Machine Learning Modeling of Disease Treatment Default: A Comparative Analysis of Classification Models

Postoperative pain is a frequent clinical concern following endodontic treatment. This study aimed to develop and validate supervised machine learning models to predict the occurrence of postoperative pain in cases of irreversible pulpitis. A prospective sample of 354 patients aged 18 to 60 years undergoing standardised endodontic treatment was analysed. In the original randomised clinical trials from which the data were derived, each patient had only one eligible tooth included. Clinical variables included postoperative pain at 24 and 72 h, treated tooth group, occlusal reduction, photobiomodulation therapy, use of non-steroidal anti-inflammatory drugs (NSAIDs), sex and age. Eight supervised machine learning algorithms were trained to predict pain occurrence, including Logistic Regression, Support Vector Machine, Gradient Boosting, Random Forest, Decision Tree, K-Nearest Neighbours, AdaBoost and Multilayer Perceptron. The dataset was divided into training (70%) and testing (30%) sets using stratified sampling. Class imbalance in the training set, characterised by a lower proportion of cases with moderate or severe pain, was addressed using the Synthetic Minority Oversampling Technique. Hyperparameters were optimised through grid search combined with stratified five-fold cross validation. Model performance was evaluated using the area under the curve (AUC), accuracy, precision, recall and F1-score, with 95% confidence intervals estimated by bootstrapping. The predictive models achieved good discrimination of pain outcomes. Logistic Regression showed the best test performance at 24 h (AUC 0.74 [95% CI: 0.61 to 0.85], precision 0.81 [95% CI: 0.73 to 0.88]). At 72 h, the Support Vector Machine achieved the highest performance (AUC 0.81 [95% CI: 0.69 to 0.92], precision 0.88 [95% CI: 0.79 to 0.94]). Age and sex emerged as the most influential predictors across models. Supervised machine learning models demonstrated promising performance for predicting postoperative pain following endodontic treatment. Logistic Regression and Support Vector Machine algorithms presented the most consistent results, supporting their potential clinical application for personalised pain management.

Background: The merging of machine learning and deep learning approaches offers a viable route for improving breast cancer prediction in this era of advanced technology and data-driven healthcare. This study focused on the use of supervised machine learning and deep learning algorithms for breast cancer prediction using Wisconsin breast cancer dataset. Methods: The features from this dataset were computed from a digitized image of a fine needle aspirate (FNA) of a breast mass. Supervised machine learning algorithms, such as logistic regression, random forests, and support vector machines were compared with deep learning algorithms like convolutional and recurrent neural networks (RNN and CNN) for the prediction of breast cancer. The techniques combine clinical, genomic, and image-based data, that both aid in early diagnosis and individualized treatment suggestions. Results: The results of model comparison were very promising, with models obtaining excellent accuracy, sensitivity, and specificity in breast cancer diagnosis. The study used a pair plot and different classifiers with their accuracy scores on test dataset to determine which machine learning model was most suitable based on the relationship of variables represented in the plot. Support vector machine (SVM) has the highest accuracy of 98.8% and Artificial Neural Network (ANN) has lowest accuracy of 95.80% using confusion matrix and the accuracy metric. Conclusion: The study revealed that Support Vector Machine (SVM) has the highest prediction capability for Breast Cancer using Supervised Machine Learning and Deep Leaning. The new classifier performed better than the existing breast cancer prediction models in the literature.

