Gradient Boosting Decision Tree Algorithm Research Articles

O-096 Effect of Day-3 embryo morphology on blastocyst quality and ploidy: a machine-learning model of 34781 embryos

Abstract Study question What is the predictive value of using Day-3 (D3) embryo morphology and clinical factors to identify good quality euploid blastocysts? Summary answer Using a machine-learning model, D3-cell count and fragmentation helps identifying embryos most and least likely to develop into euploid blastocysts. What is known already It is well-known that the pattern of embryo cleavage affects blastocyst ploidy. Less has been elucidated in relation to embryo fragmentation. Published studies often used outdated biopsy techniques (D3-biopsy) and obsolete genetic technologies (FISH). Hence, the association between embryo fragmentation and ploidy status remains controversial. Existing hypothesis is that embryo fragmentation is a regulation event to maintain homeostasis and normalize genetic constitution. Literature is lacking studies investigating this association using newer genetic technologies such as Next Generating Sequencing (NGS). Moreover, a predictive model using D3-embryo characteristics and clinical factors can be useful for triage of laboratory resources. Study design, size, duration Retrospective observational single center study including 34781 embryos from 5701 cycles, between March 2017 and March 2020. Embryos were evaluated for degree of fragmentation and cell number on D3, 68±1hrs post insemination. Female Age, AMH and BMI were annotated as patient characteristics. All blastocysts available on D5 or D6 with a quality ≥ BL3CC (n = 18361) were subjected to trophectoderm (TE) biopsy for Preimplantation-Genetic-Testing for aneuploidies (PGT-A) analysis with Next-Generation-Sequencing and ploidy rates were recorded. Participants/materials, setting, methods Degree of fragmentation was classified as follows: A( < =10%), B(11-25%), C(26-35%), D(>35%). Data on embryo fragmentation was stratified according to cell number category: <6cells, 6-10 cells, >10 cells and compacted stage. Morphology markers (cell-count and fragmentation rate), along with patient characteristics (age, anti-Mullerian hormone and body-mass index) was modeled using a gradient-boosting decision tree algorithm. Performance of the machine learning (ML) model was assessed with AUC values, calibration curves after partitioning the dataset 1:1 for training/validation. Main results and the role of chance Day-3 embryos consisting of < 6 cells (n = 5926), 6-10 cells (n = 23920), and >10 cells (n = 1612) were included, along with 3323 compacted embryos. The rate of good-quality blastocysts decreased with higher fragmentation rates (38.2%, 14.8%, 4.6%, and 1.6%, A, B, C, and D, respectively; P < 0.001). Day of biopsy was earlier for embryos with lower fragmentation rates (Day-5 biopsy: 24.2%, 9.7%, 4.0%, and 0.0%, P < 0.001). Among the biopsied blastocysts, euploidy rates were similar at 44.9%, 43.0%, 42.7%, and 66.7% in groups A vs B, C, and D, respectively (P = 0.075, 0.350 and 0.141). When stratified by cell number, euploidy rates were lowest in blastocysts derived from <6-cells, at 33.5%, 34.3%, 26.9%, and 50.0% in groups A vs B, C, and D, respectively (P = 0.803, 0.185 and 0.394). The best performance ML model was provided by using fragmentation % and cell count along with female age, BMI and AMH. This resulted in a modest predictive accuracy for predicting euploid embryo development (AUC: 0.72, 95% CI: 0.71 to 0.73). The model was well- calibrated and correctly assessed the probability of D3-embryos developing into euploid blastocyst. For instance, embryos with a predicted probability of ≤ 2.5% rarely developed into euploid blastocyst (actual rate: 2.6%) and model had a predictive value of 97.4%.Limitations, reasons for caution: The retrospective nature of the study and inter-observer variability in D3-embryo fragmentation scoring is a limitation. Nevertheless, embryologists performing the embryo scoring followed the same SOPs. Findings need to be validated in external cohorts. Wider implications of the findings The model can utilize clinical factors and D3-embryo morphology markers to estimate the probability of a D3-embryo developing into an euploid blastocyst. This model can be useful for patient information, mainly when a decision on embryo selection for PGT-A needs to take place. Trial registration number not applicable

Classification and Recognition of Building Appearance Based on Optimized Gradient-Boosted Decision Tree Algorithm.

