Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest

Land subsidence in Bangkok vicinity: Causes and long-term trend analysis using InSAR and machine learning

Land subsidence in Bangkok, a pressing environmental challenge, demands sustained long-term policy interventions. Although mitigation measures have successfully alleviated subsidence rates within inner Bangkok, neighboring provinces continue to experience escalating rates. Conventional land-based monitoring methods exhibit limitations in coverage, and the anticipated nonlinear contributions of climatic and socioeconomic factors further complicate the spatiotemporal distribution of subsidence. This study aims to provide future subsidence predictions for the near (2023-2048), mid (2049-2074), and far-future (2075-2100), employing Interferometric Synthetic Aperture Radar (InSAR), Random Forest machine learning algorithm, and combined Shared Socioeconomic Pathways-Representative Concentration Pathways (SSP-RCPs) scenarios to address these challenges. The mean Line-of-Sight (LOS) velocity was found to be -7.0 mm/year, with a maximum of -53.5 mm/year recorded in Ayutthaya. The proposed model demonstrated good performance, yielding an R2 value of 0.84 and exhibiting no signs of overfitting. Across all scenarios, subsidence rates tend to increase by more than -9.0 mm/year in the near-future. However, for the mid and far-future, scenarios illustrate varying trends. The 'only-urban-LU change' scenario predicts a gradual recovery, while other change scenarios exhibit different tendencies.

Stretchable MXene/Carbon Nanotube Bilayer Strain Sensors with Tunable Sensitivity and Working Ranges

Stretchable strain sensors have gained increasing popularity as wearable devices to convert mechanical deformation of the human body into electrical signals. Two-dimensional transition metal carbides (Ti3C2Tx MXene) are promising candidates to achieve excellent sensitivity. However, MXene films have been limited in operating strain ranges due to rapid crack propagation during stretching. In this regard, this study reports MXene/carbon nanotube bilayer films with tunable sensitivity and working ranges. The device is fabricated using a scalable process involving spray deposition of well-dispersed nanomaterial inks. The bilayer sensor's high sensitivity is attributed to the cracks that form in the MXene film, while the compliant carbon nanotube layer extends the working range by maintaining conductive pathways. Moreover, the response of the sensor is easily controlled by tuning the MXene loading, achieving a gauge factor of 9039 within 15% strain at 1.92 mg/cm2 and a gauge factor of 1443 within 108% strain at 0.55 mg/cm2. These tailored properties can precisely match the operation requirements during the wearable application, providing accurate monitoring of various body movements and physiological activities. Additionally, a smart glove with multiple integrated strain sensors is demonstrated as a human-machine interface for the real-time recognition of hand gestures based on a machine-learning algorithm. The design strategy presented here provides a convenient avenue to modulate strain sensors for targeted applications.

A comparative analysis of deep learning-based location-adaptive threshold method software against other commercially available software

Automatic segmentation of the coronary artery using coronary computed tomography angiography (CCTA) images can facilitate several analyses related to coronary artery disease (CAD). Accurate segmentation of the lumen or plaque region is one of the most important factors. This study aimed to analyze the performance of the coronary artery segmentation of a software platform with a deep learning-based location-adaptive threshold method (DL-LATM) against commercially available software platforms using CCTA. The dataset from intravascular ultrasound (IVUS) of 26 vessel segments from 19 patients was used as the gold standard to evaluate the performance of each software platform. Statistical analyses (Pearson correlation coefficient [PCC], intraclass correlation coefficient [ICC], and Bland-Altman plot) were conducted for the lumen or plaque parameters by comparing the dataset of each software platform with IVUS. The software platform with DL-LATM showed the bias closest to zero for detecting lumen volume (mean difference = -9.1 mm3, 95% confidence interval [CI] = -18.6 to 0.4 mm3) or area (mean difference = -0.72 mm2, 95% CI = -0.80 to -0.64 mm2) with the highest PCC and ICC. Moreover, lumen or plaque area in the stenotic region was analyzed. The software platform with DL-LATM showed the bias closest to zero for detecting lumen (mean difference = -0.07 mm2, 95% CI = -0.16 to 0.02 mm2) or plaque area (mean difference = 1.70 mm2, 95% CI = 1.37 to 2.03 mm2) in the stenotic region with significantly higher correlation coefficient than other commercially available software platforms (p < 0.001). The result shows that the software platform with DL-LATM has the potential to serve as an aiding system for CAD evaluation.

