Gradient Boosting Regression Research Articles

Advancing nanofluid analysis: A GBR-GSO predictive model for accurate prediction of specific heat capacity in nanofluids

Nanofluids, characterized by the dispersion of nanoparticles in a base liquid, have attracted significant attention in recent years due to their exceptional thermal properties. Specifically, the specific heat capacity of nanofluids plays a crucial role in the design and optimization of heat transfer systems. Traditional experimental methods for determining the specific heat capacity of nanofluids are often limited in terms of cost, time, and operating condition ranges. To address these limitations, this research focuses on the development of a novel predictive model for estimating the specific heat capacity of nanofluids. This study aims to develop a machine learning regression model called Gradient Boost Regression (GBR) with Grid Search optimization (GSO) for accurately predicting the specific heat capacity of aluminum nitride (Al2N3) nanoparticles that are suspended in both water and an ethylene glycol (EG) solution. The GBR-GSO model capitalizes on the strengths of GBR, which can effectively capture complex relationships, and GSO, a metaheuristic optimization technique inspired by the law of gravity. By integrating these two approaches, we aim to create a robust and accurate predictive model for specific heat capacity in nanofluids. To develop and validate the GBR-GSO model, a diverse dataset based on experimental-specific heat capacity collected from the literature has been designed. The performance of the model has been evaluated by comparing its predictions with experimental data. The GBR-GSO model achieved 99.99% accuracy with the experimental data of specific heat capacity. This research contributes to the advancement of nanofluid-based heat transfer systems by providing an effective tool for predicting the specific heat capacity of nanofluids. The developed model can facilitate the design and optimization of various engineering applications, leading to the development of energy-efficient and sustainable technologies.

Improving solar power forecast from meteorological parameters with regression models

ABSTRACT Solar power forecasting is crucial in boosting the rivalry of solar power plants in the electricity markets and minimizing economic and social dependence on fossil fuels. This paper describes a method for foretelling solar power by utilizing regression approaches. The proposed regression models are developed using an actual meteorological set of data from Qassim University, KSA for one year (September 2021- August 2022). Forecasting solar power production is crucial to dealing with the smart grid’s demand and supply challenges. This research aims to make ML models that can precisely forecast solar power production. Significantly, the following noteworthy components highlight the main contributions of this work. Primarily a framework for the analysis of data is presented, and then the dataset obtained from the solar photovoltaic (SPV) system is visualized. Secondly, we evaluate the predictive capability of machine learning (ML) models employing numerous performance indices for predicting solar power time-series dataset values. According to the experimental findings, the proposed predictive approaches can lessen forecasting complexity even with a small reconstruction error. Additionally, the GBR (Gradient Boosting regression) model significantly outperformed other benchmark techniques in terms of forecast accuracy with MAPE of 0.7674, RMSE of 0.0191, MAE of 0.0132, MSE of 0.0030, and R2 of 0.9723 respectively.

Experimental Investigation of the Influence of Various Wear Parameters on the Tribological Characteristics of AZ91 Hybrid Composites and Their Machine Learning Modeling

Abstract In the current work, the AZ91 hybrid composites are fabricated through the utilization of the stir casting technique, incorporating aluminum oxide (Al2O3) and graphene (Gr) as reinforcing elements. Wear behavior of the AZ91/Gr/Al2O3 composites was examined with the pin-on-disc setup under dry conditions. In this study, the factors such as reinforcement percentage (R), load (L), velocity (V), and sliding distance (D) have been chosen to investigate their impact on the wear-rate (WR) and coefficient of friction (COF). This study utilizes a full factorial design to conduct experiments. The experimental data was critically analyzed to examine the impact of each wear parameter (i.e., R, L, V, and D) on the WR and COF of composites. The wear mechanisms at the extreme conditions of maximum and minimum wear rates are also investigated by utilizing the scanning electron microscope (SEM) images of specimen's surface. The SEM study revealed the presence of delamination, abrasion, oxidation, and adhesion mechanisms on the surface experiencing wear. Machine learning (ML) models, such as decision tree (DT), random forest (RF), and gradient boosting regression (GBR), are employed to create a robust prediction model for predicting output responses based on input variables. The prediction model was trained and tested with 95% and 5% experimental data points, respectively. It was noticed that among all the models, the GBR model exhibited superior performance in predicting WR, with mean square error (MSE) = 0.0398, root-mean-square error (RMSE) = 0.1996, mean absolute error (MAE) = 0.1673, and R2 = 98.89, surpassing the accuracy of other models.

