Extreme Gradient Boosting Model Research Articles

Mapping model between lateral responses of bridges under random traffic loads based on data-driven approach

Abstract The lateral distribution characteristic of a bridge is one of the important features reflecting its in-service state. Conventional deterministic indicators often struggle to consider this time-varying feature. In this study, a data-driven approach is employed to establish the mapping model among responses at the different lateral positions using the eXtreme Gradient Boosting model optimized by the Bayesian optimization algorithm. The proposed method is validated based on both data from a bridge health monitoring system equipped on an actual bridge and data from numerical simulation. At different lateral positions of the actual bridge, the overall coefficient of determination (R2) of the strain response mapped by the model is above 0.991, and the overall root mean squared error (RMSE) of the strain response mapped by the model are below 1.159 με. The numerical simulation method is used to consider a variety of working conditions with different road surface roughness and different traffic densities. Under different working conditions, the overall R2 of the deflection response mapped by the model is still above 0.961, and the overall RMSE of the deflection response mapped by the model is below 0.249 mm. These indicate that the proposed model can consider time-varying mapping relationships among responses at different lateral positions, and has good accuracy and applicability.

Recognition of Longitudinal Cracks on Slab Surfaces Based on Particle Swarm Optimization and eXtreme Gradient Boosting Model

Recognition of Longitudinal Cracks on Slab Surfaces Based on Particle Swarm Optimization and eXtreme Gradient Boosting Model

Analysis and prediction of freeze-thaw resistance of concrete based on machine learning

Based on Support Vector Regression, Random Forest Regression, Gradient Boosting and Extreme Gradient Boosting, a prediction model of concrete's freeze-thaw mass loss rate with high accuracy and strong generalization ability is established. The impacts of water, cement, fly ash, slag, sand, natural coarse aggregate, recycled coarse aggregate, superplasticizer, air-entraining agent, and the number freeze-thaw cycles on the freeze-thaw resistance of concrete are systematically analyzed using feature importance analysis, global interpretation and partial dependence analysis. The main results are as follows: (1) The Gradient Boosting and Extreme Gradient Boosting models demonstrate relatively higher prediction accuracy, with the Extreme Gradient Boosting model exhibiting stronger generalization ability compared to the Gradient Boosting model. (2) Sand, natural coarse aggregate and the number freeze-thaw cycles have the most substantial impact on the freeze-thaw resistance of concrete, while the impact of recycled coarse aggregate is relatively modest. Utilizing suitable quantities of air-entraining agent, fly ash, slag, and superplasticizer can improve concrete's freeze-thaw resistance. (3) A reduced water-cement ratio is advantageous for enhancing concrete's resistance to freeze-thaw damage in cold regions. (4) The partial dependence analysis of Extreme Gradient Boosting model can provide references for optimizing the composition of each component during the preparation of concrete in cold regions. (5) A graphical user interface based on the Extreme Gradient Boosting model for predicting concrete freeze-thaw mass loss rate has been developed, facilitating user-friendly interaction with the computer program and enhancing the practicality of the model.

Comparison of an interpretable extreme gradient boosting model and an artificial neural network model for prediction of severe acute pancreatitis.

Acute pancreatitis (AP) that progresses to persistent organ failure is referred to as severe acute pancreatitis (SAP). It is a condition associated with a relatively high mortality. A prediction model that would facilitate early recognition of patients at risk for SAP is crucial for improvement of patient prognosis. The aim of this study was to evaluate the accuracy of extreme gradient boosting (XGBoost) and artificial neural network (ANN) models for predicting SAP. A total of 648 patients with AP were enrolled. XGBoost and ANN models were developed and validated in the training (519 patients) and test sets (129 patients). The accuracy and predictive performance of the XGBoost and ANN models were evaluated using both the area under the receiver operating characteristic curves (AUCs) and the area under the precision‑recall curves (AUC‑PRs). A total of 15 variables were selected for model construction through a univariable analysis. The AUCs of the XGBoost and ANN models in 5‑fold cross‑validation of the training set were 0.92 (95% CI, 0.87-0.97) and 0.86 (95% CI, 0.78-0.92), respectively, whereas the AUCs for the test set were 0.93 (95% CI, 0.85-1) and 0.87 (95% CI, 0.79-0.96), respectively. The XGBoost model outperformed the ANN model in terms of both diagnostic accuracy and AUC‑PR. Individual predictions of the XGBoost model were explained using a local interpretable model‑agnostic explanation plot. An interpretable XGBoost model showed better discriminatory efficiency for predicting SAP than the ANN model, and could be used in clinical practice to identify patients at risk for SAP.