A novel flood risk management approach based on future climate and land use change scenarios

Climate change and increasing urbanization are two primary factors responsible for the increased risk of serious flooding around the world. The prediction and monitoring of the effects of land use/land cover (LULC) and climate change on flood risk are critical steps in the development of appropriate strategies to reduce potential damage. This study aimed to develop a new approach by combining machine learning (namely the XGBoost, CatBoost, LightGBM, and ExtraTree models) and hydraulic modeling to predict the effects of climate change and LULC change on land that is at risk of flooding. For the years 2005, 2020, 2035, and 2050, machine learning was used to model and predict flood susceptibility under different scenarios of LULC, while hydraulic modeling was used to model and predict flood depth and flood velocity, based on the RCP 8.5 climate change scenario. The two elements were used to build a flood risk assessment, integrating socioeconomic data such as LULC, population density, poverty rate, number of women, number of schools, and cultivated area. Flood risk was then computed, using the analytical hierarchy process, by combining flood hazard, exposure, and vulnerability. The results showed that the area at high and very high flood risk increased rapidly, as did the areas of high/very high exposure, and high/very high vulnerability. They also showed how flood risk had increased rapidly from 2005 to 2020 and would continue to do so in 2035 and 2050, due to the dynamics of climate change and LULC change, population growth, the number of women, and the number of schools - particularly in the flood zone. The results highlight the relationships between flood risk and environmental and socio-economic changes and suggest that flood risk management strategies should also be integrated in future analyses. The map built in this study shows past and future flood risk, providing insights into the spatial distribution of urban area in flood zones and can be used to facilitate the development of priority measures, flood mitigation being most important.

Machine learning models for predicting the onset of chronic kidney disease after surgery in patients with renal cell carcinoma

BACKGROUND

Patients with renal cell carcinoma (RCC) have an elevated risk of chronic kidney disease (CKD) following nephrectomy. Therefore, continuous monitoring and subsequent interventions are necessary. It is recommended to evaluate renal function postoperatively. Therefore, a tool to predict CKD onset is essential for postoperative follow-up and management.

METHODS

We constructed a cohort using data from eight tertiary hospitals from the Korean Renal Cell Carcinoma (KORCC) database. A dataset of 4389 patients with RCC was constructed for analysis from the collected data. Nine machine learning (ML) models were used to classify the occurrence and nonoccurrence of CKD after surgery. The final model was selected based on the area under the receiver operating characteristic (AUROC), and the importance of the variables constituting the model was confirmed using the shapley additive explanation (SHAP) value and Kaplan-Meier survival analyses.

RESULTS

The gradient boost algorithm was the most effective among the various ML models tested. The gradient boost model demonstrated superior performance with an AUROC of 0.826. The SHAP value confirmed that preoperative eGFR, albumin level, and tumor size had a significant impact on the occurrence of CKD after surgery.

CONCLUSIONS

We developed a model to predict CKD onset after surgery in patients with RCC. This predictive model is a quantitative approach to evaluate post-surgical CKD risk in patients with RCC, facilitating improved prognosis through personalized postoperative care.

Improving the prediction of wildfire susceptibility on Hawai'i Island, Hawai'i, using explainable hybrid machine learning models

This study presents a comparative analysis of four Machine Learning (ML) models used to map wildfire susceptibility on Hawai'i Island, Hawai'i. Extreme Gradient Boosting (XGBoost) combined with three meta-heuristic algorithms - Whale Optimization (WOA), Black Widow Optimization (BWO), and Butterfly Optimization (BOA) - were employed to map areas susceptible to wildfire. To generate a wildfire inventory, 1408 wildfire points were identified within the study area from 2004 to 2022. The four ML models (XGBoost, WOA-XGBoost, BWO-XGBoost, and BOA-XGBoost) were run using 14 wildfire-conditioning factors categorized into four main groups: topographical, meteorological, vegetation, and anthropogenic. Six performance metrics - sensitivity, specificity, positive predictive values, negative predictive values, the Area Under the receiver operating characteristic Curve (AUC), and the average precision (AP) of Precision-Recall Curves (PRCs) - were used to compare the predictive performance of the ML models. The SHapley Additive exPlanations (SHAP) framework was also used to interpret the importance values of the 14 influential variables for the modeling of wildfire on Hawai'i Island using the four models. The results of the wildfire modeling indicated that all four models performed well, with the BWO-XGBoost model exhibiting a slightly higher prediction performance (AUC = 0.9269), followed by WOA-XGBoost (AUC = 0.9253), BOA-XGBoost (AUC = 0.9232), and XGBoost (AUC = 0.9164). SHAP analysis revealed that the distance from a road, annual temperature, and elevation were the most influential factors. The wildfire susceptibility maps generated in this study can be used by local authorities for wildfire management and fire suppression activity.

