Gradient Boosting Machine Model Research Articles

Machine-learning algorithms in screening for type 2 diabetes mellitus: Data from Fasa Adults Cohort Study.

The application of machine learning (ML) is increasingly growing in biomedical sciences. This study aimed to evaluate factors associated with type 2 diabetes mellitus (T2DM) and compare the performance of ML methods in identifying individuals with the disease in an Iranian setting. Using the baseline data from Fasa Adult Cohort Study (FACS) and in a sex-stratified manner, we studied factors associated with T2DM by applying seven different ML methods including Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbours (KNN), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGB) and Bagging classifier (BAG). We further compared the performance of these methods; for each algorithm, accuracy, precision, sensitivity, specificity, F1 score, and Area Under Curve (AUC) were calculated. 10,112 participants were recruited between 2014 and 2016, of whom 1246 had T2DM at baseline. 4566 (45%) participants were males, aged between 35 and 70 years. For males, age, sugar consumption, and history of hospitalization were the most weighted variables regarding their importance in screening for T2DM using the GBM model, respectively; these variables were sugar consumption, urine blood, and age for females. GBM outperformed other models for both males and females with AUC of 0.75 (0.69-0.82) and 0.76 (0.71-0.80), and F1 score of 0.33 (0.27-0.39) and 0.42 (0.38-0.46), respectively. GBM also showed a sensitivity of 0.24 (0.19-0.29) and a specificity of 0.98 (0.96-1.0) in males and a sensitivity of 0.38 (0.34-0.42) and specificity of 0.92 (0.89-0.95) in females. Notably, close performance characteristics were detected among other ML models. GBM model might achieve better performance in screening for T2DM in a south Iranian population.

Predictive model of acute kidney injury in critically ill patients with acute pancreatitis: a machine learning approach using the MIMIC-IV database

Background Acute kidney injury (AKI) is a common and serious complication in severe acute pancreatitis (AP), associated with high mortality rate. Early detection of AKI is crucial for prompt intervention and better outcomes. This study aims to develop and validate predictive models using machine learning (ML) to identify the onset of AKI in patients with AP. Methods Patients with AP were extracted from the MIMIC-IV database. We performed feature selection using the random forest method. Model construction involved an ensemble of ML, including random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), naive Bayes (NB), neural network (NNET), generalized linear model (GLM), and gradient boosting machine (GBM). The best-performing model was fine-tuned and evaluated through split-set validation. Results We analyzed 1,235 critically ill patients with AP, of which 667 cases (54%) experienced AKI during hospitalization. We used 49 variables to construct models, including GBM, GLM, KNN, NB, NNET, RF, and SVM. The AUC for these models was 0.814 (95% CI, 0.763 to 0.865), 0.812 (95% CI, 0.769 to 0.854), 0.671 (95% CI, 0.622 to 0.719), 0.812 (95% CI, 0.780 to 0.864), 0.688 (95% CI, 0.624 to 0.752), 0.809 (95% CI, 0.766 to 0.851), and 0.810 (95% CI, 0.763 to 0.856) respectively. In the test set, the GBM’s performance was consistent, with an area of 0.867 (95% CI, 0.831 to 0.903). Conclusions The GBM model’s precision is crucial, aiding clinicians in identifying high-risk patients and enabling timely interventions to reduce mortality rates in critical care.

A machine learning approach to differentiate wide QRS tachycardia: distinguishing ventricular tachycardia from supraventricular tachycardia.

Differential diagnosis of wide QRS tachycardia (WQCT) has been a challenging issue. Published algorithms to distinguish ventricular tachycardia (VT) and supraventricular tachycardia (SVT) have limited diagnostic capabilities. A total of 278 patients with WQCT from January 2010 to March 2022 were enrolled. The electrophysiological study confirmed SVT in 154 patients and VT in 65 ones. Two hundred nineteen WQCT 12-lead ECGs were randomly divided into development cohort (n = 165) and testing cohort (n = 54) data sets. The development cohort was split into a training group (n = 115) and an internal validation group (n = 50). Forty ECG features extracted from the 219 WQCT ECGs are fed into 9 iteratively trained ML algorithms. This novel ML algorithm was also compared with four published algorithms. In the development cohort, the Gradient Boosting Machine (GBM) model displayed the maximum area under curve (AUC) (0.91, 95% confidence interval (CI) 0.81-1.00). In the testing cohort, the GBM model had a higher AUC of 0.97 compared to 4 validated ECG algorithms, namely, Brugada (0.68), avR (0.62), RWPTII (0.72), and LLA algorithms (0.70). Accuracy, sensitivity, specificity, negative predictive value, and positive predictive value of the GBM model were 0.94, 0.97, 0.90, 0.94, and 0.95, respectively. A GBM ML model contributes to distinguishing SVT from VT based on surface ECG features. In addition, we were able to identify important indicators for distinguishing WQCT.

