Quantitative Precipitation Estimates Using Machine Learning Approaches with Operational Dual-Polarization Radar Data

The Southern Great Plains (SGP) region exhibits a relatively high frequency of periods with extremely high rainfall rates (RR) and hail. Seven months of 2017 are simulated using the Weather Research and Forecasting (WRF) Model applied at convection-permitting resolution with the Milbrandt–Yau microphysics scheme. Simulation fidelity is evaluated, particularly during intense convective events, using data from ASOS stations, dual-polarization radar, and gridded datasets and observations at the DOE Atmospheric Radiation Measurement site. The spatial gradients and temporal variability of precipitation and the cumulative density functions for both RR and wind speeds exhibit fidelity. Odds ratios > 1 indicate that WRF is also skillful in simulating high composite reflectivity (cREF, used as a measure of widespread convection) and RR > 5 mm h−1 over the domain. Detailed analyses of the 10 days with highest spatial coverage of cREF > 30 dBZ show spatially similar reflectivity fields and high RR in both radar data and WRF simulations. However, during periods of high reflectivity, WRF exhibits a positive bias in terms of very high RR (>25 mm h−1) and hail occurrence, and during the summer and transition months, maximum hail size is underestimated. For some renewable energy applications, fidelity is required with respect to the joint probabilities of wind speed and RR and/or hail. While partial fidelity is achieved for the marginal probabilities, performance during events of critical importance to these energy applications is currently not sufficient. Further research into optimal WRF configurations in support of potential damage quantification for these applications is warranted. Significance Statement Heavy rainfall and hail during convective events are challenging for numerical models to simulate in both space and time. For some applications, such as to estimate damage to wind turbine blades and solar panels, fidelity is also required with respect to hail size and joint probabilities of wind speed and hydrometeor type and rainfall rates (RR). This demands fidelity that is seldom evaluated. We show that, although this simulation exhibits fidelity for the marginal probabilities of wind speed, RR, and hail occurrence, the joint probabilities of these properties and the simulation of maximum size of hail are, as yet, not sufficient to characterize potential damage to these renewable energy industries.

Simple SummaryThe objective response rate of lenvatinib combined with transarterial chemoembolization for unresectable hepatocellular carcinoma is unsatisfactory. We aimed to develop predictive models using demographic characteristics, pre-treatment serum biomarkers and tumor characteristics of unresectable hepatocellular carcinoma patients by five machine learning algorithms to predict the response under combined treatments. We identified the 10 most important predictors, including K, low-density lipoprotein, D-dimer, red blood cell, alanine aminotransferase, albumin, monocyte, tumor size, triglyceride, and age. In addition, we applied the Shapley Additive exPlanation to explain the best-performing random forest predictive model to provide a reasonable explanation of the efficacy prediction at an individualized level. The combination of machine learning and Shapley Additive exPlanation can provide valuable suggestions for clinical decision making.Background: Lenvatinib and transarterial chemoembolization (TACE) are first-line treatments for unresectable hepatocellular carcinoma (HCC), but the objective response rate (ORR) is not satisfactory. We aimed to predict the response to lenvatinib combined with TACE before treatment for unresectable HCC using machine learning (ML) algorithms based on clinical data. Methods: Patients with unresectable HCC receiving the combination therapy of lenvatinib combined with TACE from two medical centers were retrospectively collected from January 2020 to December 2021. The response to the combination therapy was evaluated over the following 4–12 weeks. Five types of ML algorithms were applied to develop the predictive models, including classification and regression tree (CART), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The performance of the models was assessed by the receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve (AUC). The Shapley Additive exPlanation (SHAP) method was applied to explain the model. Results: A total of 125 unresectable HCC patients were included in the analysis after the inclusion and exclusion criteria, among which 42 (33.6%) patients showed progression disease (PD), 49 (39.2%) showed stable disease (SD), and 34 (27.2%) achieved partial response (PR). The nonresponse group (PD + SD) included 91 patients, while the response group (PR) included 34 patients. The top 40 most important features from all 64 clinical features were selected using the recursive feature elimination (RFE) algorithm to develop the predictive models. The predictive power was satisfactory, with AUCs of 0.74 to 0.91. The SVM model and RF model showed the highest accuracy (86.5%), and the RF model showed the largest AUC (0.91, 95% confidence interval (CI): 0.61–0.95). The SHAP summary plot and decision plot illustrated the impact of the top 40 features on the efficacy of the combination therapy, and the SHAP force plot successfully predicted the efficacy at the individualized level. Conclusions: A new predictive model based on clinical data was developed using ML algorithms, which showed favorable performance in predicting the response to lenvatinib combined with TACE for unresectable HCC. Combining ML with SHAP could provide an explicit explanation of the efficacy prediction.