There are high concentrations of urban spaces and increasingly complex land use types. Providing an efficient and scientific identification of building types has become a major challenge in urban architectural planning. This study used an optimized gradient-boosted decision tree algorithm to enhance a decision tree model for building classification. Through supervised classification learning, machine learning training was conducted using a business-type weighted database. We innovatively established a form database to store input items. During parameter optimization, parameters such as the number of nodes, maximum depth, and learning rate were gradually adjusted based on the performance of the verification set to achieve optimal performance on the verification set under the same conditions. Simultaneously, a k-fold cross-validation method was used to avoid overfitting. The model clusters trained in the machine learning training corresponded to various city sizes. By setting the parameters to determine the size of the area of land for a target city, the corresponding classification model could be invoked. The experimental results show that this algorithm has high accuracy in building recognition. Especially in R, S, and U-class buildings, the overall accuracy rate of recognition reaches over 94%.

A machine learning model to predict treatment initiation among new patients in a community oncology network.

e13539 Background: In The US Oncology Network (The Network), about one-third of new patients with a cancer diagnosis started intravenous (IV) treatment after their first visit. The rest of the patients either came in for a consult only or might have received other treatments such as radiation, surgery, or oral therapy. We developed a machine learning model to predict IV treatment initiation among new patients and discovered features associated with the patient’s decision. This model could suggest interventions to improve patient’s access to care. Methods: A retrospective cohort was formed by identifying new patients with cancer from 27 practices in The Network between July 1, 2021 and June 30, 2022. Structured data were extracted and processed from the electronic health records, claims, physician referrals, and the American Community Survey. Patient characteristics included demographics, clinical information, payor types, and socioeconomic status. The referral pattern and the geographic region of practices, and the provider workload were considered as well. Gradient-boosted decision trees, random forest, neural network, and logistic regression models were developed to predict the probability of starting IV treatment within 90 days of the first visit. Model performance was evaluated based on the area under the receiver operating characteristic (AUROC) curve using cross-valuation and 4:1 training/validation random split. Shapley Additive Explanations (SHAP) values were applied to the model to explain feature importance. Results: A total of 117,340 new patients with a cancer diagnosis were included in the study, of whom 35% initiated IV treatment within 90 days of the first visit. A gradient-boosted decision tree algorithm with control of the imbalanced label was chosen as the final model because of the performance and the ability to handle missing values. The model achieved an AUROC of 0.80 on the validation dataset with both cross-valuation and 4:1 training/validation random split. Based on the SHAP values (log odds), we found that clinical information including diagnosis and stage is the most important feature to predict the initiation of IV treatment (mean absolute SHAP = 0.31 and 1.03, respectively). Medicaid contributes least to treatment initiation among all insurance types (mean absolute SHAP = 0.01). In addition, younger age and male patients have a higher chance to start IV treatment (Pearson correlation = -0.41, p-value < 0.01 for age versus SHAP values; p-value < 0.01, two-sided T-test for SHAP values by gender). Conclusions: This study reports a machine learning model to predict IV treatment initiation among new patients with cancer. Clinical features impact the treatment decision more than others. This model could guide patient service and direct personalized care navigation. Further, the model sheds light on future interventions that could enhance patient access to treatment promptly.