AI-Based Virtual Sensing of Gaseous Pollutant Emissions at the Tailpipe of a High-Performance Vehicle

<div>This scientific publication presents the application of artificial intelligence (AI) techniques as a virtual sensor for tailpipe emissions of CO, NOx, and HC in a high-performance vehicle. The study aims to address critical challenges faced in real industrial applications, including signal alignment and signal dynamics management. A comprehensive pre-processing pipeline is proposed to tackle these issues, and a light gradient-boosting machine (LightGBM) model is employed to estimate emissions during real driving cycles. The research compares two modeling approaches: one involving a unique “direct model” and another using a “two-stage model” which leverages distinct models for the engine and the aftertreatment. The findings suggest that the direct model strikes the best balance between simplicity and accuracy. Furthermore, the study investigates two sensor setups: a standard configuration and an optimized one, which incorporates an additional lambda probe in the exhaust line after the main catalyst. The results indicate a significant enhancement in performance for NOx and CO estimations with the introduction of the third lambda probe, while HC results remain relatively unchanged. Additionally, the AI model is tested on two different electronic control unit (ECU) software calibrations, yielding excellent results in both cases. This suggests that machine learning models are robust to control software variation and can be used to optimize software calibrations in a virtual environment, reducing the reliance on extensive experimental testing. Moreover, the AI model’s performance demonstrates compatibility with real-time implementation. In conclusion, this work establishes the viability and efficiency of AI techniques in accurately estimating tailpipe emissions from an engine in an industrial context. The study showcases the potential for AI to contribute to emission estimation and optimization processes, offering a promising pathway for an innovative industrial practice.</div>

Factors influencing recurrence and model development for recurrence of minimally invasive percutaneous transhepatic lithotripsy: a single-center retrospective study.

To identify factors influencing recurrence after percutaneous transhepatic choledochoscopic lithotripsy (PTCSL) and to develop a predictive model. We retrospectively analyzed clinical data from 354 patients with intrahepatic and extrahepatic bile duct stones treated with PTCSL at Qinzhou First People's Hospital between February 2018 and January 2020. Patients were followed for three years and categorized into non-recurrence and recurrence groups based on postoperative outcome. Univariate analysis identified possible predictors of stone recurrence. Data were split using the gradient boosting machine (GBM) algorithm, assigning 70% as the training set and 30% as the test set. The predictive performance of the GBM model was assessed using the receiver operating characteristic (ROC) curve and calibration curve, and compared with a logistic regression model. Six factors were identified as significant predictors of recurrence: age, diabetes, total bilirubin, biliary stricture, number of stones, and stone diameter. The GBM model, developed based on these factors, showed high predictive accuracy. The area under the ROC curve (AUC) was 0.763 (95% CI: 0.695-0.830) for the training set and 0.709 (95% CI: 0.596-0.822) for the test set. Optimal cutoff values were 0.286 and 0.264, with sensitivities of 62.30% and 66.70%, and specificities of 77.20% and 68.50%, respectively. Calibration curves indicated good agreement between predicted probabilities and observed recurrence rates in both sets. DeLong's test revealed no significant differences between the GBM and logistic regression models in predictive performance (training set: D = 0.003, P = 0.997 > 0.05; test set: D = 0.075, P = 0.940 > 0.05). Biliary stricture, stone diameter, diabetes, stone number, age, and total bilirubin significantly influence stone recurrence after PTCSL. The GBM model, based on these factors, demonstrates robust accuracy and discrimination. Both GBM and logistic regression models effectively predicted stone recurrence post-PTCSL.

A feasibility study on utilizing machine learning technology to reduce the costs of gastric cancer screening in Taizhou, China.