Predicting the band gap of lead-free inorganic double perovskites using modified parallel residual network

The rapid and precise screening of appropriate inorganic perovskite materials poses a formidable challenge in the field of materials science. Traditional methods for material screening are not only time-consuming but also demand a substantial workforce. In this study, we introduce a modified parallel residual network (PRN) for the purpose of predicting the band gap of lead-free inorganic double perovskite materials, utilizing the atomic composition as the input data. The predictive performance of PRN is assessed using root mean square error (RMSE) and Pearson correlation coefficient ( r) as evaluation metrics. The PRN model yields a band gap prediction with an RMSE of 0.402 eV and an r value of 0.962, respectively. Notably, PRN outperforms various alternative models, including random forest regression (RFR), kernel ridge regression (KRR), support vector regression (SVR), extreme gradient boosting regression (XGBR), one-layer residual variant network (OLRN), and three-layer parallel residual variant network (TLPRN), clearly demonstrating its superior predictive accuracy.

Explainable Machine Learning-Based Prediction Model for Diabetic Nephropathy.

The aim of this study is to analyze the effect of serum metabolites on diabetic nephropathy (DN) and predict the prevalence of DN through a machine learning approach. The dataset consists of 548 patients from April 2018 to April 2019 in the Second Affiliated Hospital of Dalian Medical University (SAHDMU). We select the optimal 38 features through a least absolute shrinkage and selection operator (LASSO) regression model and a 10-fold cross-validation. We compare four machine learning algorithms, including extreme gradient boosting (XGB), random forest, decision tree, and logistic regression, by AUC-ROC curves, decision curves, and calibration curves. We quantify feature importance and interaction effects in the optimal predictive model by Shapley additive explanation (SHAP) method. The XGB model has the best performance to screen for DN with the highest AUC value of 0.966. The XGB model also gains more clinical net benefits than others, and the fitting degree is better. In addition, there are significant interactions between serum metabolites and duration of diabetes. We develop a predictive model by XGB algorithm to screen for DN. C2, C5DC, Tyr, Ser, Met, C24, C4DC, and Cys have great contribution in the model and can possibly be biomarkers for DN.

Multi-model fusion stacking ensemble learning method for the prediction of berberine by FT-NIR spectroscopy

Rhizoma Coptidis is a Chinese herbal medicine with antibacterial and anti-inflammatory properties. It has extensive applications in modern medicine. The content of berberine in Rhizoma Coptidis directly determines its quality. Fourier transforms near-infrared (FT-NIR) spectroscopy is a commonly used non-destructive method for rapidly detecting berberine content. In contrast to single-supervised learning algorithms in machine learning, ensemble learning combines individual learning algorithms to create a stable and better-performing strong-supervised model. This study collected spectral data of Rhizoma Coptidis using FT-NIR spectroscopy technology and established a chemometric model using a stacking ensemble approach with multiple models. Partial Least Squares (PLS), Adaptive Boosting (AdaBoost), Gradient boosting decision trees (GBDT), random forest (RF), and extreme gradient boosting (XGBoost) regression models were chosen as alternative base models, different Stacking models were established by random combinations. To fully leverage the strengths of each model and enhance predictive capability, an adaptive inertia weight particle swarm optimization algorithm (AWPSO) was used to search for the optimal parameters. The correlation coefficient of the test (RT) and the root mean square error of the test (RMSET) systematically evaluated the model performance. Finally, AWPSO-RF, AWPSO-XGBoost, and AWPSO-AdaBoost were selected as the base models. The RMSET and RT for RF, XGBoost, and AdaBoost were 0.226, 0.250, 0.195, and 0.871, 0.830, 0.927. After optimizing with the AWPSO algorithm, the RMSET and RT for AWPSO-RF, AWPSO-XGBoost, and AWPSO-AdaBoost were 0.226, 0.245, 0.194, and 0.871, 0.843, 0.922, respectively. The RMSET and RT values for the stacking ensemble were 0.174 and 0.932. The prediction accuracy and generalization ability of multi-model fusion stacking ensemble learning are superior to the single-model regression methods. Therefore, the stacking ensemble learning method that combines AdaBoost, RF, and XGBoost regression models is effective and feasible for assisting in the detection of berberine content in Rhizoma Coptidis.