Employing active learning in the optimization of culture medium for mammalian cells

Medium optimization is a crucial step during cell culture for biopharmaceutics and regenerative medicine; however, this step remains challenging, as both media and cells are highly complex systems. Here, we addressed this issue by employing active learning. Specifically, we introduced machine learning to cell culture experiments to optimize culture medium. The cell line HeLa-S3 and the gradient-boosting decision tree algorithm were used to find optimized media as pilot studies. To acquire the training data, cell culture was performed in a large variety of medium combinations. The cellular NAD(P)H abundance, represented as A450, was used to indicate the goodness of culture media. In active learning, regular and time-saving modes were developed using culture data at 168 h and 96 h, respectively. Both modes successfully fine-tuned 29 components to generate a medium for improved cell culture. Intriguingly, the two modes provided different predictions for the concentrations of vitamins and amino acids, and a significant decrease was commonly predicted for fetal bovine serum (FBS) compared to the commercial medium. In addition, active learning-assisted medium optimization significantly increased the cellular concentration of NAD(P)H, an active chemical with a constant abundance in living cells. Our study demonstrated the efficiency and practicality of active learning for medium optimization and provided valuable information for employing machine learning technology in cell biology experiments.

Machine-learning repurposing of DrugBank compounds for opioid use disorder

Opioid use disorder (OUD) is a chronic and relapsing condition that involves the continued and compulsive use of opioids despite harmful consequences. The development of medications with improved efficacy and safety profiles for OUD treatment is urgently needed. Drug repurposing is a promising option for drug discovery due to its reduced cost and expedited approval procedures. Computational approaches based on machine learning enable the rapid screening of DrugBank compounds, identifying those with the potential to be repurposed for OUD treatment. We collected inhibitor data for four major opioid receptors and used advanced machine learning predictors of binding affinity that fuse the gradient boosting decision tree algorithm with two natural language processing (NLP)-based molecular fingerprints and one traditional 2D fingerprint. Using these predictors, we systematically analyzed the binding affinities of DrugBank compounds on four opioid receptors. Based on our machine learning predictions, we were able to discriminate DrugBank compounds with various binding affinity thresholds and selectivities for different receptors. The prediction results were further analyzed for ADMET (absorption, distribution, metabolism, excretion, and toxicity), which provided guidance on repurposing DrugBank compounds for the inhibition of selected opioid receptors. The pharmacological effects of these compounds for OUD treatment need to be tested in further experimental studies and clinical trials. Our machine learning studies provide a valuable platform for drug discovery in the context of OUD treatment.

Identification of Potential Biomarkers for Group I Pulmonary Hypertension Based on Machine Learning and Bioinformatics Analysis.

A number of processes and pathways have been reported in the development of Group I pulmonary hypertension (Group I PAH); however, novel biomarkers need to be identified for a better diagnosis and management. We employed a robust rank aggregation (RRA) algorithm to shortlist the key differentially expressed genes (DEGs) between Group I PAH patients and controls. An optimal diagnostic model was obtained by comparing seven machine learning algorithms and was verified in an independent dataset. The functional roles of key DEGs and biomarkers were analyzed using various in silico methods. Finally, the biomarkers and a set of key candidates were experimentally validated using patient samples and a cell line model. A total of 48 key DEGs with preferable diagnostic value were identified. A gradient boosting decision tree algorithm was utilized to build a diagnostic model with three biomarkers, PBRM1, CA1, and TXLNG. An immune-cell infiltration analysis revealed significant differences in the relative abundances of seven immune cells between controls and PAH patients and a correlation with the biomarkers. Experimental validation confirmed the upregulation of the three biomarkers in Group I PAH patients. In conclusion, machine learning and a bioinformatics analysis along with experimental techniques identified PBRM1, CA1, and TXLNG as potential biomarkers for Group I PAH.

Android malware detection based on sensitive patterns

In recent years, the rapid increase in the number and type of Android malware has brought great challenges and pressure to malware detection systems. As a widely used method in android malware detection, static detecting has been a hot topic in academia and industry. However, in order to improve the accuracy of detection, the existing static detecting methods sacrifice the excessively high analysis complexity and time cost. Moreover, the correlation between static features leads to redundancy of a large amount of data. Therefore, this paper proposes a static detecting method of Android malware based on sensitive pattern. It uses an improved FP-growth algorithm to mine frequent combinations of sensitive permissions and API calls in malicious apps and benign apps, which avoids the generation of redundant information. In addition, this paper adopts multi-layered gradient boosting decision trees algorithm to train the detection model. And a dual similarity combination method is proposed to measure the similarity between different sensitive patterns. The experimental results show that our proposed detection method has high accuracy and great generalization ability.