To optimize gastric cancer screening score and reduce screening costs using machine learning models. This study included 228,634 patients from the Taizhou Gastric Cancer Screening Program. We used three machine learning models to optimize Li's gastric cancer screening score: Gradient Boosting Machine (GBM), Distributed Random Forest (DRF), and Deep Learning (DL). The performance of the binary classification models was evaluated using the area under the curve (AUC) and area under the precision-recall curve (AUCPR). In the binary classification model used to distinguish low-risk and moderate- to high-risk patients, the AUC in the GBM, DRF, and DL full models were 0.9994, 0.9982, and 0.9974, respectively, and the AUCPR was 0.9982, 0.9949, and 0.9918, respectively. Excluding Helicobacter pylori IgG antibody, pepsinogen I, and pepsinogen II, the AUC in the GBM, DRF, and DL models were 0.9932, 0.9879, and 0.9900, respectively, and the AUCPR was 0.9835, 0.9716, and 0.9752, respectively. Remodel after removing variables IgG, PGI, PGII, and G-17, the AUC in GBM, DRF, and DL was 0.8524, 0.8482, 0.8477, and AUCPR was 0.6068, 0.6008, and 0.5890, respectively. When constructing a tri-classification model, we discovered that none of the three machine learning models could effectively distinguish between patients at intermediate and high risk for gastric cancer (F1 scores in the GBM model for the low, medium and high risk: 0.9750, 0.9193, 0.5334, respectively; F1 scores in the DRF model for low, medium, and high risks: 0.9888, 0.9479, 0.6694, respectively; F1 scores in the DL model for low, medium, and high risks: 0.9812, 0.9216, 0.6394, respectively). We concluded that gastric cancer screening indicators could be optimized when distinguishing low-risk and moderate to high-risk populations, and detecting gastrin-17 alone can achieve a good discriminative effect, thus saving huge expenditures.

Development and validation of a machine learning model for clinical wellness visit classification in cats and dogs.

Early disease detection in veterinary care relies on identifying subclinical abnormalities in asymptomatic animals during wellness visits. This study introduces a model designed to distinguish between wellness and other types of veterinary visits. The purpose of this study is to validate the use of a visit classification model compared to manual classification of veterinary visits by three board-certified veterinarians. The algorithm was initially trained using a Gradient Boosting Machine model with a dataset of 11,105 clinical visits from 2012 to 2017 involving 655 animals (85.3% dogs and 14.7% cats) across 544 U.S. veterinary practices. Three validators were tasked with classifying 400 visits, including both wellness and other types of visits, selected randomly from the same database used for initial model training, aiming to maintain consistency and relevance between the training and application phases; visit classifications were subsequently categorized into "wellness" or "other" based on majority consensus among validators to assess the model's performance in identifying wellness visits. The model demonstrated a specificity of 0.94 (95% CI: 0.91 to 0.96), implying its accuracy in distinguishing non-wellness visits. The model had a sensitivity of 0.86 (95% CI: 0.80 to 0.92), indicating its ability to correctly identify wellness visits as compared to the annotations provided by veterinary experts. The balanced accuracy, calculated as 0.90 (95% CI: 0.87 to 0.93), further confirms the model's overall effectiveness. The model exhibits high specificity and sensitivity, ensuring accurate identification of a high proportion of wellness visits. Overall, this model holds promise for advancing research on preventive care's role in subclinical disease identification, but prospective studies are needed for validation.

A new prediction model for acute kidney injury following liver transplantation using grafts from donors after cardiac death.

Acute kidney injury (AKI) is a major complication following liver transplantation (LT), which utilizes grafts from donors after cardiac death (DCD). We developed a machine-learning-based model to predict AKI, using data from 894 LT recipients (January 2015-March 2021), split into training and testing sets. Five machine learning algorithms were employed to construct the prediction models using 17 clinical variables. The performance of the models was assessed by the area under the receiver operating characteristic curve (AUC), accuracy, F1-score, sensitivity and specificity. The best-performing model was further validated in an independent cohort of 195 LT recipients who received DCD grafts between April 2021 and December 2021. The Shapley additive explanations method was utilized to elucidate the predictions and identify the most crucial features. The gradient boosting machine (GBM) model demonstrated the highest AUC (0.76, 95% CI: 0.70-0.82), F1-score (0.73, 95% CI: 0.66-0.79) and sensitivity (0.74, 95% CI: 0.66-0.80) in the testing set and a comparable AUC (0.75, 95% CI: 0.67-0.81) in the validation set. The GBM model identified high preoperative indirect bilirubin, low intraoperative urine output, prolonged anesthesia duration, low preoperative platelet count and graft steatosis graded NASH Clinical Research Network 1 and above as the top five important features for predicting AKI following LT using DCD grafts. The GBM model is a reliable and interpretable tool for predicting AKI in recipients of LT using DCD grafts. This model can assist clinicians in identifying patients at high risk and providing timely interventions to prevent or mitigate AKI.