Machine learning (ML) algorithms are a portion of artificial intelligence that may be used to create more accurate algorithmic procedures for estimating an individual's dental age or defining an age classification. This study aims to use ML algorithms to evaluate the efficacy of pulp/tooth area ratio (PTR) in cone-beam CT (CBCT) images to predict dental age classification in adults. CBCT images of 236 Turkish individuals (121 males and 115 females) from 18 to 70 years of age were included. PTRs were calculated for six teeth in each individual, and a total of 1416 PTRs encompassed the study dataset. Support vector machine, classification and regression tree, and random forest (RF) models for dental age classification were employed. The accuracy of these techniques was compared. To facilitate this evaluation process, the available data were partitioned into training and test datasets, maintaining a proportion of 70% for training and 30% for testing across the spectrum of ML algorithms employed. The correct classification performances of the trained models were evaluated. The models' performances were found to be low. The models' highest accuracy and confidence intervals were found to belong to the RF algorithm. According to our results, models were found to be low in performance but were considered as a different approach. We suggest examining the different parameters derived from different measuring techniques in the data obtained from CBCT images in order to develop ML algorithms for age classification in forensic situations.

Slope stability prediction using integrated metaheuristic and machine learning approaches: A comparative study

This study aimed to develop a machine learning model for accurately predicting postoperative VTE risk in these patients. The data of this study retrospectively collected the inpatients of cervical cancer in the Affiliated Cancer Hospital of Chongqing University from January 2020 to December 2023. We utilized 1,044 observations and six variables to develop seven machine learning (ML) models and selected the best-performing model for assessing postoperative venous thromboembolism (VTE) risk. The models were evaluated using ROC, PR, and DCA curves, and the prediction of the model's process was explained using SHAP values. Among 1,044 postoperative cervical cancer patients, 82 (7.85%) developed VTE. Seven machine learning algorithms were developed and evaluated, with the random forest (RF) model showing the best overall performance (AUC = 0.852, AUPR = 0.332). Compared with other models, including logistic regression (AUC = 0.767) and XGBoost (AUC = 0.836), the RF model demonstrated superior discrimination, calibration, and generalizability. Decision curve analysis confirmed that the RF model yielded the highest net clinical benefit across a wide range of threshold probabilities (5-80%). SHAP analysis revealed that D-dimer, neutrophil-to-lymphocyte ratio (NLR), and age were the most influential variables, indicating their substantial contributions to model prediction. Our study suggests that machine learning algorithms can be practical tools for postoperative VTE risk assessment and can learn from patient characteristics to provide personalized evaluations. The RF model outperformed the other six algorithms evaluated. We developed the final RF model as a user-friendly web tool for healthcare professionals.