In recent years, cardiovascular disease (CVD) has emerged as a leading cause of mortality worldwide, highlighting the urgent need for reliable predictive models to support early diagnosis and preventive care. This study conducts a comparative analysis of various machine learning models to assess CVD risk, focusing on their ability to accurately identify individuals at high risk based on clinical and demographic data. We evaluate multiple supervised learning algorithms, including logistic regression, random forests, support vector classifiers, K-nearest neighbors, gradient boosting, and AdaBoost, comparing their predictive performance in terms of accuracy, precision, recall, and F1-score. Additionally, we propose a novel hybrid model that combines Random Forest (RF) for feature selection and Deep Neural Networks (DNN) for classification, aiming to leverage the strengths of both approaches for more accurate CVD prediction. Our findings demonstrate that ensemble models such as random forests and gradient boosting achieve superior performance, with high accuracy (0.99) and balanced precision and recall values, outperforming simpler models like logistic regression and support vector classifiers. The hybrid model further enhances prediction accuracy, achieving 92.4% accuracy, 91.7% precision, 93.0% recall, and an AUC-ROC score of 96.0%. The analysis also underscores the importance of data preprocessing techniques, including normalization and handling of missing values, in optimizing model accuracy and stability. Notably, K-nearest neighbors also performed exceptionally well with a high F1-score across classes, highlighting its robustness for this task. This study provides a detailed examination of each model's strengths and limitations, including the proposed hybrid model, offering valuable insights for healthcare practitioners and data scientists in selecting effective machine learning models for CVD risk prediction. By integrating these models into healthcare systems, real-time risk prediction can be enhanced, ultimately supporting clinical decision-making and advancing personalized care in cardiovascular health. Keywords— cardiovascular disease, machine learning, risk assessment, predictive models, supervised learning, healthcare

To construct and validate the best predictive model for 28-day death risk in patients with septic shock based on different supervised machine learning algorithms. The patients with septic shock meeting the Sepsis-3 criteria were selected from Medical Information Mart for Intensive Care-IV v2.0 (MIMIC-IV v2.0). According to the principle of random allocation, 70% of these patients were used as the training set, and 30% as the validation set. Relevant predictive variables were extracted from three aspects: demographic characteristics and basic vital signs, serum indicators within 24 hours of intensive care unit (ICU) admission and complications possibly affecting indicators, functional scoring and advanced life support. The predictive efficacy of models constructed using five mainstream machine learning algorithms including decision tree classification and regression tree (CART), random forest (RF), support vector machine (SVM), linear regression (LR), and super learner [SL; combined CART, RF and extreme gradient boosting (XGBoost)] for 28-day death in patients with septic shock was compared, and the best algorithm model was selected. The optimal predictive variables were determined by intersecting the results from LASSO regression, RF, and XGBoost algorithms, and a predictive model was constructed. The predictive efficacy of the model was validated by drawing receiver operator characteristic curve (ROC curve), the accuracy of the model was assessed using calibration curves, and the practicality of the model was verified through decision curve analysis (DCA). A total of 3 295 patients with septic shock were included, with 2 164 surviving and 1 131 dying within 28 days, resulting in a mortality of 34.32%. Of these, 2 307 were in the training set (with 792 deaths within 28 days, a mortality of 34.33%), and 988 in the validation set (with 339 deaths within 28 days, a mortality of 34.31%). Five machine learning models were established based on the training set data. After including variables at three aspects, the area under the ROC curve (AUC) of RF, SVM, and LR machine learning algorithm models for predicting 28-day death in septic shock patients in the validation set was 0.823 [95% confidence interval (95%CI) was 0.795-0.849], 0.823 (95%CI was 0.796-0.849), and 0.810 (95%CI was 0.782-0.838), respectively, which were higher than that of the CART algorithm model (AUC = 0.750, 95%CI was 0.717-0.782) and SL algorithm model (AUC = 0.756, 95%CI was 0.724-0.789). Thus above three algorithm models were determined to be the best algorithm models. After integrating variables from three aspects, 16 optimal predictive variables were identified through intersection by LASSO regression, RF, and XGBoost algorithms, including the highest pH value, the highest albumin (Alb), the highest body temperature, the lowest lactic acid (Lac), the highest Lac, the highest serum creatinine (SCr), the highest Ca2+, the lowest hemoglobin (Hb), the lowest white blood cell count (WBC), age, simplified acute physiology score III (SAPS III), the highest WBC, acute physiology score III (APS III), the lowest Na+, body mass index (BMI), and the shortest activated partial thromboplastin time (APTT) within 24 hours of ICU admission. ROC curve analysis showed that the Logistic regression model constructed with above 16 optimal predictive variables was the best predictive model, with an AUC of 0.806 (95%CI was 0.778-0.835) in the validation set. The calibration curve and DCA curve showed that this model had high accuracy and the highest net benefit could reach 0.3, which was significantly outperforming traditional models based on single functional score [APS III score, SAPS III score, and sequential organ failure assessment (SOFA) score] with AUC (95%CI) of 0.746 (0.715-0.778), 0.765 (0.734-0.796), and 0.625 (0.589-0.661), respectively. The Logistic regression model, constructed using 16 optimal predictive variables including pH value, Alb, body temperature, Lac, SCr, Ca2+, Hb, WBC, SAPS III score, APS III score, Na+, BMI, and APTT, is identified as the best predictive model for the 28-day death risk in patients with septic shock. Its performance is stable, with high discriminative ability and accuracy.