Major Depressive Disorder Prediction Based on Sleep-Wake Disorders Symptoms in US Adolescents: A Machine Learning Approach from National Sleep Research Resource.

There is substantial evidence from previous studies that abnormalities in sleep parameters associated with depression are demonstrated in almost all stages of sleep architecture. Patients with symptoms of sleep-wake disorders have a much higher risk of developing major depressive disorders (MDD) compared to those without. The aim of the present study is to establish and compare the performance of different machine learning models based on sleep-wake disorder symptoms data and to select the optimal model to interpret the importance of sleep-wake disorder symptoms to predict MDD occurrence in adolescents. We derived data for this work from 2020 to 2021 Assessing Nocturnal Sleep/Wake Effects on Risk of Suicide Phase I Study from National Sleep Research Resource. Using demographic and sleep-wake disorder symptoms data as predictors and the occurrence of MDD measured base on the center for epidemiologic studies depression scale as an outcome, the following six machine learning predictive models were developed: eXtreme Gradient Boosting model (XGBoost), Light Gradient Boosting mode, AdaBoost, Gaussian Naïve Bayes, Complement Naïve Bayes, and multilayer perceptron. The models' performance was assessed using the AUC and other metrics, and the final model's predictor importance ranking was explained. XGBoost is the optimal predictive model in comprehensive performance with the AUC of 0.804 in the test set. All sleep-wake disorder symptoms were significantly positively correlated with the occurrence of adolescent MDD. The insomnia severity was the most important predictor compared with the other predictors in this study. This machine learning predictive model based on sleep-wake disorder symptoms can help to raise the awareness of risk of symptoms between sleep-wake disorders and MDD in adolescents and improve primary care and prevention.

Meteorological drought migration characteristics based on an improved spatiotemporal structure approach in the Loess Plateau of China

The development of drought has spatial and temporal synchronization. Previous studies usually explore the spatial and temporal evolution of drought separately. Moreover, existing approaches are based on a fixed overlapping area and do not consider the variable drought cluster area during development. This study proposes an improved and simple approach to derive dynamic overlapping area threshold for 3-dimensional droughts extraction. Based on the one monthly Nonparametric Standardized Precipitation Index (NSPI), this improved approach was applied for investigating the migration characteristics of meteorological drought events in the Loess Plateau of China. Then, Random Forest and Extreme Gradient Boosting model with Shapley additive explanation values were used to quantify the importance of driving factors on the dynamics of drought characteristics. The results showed that: (1) the improved approach has a better performance on identifying prolonged droughts than the method using a fixed overlap area threshold; (2) spatially, meteorological drought events with high severity (DS), long duration (DD), large effected area (DA) and fast migration velocity (DV) mainly occur in the central region; (3) temporally, droughts are expected to aggravate with significantly increased DS and DA which are mainly caused by increased temperature and vegetation; and (4) meteorological droughts have a preferred westward migration direction and three dominant migration paths, which are crucial for local drought prevention and control. The findings of this study provide new perspectives on drought migration characteristics, which are important for the exploration of drought-driven mechanisms, risk assessment and future prediction.

Machine learning algorithms improve MODIS GPP estimates in United States croplands

