Letter to the Editor-"Reply-letter to the editor".

Takefuji Y 《-》

Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants.

To develop and validate a machine learning model incorporating dietary antioxidants to predict cardiovascular disease (CVD)-cancer comorbidity and to elucidate the role of antioxidants in disease prediction. Data were sourced from the National Health and Nutrition Examination Survey. Antioxidants, including vitamins, minerals, and polyphenols, were selected as key features. Additionally, demographic, lifestyle, and health condition features were incorporated to improve model accuracy. Feature preprocessing included removing collinear features, addressing class imbalance, and normalizing data. Models constructed within the mlr3 framework included recursive partitioning and regression trees, random forest, kernel k-nearest neighbors, naïve bayes, and light gradient boosting machine (LightGBM). Benchmarking provided a systematic approach to evaluating and comparing model performance. SHapley Additive exPlanation (SHAP) values were calculated to determine the prediction role of each feature in the model with the highest predictive performance. This analysis included 10,064 participants, with 353 identified as having comorbid CVD and cancer. After excluding collinear features, the machine learning model retained 29 dietary antioxidant features and 9 baseline features. LightGBM achieved the highest predictive accuracy at 87.9 %, a classification error rate of 12.1 %, and the top area under the receiver operating characteristic curve (0.951) and the precision-recall curve (0.930). LightGBM also demonstrated balanced sensitivity and specificity, both close to 88 %. SHAP analysis indicated that naringenin, magnesium, theaflavin, kaempferol, hesperetin, selenium, malvidin, and vitamin C were the most influential contributors. LightGBM exhibited the best performance for predicting CVD-cancer comorbidity. SHAP values highlighted the importance of antioxidants, with naringenin and magnesium emerging as primary factors in this model.

Qi X ，Wang S ，Fang C ，Jia J ，Lin L ，Yuan T ... -  《Redox Biology》

An interpretable (explainable) model based on machine learning and SHAP interpretation technique for mapping wind erosion hazard.

Soil erosion by wind poses a significant threat to various regions across the globe, such as drylands in the Middle East and Iran. Wind erosion hazard maps can assist in identifying the regions of highest wind erosion risk and are a valuable tool for the mitigation of its destructive consequences. This study aims to map wind erosion hazards by developing an interpretable (explainable) model based on machine learning (ML) and Shapley additive exPlanation (SHAP) interpretation techniques. Four ML models, namely random forest (RF), support vector machine (SVM), extreme gradient boosting (XGB), and quadratic discriminant analysis (QDA) were used. Thirteen features associated with wind erosion were mapped spatially and then subjected to a multivariate adaptive regression spline (MARS) feature selection algorithm, and then, tolerance coefficient (TC) and variance inflation factor (VIF) statistical tests were used to explore multicollinearity among the variables. MARS analysis shows that eight features consisting of elevation (or DEM), soil bulk density, precipitation, aspect, slope, soil sand content, vegetation cover (or NDVI), and lithology were the most effective for wind erosion, while no collinearity existed among these variables. The ML models were used for ranking the effective features, and the research introduces the application of an interpretable ML model for the interpretation of predictive model's output. The ranking of effective features by RF-as the most typical ML model-revealed that elevation and soil bulk density were the two most important features. According to the area under the receiver operating characteristic curve (AUROC) (with a value > 90%) and precision-recall (PR) (with a value > 90%) curves, all four ML models performed with great accuracy. According to the PR curve, the SVM model performed slightly better than others, and its results revealed that 20.9%, 23%, and 16.6% of the total area in Hormozgan Province is characterized by moderate, high, and very high hazard classes to wind erosion, respectively. SHAP revealed that soil sand content and elevation are the most important variables contributing to the predictive model output. Overall, our research is one of the pioneering applications of interpretable ML models in mapping wind erosion hazards in Southern Iran. We recommend that future research should address the aspect of interpretability in order to better understand predictive model outputs.

Gholami H ，Darvishi E ，Moradi N ，Mohammadifar A ，Song Y ，Li Y ，Niu B ，Kaskaoutis D ，Pradhan B ... -  《-》

Construction of a risk prediction model for postoperative deep vein thrombosis in colorectal cancer patients based on machine learning algorithms.