CBM Gas Content Prediction Model Based on the Ensemble Tree Algorithm with Bayesian Hyper-Parameter Optimization Method: A Case Study of Zhengzhuang Block, Southern Qinshui Basin, North China

Gas content is an important parameter for evaluating coalbed methane reservoirs, so it is an important prerequisite for coalbed methane resource evaluation and favorable area optimization to predict the gas content accurately. To improve the accuracy of CBM gas content prediction, the Bayesian hyper-parameter optimization method (BO) is introduced into the random forest algorithm (RF) and gradient boosting decision tree algorithm (GBDT) to establish CBM gas content prediction models using well-logging data in the Zhengzhuang block, south of Qinshui Basin, China. As a result, the GBDT model based on the BO method (BO-GBDT model) and the RF model based on the BO method (BO-RF model) were proposed. The results show that the mean-square-error (MSE) of the BO-RF model and the BO-GBDT model can be reduced by 8.83% and 37.94% on average less than that of the RF and GBDT modes, indicating that the accuracy of the models optimized by the BO method is improved. The prediction effect of the BO-GBDT model is better than that of the BO-RF model, especially in low gas content wells, and the R-squared (RSQ) of the BO-GBDT model and the BO-RF model is 0.82 and 0.66. The accuracy order of different models was BO-GBDT > GBDT > BO-RF > RF. Compared with other models, the gas content curve predicted by the BO-GBDT model has the best fitness with the measured gas content. The rule of gas distribution predicted by all four models is consistent with the measured gas content distribution.

Efficient Energy Management Strategy for an Electric Vehicle Powered by a Hybrid Energy Storage System Based on Hybrid GBDT-RSA Approach

This paper proposes an efficient energy management scheme for an EV with a hybrid energy storage system like super capacitor and battery based on hybrid optimization method. The proposed hybrid approach is a parallel performance of gradient boosting decision tree algorithm and reptile search algorithm. The major purpose is to diminish the variance among real and reference power on battery and super capacitor. The HESS is divided into two segments: (1) Determine the super capacitor reference voltage, which is affected by load dynamics. (2) Maximize the power flow via the HESS. The super capacitor reference voltage is first calculated by assessing the load dynamics on real time, such as vehicle dynamics, motor characteristics, and regenerative braking systems. The super capacitor’s input parameters include load current, battery current, and state of charge. The RSA is created on proposed system by combining the probable data set of HESS control signals. The GBDT algorithm is trained and forecasts optimal HESS parameters using the RSA’s practiced data set. The proposed approach also improves battery current magnitude, super capacitor voltage, battery current ranges, and battery power. It optimizes the HESS parameter provides specific solutions. The proposed hybrid system is implemented on MATLAB and its performance is related to that of existing approaches.

DeepAD: A deep learning application for predicting amyloid standardized uptake value ratio through PET for Alzheimer's prognosis.

Amyloid deposition is a vital biomarker in the process of Alzheimer's diagnosis. 18F-florbetapir PET scans can provide valuable imaging data to determine cortical amyloid quantities. However, the process is labor and doctor intensive, requiring extremely specialized education and resources that may not be accessible to everyone, making the amyloid calculation process inefficient. Deep learning is a rising tool in Alzheimer's research which could be used to determine amyloid deposition. Using data from the Alzheimer's Disease Neuroimaging Initiative, we identified 2,980 patients with PET imaging, clinical, and genetic data. We tested various ResNet, EfficientNet, and RegNet convolutional neural networks and later combined the best performing model with Gradient Boosting Decision Tree algorithms to predict standardized uptake value ratio (SUVR) of amyloid in each patient session. We tried several configurations to find the best model tuning for regression-to-SUVR. We found that the RegNet X064 architecture combined with a grid search-tuned Gradient Boosting Decision Tree with 3 axial input slices and clinical and genetic data achieved the lowest loss. Using the mean-absolute-error metric, the loss converged to an MAE of 0.0441, equating to 96.4% accuracy across the 596-patient test set. We showed that this method is more consistent and accessible in comparison to human readers from previous studies, with lower margins of error and substantially faster calculation times. We implemented our deep learning model on to a web application named DeepAD which allows our diagnostic tool to be accessible. DeepAD could be used in hospitals and clinics with resource limitations for amyloid deposition and shows promise for more imaging tasks as well.