Dynamic real-time forecasting technique for reclaimed water volumes in urban river environmental management

In recent years, the utilization of wastewater recycling as an alternative water source has gained significant traction in addressing urban water shortages. Accurate prediction of wastewater quantity is paramount for effective urban river water resource management. There is an urgent need to develop advanced forecasting technologies to further enhance the accuracy and efficiency of water quantity predictions. Decomposition ensemble models have shown excellent predictive capabilities but are challenged by boundary effects when decomposing the original data sequence. To address this, a rolling forecast decomposition ensemble scheme was developed. It involves using a machine learning (ML) model for prediction and progressively integrating prediction outcomes into the original sequence using complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Long short-term memory (LSTM) is then applied for sub-signal prediction and ensemble. The ML-CEEMDAN-LSTM model was introduced for wastewater quantity prediction, compared with non-decomposed ML models, CEEMDAN-based LSTM models, and ML-CEEMDAN-based LSTM models. Three ML algorithms—linear regression (LR), gradient boosting regression (GBR), and LSTM—were examined, using real-time prediction data and historical monitoring data, with historical data selected using the decision tree method. The study used daily water volumes data from two reclaimed water plants, CH and WQ, in Beijing. The results indicate that (1) ML models varied in their selection of real-time factors, with LR performing best among ML models during testing; (2) the ML-CEEMDAN-LSTM model consistently outperformed ML models; (3) the ML-CEEMDAN-LSTM hybrid model performed better than the CEEMDAN-LSTM model across different seasons. This study offers a reliable and accurate approach for reclaimed water volumes forecasting, critical for effective water environment management.

Vessel turnaround time prediction: A machine learning approach

Uncertainty in vessel turnaround time (VTT) is troublesome and would reduce the operational efficiency in port management, potentially causing economic losses. Despite vessels generally providing their estimated departure time (EDT), there is frequently a considerable difference between the EDT and the actual departure time (ADT) of vessels due to various factors such as unexpected port handling inefficiency. This variability complicates the coordination of efficient port operations. Our research aims to address this issue by employing an extreme gradient boosting (XGBoost) regression model to predict the VTT, using vessel arrival and departure data at the Hong Kong Port for the year 2022 and the first quarter of 2023. The proposed machine learning approach can provide more accurate predictions on VTT on average compared to the EDT data reported by vessels themselves, with a substantial reduction in both mean absolute error (MAE) and root mean square error (RMSE) of 23% (from 5.1 h to 3.9 h) and 24% (from 8.0 h to 6.1 h), respectively. These results present a significant leap forward in the predictive capabilities for the VTT and lay the foundation for further research into improving vessel scheduling efficiency, reducing port congestion and enhancing overall port performance.

