the variance, showing clear clustering between groups. PCA in the 1712-1711 cm-1, 1666-1646 cm-1, and 1385-1383 cm-1 regions also identified two clear clusters. The PCA and the HCA model in the 1646-1642 cm-1 region distinguished κ light chain, λ light chain, and transthyretin cases. This pilot study suggests ATR-FTIR spectroscopy as a novel, non-destructive, rapid, and inexpensive tool for diagnosing and subtyping amyloidosis. This study was limited by a small dataset and variability in measurements across different instruments and laboratories. The PLS-DA model's performance may suffer from overfitting and class imbalance. Larger, more diverse datasets are needed for validation.

A clinical prognostic model related to T cells based on machine learning for predicting the prognosis and immune response of ovarian cancer

BackgroundOvarian cancer (OV) is regarded as one of the most lethal malignancies affecting the female reproductive system, with individuals diagnosed with OV often facing a dismal prognosis due to resistance to chemotherapy and the presence of an immunosuppressive environment. T cells serve as a crucial mediator for immune surveillance and cancer elimination. This study aims to analyze the mechanism of T cell-associated markers in OV and create a prognostic model for clinical use in enhancing outcomes for OV patients. MethodsBased on the single-cell dataset GSE184880, this study used single-cell data analysis to identify characteristic T cell subsets. Analysis of high dimensional weighted gene co-expression network analysis (hdWGCNA) is utilized to identify crucial gene modules along with their corresponding hub genes. A grand total of 113 predictive models were formed utilizing ten distinct machine learning algorithms along with the combination of the cancer genome atlas (TCGA)-OV dataset and the GSE140082 dataset. The most dependable clinical prognostic model was created utilizing the leave one out cross validation (LOOCV) framework. The validation process for the models was achieved by conducting survival curve analysis and receiver operating characteristic (ROC) analysis. The relationship between risk scores and immune cells was explored through the utilization of the Cibersort algorithm. Additionally, an analysis of drug sensitivity was carried out to anticipate chemotherapy responses across various risk groups. The genes implicated in the model were authenticated utilizing qRT-PCR, cell viability experiments, and EdU assay. ResultsThis study developed a clinical prognostic model that includes ten risk genes. The results obtained from the training set of the study indicate that patients classified in the low-risk group experience a significant survival advantage compared to those in the high-risk group. The ROC analysis demonstrates that the model holds significant clinical utility. These results were verified using an independent dataset, strengthening the model's precision and dependability. The risk assessment provided by the model also serves as an independent prognostic factor for OV patients. The study also unveiled a noteworthy relationship between the risk scores calculated by the model and various immune cells, suggesting that the model may potentially serve as a valuable tool in forecasting responses to both immune therapy and chemotherapy in ovarian cancer patients. Notably, experimental evidence suggests that PFN1, one of the genes included in the model, is upregulated in human OV cell lines and has the capacity to promote cancer progression in in vitro models. ConclusionWe have created an accurate and dependable clinical prognostic model for OV capable of predicting clinical outcomes and categorizing patients. This model effectively forecasts responses to both immune therapy and chemotherapy. By regulating the immune microenvironment and targeting the key gene PFN1, it may improve the prognosis for high-risk patients.

Estimation of lithium-ion battery health state using MHATTCN network with multi-health indicators inputs

Accurately predicting the state of health (SOH) of lithium-ion batteries is fundamental in estimating their remaining lifespan. Various parameters such as voltage, current, and temperature significantly influence the battery’s SOH. However, existing data-driven methods necessitate substantial data from the target domain for training, which hampers the assessment of lithium-ion battery health at the initial stage. To address these challenges, this paper introduces the multi-head attention-time convolution network (MHAT-TCN), amalgamating multi-head attention learning with random block dropout techniques. Additionally, it employs grey relational analysis (GRA) to select health indicators (HIs) highly correlated with battery capacity, thereby enhancing the accuracy of the model training. Employing leave-one-out crossvalidation (LOOCV), the MHAT-TCN network is pre-trained using data from batteries of the same model to facilitate comprehensive prediction of the target battery throughout its operational period. Results demonstrate that the MHAT-TCN network trained on HIs outperforms other models, enabling precise predictions across the entire operational period.