Introduction: Machine learning methods combined with satellite imagery have the potential to improve estimates of carbon uptake of terrestrial ecosystems, including croplands. Studying carbon uptake patterns across the U.S. using research networks, like the Long-Term Agroecosystem Research (LTAR) network, can allow for the study of broader trends in crop productivity and sustainability.Methods: In this study, gross primary productivity (GPP) estimates from the Moderate Resolution Imaging Spectroradiometer (MODIS) for three LTAR cropland sites were integrated for use in a machine learning modeling effort. They are Kellogg Biological Station (KBS, 2 towers and 20 site-years), Upper Mississippi River Basin (UMRB - Rosemount, 1 tower and 12 site-years), and Platte River High Plains Aquifer (PRHPA, 3 towers and 52 site-years). All sites were planted to maize (Zea mays L.) and soybean (Glycine max L.). The MODIS GPP product was initially compared to in-situ measurements from Eddy Covariance (EC) instruments at each site and then to all sites combined. Next, machine learning algorithms were used to create refined GPP estimates using air temperature, precipitation, crop type (maize or soybean), agroecosystem, and the MODIS GPP product as inputs. The AutoML program in the h2o package tested a variety of individual and combined algorithms, including Gradient Boosting Machines (GBM), eXtreme Gradient Boosting Models (XGBoost), and Stacked Ensemble.Results and discussion: The coefficient of determination (r2) of the raw comparison (MODIS GPP to EC GPP) was 0.38, prior to machine learning model incorporation. The optimal model for simulating GPP across all sites was a Stacked Ensemble type with a validated r2 value of 0.87, RMSE of 2.62 units, and MAE of 1.59. The machine learning methodology was able to successfully simulate GPP across three agroecosystems and two crops.

Characteristics of secondary inorganic aerosols and contributions to PM2.5 pollution based on machine learning approach in Shandong Province

Primary emissions of particulate matter and gaseous pollutants, such as SO2 and NOx have decreased in China following the implementation of a series of policies by the Chinese government to address air pollution. However, controlling secondary inorganic aerosol pollution requires attention. This study examined the characteristics of the secondary conversion of nitrate (NO3−) and sulfate (SO42−) in three coastal cities of Shandong Province, namely Binzhou (BZ), Dongying (DY), and Weifang (WF), and an inland city, Jinan (JN), during December 2021. Furthermore, the Shapley Additive Explanation (SHAP), an interpretable attribution technique, was adopted to accurately calculate the contributions of secondary formations to PM2.5. The nitrogen oxidation rate exhibited a significant dependence on the concentration of O3. High humidity facilitates sulfur oxidation. Compared to BZ, DY, and WF, the secondary conversion of NO3− and SO42− was more intense in JN. The light-gradient boosting model outperformed the random forest and extreme-gradient boosting models, achieving a mean R2 value of 0.92. PM2.5 pollution events in BZ, DY, and WF were primarily attributable to biomass burning, whereas pollution in Jinan was contributed by the secondary formation of NO3− and vehicle emissions. Machine learning and the SHAP interpretable attribution technique offer a precise analysis of the causes of air pollution, showing high potential for addressing environmental concerns.

Novel Machine Learning Algorithms for Prediction of Treatment Decisions in Adult Patients With Class III Malocclusion

Management of Class III (Cl III) dentoskeletal phenotype is often expert-driven. The aim is to identify critical morphological features in postcircumpubertal Cl III treatment and appraise the predictive ability of innovative machine learning (ML) algorithms for adult Cl III malocclusion treatment planning. The Orthodontics Department at the University of Illinois Chicago undertook a retrospective cross-sectional study analyzing Cl III malocclusion cases (2003-2020) through dental records and pretreatment lateral cephalograms. Forty features were identified through a literature review and gathered from pretreatment records, serving as ML model inputs. Eight ML models were trained to predict the best treatment for adult Cl III malocclusion. Predictive accuracy, sensitivity, and specificity of the models, along with the highest-contributing features, were evaluated for performance assessment. Demographic covariates, including age, gender, race, and ethnicity, were assessed. Inclusion criteria targeted patients with cervical vertebral maturation stage 4 or above. Operative covariates such as tooth extraction and types of orthognathic surgical maneuvers were also analyzed. Demographic characteristics of the camouflage and surgical study groups were described statistically. Shapiro-Wilk Normality test was employed to check data distribution. Differences in means between groups were evaluated using parametric and nonparametric independent sample tests, with statistical significance set at <0.05. The study involved 182 participants; 65 underwent camouflage mechanotherapy, and 117 received orthognathic surgery. No statistical differences were found in demographic characteristics between the two groups (P>.05). Extreme values of pretreatment parameters suggested a surgical approach. Artificial neural network algorithms predicted treatment approach with 91% accuracy, while the Extreme Gradient Boosting model achieved 93% accuracy after recursive feature elimination optimization. The Extreme Gradient Boosting model highlighted Wit's appraisal, anterior overjet, and Mx/Md ratio as key predictors. The research identified significant cephalometric differences between Cl III adults requiring orthodontic camouflage or surgery. A 93% accurate artificial intelligence model was formulated based on these insights, highlighting the potential role of artificial intelligence and ML as adjunct tools in orthodontic diagnosis and treatment planning. This may assist in minimizing clinician subjectivity in borderline cases.