Predicting the Productivity of Municipality Workers: A Comparison of Six Machine Learning Algorithms

One of the most significant areas of local government in the world is the municipality sector. It provides various services to the residents and businesses in their areas, such as water supply, sewage disposal, healthcare, education, housing, and transport. Municipalities also promote social and economic development and ensure democratic and accountable governance. It also helps in encouraging the involvement of communities in local matters. Workers of Municipalities need to maintain their services regularly to the public. The productivity of the employees is just one of the main important factors that influence the overall organizational performance. This article compares various machine learning algorithms such as XG Boost, Random Forest (RF), Histogram Gradient Boosting Regressor, LGBM Regressor, Ada Boost Regressor, and Gradient Boosting Regressor on the dataset of municipality workers. The study aims to propose a machine learning approach to predict and evaluate the productivity of municipality workers. The evaluation of the overall targeted and actual productivity of each department shows that out of 12 different departments, only 5 departments were able to meet their targeted productivity. A 3D Scatter plot visually displays the incentive given by the department to each worker based on their productivity. The results show that XG Boost performs best in comparison with the other five algorithms, as the value of R Squared is 0.71 and MSE (Mean Squared Error) is 0.01.

Predicting radiographic outcomes of vertebral body tethering in adolescent idiopathic scoliosis patients using machine learning.

Anterior Vertebral Body Tethering (AVBT) is a growing alternative treatment for adolescent idiopathic scoliosis (AIS), offering an option besides spinal fusion. While AVBT aims to correct spinal deformity through growth correction, its outcomes have been mixed. To improve surgical outcomes, this study aimed to develop a machine learning-based tool to predict short- and midterm spinal curve correction in AIS patients who underwent AVBT surgery, using the most predictive clinical, radiographic, and surgical parameters. After institutional review board approval and based on inclusion criteria, 91 AIS patients who underwent AVBT surgery were selected from the Shriners Hospitals for Children, Philadelphia. For all patients, longitudinal standing (PA or AP, and lateral) and side bending spinal Radiographs were retrospectively obtained at six visits: preop and first standing, one year, two years, five years postop, and at the most recent follow-up. Demographic, radiographic, and surgical features associated with curve correction were collected. The sequential backward feature selection method was used to eliminate correlated features and to provide a rank-ordered list of the most predictive features of the AVBT correction. A Gradient Boosting Regressor (GBR) model was trained and tested using the selected features to predict the final correction of the curve in AIS patients. Eleven most predictive features were identified. The GBR model predicted the final Cobb angle with an average error of 6.3 ± 5.6 degrees. The model also provided a prediction interval, where 84% of the actual values were within the 90% prediction interval. A list of the most predictive features for AVBT curve correction was provided. The GBR model, trained on these features, predicted the final curve magnitude with a clinically acceptable margin of error. This model can be used as a clinical tool to plan AVBT surgical parameters and improve outcomes.

Application of Machine Learning Algorithms in Predicting Rheological Behavior of BN-diamond/Thermal Oil Hybrid Nanofluids

The use of nanofluids in heat transfer applications has significantly increased in recent times due to their enhanced thermal properties. It is therefore important to investigate the flow behavior and, thus, the rheology of different nanosuspensions to improve heat transfer performance. In this study, the viscosity of a BN-diamond/thermal oil hybrid nanofluid is predicted using four machine learning (ML) algorithms, i.e., random forest (RF), gradient boosting regression (GBR), Gaussian regression (GR) and artificial neural network (ANN), as a function of temperature (25–65 °C), particle concentration (0.2–0.6 wt.%), and shear rate (1–2000 s−1). Six different error matrices were employed to evaluate the performance of these models by providing a comparative analysis. The data were randomly divided into training and testing data. The algorithms were optimized for better prediction of 700 experimental data points. While all ML algorithms produced R2 values greater than 0.99, the most accurate predictions, with minimum error, were obtained by GBR. This study indicates that ML algorithms are highly accurate and reliable for the rheological predictions of nanofluids.

Evaluating the generality of machine learning-based universal models used for prediction of condensation heat transfer coefficient in mini/macro channels