Sepsis is a leading cause of mortality in the intensive care unit. Early prediction of sepsis can reduce the overall mortality rate and cost of sepsis treatment. Some studies have predicted mortality and development of sepsis using machine learning models. However, there is a gap between the creation of different machine learning algorithms and their implementation in clinical practice.This study utilized data from the Medical Information Mart for Intensive Care III. We established and compared the gradient boosting decision tree (GBDT), logistic regression (LR), k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM).A total of 3937 sepsis patients were included, with 34.3% mortality in the Medical Information Mart for Intensive Care III group. In our comparison of 5 machine learning models (GBDT, LR, KNN, RF, and SVM), the GBDT model showed the best performance with the highest area under the receiver operating characteristic curve (0.992), recall (94.8%), accuracy (95.4%), and F1 score (0.933). The RF, SVM, and KNN models showed better performance (area under the receiver operating characteristic curve: 0.980, 0.898, and 0.877, respectively) than the LR (0.876).The GBDT model showed better performance than other machine learning models (LR, KNN, RF, and SVM) in predicting the mortality of patients with sepsis in the intensive care unit. This could be used to develop a clinical decision support system in the future.

After radical prostatectomy (RP), one-third of patients will experience biochemical recurrence (BCR), which is associated with subsequent metastasis and cancer-specific mortality. We employed machine learning (ML) algorithms to predict BCR after RP, and compare them with traditional regression models and nomograms. Utilizing a prospective Uro-oncology registry, 18 clinicopathological parameters of 1130 consecutive patients who underwent RP (2009-2018) were recorded, yielding over 20,000 data points for analysis. The data set was split into a 70:30 ratio for training and validation. Three ML models: Naïve Bayes (NB), random forest (RF), and support vector machine (SVM) were studied, and compared with traditional regression models and nomograms (Kattan, CAPSURE, John Hopkins [JHH]) to predict BCR at 1, 3, and 5 years. Over a median follow-up of 70.0 months, 176 (15.6%) developed BCR, at a median time of 16.0 months (interquartile range [IQR]: 11.0-26.0). Multivariate analyses demonstrated strongest association of BCR with prostate-specific antigen (PSA) (p: 0.015), positive surgical margins (p < 0.001), extraprostatic extension (p: 0.002), seminal vesicle invasion (p: 0.004), and grade group (p < 0.001). The 3 ML models demonstrated good prediction of BCR at 1, 3, and 5 years, with the area under curves (AUC) of NB at 0.894, 0.876, and 0.894, RF at 0.846, 0.875, and 0.888, and SVM at 0.835, 0.850, and 0.855, respectively. All models demonstrated (1) robust accuracy (>0.82), (2) good calibration with minimal overfitting, (3) longitudinal consistency across the three time points, and (4) inter-model validity. The ML models were comparable to traditional regression analyses (AUC: 0.797, 0.848, and 0.862) and outperformed the three nomograms: Kattan (AUC: 0.815, 0.798, and 0.799), JHH (AUC: 0.820, 0.757, and 0.750) and CAPSURE nomograms (AUC: 0.706, 0.720, and 0.749) (p < 0.001). Supervised ML algorithms can deliver accurate performances and outperform nomograms in predicting BCR after RP. This may facilitate tailored care provisions by identifying high-risk patients who will benefit from multimodal therapy.