High-Resolution Digital Soil Maps of Forest Soil Nitrogen across South Korea Using Three Machine Learning Algorithms

Reliable estimation of the forest soil nitrogen spatial distribution is necessary for effective forest ecosystem management. This study aimed to develop high-resolution digital soil maps of forest soil nitrogen across South Korea using three powerful machine learning methods to better understand the spatial variations of forest soil nitrogen and its environmental drivers. To achieve this, the study used national-level forest soil nitrogen data and environmental data to construct various geographic and environmental variables including geological, topographic, and vegetation factors for digital soil mapping. The results show that of the machine learning methods, the random forest model had the best performance at predicting total soil nitrogen in the A and B horizons, closely followed by the extreme gradient-boosting model. The most critical predictors were found to be geographic variables, quantitatively confirming the significant role of spatial autocorrelation in predicting soil nitrogen. The digital soil maps revealed that areas with high elevation, concave slopes, and deciduous forests had high nitrogen contents. This finding highlights the potential usefulness of digital soil maps in supporting forest management decision-making and identifying the environmental drivers of forest soil nitrogen distribution.

COVID-19 and China’s Foreign Direct Investment Inflow- Stress Tests Based on Extreme Gradient Boosting Model and Policy Implications

Foreign direct investment (FDI) is essential to world economic growth, global industrial chain optimization, technology diffusion, and product innovation. This study identifies several macro-level factors affecting FDI inflow to China after discussing possible mechanisms through which COVID-19 influences FDI. Then, it tests three different stressful scenarios simulating the COVID-19 influence on China’s FDI inflow with a regression model estimated by extreme gradient boosting (XGBoost) in Python. Results show that the rampant COVID-19 pandemic and increasing global investment risks would have a substantial and negative impact not only on global FDI size, investment rules, and investment structure, but also on FDI inflow to China. Without effective measures being taken, from January 2020 to March 2022, losses in China’s annual FDI inflow could reach 5.71 percent to 11.28 percent, but the country’s actual annual FDI inflow is much higher. The extraordinary measures adopted by the Chinese government include preventing pandemic measures that are prompt and effective as well as targeted macroeconomic regulation policies. They make a rapid recovery or even improvement in China’s economic fundamentals, which in turn enhance China’s attractiveness to FDI and the FDI size, more than offsetting the negative effect of COVID-19 on FDI inflow to China. Finally, this paper proposes several countermeasures in macro-economic regulation and industrial policy adjustment to prevent and mitigate the negative influence of COVID-19 on FDI.

A machine learning approach to determine resilience utilizing wearable device data: analysis of an observational cohort.

To assess whether an individual's degree of psychological resilience can be determined from physiological metrics passively collected from a wearable device. Data were analyzed in this secondary analysis of the Warrior Watch Study dataset, a prospective cohort of healthcare workers enrolled across 7 hospitals in New York City. Subjects wore an Apple Watch for the duration of their participation. Surveys were collected measuring resilience, optimism, and emotional support at baseline. We evaluated data from 329 subjects (mean age 37.4 years, 37.1% male). Across all testing sets, gradient-boosting machines (GBM) and extreme gradient-boosting models performed best for high- versus low-resilience prediction, stratified on a median Connor-Davidson Resilience Scale-2 score of 6 (interquartile range = 5-7), with an AUC of 0.60. When predicting resilience as a continuous variable, multivariate linear models had a correlation of 0.24 (P = .029) and RMSE of 1.37 in the testing data. A positive psychological construct, comprised of resilience, optimism, and emotional support was also evaluated. The oblique random forest method performed best in estimating high- versus low-composite scores stratified on a median of 32.5, with an AUC of 0.65, a sensitivity of 0.60, and a specificity of 0.70. In a post hoc analysis, machine learning models applied to physiological metrics collected from wearable devices had some predictive ability in identifying resilience states and a positive psychological construct. These findings support the further assessment of psychological characteristics from passively collected wearable data in dedicated studies.