This research concerns the development of universal models founded on machine learning to predict the condensation heat transfer coefficient. In this regard, a consolidated database has been employed encompassing 8340 data points which belong to the flow condensation inside mini/macro channels. The database consists of 25 working fluids with hydraulic diameters ranging from 0.42 to 20.8 mm, mass velocities ranging from 13.1 to 1400 Kg m−2 s− 1 and reduced pressures ranging from 0.03 to 0.9. Four machine learning regression models namely artificial neural network (ANN), gradient-boosted regression (GBR), random forest regression (RFR) and support vector regression (SVR) are trained utilizing the database, and subsequently their accuracy and generality are compared. A multitude of dimensionless parameters are regarded as features, while three parameters specifically the heat transfer coefficient, Nusselt number and Nusselt number correction factor are each considered individually as targets. Within each model, the optimal values of the important hyper-parameters are tuned through appropriate search methods. In order to evaluate the generality of the models, the idea is to sequentially exclude each individual database from the consolidated database. The comparison of accuracy and generality of the models reveals that the RFR model using Nusselt number correction factor as target with a mean absolute relative deviation (MARD) of 3.01 % exhibits the highest level of accuracy, whereas the RFR model employing Nusselt number as target with a MARD for the predicted excluded values equal to 19.49 % demonstrates the superior generality.

Feature engineering for improved machine-learning-aided studying heavy metal adsorption on biochar

Due to the broad interest in using biochar from biomass pyrolysis for the adsorption of heavy metals (HMs) in wastewater, machine learning (ML) has recently been adopted by many researchers to predict the adsorption capacity (η) of HMs on biochar. However, previous studies focused mainly on developing different ML algorithms to increase predictive performance, and no study shed light on engineering features to enhance predictive performance and improve model interpretability and generalizability. Here, based on a dataset widely used in previous ML studies, features of biochar were engineered—elemental compositions of biochar were calculated on mole basis—to improve predictive performance, achieving test R2 of 0.997 for the gradient boosting regression (GBR) model. The elemental ratio feature (H-O-2N)/C, representing the H site links to C (non-active site to HMs), was proposed for the first time to help interpret the GBR model. The (H-O-2N)/C and pH of biochar played essential roles in replacing cation exchange capacity (CEC) for predicting η. Moreover, expanding the coverages of variables by adding cases from references improved the generalizability of the model, and further validation using cases without CEC and specific surface area (R2 0.78) and adsorption experimental results (R2 0.72) proved the ML model desirable. Future studies in this area may take into account algorithm innovation, better description of variables, and higher coverage of variables to further increase the model's generalizability.

Predicting coronary heart disease in Chinese diabetics using machine learning

Diabetes, a common chronic disease worldwide, can induce vascular complications, such as coronary heart disease (CHD), which is also one of the main causes of human death. It is of great significance to study the factors of diabetic patients complicated with CHD for understanding the occurrence of diabetes/CHD comorbidity. In this study, by analyzing the risk of CHD in more than 300,000 diabetes patients in southwest China, an artificial intelligence (AI) model was proposed to predict the risk of diabetes/CHD comorbidity. Firstly, we statistically analyzed the distribution of four types of features (basic demographic information, laboratory indicators, medical examination, and questionnaire) in comorbidities, and evaluated the predictive performance of three traditional machine learning methods (eXtreme Gradient Boosting, Random Forest, and Logistic regression). In addition, we have identified nine important features, including age, WHtR, BMI, stroke, smoking, chronic lung disease, drinking and MSP. Finally, the model produced an area under the receiver operating characteristic curve (AUC) of 0.701 on the test samples. These findings can provide personalized guidance for early CHD warning for diabetic populations.

A machine learning based approach for prediction and interpretation of soil properties from soil spectral data

Aim: An active agricultural sector depends on good soil quality, essential for sustained food cultivation. However, intensive farming and rising demand can lead to soil deterioration, affecting crop yields. Smart soil prediction driven by machine learning is crucial for precision farming and efficient nutrient distribution. Methodology: Visible-near infrared Spectroscopy (vis-NIRS) is used to capture the soil's spectral data.Then, the spectral data is preprocessed with Savitzky-Golay Smoothing.The data that has been preprocessed is then used to train the machine learning model.The preprocessed data enhances model performance compared to spectral reflectance data in its unprocessed state.The machine learning model acquires data-based knowledge, identifies patterns, and predicts soil quality parameters. The Random Forest and Gradient Boosted Regression Tree are two algorithms employed in this study. Results: The spectral reflectance data is used to train, validate, and evaluate the machine learning model.In determining soil properties, both algorithms demonstrated a high degree of prediction accuracy, as demonstrated by the results.Gradient Boosted Regression Tree out performs Random Forest, but is expensive and requires sequential data. Random forest algorithm works well with large datasets, but over-fitting issues arise in some instances. Interpretation: The findings of the study indicate that machine learning can automate the current soil testing procedure in laboratories, thereby making it more efficient, affordable, and environmentally friendly. Key words: Gradient Boosted Regression Tree, Machine learning, Random forest, Soil fertility, Soil moisture