G4Beacon: An In Vivo G4 Prediction Method Using Chromatin and Sequence Information.

G-quadruplex (G4) structures are critical epigenetic regulatory elements, which usually form in guanine-rich regions in DNA. However, predicting the formation of G4 structures within living cells remains a challenge. Here, we present an ultra-robust machine learning method, G4Beacon, which utilizes the Gradient-Boosting Decision Tree (GBDT) algorithm, coupled with the ATAC-seq data and the surrounding sequences of in vitro G4s, to accurately predict the formation ability of these in vitro G4s in different cell types. As a result, our model achieved excellent performance even when the test set was extremely skewed. Besides this, G4Beacon can also identify the in vivo G4s of other cell lines precisely with the model built on a special cell line, regardless of the experimental techniques or platforms. Altogether, G4Beacon is an accurate, reliable, and easy-to-use method for the prediction of in vivo G4s of various cell lines.

Physics-based Bayesian linear regression model for predicting length of mixed oil

Precise estimation of the length of mixed oil is important to optimize the operation efficiency of products pipeline. The feasibility of physics models is limited by low accuracy or numerical simulation burden. The current frequentist predictive models require a sufficient number of historical samples, or they are easily encountered with over-fitting phenomenon. Bayesian linear regression model may alleviate this issue while predictive performance is also unsatisfactory without fusion of physical knowledge. To tackle such problems, this article proposes a new modeling method by employing the physics model to provide the nonlinear expression form and the underlying prior knowledge to the Bayesian linear regression model (BLR), and a physics-based Bayesian linear regression model (PBBLR) is developed. Based on the real product oil pipeline dataset, a performance comparison experiment with the Artificial Neural Network, the Gradient Boosting Decision Tree algorithm, two state-of-the-art predictive models, least squares estimation and pure Bayesian linear regression model is carried out, and the results verify the effectiveness of the proposed modeling method as the PBBLR shows optimal predictive performance in all scenarios. This research can help promote the predictive accuracy of mixed oil length of product oil pipelines and provide reference for the physics-data hybrid modeling method.

Informing antimicrobial stewardship with explainable AI.

The accuracy and flexibility of artificial intelligence (AI) systems often comes at the cost of a decreased ability to offer an intuitive explanation of their predictions. This hinders trust and discourage adoption of AI in healthcare, exacerbated by concerns over liabilities and risks to patients' health in case of misdiagnosis. Providing an explanation for a model's prediction is possible due to recent advances in the field of interpretable machine learning. We considered a data set of hospital admissions linked to records of antibiotic prescriptions and susceptibilities of bacterial isolates. An appropriately trained gradient boosted decision tree algorithm, supplemented by a Shapley explanation model, predicts the likely antimicrobial drug resistance, with the odds of resistance informed by characteristics of the patient, admission data, and historical drug treatments and culture test results. Applying this AI-based system, we found that it substantially reduces the risk of mismatched treatment compared with the observed prescriptions. The Shapley values provide an intuitive association between observations/data and outcomes; the associations identified are broadly consistent with expectations based on prior knowledge from health specialists. The results, and the ability to attribute confidence and explanations, support the wider adoption of AI in healthcare.