External Validation of an Extreme Gradient Boosting Model for Prediction of Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage

Delayed cerebral ischemia (DCI) may significantly worsen the functional status of patients with aneurysmal subarachnoid hemorrhage (aSAH). Several authors have designed predictive models for early identification of patients at risk of post-aSAH DCI. In this study, we externally validate an extreme gradient boosting (EGB) forecasting model for post-aSAH DCI prediction. A 9-year institutional retrospective review of patients with aSAH was performed. Patients were included if they underwent surgical or endovascular treatment and had available follow-up data. DCI was diagnosed as new-onset neurologic deficits at 4-12 days after aneurysm rupture, defined as worsening Glasgow Coma Scale score for ≥2 points, and new ischemic infarcts at imaging. We collected 267 patients with aSAH. At admission, median Hunt-Hess score was 2 (range, 1-5), median Fisher score 3 (range, 1-4), and median modified Fisher score 3 (range, 1-4). One-hundred and forty-five patients underwent external ventricular drainage placement for hydrocephalus (54.3%). The ruptured aneurysms were treated with clipping (64%), coiling (34.8%), and stent-assisted coiling (1.1%). Fifty-eight patients (21.7%) were diagnosed with clinical DCI and 82 (30.7%) with asymptomatic imaging vasospasm. The EGB classifier correctly predicted 19 cases of DCI (7.1%) and 154 cases of no-DCI (57.7%), achieving sensitivity of 32.76% and specificity of 73.68%. The calculated F1 score and accuracy were 0.288% and 64.8%, respectively. We validated that the EGB model is a potential assistant tool to predict post-aSAH DCI in clinical practice, finding moderate-high specificity but low sensitivity. Future research should investigate the underlying pathophysiology of DCI to allow the development of high-performing forecasting models.

Clinical utility of a deep-learning mortality prediction model for cardiac surgery decision making

ObjectivesThe aim of this study using decision curve analysis (DCA) was to evaluate the clinical utility of a deep-learning mortality prediction model for cardiac surgery decision making compared with the European System for Cardiac Operative Risk Evaluation (EuroSCORE) II and to 2 machine-learning models. MethodsUsing data from a French prospective database, this retrospective study evaluated all patients who underwent cardiac surgery in 43 hospital centers between January 2012 and December 2020. A receiver operating characteristic analysis was performed to compare the accuracy of the EuroSCORE II, machine-learning models, and an adapted Tabular Bidirectional Encoder Representations from Transformers deep-learning model in predicting postoperative in-hospital mortality. The clinical utility of these models for cardiac surgery decision making was compared using DCA. ResultsOver the study period, 165,640 patients underwent cardiac surgery, with a mean EuroSCORE II of 3.99 ± 6.67%. In the receiver operating characteristic analysis, the area under the curve was significantly greater for the deep-learning model (0.834; 95% confidence interval, 0.831-0.838) than the EuroSCORE II (P < .001), the random forest model (P = .03), and the Extreme Gradient Boosting model (P = .03). In the DCA, the clinical utility of the 3 artificial intelligence models was superior to that of the EuroSCORE II, especially when the threshold probability of death was high (>45%). The deep-learning model showed the greatest advantage over the EuroSCORE II. ConclusionsThe deep-learning model had better predictive accuracy and greater clinical utility than the EuroSCORE II and the 2 machine-learning models. These findings suggest that deep learning with Tabular Bidirectional Encoder Representations from Transformers prediction model could be used in the future as the gold standard for cardiac surgery decision making.

Large-scale computational screening of metal–organic frameworks for D2/H2 separation