Background Predicting the prognosis of patients with acute myocardial infarction (AMI) combined with diabetes mellitus (DM) is crucial due to high in-hospital mortality rates. This study aims to develop and validate a mortality risk prediction model for these patients by interpretable machine learning (ML) methods. Methods Data were sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV, version 2.2). Predictors were selected by Least absolute shrinkage and selection operator (LASSO) regression and checked for multicollinearity with Spearman’s correlation. Patients were randomly assigned to training and validation sets in an 8:2 ratio. Seven ML algorithms were used to construct models in the training set. Model performance was evaluated in the validation set using metrics such as area under the curve (AUC) with 95% confidence interval (CI), calibration curves, precision, recall, F1 score, accuracy, negative predictive value (NPV), and positive predictive value (PPV). The significance of differences in predictive performance among models was assessed utilising the permutation test, and 10-fold cross-validation further validated the model’s performance. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were applied to interpret the models. Results The study included 2,828 patients with AMI combined with DM. Nineteen predictors were identified through LASSO regression and Spearman’s correlation. The Random Forest (RF) model was demonstrated the best performance, with an AUC of 0.823 (95% CI: 0.774–0.872), high precision (0.867), accuracy (0.873), and PPV (0.867). The RF model showed significant differences (p < 0.05) compared to the K-Nearest Neighbours and Decision Tree models. Calibration curves indicated that the RF model’s predicted risk aligned well with actual outcomes. 10-fold cross-validation confirmed the superior performance of RF model, with an average AUC of 0.828 (95% CI: 0.800–0.842). Significant Variables in RF model indicated that the top eight significant predictors were urine output, maximum anion gap, maximum urea nitrogen, age, minimum pH, maximum international normalised ratio (INR), mean respiratory rate, and mean systolic blood pressure. Conclusion This study demonstrates the potential of ML methods, particularly the RF model, in predicting in-hospital mortality risk for AMI patients with DM. The SHAP and LIME methods enhance the interpretability of ML models.

Background and aimsThe birth weight of a newborn is a crucial factor that affects their overall health and future well-being. Low birth weight (LBW) is a widespread global issue, which the World Health Organization defines as weighing less than 2,500 g. LBW can have severe negative consequences on an individual’s health, including neonatal mortality and various health concerns throughout their life. To address this problem, this study has been conducted using BDHS 2017–2018 data to uncover important aspects of LBW using a variety of machine learning (ML) approaches and to determine the best feature selection technique and best predictive ML model.MethodsTo pick out the key features, the Boruta algorithm and wrapper method were used. Logistic Regression (LR) used as traditional method and several machine learning classifiers were then used, including, DT (Decision Tree), SVM (Support Vector Machine), NB (Naïve Bayes), RF (Random Forest), XGBoost (eXtreme Gradient Boosting), and AdaBoost (Adaptive Boosting), to determine the best model for predicting LBW. The model’s performance was evaluated based on the specificity, sensitivity, accuracy, F1 score and AUC value.ResultsResult shows, Boruta algorithm identifies eleven significant features including respondent’s age, highest education level, educational attainment, wealth index, age at first birth, weight, height, BMI, age at first sexual intercourse, birth order number, and whether the child is a twin. Incorporating Boruta algorithm’s significant features, the performance of traditional LR and ML methods including DT, SVM, NB, RF, XGBoost, and AB were evaluated where LR, had a specificity, sensitivity, accuracy and F1 score of 0.85, 0.5, 85.15% and 0.915. While the ML methods DT, SVM, NB, RF, XGBoost, and AB model’s respective accuracy values were 85.35%, 85.15%, 84.54%, 81.18%, and 84.41%. Based on the specificity, sensitivity, accuracy, F1 score and AUC, RF (specificity = 0.99, sensitivity = 0.58, accuracy = 85.86%, F1 score = 0.9243, AUC = 0.549) outperformed the other methods. Both the classical (LR) and machine learning (ML) models’ performance has improved dramatically when important characteristics are extracted using the wrapper method. The LR method identified five significant features with a specificity, sensitivity, accuracy and F1 score of 0.87, 0.33, 87.12% and 0.9309. The region, whether the infant is a twin, and cesarean delivery were the three key features discovered by the DT and RF models, which were implemented using the wrapper technique. All three models had the identical F1 score of 0.9318. However, “child is twin” was recognized as a significant feature by the SVM, NB, and AB models, with an F1 score of 0.9315. Ultimately, with an F1 score of 0.9315, the XGBoost model recognized “child is twin” and “age at first sex” as relevant features. Random Forest again beat the other approaches in this instance.ConclusionsThe study reveals Wrapper method as the optimal feature selection technique. The ML method outperforms traditional methods, with Random Forest (RF) being the most effective predictive model for Low-Birth-Weight prediction. The study suggests that policymakers in Bangladesh can mitigate low birth weight newborns by considering identified risk factors.