Application of gradient boosting decision tree algorithm in operation quality evaluation of electric energy metering device in electric power company

Application of gradient boosting decision tree algorithm in operation quality evaluation of electric energy metering device in electric power company

A Data-Driven Oil Production Prediction Method Based on the Gradient Boosting Decision Tree Regression

Accurate prediction of monthly oil and gas production is essential for oil enterprises to make reasonable production plans, avoid blind investment and realize sustainable development. Traditional oil well production trend prediction methods are based on years of oil field production experience and expertise, and the application conditions are very demanding. With the rapid development of artificial intelligence technology, big data analysis methods are gradually applied in various sub-fields of the oil and gas reservoir development. Based on the data-driven artificial intelligence algorithm Gradient Boosting Decision Tree (GBDT), this paper predicts the initial single-layer production by considering geological data, fluid PVT data and well data. The results show that the GBDT algorithm prediction model has great accuracy, significantly improving efficiency and strong universal applicability. The GBDT method trained in this paper can predict production, which is helpful for well site optimization, perforation layer optimization and engineering parameter optimization and has guiding significance for oilfield development.

Deployment and Operation of Battery Swapping Stations for Electric Two-Wheelers Based on Machine Learning

Battery swapping stations effectively address the challenges of long charging times, lack of charging stations, and safety hazards for electric two-wheelers. With the rapid development of shared electric bicycles and takeaways, the scale of electric two-wheeler users is expanding while generating a huge demand for battery swapping. The research on the planning and operation of battery swapping stations (BSSs) for electric two-wheelers has yet to be widely discussed. This study developed a data-driven optimization model based on machine learning algorithms using Beijing’s battery swapping stations and point of interest (POI) dataset. First, through the spatial features of BSS analyzed by ArcGIS, we found that the coverage of BSSs was mainly concentrated within the fifth ring road, and the utilization rate was unbalanced. Then, on a 3000 m grid scale, a prediction model of BSS quantity with random forest, support vector regression, and gradient-boosting decision tree algorithm was built. The final stacking model was constructed by strengthening three single models with an accuracy of 86.21%. Compared with the original BSSs layout, the machine-learning algorithm proposed in this study can cover more factors and avoid the subjectivity of site selection. Finally, the queuing model for BSSs based on the Monte Carlo simulation was proposed. Through two scenarios, we found that the key parameters m (the number of charging slots) and λ (the user arrival rate) were influential to the outputs of service capability.

An effective approach for VARANS-VOF modelling interactions of wave and perforated breakwater using gradient boosting decision tree algorithm

In this paper, we propose a systematic and time-efficient approach to calibrate 2D VARANS-VOF models for simulation of wave interaction with porous plate in numerical wave tank. To reach this goal, we develop a data-driven approach in combination with numerical and experimental data to figure out the optimal empirical coefficient associated with linear and non-linear drag force coefficients (α, β). Advanced gradient boosting decision trees algorithms (GBDT) are adopted to capture the accuracy of the prediction model. Although only limited samples, for instance 72 samples are generated and chosen to train and test the prediction model, the GBDT model is able to identify the trend in non-linear influence of model parameters. The advantage of GBDT algorithm can obviously be seen through the regression analysis with very high regression coefficient (R2 > 0.99). The developed model is subsequently employed for a large range of considered parameters as input features of the models to predict the possible hydrodynamics characteristics. The smallest mean squared error between predicted and experimental results, which is 0.00204, is found and used to determine the best performing combination of these model parameters. The numerical model together with selected values of empirical coefficients is then validated using available experimental data in literature. The free surface elevations in front of and behind the structure from the numerical model are nearly identical with the experimental data.