Previous studies have investigated predictive factors for parenting stress in caregivers of autism spectrum disorder (ASD) patients using traditional statistical approaches, but their study settings and results were inconsistent. Herein, this study aimed to identify major predictors for parenting stress in this population by developing explainable machine learning models. Study participants were collected from the Department of Child and Adolescent Psychiatry, Severance Hospital, Yonsei University College of Medicine, Seoul, the Republic of Korea between March 2016 and October 2020. A total of 36 model features were used, which include subscales of the Minnesota Multiphasic Personality Inventory-2 (MMPI-2) for caregivers' psychopathology, Social Responsiveness Scale-2 for core symptoms, and Child Behavior Checklist (CBCL) for behavioral problems. Machine learning classifiers [eXtreme Gradient Boosting (XGBoost), random forest (RF), logistic regression, and support vector machine (SVM) classifier] were generated to predict severe total parenting stress and its subscales (parental distress, parent-child dysfunctional interaction, and difficult child). Model performance was assessed by area under the receiver operating curve (AUC), sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. We utilized the SHapley Additive exPlanations tree explainer to investigate major predictors. A total of 496 participants were included [mean age of ASD patients 6.39 (SD 2.24); 413 men (83.3%)]. The best-performing models achieved an AUC of 0.831 (RF model; 95% CI 0.740-0.910) for parental distress, 0.814 (SVM model; 95% CI 0.720-0.896) for parent-child dysfunctional interaction, 0.813 (RF model; 95% CI 0.724-0.891) for difficult child, and 0.862 (RF model; 95% CI 0.783-0.930) for total parenting stress on the test set. For the total parenting stress, ASD patients' aggressive behavior and anxious/depressed, and caregivers' depression, social introversion, and psychasthenia were the top 5 leading predictors. By using explainable machine learning models (XGBoost and RF), we investigated major predictors for each subscale of the parenting stress index in caregivers of ASD patients. Identified predictors for parenting stress in this population might help alert clinicians whether a caregiver is at a high risk of experiencing severe parenting stress and if so, providing timely interventions, which could eventually improve the treatment outcome for ASD patients.

647 Background: The primary treatment of most mNSTC is chemotherapy followed by surgery if the residual disease (RD) is &gt;1 cm. However, conventional imaging lacks the specificity to characterize the tissue, often leading to overtreatment. This study hypothesizes that integrating CT-driven radiomics features with plasma miR371 and miR375 will enhance the predictive accuracy of Machine Learning (ML) models to predict teratoma, viable germ cell (vGCT) and fibrosis/necrosis (F/N) in mNSTC patients with RD. Methods: 111 lesions from52 patients, including residual teratoma (n=57), F/N (n=33), vGCT (n=10), and additional seminoma (n=11) for training purposes were included, split into training (N=78) and test cohorts (N=33). Lesions were lymph nodes (n=87), lung (n=21), and brain (n=3) with a median size of 1.6 cm (Q1-Q3 interval=1.2-2.73 cm). 3D Slicer version 5.6.1 was used to segment the RD &gt; 1 cm (short axis) and extract radiomics features. Plasma miRNA levels before resection were measured by RT-PCR. Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GB), and CatBoost (CB) ML models were evaluated to define the operating characteristics of radiomics alone (R-only) and in combination with miR371 (371) and/or miR375 (375) levels in predicting teratoma, vGCT and F/N. Results: For predicting teratoma, the best models were RF (R+375 and R+371+375), CB (R+371+375), and GB (R+371 and R+371+375). While adding miR371 or miR375 to R-only slightly improved AUC across models, the best results were achieved with the R+375+371 dataset. CB achieved AUCs ranging from 0.94 to 0.97 in training and 0.81 to 0.93 in test sets, with its highest AUC of 0.93 (95% CI: 0.78-0.97) on the R+375+371 dataset to differentiate all three classes. Similarly, GB demonstrated strong performance, achieving its highest AUC of 0.93 (95% CI: 0.79-0.96) on the R+375+371 dataset (Table). Conclusions: Integration of plasma miR371, miR375 and radiomics improved accuracy of predicting histologies across all ML models. These methods could be used to characterize the histology of RD in mNSTC patients to better inform treatment decisions. Further refinement, including incorporation of histological findings of the primary tumor, will be reported. AUC values of different ML algorithms on training and test sets. TRAINING SET TEST SET Model ±SD R R+375 R+371 R+375+371 Model (95% CI) R R+375 R+371 R+375+371 RF 0.93±0.05 0.95±0.04 0.95±0.03 0.96±0.04 RF 0.8(0.59-0.89) 0.85(0.72-0.93) 0.87(0.76-0.95) 0.91(0.78-0.95) SVM 0.84±0.06 0.84±0.09 0.89±0.11 0.89±0.09 SVM 0.72(0.54-0.80) 0.74(0.56-0.82) 0.83(0.69-0.92) 0.84(0.76-0.94) GB 0.94±0.04 0.91±0.08 0.95±0.05 0.97±0.03 GB 0.84(0.61-0.96) 0.89(0.77-0.97) 0.89(0.79-0.96) 0.93(0.79-0.96) CB 0.95±0.03 0.94±0.03 0.94±0.04 0.97±0.03 CB 0.81(0.6-0.93) 0.86(0.73-0.94) 0.89(0.78-0.97) 0.93(0.78-0.97)