Colorectal cancer is a prevalent malignancy of the digestive system, with an increasing incidence. Lower extremity deep vein thrombosis (DVT) is a frequent postoperative complication, occurring in up to 40% of cases. This research aims to develop and validate a machine learning model (ML) to predict the risk of lower limb deep vein thrombosis in patients with colorectal cancer, facilitating preventive and therapeutic measures to enhance recovery and ensure safety. In this retrospective cohort study, we collected data from 429 colorectal cancer patients from January 2021 to January 2024. The medical records included age, blood test results, body mass index, underlying diseases, clinical staging, histological typing, surgical methods, and postoperative complications. We employed the Synthetic Minority Oversampling Technique to address imbalanced data and split the dataset into training and validation sets in a 7:3 ratio. Feature selection was performed using Random Forest (RF), XGBoost, and Least Absolute Shrinkage and Selection Operator algorithms (LASSO). We then trained six machine learning models: Logistic Regression (LR), Naive Bayes (NB), Gaussian Process (GP), Random Forest, XGBoost, and Multilayer Perceptron (MLP). The model's performance was evaluated using metrics such as area under the Receiver Operating Characteristic curve, accuracy, sensitivity, specificity, F1 score, and confusion matrix. Additionally, SHAP and LIME were used to enhance the interpretability of the results. The study combined Random Forest, XGBoost algorithms, and LASSO regression with univariate regression analysis to identify significant predictive factors, including age, preoperative prealbumin, preoperative albumin, preoperative hemoglobin, operation time, PIKVA2, CEA, and preoperative neutrophil count. The XGBoost model outperformed other ML algorithms, achieving an AUC of 0.996, an accuracy of 0.9636, a specificity of 0.9778, and an F1 score of 0.9576. Moreover, the SHAP method identified age and preoperative prealbumin as the primary determinants influencing ML model predictions. Finally, the study employed LIME for more precise prediction and interpretation of individual predictions. The machine learning algorithms effectively predicted postoperative lower limb deep vein thrombosis in colorectal cancer patients. The XGBoost model demonstrated strong potential for improving early detection and treatment in clinical settings.

Liu X ，Shu X ，Zhou Y ，Jiang Y ... -  《Frontiers in Oncology》

Predicting Treatment Outcomes in Patients with Low Back Pain Using Gene Signature-Based Machine Learning Models.

Low back pain (LBP) is a significant global health burden, with variable treatment outcomes and an unclear underlying molecular mechanism. Effective prediction of treatment responses remains a challenge. In this study, we aimed to develop gene signature-based machine learning models using transcriptomic data from peripheral immune cells to predict treatment outcomes in patients with LBP. The transcriptomic data of patients with LBP from peripheral immune cells were retrieved from the GEO database. Patients with LBP were recruited, and treatment outcomes were assessed after 3 months. Patients were classified into two groups: those with resolved pain and those with persistent pain. Differentially expressed genes (DEGs) between the two groups were identified through bioinformatic analysis. Key genes were selected using five machine learning models, including Lasso, Elastic Net, Random Forest, SVM, and GBM. These key genes were then used to train 45 machine learning models by combining nine different algorithms: Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, Random Forest, Gradient Boosting Machine, Multilayer Perceptron, Naive Bayes, and Linear Discriminant Analysis. Five-fold cross-validation was employed to ensure robust model evaluation and minimize overfitting. In each fold, the dataset was split into training and validation sets, with model performance assessed using multiple metrics including accuracy, precision, recall, and F1 score. The final model performance was reported as the mean and standard deviation across all five folds, providing a more reliable estimate of the models' ability to predict LBP treatment outcomes using gene expression data from peripheral immune cells. A total of 61 DEGs were identified between patients with resolved and persistent pain. From these genes, 45 machine learning models were constructed using different combinations of feature selection methods and classification algorithms. The Elastic Net with Logistic Regression achieved the highest accuracy of 88.7% ± 8.0% (mean ± standard deviation), followed closely by Elastic Net with Linear Discriminant Analysis (88.7% ± 7.5%) and Lasso with Multilayer Perceptron (87.7% ± 6.7%). Overall, 15 models demonstrated robust performance with accuracy > 80%, suggesting the reliability of our machine learning approach in predicting LBP treatment outcomes. The SHapley Additive exPlanations (SHAP) method was used to visualize the contribution of core genes to model performance, highlighting their roles in predicting treatment outcomes. The study demonstrates the potential of using transcriptomic data from peripheral immune cells and machine learning models to predict treatment outcomes in patients with LBP. The identification of key genes and the high accuracy of certain models provide a basis for future personalized treatment strategies in LBP management. Visualizing gene importance with SHAP adds interpretability to the predictive models, enhancing their clinical relevance.

Lian Y ，Shi Y ，Shang H ，Zhan H ... -  《-》