Air pollution in Macau has become a serious problem following the Pearl River Delta’s (PRD) rapid industrialization that began in the 1990s. With this in mind, Macau needs an air quality forecast system that accurately predicts pollutant concentration during the occurrence of pollution episodes to warn the public ahead of time. Five different state-of-the-art machine learning (ML) algorithms were applied to create predictive models to forecast PM2.5, PM10, and CO concentrations for the next 24 and 48 h, which included artificial neural networks (ANN), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and multiple linear regression (MLR), to determine the best ML algorithms for the respective pollutants and time scale. The diurnal measurements of air quality data in Macau from 2016 to 2021 were obtained for this work. The 2020 and 2021 datasets were used for model testing, while the four-year data before 2020 and 2021 were used to build and train the ML models. Results show that the ANN, RF, XGBoost, SVM, and MLR models were able to provide good performance in building up a 24-h forecast with a higher coefficient of determination (R2) and lower root mean square error (RMSE), mean absolute error (MAE), and biases (BIAS). Meanwhile, all the ML models in the 48-h forecasting performance were satisfactory enough to be accepted as a two-day continuous forecast even if the R2 value was lower than the 24-h forecast. The 48-h forecasting model could be further improved by proper feature selection based on the 24-h dataset, using the Shapley Additive Explanations (SHAP) value test and the adjusted R2 value of the 48-h forecasting model. In conclusion, the above five ML algorithms were able to successfully forecast the 24 and 48 h of pollutant concentration in Macau, with the RF and SVM models performing the best in the prediction of PM2.5 and PM10, and CO in both 24 and 48-h forecasts.

This work introduces a predictive Length of Stay (LOS) framework for lung cancer patients using machine learning (ML) models. The framework proposed to deal with imbalanced datasets for classification-based approaches using electronic healthcare records (EHR). We have utilized supervised ML methods to predict lung cancer inpatients LOS during ICU hospitalization using the MIMIC-III dataset. Random Forest (RF) Model outperformed other models and achieved predicted results during the three framework phases. With clinical significance features selection, over-sampling methods (SMOTE and ADASYN) achieved the highest AUC results (98% with CI 95%: 95.3–100%, and 100% respectively). The combination of Over-sampling and under-sampling achieved the second-highest AUC results (98%, with CI 95%: 95.3–100%, and 97%, CI 95%: 93.7–100% SMOTE-Tomek, and SMOTE-ENN respectively). Under-sampling methods reported the least important AUC results (50%, with CI 95%: 40.2–59.8%) for both (ENN and Tomek- Links). Using ML explainable technique called SHAP, we explained the outcome of the predictive model (RF) with SMOTE class balancing technique to understand the most significant clinical features that contributed to predicting lung cancer LOS with the RF model. Our promising framework allows us to employ ML techniques in-hospital clinical information systems to predict lung cancer admissions into ICU.

