A hybrid machine learning model for predicting Real-Time secondary crash likelihood

Real-time estimation of secondary crash likelihood on freeways using high-resolution loop detector data

Secondary crashes are generally understood as crashes that occur as a result of primary incidents. Research is needed to determine the nature and cause of these crashes. However, to date, this research has been limited for two reasons. First, there is no uniform definition of secondary crashes. Second, the usually poor quality of incident data and the unavailability of related traffic data make any analysis of secondary crashes difficult. This paper describes a study that uses a comprehensive incident database from District 4 of the Florida Department of Transportation to identify freeway secondary crashes and their contributing factors. A method based on a cumulative arrival and departure traffic delay model was developed to estimate the maximum queue length and the associated queue recovery time for incidents with lane blockages. Descriptive statistics and logistic regression analysis were applied to understand the factors contributing to secondary crashes. The logistic regression analysis indicates that the following four factors have significant effects on the likelihood of secondary crashes: primary incident type, primary incident lane-blockage duration, time of day, and whether the incident occurred on northbound I-95.

A percentage of crashes on freeways are suspected to be caused in part by congestion or distraction from earlier incidents. Identification and prevention of these secondary crashes are major goals of transportation agencies, yet the characteristics of secondary crashes—in particular the probability of their occurrence—are poorly understood. Many secondary crashes occur when a vehicle encounters nonrecurring congestion, yet previous efforts to identify incident queues and their secondary crashes have relied either on deterministic queuing theory or on data from uniformly spaced dense loop detectors. This study is the first analysis of secondary crash occurrence to integrate incident timelines and traffic volumes with widely available and legally obtained private-sector speed data. Analysis found that 9.2% of all vehicle crashes were secondary to another incident and that 6.2% of these crashes were tertiary to another primary incident. Secondary crashes occurred on average once every 10 crashes and 54 disabled vehicles. The findings support a fast incident response, because the probability of a secondary crash occurrence increases approximately 1 percentage point for every additional 2 to 3 min spent on the scene in high-volume scenarios.

Background This study aimed to establish and validate a machine learning (ML) model for predicting in-hospital mortality in critically ill patients with chronic kidney disease (CKD). Methods This study collected data on CKD patients from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. Six ML approaches were used to build the model. Accuracy and area under the curve (AUC) were used to choose the best model. In addition, the best model was interpreted using SHapley Additive exPlanations (SHAP) values. Results There were 8527 CKD patients eligible for participation; the median age was 75.1 (interquartile range: 65.0–83.5) years, and 61.7% (5259/8527) were male. We developed six ML models with clinical variables as input factors. Among the six models developed, the eXtreme Gradient Boosting (XGBoost) model had the highest AUC, at 0.860. According to the SHAP values, the sequential organ failure assessment score, urine output, respiratory rate, and simplified acute physiology score II were the four most influential variables in the XGBoost model. Conclusions In conclusion, we successfully developed and validated ML models for predicting mortality in critically ill patients with CKD. Among all ML models, the XGBoost model is the most effective ML model that can help clinicians accurately manage and implement early interventions, which may reduce mortality in critically ill CKD patients with a high risk of death.

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

Accurate shale gas reserves estimation is essential for development. Existing machine learning (ML) models for predicting gas isothermal adsorption are limited by small datasets and lack verified generalization. We constructed an “original dataset” containing 2112 data points from 11 measurements on samples from 8 formations in 3 countries to develop ML‐based prediction models. Similar to previous ML models, total organic matter, pressure, and temperature are characterized as the three most significant features using the mean impurity method. In contrast to previous ML models, the study reveals that these three features are inadequate to be used to make reasonable predictions for the datasets from the measurements different from those used to train the models. Instead, the extreme gradient boosting decision trees (XGBoost) model with two more features (specific surface area and moisture) exhibits good robustness, generalization, and precision in the prediction of gas isothermal adsorption. Overall, An XGBoost model with optimal input features is developed in this work, which exhibits both good performance in gas adsorption prediction and good potential for the estimation of gas storage in shale gas development.

Stent malapposition (SM) following percutaneous coronary intervention (PCI) for myocardial infarction continues to present significant clinical challenges. In recent years, machine learning (ML) models have demonstrated potential in disease risk stratification and predictive modeling. ML models based on optical coherence tomography (OCT) imaging, laboratory tests, and clinical characteristics can predict the occurrence of SM. We studied 337 patients from the Affiliated Hospital of Zunyi Medical University, China, who had PCI and coronary OCT from May to October 2023. We employed nested cross-validation to partition patients into training and test sets. We developed five ML models: XGBoost, LR, RF, SVM, and NB based on calcification features. Performance was assessed using ROC curves. Lasso regression selected features from 46 clinical and 21 OCT imaging features, which were optimized with the five ML algorithms. In the prediction model based on calcification features, the XGBoost model and SVM model exhibited higher AUC values. Lasso regression identified five key features from clinical and imaging data. After incorporating selected features into the model for optimization, the AUC values of all algorithmic models showed significant improvements. The XGBoost model demonstrated the highest calibration accuracy. SHAP values revealed that the top five ranked features influencing the XGBoost model were calcification length, age, coronary dissection, lipid angle, and troponin. ML models developed using plaque imaging features and clinical characteristics can predict the occurrence of SM. ML models based on clinical and imaging features exhibited better performance.