Comparative analysis of BERT and FastText representations on crowdfunding campaign success prediction.

Crowdfunding has become a popular financing method, attracting investors, businesses, and entrepreneurs. However, many campaigns fail to secure funding, making it crucial to reduce participation risks using artificial intelligence (AI). This study investigates the effectiveness of advanced AI techniques in predicting the success of crowdfunding campaigns on Kickstarter by analyzing campaign blurbs. We compare the performance of two widely used text representation models, bidirectional encoder representations from transformers (BERT) and FastText, in conjunction with long-short term memory (LSTM) and gradient boosting machine (GBM) classifiers. Our analysis involves preprocessing campaign blurbs, extracting features using BERT and FastText, and evaluating the predictive performance of these features with LSTM and GBM models. All experimental results show that BERT representations significantly outperform FastText, with the highest accuracy of 0.745 achieved using a fine-tuned BERT model combined with LSTM. These findings highlight the importance of using deep contextual embeddings and the benefits of fine-tuning pre-trained models for domain-specific applications. The results are benchmarked against existing methods, demonstrating the superiority of our approach. This study provides valuable insights for improving predictive models in the crowdfunding domain, offering practical implications for campaign creators and investors.

Machinelearning-Basedmodelforprediction of Narcolepsy Type 1 in Patients with Obstructive Sleep Apnea with Excessive Daytime Sleepiness.

Excessive daytime sleepiness (EDS) forms a prevalent symptom of obstructive sleep apnea (OSA) and narcolepsy type 1 (NT1), while the latter might always be overlooked. Machine learning (ML) models can enable the early detection of these conditions, which has never been applied for diagnosis of NT1. The study aimed to develop ML prediction models to help non-sleep specialist clinicians identify high probability of comorbid NT1 in patients with OSA early. Totally, clinical features of 246 patients with OSA in three sleep centers were collected and analyzed for the development of nine ML models. LASSO regression was used for feature selection. Various metrics such as the area under the receiver operating curve (AUC), calibration curve, and decision curve analysis (DCA) were employed to evaluate and compare the performance of these ML models. Model interpretability was demonstrated by Shapley Additive explanations (SHAP). Based on the analysis of AUC, DCA, and calibration curves, the Gradient Boosting Machine (GBM) model demonstrated superior performance compared to other machine learning (ML) models. The top five features used in the GBM model, ranked by feature importance, were age of onset, total limb movements index, sleep latency, non-REM (Rapid Eye Movement)sleepstage 2 and severity of OSA. The study yielded a simple and feasible screening ML-based model for the early identification of NT1 in patients with OSA, which warrants further verification in more extensive clinical practices.

Prediction Model of Ocular Metastases in Gastric Adenocarcinoma: Machine Learning-Based Development and Interpretation Study.

Background: Although gastric adenocarcinoma (GA) related ocular metastasis (OM) is rare, its occurrence indicates a more severe disease. We aimed to utilize machine learning (ML) to analyze the risk factors of GA-related OM and predict its risks. Methods: This is a retrospective cohort study. The clinical data of 3532 GA patients were collected and randomly classified into training and validation sets in a ratio of 7:3. Those with or without OM were classified into OM and non-OM (NOM) groups. Univariate and multivariate logistic regression analyses and least absolute shrinkage and selection operator were conducted. We integrated the variables identified through feature importance ranking and further refined the selection process using forward sequential feature selection based on random forest (RF) algorithm before incorporating them into the ML model. We applied six ML algorithms to construct the predictive GA model. The area under the receiver operating characteristic (ROC) curve indicated the model's predictive ability. Also, we established a network risk calculator based on the best performance model. We used Shapley additive interpretation (SHAP) to identify risk factors and to confirm the interpretability of the black box model. We have de-identified all patient details. Results: The ML model, consisting of 13 variables, achieved an optimal predictive performance using the gradient boosting machine (GBM) model, with an impressive area under the curve (AUC) of 0.997 in the test set. Utilizing the SHAP method, we identified crucial factors for OM in GA patients, including LDL, CA724, CEA, AFP, CA125, Hb, CA153, and Ca2+. Additionally, we validated the model's reliability through an analysis of two patient cases and developed a functional online web prediction calculator based on the GBM model. Conclusion: We used the ML method to establish a risk prediction model for GA-related OM and showed that GBM performed best among the six ML models. The model may identify patients with GA-related OM to provide early and timely treatment.