In recent years, the microbiome has been recognized as an important factor associated with cardiovascular disease (CVD), which is the leading cause of human mortality worldwide. Disparities in gut microbial compositions between individuals with and without CVD were reported, whereby, we hypothesized that utilizing such microbiome-based data for training with supervised machine learning (ML) models could be exploited as a new strategy for evaluation of cardiovascular health. To test our hypothesis, we analyzed the metagenomics data extracted from the American Gut Project. Specifically, 16S rRNA reads from stool samples of 478 CVD and 473 non-CVD control samples were analyzed using five supervised ML algorithms: random forest (RF), support vector machine with radial kernel (svmRadial), decision tree (DT), elastic net (ENet) and neural networks (NN). Thirty-nine differential bacterial taxa (LEfSe: LDA &gt; 2) were identified between CVD and non-CVD groups. ML classifications, using these taxonomic features, achieved an AUC (area under the receiver operating characteristic curve) of ~0.58 (RF). However, by choosing the top 500 high-variance features of operational taxonomic units (OTUs) for training ML models, an improved AUC of ~0.65 (RF) was achieved. Further, by limiting the selection to only the top 25 highly contributing OTU features to reduce the dimensionality of feature space, the AUC was further significantly enhanced to ~0.70 (RF). In summary, this study is the first to demonstrate the successful development of a ML model using microbiome-based datasets for a systematic diagnostic screening of CVD.

The accurate and early detection of coronary heart disease (CHD) is crucial for reducing mortality rates.This study evaluates the predictive performance of three machine learning models-Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM)-for classifying CHD.The models were trained on a comprehensive heart disease dataset and assessed using metrics such as Accuracy, Specificity, Sensitivity, F1-score, Negative Predictive Value, and Positive Predictive Value.Among the models, RF demonstrated the highest accuracy (93.5%), while SVM excelled in sensitivity (97.5%).The findings highlight the potential of machine learning techniques in clinical decision-making and personalized medicine.

Aims: Obstructive sleep apnea (OSA) is a prevalent disorder characterized by recurrent upper airway collapse during sleep, causing intermittent hypoxia and sleep fragmentation. Diagnosis depends on polysomnography (PSG), which is resource intensive and not always available. This study aimed to develop and validate a machine learning (ML) model to predict clinically significant OSA (apnea-hypopnea index [AHI]≥15) using only demographic, behavioral, symptomatic, and comorbidity data, without PSG-derived parameters. Methods: A retrospective dataset of 1281 adults evaluated for suspected OSA was analyzed. Variables included age, sex, body-mass index (BMI), neck circumference, Epworth Sleepiness Scale (ESS), smoking status, and comorbidities such as hypertension and diabetes. Four algorithms Random Forest (RF), Gradient Boosting, Logistic Regression, and Support Vector Machine were trained and tested using an 80/20 split and five-fold cross-validation. Model performance was assessed by accuracy, recall, precision, F1-score, and ROC-AUC. Results: Among 1281 participants, 42.6% had AHI≥15. The RF model achieved the best performance with 78.6% accuracy, 0.95 recall, 0.81 precision, 0.88 F1-score, and 0.86 ROC-AUC. ESS and BMI were the strongest predictors, followed by age, neck circumference, smoking, hypertension, and diabetes. The model effectively identified moderate-to-severe OSA cases, offering a practical triage tool for prioritizing PSG in resource-limited settings. Conclusion: The ML model accurately predicted clinically significant OSA using only accessible clinical variables. Its high sensitivity and interpretability support potential integration into clinical workflows for efficient risk stratification and PSG allocation. Prospective multicenter validation is warranted.