Machine-learning to predict anharmonic frequencies: a study of models and transferability.

With more and more accurate electronic structure methods at hand, the inclusion of anharmonic effects in the post-processing of such data towards thermochemical properties is the next step. In this context, the description of anharmonicity has been an important topic of physical chemistry and chemical physics for a long time. In this study, anharmonic frequencies of various hydrogen-halides and halogenated hydrocarbon molecular clusters are calculated using harmonic as well as explicitly anharmonic methods, i.e., normal mode analysis and vibrational self-consistent field. Simple harmonic model based descriptors were used to predict anharmonic frequencies via multilinear regression and gradient boosting regression. Gradient boosting regression is capable of predicting reliable anharmonic data and even the simple multilinear regression model yields reasonable predictions that can account for mode-to-mode couplings. Moreover, the transferability to unseen chemical systems is assessed and it is confirmed that the machine-learned models can be applied to larger, unseen molecules.

Machine learning for forecasting the biomechanical behavior of orthopedic bone plates fabricated by fused deposition modeling

Purpose Three-dimensional (3D) printing is highly dependent on printing process parameters for achieving high mechanical strength. It is a time-consuming and expensive operation to experiment with different printing settings. The current study aims to propose a regression-based machine learning model to predict the mechanical behavior of ulna bone plates. Design/methodology/approach The bone plates were formed using fused deposition modeling (FDM) technique, with printing attributes being varied. The machine learning models such as linear regression, AdaBoost regression, gradient boosting regression (GBR), random forest, decision trees and k-nearest neighbors were trained for predicting tensile strength and flexural strength. Model performance was assessed using root mean square error (RMSE), coefficient of determination (R2) and mean absolute error (MAE). Findings Traditional experimentation with various settings is both time-consuming and expensive, emphasizing the need for alternative approaches. Among the models tested, GBR model demonstrated the best performance in predicting both tensile and flexural strength and achieved the lowest RMSE, highest R2 and lowest MAE, which are 1.4778 ± 0.4336 MPa, 0.9213 ± 0.0589 and 1.2555 ± 0.3799 MPa, respectively, and 3.0337 ± 0.3725 MPa, 0.9269 ± 0.0293 and 2.3815 ± 0.2915 MPa, respectively. The findings open up opportunities for doctors and surgeons to use GBR as a reliable tool for fabricating patient-specific bone plates, without the need for extensive trial experiments. Research limitations/implications The current study is limited to the usage of a few models. Other machine learning-based models can be used for prediction-based study. Originality/value This study uses machine learning to predict the mechanical properties of FDM-based distal ulna bone plate, replacing traditional design of experiments methods with machine learning to streamline the production of orthopedic implants. It helps medical professionals, such as physicians and surgeons, make informed decisions when fabricating customized bone plates for their patients while reducing the need for time-consuming experimentation, thereby addressing a common limitation of 3D printing medical implants.