Anomaly detection is an important task in finding out the irregular patterns or behaviors in different applications such as cybersecurity, financial systems, healthcare applications, and industrial automation. Recent studies have shown that machine learning models have appeared to be promising in enhancing anomaly detection systems in terms of their accuracy and efficiency. This article aims to introduce a comparative study of the efficiency of different machine learning models in implementing anomaly detection. Different machine learning models such as support vector machines, K-Nearest Neighbor algorithms, hybrid models, and decision trees have been used in this article. Standard models such as Support Vector Machine, K-Nearest Neighbors, Decision Tree Classifier, XGBoost models have been subjected to testing through benchmarking. The models have undergone testing based on some primary factors such as accuracy rates, precision rates, recall rates, F1 Score, and efficiency. The results obtained from this study indicate that the XGBoost model and Random Forest model perform better than the existing models in terms of anomaly detection efficiency.

This study aimed to preliminarily develop machine learning (ML) models capable of predicting the risk of device-associated infection and 30-day outcomes following invasive device procedures in intensive care unit (ICU) patients. The study utilized data from 8574 ICU patients who underwent invasive procedures, sourced from the Medical Information Mart for Intensive Care (MIMIC)-IV version 2.2 database. Patients were allocated into training and validation datasets in a 7:3 ratio. Seven ML models were employed for predicting device-associated infections, while five models were used for predicting 30-day survival outcomes. Model performance was primarily evaluated using the receiver operating characteristic (ROC) curve for infection prediction and the survival model’s concordance index (C-index). Top-performing models progressively reduced the number of variables based on their importance, thereby optimizing practical utility. The inclusion of all variables demonstrated that extreme gradient boosting (XGBoost) and extra survival trees (EST) models yielded superior discriminatory performance. Notably, when restricted to the top 10 variables, both models maintained performance levels comparable to when all variables were included. In the validation cohort, the XGBoost model, with the top 10 variables, achieved an area under the curve (AUC) of 0.810 (95% CI 0.808–0.812), an area under the precision-recall curve (AUPRC) of 0.226 (95% CI 0.222–0.230), and a Brier score (BS) of 0.053 (95% CI 0.053–0.054). The EST model, with the top 10 variables, reported a C-index of 0.756 (95% CI 0.754–0.757), a time-dependent AUC of 0.769 (95% CI 0.763–0.775), and an integrated Brier score (IBS) of 0.087 (95% CI 0.087–0.087). Both models are accessible via a web application. The internally evaluated XGBoost and EST models demonstrated exceptional predictive accuracy for device-associated infection risks and 30-day survival outcomes post-invasive procedures in ICU patients. Further validation is required to confirm the clinical utility of these two models in future studies.

Category:Ankle Arthritis; AnkleIntroduction/Purpose:Ankle arthrodesis and total ankle replacement are the most commonly performed procedures for surgical management of ankle arthritis. Arthrodesis provides effective pain relief but the rate of complications after arthrodesis is higher as it is more commonly performed in patients with comorbidities that preclude ankle replacement. Accurately risk- stratifying patients who undergo ankle arthrodesis would be of great utility, given the significant cost and morbidity associated with developing major perioperative complications. There is a paucity of accurate prediction models that can be used to pre- operatively risk-stratify patients for ankle arthrodesis. We aim to develop a machine learning (ML) algorithm for prediction of major perioperative complication after ankle arthrodesis as well as compare its performance against traditional predictive models based on logistic regression.Methods:This is a retrospective cohort study of adult patients who underwent ankle arthrodesis at any non-federal California hospital between 2015 and 2017. The primary outcome was readmission within 30 days or major perioperative complication - venous thromboembolism within 30 days, myocardial infarction within 7 days, pneumonia within 7 days, systemic infection within 7 days, surgical site bleeding within 90 days, and wound complications within 90 days. We build ML and logistic regression models that span different classes of modeling approaches: XGBoost, AdaBoost, Gradient Boosting, and Random Forest. Discrimination and calibration were assessed using area under the receiver operating characteristic curve (AUROC) and Brier score, respectively. We utilize a partial dependence function to measure the importance of an individual feature by assessing the average effect in predicted risks when its value is altered. We rank the contribution of the included variables to the prediction of adverse outcomes.Results:A total of 1,084 patients met inclusion criteria for this study. There were 131 major complications or readmission (12.1%). The optimized XGBoost algorithm demonstrates higher discrimination (AUROC: 0.707 + 0.052) compared to LR (0.691 + 0.055). The receiver operating characteristic curves for the XGBoost and logistic regression models are visualized in Figure 1. XGBoost also outperforms the three other ML models. This model was well calibrated (Brier score: 0.103 + 0.001). The variables most important for the XGBoost model include diabetes, chronic kidney disease, implant complication, and major fracture. Five of the ten most important features for XGBoost were markedly less important for the traditional logistic regression model: male sex, prior hip fracture, cardiorespiratory failure, acute renal failure, and dialysis status.Conclusion:We report a ML algorithm for prediction of major perioperative complications after ankle arthrodesis. The optimized XGBoost model is well-calibrated and demonstrates superior risk prediction to logistic regression. This tool may identify and address potentially modifiable risk factors, helping to accurately risk-stratify patients and decrease likelihood of major complications. Notably, the predictors most important for XGBoost are different from those for logistic regression. This suggests that the superior discriminative capability of ML methods stems from their ability to capture complex non-linear relationships between variables that logistic regression is unable to detect.