Deuterium (D 2 ) is one of the important fuel sources that power nuclear fusion reactors. The existing D 2 /H 2 separation technologies that obtain high-purity D 2 are cost-intensive. Recent research has shown that metal–organic frameworks (MOFs) are of good potential for D 2 /H 2 separation application. In this work, a high-throughput computational screening of 12,020 Computation-Ready Experimental MOFs is carried out to determine the best MOFs for hydrogen isotope separation application. Meanwhile, the detailed structure-performance correlation is systematically investigated with the aid of machine learning. The results indicate that the ideal D 2 /H 2 adsorption selectivity calculated based on Henry coefficient is strongly correlated with the 1/Δ AD feature descriptor; that is, inverse of the adsorbility difference of the two adsorbates. Meanwhile, the machine learning (ML) results show that the prediction accuracy of all the four ML methods is significantly improved after the addition of this feature descriptor. In addition, the ML results based on eXtreme Gradient Boosting model also revealed that the 1/Δ AD descriptor has the highest relative importance compared to other commonly-used descriptors. To further explore the effect of hydrogen isotope separation in binary mixture, 1,548 MOFs with ideal adsorption selectivity greater than 1.5 are simulated at equimolar conditions. The structure-performance relationship shows that high adsorption selectivity MOFs generally have smaller pore size (3–5 Å, 1 Å=0.1 nm) and lower surface area. Among the top 200 performers, the materials mainly have the sql, pcu, cds, hxl, and ins topologies. Finally, three MOFs with high D 2 /H 2 selectivity and good D 2 uptake are identified as the best candidates, of all which had one-dimensional channel pore. The findings obtained in this work may be helpful for the identification of potentially promising candidates for hydrogen isotope separation.

Detection of Intermittent Claudication from Smartphone Inertial Data in Community Walks Using Machine Learning Classifiers.

Peripheral arterial disease (PAD) causes blockage of the arteries, altering the blood flow to the lower limbs. This blockage can cause the individual with PAD to feel severe pain in the lower limbs. The main contribution of this research is the discovery of a solution that allows the automatic detection of the onset of claudication based on data analysis from patients' smartphones. For the data-collection procedure, 40 patients were asked to walk with a smartphone on a thirty-meter path, back and forth, for six minutes. Each patient conducted the test twice on two different days. Several machine learning models were compared to detect the onset of claudication on two different datasets. The results suggest that we can identify the onset of claudication using inertial sensors with a best case accuracy of 92.25% for the Extreme Gradient Boosting model.

Modeling Daily Reference Evapotranspiration from Climate Variables: Assessment of Bagging and Boosting Regression Approaches

The increasing frequency of droughts and floods due to climate change has severely affected water resources across the globe in recent years. An optimal design for the scheduling and management of irrigation is thus urgently needed to adapt agricultural activities to the changing climate. The accurate estimation of reference crop evapotranspiration (ET0), a vital hydrological component of the water balance and crop water need, is a tiresome task if all the relevant climatic variables are unavailable. This study investigates the potential of four ensemble techniques for estimating precise values of the daily ET0 at representative stations in 10 agro-climatic zones in the state of Karnataka, India, from 1979 to 2014. The performance of these models was evaluated by using several combinations of climatic variables as inputs by using tenfold cross-validation. The outcomes indicated that predictions of ET0 by all four ensemble models based on all climatic variables were the most accurate in comparison with other input combinations. The random forest regressor was found to deliver the best performance among the four models on all measures considered (Nash–Sutcliffe efficiency, 1.0, root-mean-squared error, 0.016 mm/day, and mean absolute error, 0.011 mm/day). However, it incurred the highest computational cost, whereas the computational cost of the bagging model for linear regression was the lowest. The extreme gradient-boosting model delivered the most stable performance with a modified training dataset. The work here shows that these models can be recommended for daily ET0 estimation based on the users’ interests.

Predictive Models for Knee Pain in Middle-Aged and Elderly Individuals Based on Machine Learning Methods.

Aim This study used machine learning methods to develop a prediction model for knee pain in middle-aged and elderly individuals. Methods A total of 5386 individuals above 45 years old were obtained from the National Health and Nutrition Examination Survey. Participants were randomly divided into a training set and a test set at a 7 : 3 ratio. The training set was used to create a prediction model, whereas the test set was used to validate the proposed model. We constructed multiple predictive models based on three machine learning methods: logistic regression, random forest, and Extreme Gradient Boosting. The model performance was evaluated by areas under the receiver (AUC), sensitivity, specificity, positive predictive value, and negative predictive value. Additionally, we created a simplified nomogram based on logistic regression for better clinical application. Results About 31.4% (1690) individuals were with self-reported knee pain. The logistic regression showed that female gender (odds ratio [OR] = 1.28), pain elsewhere (OR = 4.64), and body mass index (OR = 1.05) were significantly associated with increased risk of knee pain. In the test set, the logistic regression (AUC = 0.71) showed similar but slightly higher accuracy than the random forest (AUC = 0.70), while the performance of the Extreme Gradient Boosting model was less reliable (AUC = 0.59). Based on mean decrease accuracy, the most important first five predictions were pain elsewhere, waist circumference, body mass index, age, and gender. Additionally, the most important first five predictions with the highest mean decrease Gini index were pain elsewhere, body mass index, waist circumference, triglycerides, and age. The nomogram model showed good discrimination ability with an AUC of 0.75 (0.73-0.77), a sensitivity of 0.72, specificity of 0.71, a positive predictive value of 0.45, and a negative predictive value of 0.88. Conclusion This study proposed a convenient nomogram tool to evaluate the risk of knee pain for the middle-aged and elderly US population in primary care. All the input variables can be easily obtained in a clinical setting, and no additional radiologic assessments were required.