The prediction of wind energy generation is important to enhance the performance and dependability of renewable energy systems due to the rising demand for wind-generated electricity and advancements in wind energy technology competitiveness. This study leverages advanced machine learning (ML) and some other statistical and deep learning based time series forecasting models to enhance the accuracy of wind energy predictions. This comprehensive analysis includes nine ML models—Linear Regression, Random Forests (RF), Gradient Boosting Machines (GBM), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), AdaBoost, XGBoost, Support Vector Regression (SVR), and Neural Networks—as well as Four time-series forecasting models—ARIMA, Temporal Convolutional Networks (TCNs), Long Short-Term Memory (LSTM) networks and GRU. Each ML model underwent rigorous cross-validation to ensure optimal performance. The assessment criteria utilized here comprised the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² Score. It was found that among the nine ML models, Random Forests, GBM and KNN consistently provided superior accuracy and robustness, making them the top choices for wind energy prediction whereas the performance of linear regression, SVM and SVR were very poor for the considered dataset. From the experiment, Random Forest, GBM, and KNN showed the best performance with low MSE values of 0.77, 1.95, and 1.51 respectively, while other models had MSEs above 7.5, with AdaBoost reaching 30. Their RMSEs (0.88, 1.40, 1.23) and MAEs (0.093, 0.73, 0.10) also indicate strong predictive accuracy compared to the rest.In this paper, time series forecasting, TCNs, LSTM and GRU networks showed strong capabilities in capturing temporal dependencies and trends within the wind energy data. Visualization techniques were employed to compare model performances comprehensively, providing clear insights into their predictive power. Therefore, this present study offers a robust framework for researchers and practitioners aiming to leverage machine learning and time series forecasting in the realm of renewable energy prediction.

Radiomics and machine learning have been extensively utilized in the realm of urinary stones, particularly in forecasting stone treatment outcomes. The objective of this study was to integrate clinical variables and radiomic features to develop a machine learning model for predicting the stone-free rate (SFR) following percutaneous nephrolithotomy (PCNL).A total of 212 eligible patients who underwent PCNL surgery at the Second Affiliated Hospital of Nanchang University were included in a retrospective analysis. Preoperative clinical variables and non-contrast-enhanced CT images of all patients were collected, and radiomic features were extracted after delineating the stone ROI. Univariate analysis was conducted to identify clinical variables strongly correlated with the stone-free rate after PCNL, and the least absolute shrinkage and selection operator algorithm (lasso regression) was utilized to screen radiomic features. Four supervised machine learning algorithms, including Logistic Regression, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Decision Tree (GBDT), were employed. The clinical variables with strong correlation and screened radiomic features were integrated into the four machine learning algorithms to construct a prediction model, and the receiver operating curve was plotted. The area under the receiver operating curve (AUC), the accuracy rate, the specificity, etc., were used to evaluate the predictive performance of the four models.After analyzing postoperative statistics, the stone-free rate following the procedure was found to be 70.3% (n = 149). Among the various clinical variables examined, factors, such as stone number, stone diameter, stone CT value, stone location, and history of stone surgery, were identified as statistically significant in relation to the stone-free rate after PCNL. A total of 121 radiomic features were extracted, and through lasso regression, 7 features most closely associated with the stone-free rate post-PCNL were identified. The predictive accuracy of different models (Logistic Regression, RF, XGBoost, and GBDT) for determining the stone-free rate after PCNL was evaluated, yielding accuracies of 78.1%, 76.6%, 75.0%, and 73.4%, respectively. The corresponding area under the curve AUC (95%CI) were 0.85 (0.83-0.89), 0.81 (0.76-0.85), 0.82 (0.78-0.85), and 0.77 (0.73-0.81), positioning these models among the top performers in logistic regression prediction. In terms of predictive importance scores, the key factors identified by the logistic regression model were number of stone, zone percentage, stone diameter, and surface area. Similarly, the RF model highlighted number of stone, stone CT value, stone diameter, and surface area as the top predictors.Among the four machine learning models, the logistic regression model demonstrated the highest accuracy and discrimination ability in predicting the stone-free rate following PCNL. In comparison to XGBoost and GBDT, RF also exhibited superior accuracy and a certain level of discrimination ability. However, based on the performance of all four models, logistic regression is more likely to aid in clinical decision-making by assisting clinicians in diagnosing PCNL in patients. This enables us to effectively predict the presence of residual stones post-surgery and ultimately select patients who are suitable candidates for PCNL.