Background:Systemic lupus erythematosus (SLE) is a chronic autoimmune disease that affects multiple organs and systems. However, in addition to physical damage, patients with SLE have an increased risk of mental...

ObjectivesThis study aims to build a machine learning (ML) model to predict the recurrence probability for postoperative non-lactating mastitis (NLM) by Random Forest (RF) and XGBoost algorithms. It can provide the ability to identify the risk of NLM recurrence and guidance in clinical treatment plan.MethodsThis study was conducted on inpatients who were admitted to the Mammary Department of Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine between July 2019 to December 2021. Inpatient data follow-up has been completed until December 2022. Ten features were selected in this study to build the ML model: age, body mass index (BMI), number of abortions, presence of inverted nipples, extent of breast mass, white blood cell count (WBC), neutrophil to lymphocyte ratio (NLR), albumin-globulin ratio (AGR) and triglyceride (TG) and presence of intraoperative discharge. We used two ML approaches (RF and XGBoost) to build models and predict the NLM recurrence risk of female patients. Totally 258 patients were randomly divided into a training set and a test set according to a 75%-25% proportion. The model performance was evaluated based on Accuracy, Precision, Recall, F1-score and AUC. The Shapley Additive Explanations (SHAP) method was used to interpret the model.ResultsThere were 48 (18.6%) NLM patients who experienced recurrence during the follow-up period. Ten features were selected in this study to build the ML model. For the RF model, BMI is the most important influence factor and for the XGBoost model is intraoperative discharge. The results of tenfold cross-validation suggest that both the RF model and the XGBoost model have good predictive performance, but the XGBoost model has a better performance than the RF model in our study. The trends of SHAP values of all features in our models are consistent with the trends of these features’ clinical presentation. The inclusion of these ten features in the model is necessary to build practical prediction models for recurrence.ConclusionsThe results of tenfold cross-validation and SHAP values suggest that the models have predictive ability. The trend of SHAP value provides auxiliary validation in our models and makes it have more clinical significance.

Background: Ensemble tree-based models such as Xgboost are highly prognostic in cardiovascular medicine, as measured by the Clinical Effectiveness Metric (CEM). However, their ability to handle correlated data, such as hospital-level effects, is limited. Objectives: The aim of this work is to develop a binary-outcome mixed-effects Xgboost (BME) model that integrates random effects at the hospital level. To ascertain how well the model handles correlated data in cardiovascular outcomes, we aim to assess its performance and compare it to fixed-effects Xgboost and traditional logistic regression models. Methods: A total of 227,087 patients over 17 years of age, undergoing cardiac surgery from 42 UK hospitals between 1 January 2012 and 31 March 2019, were included. The dataset was split into two cohorts: training/validation (n = 157,196; 2012–2016) and holdout (n = 69,891; 2017–2019). The outcome variable was 30-day mortality with hospitals considered as the clustering variable. The logistic regression, mixed-effects logistic regression, Xgboost and binary-outcome mixed-effects Xgboost (BME) were fitted to both standardized and unstandardized datasets across a range of sample sizes and the estimated prediction power metrics were compared to identify the best approach. Results: The exploratory study found high variability in hospital-related mortality across datasets, which supported the adoption of the mixed-effects models. Unstandardized Xgboost BME demonstrated marked improvements in prediction power over the Xgboost model at small sample size ranges, but performance differences decreased as dataset sizes increased. Generalized linear models (glms) and generalized linear mixed-effects models (glmers) followed similar results, with the Xgboost models also excelling at greater sample sizes. Conclusions: These findings suggest that integrating mixed effects into machine learning models can enhance their performance on datasets where the sample size is small.

Development and validation of interpretable machine learning model for pre-treatment predicting the response to targeted and immune therapy in hepatocellular carcinoma.

Glass forming ability prediction of bulk metallic glasses based on fused strategy