Discriminating insulin resistance in middle-aged nondiabetic women using machine learning approaches.

We employed machine learning algorithms to discriminate insulin resistance (IR) in middle-aged nondiabetic women. The data was from the National Health and Nutrition Examination Survey (2007-2018). The study subjects were 2084 nondiabetic women aged 45-64. The analysis included 48 predictors. We randomly divided the data into training (n = 1667) and testing (n = 417) datasets. Four machine learning techniques were employed to discriminate IR: extreme gradient boosting (XGBoosting), random forest (RF), gradient boosting machine (GBM), and decision tree (DT). The area under the curve (AUC) of receiver operating characteristic (ROC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score were compared as performance metrics to select the optimal technique. The XGBoosting algorithm achieved a relatively high AUC of 0.93 in the training dataset and 0.86 in the testing dataset to discriminate IR using 48 predictors and was followed by the RF, GBM, and DT models. After selecting the top five predictors to build models, the XGBoost algorithm with the AUC of 0.90 (training dataset) and 0.86 (testing dataset) remained the optimal prediction model. The SHapley Additive exPlanations (SHAP) values revealed the associations between the five predictors and IR, namely BMI (strongly positive impact on IR), fasting glucose (strongly positive), HDL-C (medium negative), triglycerides (medium positive), and glycohemoglobin (medium positive). The threshold values for identifying IR were 29 kg/m2, 100 mg/dL, 54.5 mg/dL, 89 mg/dL, and 5.6% for BMI, glucose, HDL-C, triglycerides, and glycohemoglobin, respectively. The XGBoosting algorithm demonstrated superior performance metrics for discriminating IR in middle-aged nondiabetic women, with BMI, glucose, HDL-C, glycohemoglobin, and triglycerides as the top five predictors.

Low CDKN1B Expression Associated with Reduced CD8+ T Lymphocytes Predicts Poor Outcome in Breast Cancer in a Machine Learning Analysis.

The cyclin-dependent kinase inhibitor 1B (CDKN1B) gene, which encodes the p27Kip1 protein, is important in regulating the cell cycle process and cell proliferation. Its role in breast cancer prognosis is controversial. We evaluated the significance and predictive role of CDKN1B expression in breast cancer prognosis. We investigated the clinicopathologic factors, survival rates, immune cells, gene sets, and prognostic models according to CDKN1B expression in 3794 breast cancer patients. We performed gene set enrichment analysis (GSEA), in silico cytometry, pathway network analyses, gradient boosting machine (GBM) learning, and in vitro drug screening. High CDKN1B expression levels in breast cancer correlated with high lymphocyte infiltration signature scores and increased CD8+ T cells, both of which were associated with improved prognosis in breast cancer. which were associated with a better prognosis. CDKN1B expression was associated with gene sets for the upregulation of T-cell receptor signaling pathways and downregulation of CD8+ T cells. Pathway network analysis revealed a direct link between CDKN1B and the pathway involved in the positive regulation of the protein catabolic process pathway. In addition, an indirect link was identified between CDKN1B and the T-cell receptor signaling pathway. In in vitro drug screening, BMS-345541 demonstrated efficacy as a therapeutic targeting of CDKN1B, effectively impeding the growth of breast cancer cells characterized by low CDKN1B expression. The inclusion of CDKN1B expression in GBM models increased the accuracy of survival predictions. CDKN1B expression plays a significant role in breast cancer progression, implying that targeting CDKN1B might be a promising strategy for treating breast cancer.