Investigation of optimal feature for milling chatter identification using supervised machine learning techniques

Anemia is one of the common adverse reactions after hip fracture surgery. The traditional method to solve anemia is allogeneic transfusion. However, the transfusion may lead to some complications such as septicemia and fever. So far, few studies have reported roles of machine learning in predicting whether blood transfusion is needed or not after hip fracture surgery. Therefore, the purpose of this study is to develop machine learning models to predict the likelihood of postoperative blood transfusion in patients undergoing hip fracture surgery. This study enrolled 1355 patients who underwent hip fracture surgery at the Affiliated Hospital of Qingdao University from January 2016 to December 2021. Among all patients, 210 cases received postoperative blood transfusion. All patients were randomly divided into a training group and a testing group at a ratio of 7:3. In the training group, univariate and multivariate logistic regression analyses were used to determine independent risk factors for the postoperative transfusion. Then, based on these independent risk factors, tenfold cross-validation method was utilized to develop five machine learning models, including logistic, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The receiver operating characteristic (ROC) curve, area under ROC curve (AUC), and Matthews correlation coefficient (MCC) were generated to evaluate the performance of the models. Calibration plot and decision curve analysis (DCA) were used to test the performance, stability, and clinical applicability of the models. The models were validated using the testing group; and the ROC curve, MCC, calibration plot, and DCA curves were also generated to validate the performance, stability, and clinical applicability of the models. To further verify the robustness of the model, we randomly grabbed 70% of the samples in the testing set, performed 1000 iterations, and calculated the AUC and confidence interval of the five models. Finally, we used SHapley Additive exPlanations (SHAP) to explain these models. Multivariate logistic regression analysis showed that there were 8 independent risk factors, including age, blood transfusion history, albumin (ALB), globulin (GLO), total bilirubin (TBIL), indirect bilirubin (IBIL), hemoglobin (HB), and blood loss > 200ml. We finally selected five independent risk factors including HB, GLO, age, IBIL, and blood loss > 200ml. Based on these five independent risk factors, we generated six characteristic variables, namely HB, HB × HB, HB × blood loss, GLO × HB, age, age × IBIL, and established five machine learning models using a tenfold cross-validation method. In the training group, the AUC values of logistic, RF, MLP, SVM, and XGB were 0.9320, 0.8911, 0.9327, 0.9225, and 0.8825, respectively, and the average AUC was 0.9122 ± 0.0212. The MCC values were 0.65, 0.77, 0.65, 0.66, and 0.68, respectively, and the calibration plot and DCA performed well. In the testing group the AUC values of logistic, RF, MLP, SVM, and XGB were 0.8483, 0.7978, 0.8576, 0.8598, and 0.8216, respectively. The average AUC was 0.8370 ± 0.0238, and the MCC values were 0.41, 0.35, 0.40, 0.41, and 0.41, respectively. The calibration plot and DCA in the testing group also showed good performance. The AUC values and confidence intervals of the 1000-iteration model were: logistic (AUC, min confidence interval [CI]-max confidence interval [CI] 0.848, 0.804-0.903), RF (AUC, minCI-maxCI 0.797, 0.734-0.857), MLP (AUC, minCI-maxCI 0.858, 0.812-0.902), SVM (AUC, minCI-maxCI 0.859, 0.819-0.910), and XGB (AUC, minCI-maxCI 0.821, 0.764-0.894). The model performed well. Finally, according to SHAP, among all five models, HB played the most important role in model prediction and interpretation. The five models we developed all performed well in predicting the likelihood of blood transfusion after hip fracture surgery. Therefore, we believed that the prediction model based on machine learning had great application prospects in clinical practice, which could help clinicians better predict the risk of blood transfusion after hip fracture surgery.