Land degradation from gully erosion poses a significant threat to the Erer watershed in Eastern Ethiopia, particularly due to agricultural activities and resource exploitation. Identifying erosion-prone areas and underlying factors using advanced machine learning algorithms (MLAs) and geospatial analysis is crucial for addressing this problem and prioritizing adaptive and mitigating strategies. However, previous studies have not leveraged machine learning (ML) and GIS-based approaches to generate susceptibility maps identifying these areas and conditioning factors, hindering sustainable watershed management solutions. This study aimed to predict gully erosion susceptibility (GES) and identify underlying areas and factors in the Erer watershed. Four ML models, namely, XGBoost, random forest (RF), support vector machine (SVM), and artificial neural network (ANN), were integrated with geospatial analysis using 22 geoenvironmental predictors and 1,200 inventory points (70% used for training and 30% for testing). Model performance and robustness were validated through the area under the curve (AUC), accuracy, precision, sensitivity, specificity, kappa coefficient, F1 score, and logarithmic loss. The relative slope position is most influential, with 100% importance in SVM and RF and 95% importance in XGBoost, while annual rainfall (AR) dominated ANN (100% importance). Notably, XGBoost demonstrated robustness and superior prediction/mapping, achieving an AUC of 0.97, 91% accuracy, 92% precision, and 81% kappa while maintaining a low logloss (0.0394). However, SVM excelled in classifying gully resistant/susceptible areas (97% sensitivity, 98% specificity, and 91% F1 score). The ANN model predicted the most areas with very high gully susceptibility (13.74%), followed by the SVM (11.69%), XGBoost (10.65%), and RF (7.85%) models, while XGBoost identified the most areas with very low susceptibility (70.19%). The ensemble technique was employed to further enhance GES modeling, and it outperformed the individual models, achieving an AUC of 0.99, 93.5% accuracy, 92.5% precision, 97.5% sensitivity, 95.4% specificity, 85.8% kappa, and 94.9% F1 score. This technique also classified the GES of the watershed as 36.48% very low, 26.51% low, 16.24% moderate, 11.55% high, and 9.22% very high. Furthermore, district-level analyses revealed the most susceptible areas, including the Babile, Fedis, Harar, and Meyumuluke districts, with high GES areas of 32.4%, 21.3%, 14.3%, and 13.6%, respectively. This study offers robust and flexible ML models with comprehensive validation metrics to enhance GES modeling and identify gully prone areas and factors, thereby supporting decision-making for sustainable watershed conservation and land degradation prevention.

Generating high-resolution daily soil moisture by using spatial downscaling techniques: a comparison of six machine learning algorithms

Predictive artificial intelligence (AI) models for the assessment of factors and trends related to disease prevalence, prognosis, and the risk prediction of mortality in the early phases, seem to be effective techniques. Machine learning (ML) algorithms as a branch of AI methods have had a considerable role in controlling and management of COVID-19 and previous pandemics. The present study estimates the mortality risk among COVID-19 patients based on ML algorithms, prediction of outcomes in new cases, and also determines the top significant features related to morality in the patients. In this retrospective research, 7115 patients with confirmed COVID-19 disease were included in the study. The information was collected from 35 different hospitals across Khorasan-Razavi province, Northeast of Iran during 20 February 2020 - 21 June 2021. We employed random forests (RF), decision tree (DT), artificial neural networks (ANN), support vector machines (SVM), logistic regression (LR), and boosted trees (BT) ML algorithms. Our findings indicated that the RF model had better performance in different criteria. The RF algorithm had area under curve (AUC) of 88%, accuracy of 96%, precision of 96%, sensitivity of 99%, and specificity of 80%. Intubation, SpO2, age, time from symptoms, loss of consciousness, reception season, and diabetes were the seven ordered and significant predictors of the risk of COVID-19 patients’ death. RF model can aid in clinical decision-making and limited resource allocation. This model needs to be externally validated in larger populations, more features, and multicenter settings. Received: August 4, 2023Accepted: September 13, 2023