Leveraging multimodal MRI-based radiomics analysis with diverse machine learning models to evaluate lymphovascular invasion in clinically node-negative breast cancer

ObjectiveThis study aimed to investigate and validate the effectiveness of diverse radiomics models for preoperatively differentiating lymphovascular invasion (LVI) in clinically node-negative breast cancer (BC). MethodsThis study included 198 patients diagnosed with clinically node-negative bc and pathologically confirmed LVI status from January 2018–July 2023. The training dataset consisted of 138 patients, while the validation dataset included 60. Radiomics features were extracted from multimodal magnetic resonance imaging obtained from T1WI, T2WI, DCE, DWI, and ADC sequences. Dimensionality reduction and feature selection techniques were applied to the extracted features. Subsequently, machine learning approaches, including logistic regression, support vector machine, classification and regression trees, k-nearest neighbors, and gradient boosting machine models (GBM), were constructed using the radiomics features. The best-performing radiomic model was selected based on its performance using the confusion matrix. Univariate and multivariable logistic regression analyses were conducted to identify variables for developing a clinical-radiological (Clin-Rad) model. Finally, a combined model incorporating both radiomics and clinical-radiological model features was created. ResultsA total of 6195 radiomic features were extracted from multimodal magnetic resonance imaging. After applying dimensionality reduction and feature selection, seven valuable radiomics features were identified. Among the radiomics models, the GBM model demonstrated superior predictive efficiency and robustness, achieving area under the curve values (AUC) of 0.881 (0.823,0.940) and 0.820 (0.693,0.947) in the training and validation datasets, respectively. The Clin-Rad model was developed based on the peritumoral edema and DWI rim sign. In the training dataset, it achieved an AUC of 0.767 (0.681, 0.854), while in the validation dataset, it achieved an AUC of 0.734 (0.555–0.913). The combined model, which incorporated radiomics and the Clin-Rad model, showed the highest discriminatory capability. In the training dataset, it had an AUC value of 0.936 (0.892, 0.981), and in the validation dataset, it had an AUC value of 0.876 (0.757, 0.995). Additionally, decision curve analysis of the combined model revealed its optimal clinical efficacy. ConclusionThe combined model, integrating radiomics and clinical-radiological features, exhibited excellent performance in distinguishing LVI status. This non-invasive and efficient approach holds promise for aiding clinical decision-making in the context of clinically node-negative BC.

Machine learning-based water quality prediction using octennial in-situ Daphnia magna biological early warning system data

Biological early warning system (BEWS) has been globally used for surface water quality monitoring. Despite its extensive use, BEWS has exhibited limitations, including difficulties in biological interpretation and low alarm reproducibility. This study addressed these issues by applying machine learning (ML) models to eight years of in-situ BEWS data for Daphnia magna. Six ML models were adopted to predict contamination alarms from Daphnia behavioral parameters. The light gradient boosting machine model demonstrated the most significant improvement in predicting alarms from Daphnia behaviors. Compared with the traditional BEWS alarm index, the ML model enhanced the precision and recall by 29.50% and 43.41%, respectively. The speed distribution index and swimming speed were significant parameters for predicting water quality warnings. The nonlinear relationships between the monitored Daphnia behaviors and water physicochemical water quality parameters (i.e., flow rate, Chlorophyll-a concentration, water temperature, and conductivity) were identified by ML models for simulating Daphnia behavior based on the water contaminants. These findings suggest that ML models have the potential to establish a robust framework for advancing the predictive capabilities of BEWS, providing a promising avenue for real-time and accurate assessment of water quality. Thereby, it can contribute to more proactive and effective water quality management strategies.

Synthetic Tabular Data Based on Generative Adversarial Networks in Health Care: Generation and Validation Using the Divide-and-Conquer Strategy.