A Machine Learning Model for Lightning-Related Deaths in Brazil

Abstract Brazil presents the highest number of lightning-related deaths in the world. This study aimed to identify the key victims’ characteristics associated with such fatalities in Brazil and to develop a model that predicts the number of deaths as function of the victims’ data. The dataset provided by the Department of Informatics of the Unified Health System in Brazil (DATASUS) was analyzed and machine learning regression techniques were applied. The gradien-boosting regressor (GBR) model was found to be the most effective, achieving a prediction accuracy of 97%. Through the analysis of 34 initial variables, 10 variables were identified as having the greatest influence on the model’s outcomes. These variables included race, gender, age group, occupational accidents, education, and location of death. Understanding these characteristics is crucial for implementing targeted prevention and safety strategies in various regions, helping to mitigate the risk of lightning-related deaths worldwide. Additionally, the methodology used in this study can serve as a framework for similar research in different locations, allowing for the identification of important factors specific to each region. By adapting the machine learning regression techniques and incorporating local datasets, researchers can gain valuable insights into the determinants of lightning-related fatalities, enabling the development of effective prevention and safety measures tailored to specific geographical areas. Significance Statement This study presents a machine learning approach using the gradient-boosting regressor (GBR) method to estimate the weekly number of lightning-related deaths with an impressive 97% prediction accuracy. The research includes a comprehensive analysis of various factors, such as race, gender, age group, occupational accidents, education, and location of death, providing valuable insights for targeted preventive strategies and safety measures. The findings significantly contribute to understanding lightning-related fatalities in Brazil. The proposed machine learning model demonstrates a robust and accurate fit to the data, allowing for a comprehensive understanding of patterns and underlying trends in lightning fatalities.

Machine learning guided tuning charge distribution by composition in MOFs for oxygen evolution reaction.

Traditional design/optimization of metal-organic frameworks (MOFs) is time-consuming and labor-intensive. In this study, we utilize machine learning (ML) to accelerate the synthesis of MOFs. We have built a library of over 900 MOFs with different metal salts, solvent ratios, reaction durations and temperatures, and utilize zeta potentials as target variables for ML training. A total of four ML models have been used to train the collected dataset and assess their convergence performances, where Random Forest Regression (RFR) and Gradient Boosting Regression (GBR) models show strong correlation and accurate predictions. We then predicted two kinds of MOFs from RFR and GBR models. Remarkably, the experimentally data of the synthesized MOFs closely matched the predicted results, and these MOFs exhibited excellent electrocatalytic performances for oxygen evolution. This study would have general implications in the utilization of machine learning for accelerating the synthesis of MOFs for diverse applications.

Clinical decision support systems for 3-month mortality in elderly patients admitted to ICU with ischemic stroke using interpretable machine learning.

Elderly patients are more likely to suffer from severe ischemic stroke (IS) and have worse outcomes, including death and disability. We aimed to develop and validate predictive models using novel machine learning algorithms for the 3-month mortality in elderly patients with IS admitted to the intensive care unit (ICU). We conducted a retrospective cohort study. Data were extracted from Medical Information Mart for Intensive Care (MIMIC)-IV and International Stroke Perfusion Imaging Registry (INSPIRE) database. Ten machine learning algorithms including Categorical Boosting (CatBoost), Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), Gradient Boosting Machine (GBM), K-Nearest Neighbors (KNNs), Multi-Layer Perceptron (MLP), Naive Bayes (NB), eXtreme Gradient Boosting (XGBoost) and Logistic Regression (LR) were used to build the models. Performance was measured using area under the curve (AUC) and accuracy. Finally, interpretable machine learning (IML) models presenting as Shapley additive explanation (SHAP) values were applied for mortality risk prediction. A total of 1826 elderly patients with IS admitted to the ICU were included in the analysis, of whom 624 (34.2%) died, and endovascular treatment was performed in 244 patients. After feature selection, a total of eight variables, including minimum Glasgow Coma Scale values, albumin, lactate dehydrogenase, age, alkaline phosphatase, body mass index, platelets, and types of surgery, were finally used for model construction. The AUCs of the CatBoost model were 0.737 in the testing set and 0.709 in the external validation set. The Brier scores in the training set and testing set were 0.12 and 0.21, respectively. The IML of the CatBoost model was performed based on the SHAP value and the Local Interpretable Model-Agnostic Explanations method. The CatBoost model had the best predictive performance for predicting mortality in elderly patients with IS admitted to the ICU. The IML model would further aid in clinical decision-making and timely healthcare services by the early identification of high-risk patients.