Using machine learning (ML) to explore the noninvasive differential diagnosis of Cushing's disease (CD) and ectopic corticotropin (ACTH) secretion (EAS) model is the next hot research topic. This study was to develop and evaluate ML models for differentially diagnosing CD and EAS in ACTH-dependent Cushing's syndrome (CS). Two hundred sixty-four CD and forty-seven EAS were randomly divided into training and validation and test datasets. We applied 8 ML algorithms to select the most suitable model. The diagnostic performance of the optimal model and bilateral petrosal sinus sampling (BIPSS) were compared in the same cohort. Eleven adopted variables included age, gender, BMI, duration of disease, morning cortisol, serum ACTH, 24-h UFC, serum potassium, HDDST, LDDST, and MRI. After model selection, the Random Forest (RF) model had the most extraordinary diagnostic performance, with a ROC AUC of 0.976 ± 0.03, a sensitivity of 98.9% ± 4.4%, and a specificity of 87.9% ± 3.0%. The serum potassium, MRI, and serum ACTH were the top three most important features in the RF model. In the validation dataset, the RF model had an AUC of 0.932, a sensitivity of 95.0%, and a specificity of 71.4%. In the complete dataset, the ROC AUC of the RF model was 0.984 (95% CI 0.950-0.993), which was significantly higher than HDDST and LDDST (both p < 0.001). There was no significant statistical difference in the comparison of ROC AUC between the RF model and BIPSS (baseline ROC AUC 0.988 95% CI 0.983-1.000, after stimulation ROC AUC 0.992 95% CI 0.983-1.000). This diagnostic model was shared as an open-access website. A machine learning-based model could be a practical noninvasive approach to distinguishing CD and EAS. The diagnostic performance might be close to BIPSS.

Accurate oil palm yield prediction is necessary to sustain oil palm production for food security and economic return. However, there are limited studies on comprehensive mapping and accurate oil palm yield prediction using advanced machine learning algorithms. Using multi-temporal remote sensing data, this paper proposed a new approach to predict oil palm yield based on the normalized difference vegetation index (NDVI) and ensemble machine learning algorithm. ReliefF algorithm with linear projection was employed to select the best combination of spectral indices in oil palm discrimination. Oil palm land cover was classified using random forest (RF) and modified AdaBoost algorithms. A time-series approach known as walk-forward validation was firstly introduced to train the model using the 2016-2019 data and the one-step prediction was performed for 2020 using RF and AdaBoost. Result of the study revealed that the RF model (RMSE = 0.384; MSE = 0.148; MAE = 0.147) outperformed the AdaBoost model (RMSE = 0.410; MSE = 0.168; MAE = 0.176). Our research has demonstrated the value of detailed mapping and subsequent yield prediction by developing a novel approach utilising time-series satellite imagery, ensemble machine learning, and NDVI, which will assist decision-makers in managing their practices related to oil palm.

Land-use regression model and machine learning algorithms in assessing outdoor noise exposure in Hong KongBackground/Aim: There are epidemiological studies in reporting the association between environmental noise exposure and various health outcomes, including cardiovascular diseases and cognitive decline. However, evidence in using land-use regression (LUR) model in predicting noise is limited and not conclusive, while machine learning algorithms are seemed to be a novel method in improving the explanative power of noise prediction. In this study, random forest (RF) model was adopted to estimate outdoor noise level in Hong Kong and compare the performance between LUR and RF. Methods: A total of 102 measurement sites with 27 environment-related variables were used to estimate the spatial environmental noise variation. Two separate measurements for A-weighted equivalent sound pressure levels over 24 hours (Leq,24h) were conducted at each site during the 2019-2020 period. Land use types, traffic information and geographic information systems were chosen to the related variables for building models. Ordinary linear regression was adopted to be the traditional land-use regression model. Results: The annual mean of 102 measurement sites of Leq,24h was 66.3 dB(A). The proportion of variation (R2) explained by the random forest model in full-frequency noise was higher than the traditional LUR (R2: RF: 0.76, LUR: 0.69). Random forest performed also better in lower root mean squared errors (RF: 2.91 dB(A), LUR: 3.22 dB(A)). Further results on the noise level in different time periods and frequencies will be described in the conference. Conclusion: Random forest model is suggested to be a better alternative in estimating noise exposure. Further study on the application of the model on epidemiological studies can be conducted.