Synthetic data generation (SDG) based on generative adversarial networks (GANs) is used in health care, but research on preserving data with logical relationships with synthetic tabular data (STD) remains challenging. Filtering methods for SDG can lead to the loss of important information. This study proposed a divide-and-conquer (DC) method to generate STD based on the GAN algorithm, while preserving data with logical relationships. The proposed method was evaluated on data from the Korea Association for Lung Cancer Registry (KALC-R) and 2 benchmark data sets (breast cancer and diabetes). The DC-based SDG strategy comprises 3 steps: (1) We used 2 different partitioning methods (the class-specific criterion distinguished between survival and death groups, while the Cramer V criterion identified the highest correlation between columns in the original data); (2) the entire data set was divided into a number of subsets, which were then used as input for the conditional tabular generative adversarial network and the copula generative adversarial network to generate synthetic data; and (3) the generated synthetic data were consolidated into a single entity. For validation, we compared DC-based SDG and conditional sampling (CS)-based SDG through the performances of machine learning models. In addition, we generated imbalanced and balanced synthetic data for each of the 3 data sets and compared their performance using 4 classifiers: decision tree (DT), random forest (RF), Extreme Gradient Boosting (XGBoost), and light gradient-boosting machine (LGBM) models. The synthetic data of the 3 diseases (non-small cell lung cancer [NSCLC], breast cancer, and diabetes) generated by our proposed model outperformed the 4 classifiers (DT, RF, XGBoost, and LGBM). The CS- versus DC-based model performances were compared using the mean area under the curve (SD) values: 74.87 (SD 0.77) versus 63.87 (SD 2.02) for NSCLC, 73.31 (SD 1.11) versus 67.96 (SD 2.15) for breast cancer, and 61.57 (SD 0.09) versus 60.08 (SD 0.17) for diabetes (DT); 85.61 (SD 0.29) versus 79.01 (SD 1.20) for NSCLC, 78.05 (SD 1.59) versus 73.48 (SD 4.73) for breast cancer, and 59.98 (SD 0.24) versus 58.55 (SD 0.17) for diabetes (RF); 85.20 (SD 0.82) versus 76.42 (SD 0.93) for NSCLC, 77.86 (SD 2.27) versus 68.32 (SD 2.37) for breast cancer, and 60.18 (SD 0.20) versus 58.98 (SD 0.29) for diabetes (XGBoost); and 85.14 (SD 0.77) versus 77.62 (SD 1.85) for NSCLC, 78.16 (SD 1.52) versus 70.02 (SD 2.17) for breast cancer, and 61.75 (SD 0.13) versus 61.12 (SD 0.23) for diabetes (LGBM). In addition, we found that balanced synthetic data performed better. This study is the first attempt to generate and validate STD based on a DC approach and shows improved performance using STD. The necessity for balanced SDG was also demonstrated.

Machine learning-based prediction of 30-day major adverse cardiac and cerebrovascular events in non-cardiac surgery patients

Abstract Background The number of non-cardiac surgeries performed worldwide has been steadily increasing, presenting a challenge for clinicians to accurately identify patients at high risk of complications and to allocate the appropriate level of perioperative care. Accurate prediction of postoperative mortality is crucial not only for successful patient care, but also for information-based shared decision-making with patients and efficient allocation of medical resources. Purpose In this study, we aimed to develop a novel predictive model using machine learning methods applied to electronic health record data. Our objective is to identify the risk factors most likely to lead to 30-day major adverse cardiac and cerebrovascular events after non-cardiac surgery Methods We conducted a retrospective analysis of data from a single tertiary care institution that included patients aged 65 years or over who underwent non-cardiac surgery from May 2003 and December 2020. The Observational Medical Outcomes Partnership (OMOP) common data model (CDM) data was used to build predictive models, which allowed for the utilization of demographic data, as well as preoperative characteristics such as diagnosis, lab results, vital signs, medications, and information on operations and procedures from the electronic health records (EHRs) in a standardized way. We employed machine learning models, which were developed and validated using the OHDSI Patient-Level-Prediction framework. Results We included a total of 47,915 patients to train (75%) and test (25%) our predictive models. To compare prediction performances, we applied gradient boosting machine (GBM), logistic regression (LR), random forest (RF), AdaBoost (AB), and decision tree (DT). Our results for a test data (Fig 1.) showed that the GBM model had the best performance in terms of the area under the receiver operating characteristic curve (AUROC) (0.903) and the area under the precision-recall curve (AUPRC) (0.395). Conclusions Our study demonstrates that applying machine learning algorithms to electronic health record data can effectively identify patients at high risk of major adverse cardiac and cerebrovascular events following non-cardiac surgery. This algorithm has the potential to support clinicians in effectively identifying patients at high risk and provide appropriate perioperative care. Further work is needed to validate and refine the proposed model to ensure its external validity and broader applicability in clinical practice.We plan to validate the proposed model externally by testing it on a cohort of approximately 280,000 patients from other tertiary care institution, and present the results at the 2023 ESC Congress.