Dual-IDS: A bagging-based gradient boosting decision tree model for network anomaly intrusion detection system

The mission of an intrusion detection system (IDS) is to monitor network activities and assess whether or not they are malevolent. Specifically, anomaly-based IDS can discover irregular activities by discriminating between normal and anomalous deviations. Nonetheless, existing strategies for detecting anomalies generally rely on single classification models that are still incapable of reducing the false alarm rate and increasing the detection rate. This study introduces a dual ensemble model by combining two existing ensemble techniques, such as bagging and gradient boosting decision tree (GBDT). Multiple dual ensemble schemes involving various fine-tuned GBDT algorithms such as gradient boosting machine (GBM), LightGBM, CatBoost, and XGBoost, are extensively appraised using multiple publicly available data sets, such as NSL-KDD, UNSW-NB15, and HIKARI-2021. The results indicate that the proposed technique is a reasonable solution for the anomaly-based IDS task. Furthermore, we demonstrate that the combination of Bagging and GBM is superior to all alternative combination schemes. In addition, the proposed dual ensemble (e.g., Bagging-GBM) is considerably more competitive than similar techniques reported in the current literature.

Efficient Machine Learning Models for the Uplift Behavior of Helical Anchors in Dense Sand for Wind Energy Harvesting

Helical anchors are widely used in engineering to resist tension, especially during offshore wind energy harvesting, and their uplift behavior in sand is influenced by many factors. Experimental studies are often used to investigate these anchors; however, scale effects are inevitable in 1× g model tests, soil conditions for in situ tests are challenging to control, and centrifuge tests are expensive and rare. To make full use of the limited valid data and to gain more knowledge about the uplift behaviors of helical anchors in sand, a prediction model integrating gradient-boosting decision trees (GBDT) and particle swarm optimization (PSO) was proposed in this study. Data obtained from a series of centrifuge tests formed the dataset of the prediction model. The relative density of soil, embedment ratio, helix spacing ratio, and the number of helices were used as input parameters, while the anchor mobilization distance and the ultimate monotonic uplift resistance were set as output parameters. A GBDT algorithm was used to construct the model, and a PSO algorithm was used for hyperparameter tuning. The results show that the optimal GBDT model accurately predicted the anchor mobilization distance and the ultimate monotonic uplift resistance of helical anchors in dense fine silica sand. By analyzing the relative importance of influencing variables, the embedment ratio was found to be the most significant variable in the model, while the relative density of the fine silica sand soil, the helix spacing ratio, and the number of helices had relatively minor influence. In particular, the helix spacing ratio was found to have no influence on the capacity of adjacent helices when S/D > 6.

Development and validation of prediction models for hypertension risks: A cross-sectional study based on 4,287,407 participants.

ObjectiveTo develop an optimal screening model to identify the individuals with a high risk of hypertension in China by comparing tree-based machine learning models, such as classification and regression tree, random forest, adaboost with a decision tree, extreme gradient boosting decision tree, and other machine learning models like an artificial neural network, naive Bayes, and traditional logistic regression models.MethodsA total of 4,287,407 adults participating in the national physical examination were included in the study. Features were selected using the least absolute shrinkage and selection operator regression. The Borderline synthetic minority over-sampling technique was used for data balance. Non-laboratory and semi-laboratory analyses were carried out in combination with the selected features. The tree-based machine learning models, other machine learning models, and traditional logistic regression models were constructed to identify individuals with hypertension, respectively. Top features selected using the best algorithm and the corresponding variable importance score were visualized.ResultsA total of 24 variables were finally included for analyses after the least absolute shrinkage and selection operator regression model. The sample size of hypertensive patients in the training set was expanded from 689,025 to 2,312,160 using the borderline synthetic minority over-sampling technique algorithm. The extreme gradient boosting decision tree algorithm showed the best results (area under the receiver operating characteristic curve of non-laboratory: 0.893 and area under the receiver operating characteristic curve of semi-laboratory: 0.894). This study found that age, systolic blood pressure, waist circumference, diastolic blood pressure, albumin, drinking frequency, electrocardiogram, ethnicity (uyghur, hui, and other), body mass index, sex (female), exercise frequency, diabetes mellitus, and total bilirubin are important factors reflecting hypertension. Besides, some algorithms included in the semi-laboratory analyses showed less improvement in the predictive performance compared to the non-laboratory analyses.ConclusionUsing multiple methods, a more significant prediction model can be built, which discovers risk factors and provides new insights into the prediction and prevention of hypertension.