HTFSMMA: Higher-Order Topological Guided Small Molecule-MicroRNA Associations Prediction.

Small molecules (SMs) play a pivotal role in regulating microRNAs (miRNAs). Existing prediction methods for associations between SM-miRNA have overlooked crucial aspects: the incorporation of local topological features between nodes, which represent either SMs or miRNAs, and the effective fusion of node features with topological features. This study introduces a novel approach, termed high-order topological features for SM-miRNA association prediction (HTFSMMA), which specifically addresses these limitations. Initially, an association graph is formed by integrating SM-miRNA association data, SM similarity, and miRNA similarity. Subsequently, we focus on the local information of links and propose target neighborhood graph convolutional network for extracting local topological features. Then, HTFSMMA employs graph attention networks to amalgamate these local features, thereby establishing a platform for the acquisition of high-order features through random walks. Finally, the extracted features are integrated into the multilayer perceptron to derive the association prediction scores. To demonstrate the performance of HTFSMMA, we conducted comprehensive evaluations including five-fold cross-validation, leave-one-out cross-validation (LOOCV), SM-fixed local LOOCV, and miRNA-fixed local LOOCV. The area under receiver operating characteristic curve values were 0.9958 ± 0.0024 (0.8722 ± 0.0021), 0.9986 (0.9504), 0.9974 (0.9111), and 0.9977 (0.9074), respectively. Our findings demonstrate the superior performance of HTFSMMA over existing approaches. In addition, three case studies and the DeLong test have confirmed the effectiveness of the proposed method. These results collectively underscore the significance of HTFSMMA in facilitating the inference of associations between SMs and miRNAs.

KNNDM CV: k-fold nearest-neighbour distance matching cross-validation for map accuracy estimation

Abstract. Random and spatial cross-validation (CV) methods are commonly used to evaluate machine-learning-based spatial prediction models, and the performance values obtained are often interpreted as map accuracy estimates. However, the appropriateness of such approaches is currently the subject of controversy. For the common case where no probability sample for validation purposes is available, in Milà et al. (2022) we proposed the nearest-neighbour distance matching (NNDM) leave-one-out (LOO) CV method. This method produces a distribution of geographical nearest-neighbour distances (NNDs) between test and training locations during CV that matches the distribution of NNDs between prediction and training locations. Hence, it creates predictive conditions during CV that are comparable to what is required when predicting a defined area. Although NNDM LOO CV produced largely reliable map accuracy estimates in our analysis, as a LOO-based method, it cannot be applied to the large datasets found in many studies. Here, we propose a novel k-fold CV strategy for map accuracy estimation inspired by the concepts of NNDM LOO CV: the k-fold NNDM (kNNDM) CV. The kNNDM algorithm tries to find a k-fold configuration such that the empirical cumulative distribution function (ECDF) of NNDs between test and training locations during CV is matched to the ECDF of NNDs between prediction and training locations. We tested kNNDM CV in a simulation study with different sampling distributions and compared it to other CV methods including NNDM LOO CV. We found that kNNDM CV performed similarly to NNDM LOO CV and produced reasonably reliable map accuracy estimates across sampling patterns. However, compared to NNDM LOO CV, kNNDM resulted in significantly reduced computation times. In an experiment using 4000 strongly clustered training points, kNNDM CV reduced the time spent on fold assignment and model training from 4.8 d to 1.2 min. Furthermore, we found a positive association between the quality of the match of the two ECDFs in kNNDM and the reliability of the map accuracy estimates. kNNDM provided the advantages of our original NNDM LOO CV strategy while bypassing its sample size limitations.