A generalizable electrocardiogram-based artificial intelligence model for 10-year heart failure risk prediction

BackgroundHeart failure (HF) is a progressive condition with high global incidence. HF has two main subtypes: HF with preserved ejection fraction (HFpEF) and HF with reduced ejection fraction (HFrEF). There is an inherent need for simple yet effective ECG-based artificial intelligence (AI; ECG-AI) models which can predict HF risk early to allow for risk modification. ObjectiveThe main objectives were to validate HF risk prediction models using Multi-Ethnic Study of Atherosclerosis (MESA) data and assess performance of on HFpEF and HFrEF classification. MethodsECG-AI model was developed using raw 12-lead ECGs within a convolutional neural network (CNN). The clinical models from ARIC (ARIC-HF) and Framingham Heart Study (FHS-HF) used nine and eight variables, respectively. ECG-AI plus the clinical data within a Cox Proportional Hazard model (ECG-AI-Cox) and, for ECG-based comparison, a new Light Gradient Boosting Machine model using 288 ECG Characteristics (ECG-Chars) were developed. All the models were validated on MESA. The performances of these models were evaluated using the area under the receiver operating characteristic curve (ROC AUC) and compared using De-Long Test. ResultsECG-AI, ECG-Chars, and ECG-AI-Cox resulted in validation AUCs of 0.77, 0.73, and 0.84, respectively. ARIC-HF and FHS-HF yielded AUCs=0.76 and 0.74, respectively and CPH resulted in AUC=0.78. ECG-AI-Cox outperformed all other models. ECG-AI-Cox provided an AUC of 0.85 for HFrEF and 0.83 for HFpEF. ConclusionECG-AI utilizing ECGs provides better validated predictions when compared to HF risk calculators and the ECG feature model and also works well with HFpEF and HFrEF classification.

Dynamic geospatial modeling of mycotoxin contamination of corn in Illinois: unveiling critical factors and predictive insights with machine learning.

Mycotoxin contamination of corn is a pervasive problem that negatively impacts human and animal health and causes economic losses to the agricultural industry worldwide. Historical aflatoxin (AFL) and fumonisin (FUM) mycotoxin contamination data of corn, daily weather data, satellite data, dynamic geospatial soil properties, and land usage parameters were modeled to identify factors significantly contributing to the outbreaks of mycotoxin contamination of corn grown in Illinois (IL), AFL >20 ppb, and FUM >5 ppm. Two methods were used: a gradient boosting machine (GBM) and a neural network (NN). Both the GBM and NN models were dynamic at a state-county geospatial level because they used GPS coordinates of the counties linked to soil properties. GBM identified temperature and precipitation prior to sowing as significant influential factors contributing to high AFL and FUM contamination. AFL-GBM showed that a higher aflatoxin risk index (ARI) in January, March, July, and November led to higher AFL contamination in the southern regions of IL. Higher values of corn-specific normalized difference vegetation index (NDVI) in July led to lower AFL contamination in Central and Southern IL, while higher wheat-specific NDVI values in February led to higher AFL. FUM-GBM showed that temperature in July and October, precipitation in February, and NDVI values in March are positively correlated with high contamination throughout IL. Furthermore, the dynamic geospatial models showed that soil characteristics were correlated with AFL and FUM contamination. Greater calcium carbonate content in soil was negatively correlated with AFL contamination, which was noticeable in Southern IL. Greater soil moisture and available water-holding capacity throughout Southern IL were positively correlated with high FUM contamination. The higher clay percentage in the northeastern areas of IL negatively correlated with FUM contamination. NN models showed high class-specific performance for 1-year predictive validation for AFL (73%) and FUM (85%), highlighting their accuracy for annual mycotoxin prediction. Our models revealed that soil, NDVI, year-specific weekly average precipitation, and temperature were the most important factors that correlated with mycotoxin contamination. These findings serve as reliable guidelines for future modeling efforts to identify novel data inputs for the prediction of AFL and FUM outbreaks and potential farm-level management practices.

Machine Learning for COVID-19 and Influenza Classification during Coexisting Outbreaks

This study compares the performance of machine learning models for selecting COVID-19 and influenza tests during coexisting outbreaks in Brazil, avoiding the waste of resources in healthcare units. We used COVID-19 and influenza datasets from Brazil to train the Decision Tree (DT), Multilayer Perceptron (MLP), Gradient Boosting Machine (GBM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), K-Nearest Neighbors, Support Vector Machine (SVM), and Logistic Regression algorithms. Moreover, we tested the models using the 10-fold cross-validation method to increase confidence in the results. During the experiments, the GBM, DT, RF, XGBoost, and SVM models showed the best performances, with similar results. The high performance of tree-based models is relevant for the classification of COVID-19 and influenza because they are usually easier to interpret, positively impacting the decision-making of health professionals.