Optimal flood susceptibility model based on performance comparisons of LR, EGB, and RF algorithms

Wadi El-Matulla, located in the eastern desert of Egypt, is the most important water basin. The Qift–Qusayr highway (west–east direction) and the Cairo–Aswan eastern desert highway (north–south direction) pass through the watershed. Many urban areas (villages and industrial areas) and agricultural lands are located at the outlet of these basins. In addition, the basin has promising potential for future economic and urban development as it is located within the Golden Triangle (governmental megaproject). The current study investigates flood hazard modeling and its impact on the area. To determine the optimal flood susceptibility mapping algorithm, performance comparisons of three techniques were conducted: logistic regression (LR), extreme gradient boosting (EGB), and random forest (RF). Remote sensing, topographic, geologic, and meteorological data were used with the help of field visits to provide the spatial and inventory database required by the models. The performance and reliability of the predictions of the proposed models were evaluated using five statistical indices: receiver operating characteristic–area under the curve, overall accuracy (OAC), kappa index, root mean square error (RMSE), and mean absolute error (MAE). The performance of the models showed that the values of ROC (93, 86 and 80%), OAC (88, 82 and 76%), kappa index (0.85, 0.75 and 0.51), RMSE (0.34, 0.42 and 0.49) and MAE (0.12, 0.18 and 0.24) for RF, EGB, and LR, respectively. Based on AUC values, RF and EGB models provide excellent and very good prediction for flood susceptibility. Our results show that RF is the optimal algorithm for flood susceptibility mapping, followed by EGB and LR. Consequently, the predictive power of RF model is quite good and the flood susceptibility map was classified into five classes, namely very low (51.7%), low (23.7%), moderate (16.2%), high (7.1%), and very high (1.3%). Ultimately, the RF model was verified using sentinel-1 imagery for real floods in 2016 and 2021, and it provides good agreement. The optimal model could be useful for decision makers and planners to protect existing facilities and plan future projects in non-flood-prone areas. Accordingly, the most suitable areas for future development need to be distributed mainly in the low and very low flood hazard areas.

Machine learning models to prognose 30-Day Mortality in Postoperative Disseminated Cancer Patients

Patients with disseminated cancer at higher risk for postoperative mortality see improved outcomes with altered clinical management. Being able to risk stratify patients immediately after their index surgery to flag high risk patients for healthcare providers is vital. The combination of physician uncertainty and a demonstrated optimism bias often lead to an overestimation of patient life expectancy which can precent proper end of life counseling and lead to inadequate postoperative follow up. In this cohort study of 167,474 postoperative patients with multiple types of disseminated cancer, patients at high risk of 30-day postoperative mortality were accurately identified using our machine learning models based solely on clinical features and preoperative lab values. Extreme Gradient Boosting, Random Forest, and Logistic Regression machine learning models were developed on the cohort. Among 167,474 disseminated cancer patients, 50,669 (30.3%) died within 30 days of their index surgery; After preprocessing, 28 features were included in the model development. The cohort was randomly divided into 133,979 patients (80%) for training the models and 33,495 patients (20%) for testing. The extreme gradient boosting model had an AUC of 0.93 (95% CI: 0.926–0.931), the random forest model had an AUC of 0.93 (95% CI: 0.930–0.934), and the logistic regression model had an AUC of 0.90 (95% CI: 0.900–0.906 the index operation. Ultimately, Machine learning models were able to accurately predict short-term postoperative mortality among a heterogenous population of disseminated cancer patients using commonly accessible medical features. These models can be included in electronic health systems to guide clinical judgements that affect direct patient care, particularly in low-resource settings.