Anthropogenic impacts on urban blue space and its reciprocal effect on human and socio-ecological health

Quantifying anthropogenic impacts on blue space (BS) and its effect on human and socio-ecological health was least explored. The present study aimed to do this in reference to the urban BS transformation scenario of Eastern India. To measure BS transformation, Landsat image-based water indices were run from 1990 to 2021. Anthropogenic impact score (AIS) and 7 components scores of 78 selected BS on 70 parameters related data driven from the field. Total 345 respondents were taken for human and socio-ecological health assessment. For this, depression (DEP), anxiety (ANX), stress (STR), physical activities (PA), social capital (SC), therapeutic landscape (TL) and environment building (EB) parameters were taken. The result exhibited that BS was reduced. About 50% of urban core BS was reported highly impacted. Human and socio-ecological health was identified as good in proximity to BS, but it was observed better in the cases of larger peripheral BS. AIS on BS was found to be positively associated with mental health (0.47-0.63) and negatively associated with PA, SC, TL and EB (-0.50 to -0.90). Standard residual in ordinary least square was reported low (-1.5 to 1.5) in 95% BS. Therefore, BS health restoration and management is crucial for sustaining the living environment.

Enhancing Health Equity by Predicting Missed Appointments in Health Care: Machine Learning Study

BACKGROUND

The phenomenon of patients missing booked appointments without canceling them-known as Did Not Show (DNS), Did Not Attend (DNA), or Failed To Attend (FTA)-has a detrimental effect on patients' health and results in massive health care resource wastage.

OBJECTIVE

Our objective was to develop machine learning (ML) models and evaluate their performance in predicting the likelihood of DNS for hospital outpatient appointments at the MidCentral District Health Board (MDHB) in New Zealand.

METHODS

We sourced 5 years of MDHB outpatient records (a total of 1,080,566 outpatient visits) to build the ML prediction models. We developed 3 ML models using logistic regression, random forest, and Extreme Gradient Boosting (XGBoost). Subsequently, 10-fold cross-validation and hyperparameter tuning were deployed to minimize model bias and boost the algorithms' prediction strength. All models were evaluated against accuracy, sensitivity, specificity, and area under the receiver operating characteristic (AUROC) curve metrics.

RESULTS

Based on 5 years of MDHB data, the best prediction classifier was XGBoost, with an area under the curve (AUC) of 0.92, sensitivity of 0.83, and specificity of 0.85. The patients' DNS history, age, ethnicity, and appointment lead time significantly contributed to DNS prediction. An ML system trained on a large data set can produce useful levels of DNS prediction.

CONCLUSIONS

This research is one of the very first published studies that use ML technologies to assist with DNS management in New Zealand. It is a proof of concept and could be used to benchmark DNS predictions for the MDHB and other district health boards. We encourage conducting additional qualitative research to investigate the root cause of DNS issues and potential solutions. Addressing DNS using better strategies potentially can result in better utilization of health care resources and improve health equity.

Sequential virtual screening collaborated with machine-learning strategies for the discovery of precise medicine against non-small cell lung cancer

Dysregulation of MAPK pathway receptors are crucial in causing uncontrolled cell proliferation in many cancer types including non-small cell lung cancer. Due to the complications in targeting the upstream components, MEK is an appealing target to diminish this pathway activity. Hence, we have aimed to discover potent MEK inhibitors by integrating virtual screening and machine learning-based strategies. Preliminary screening was conducted on 11,808 compounds using the cavity-based pharmacophore model AADDRRR. Further, seven ML models were accessed to predict the MEK active compounds using six molecular representations. The LGB model with morgan2 fingerprints surpasses other models ensuing 0.92 accuracy and 0.83 MCC value versus test set and 0.85 accuracy and 0.70 MCC value with external set. Further, the binding ability of screened hits were examined using glide XP docking and prime-MM/GBSA calculations. Note that we have utilized three ML-based scoring functions to predict the various biological properties of the compounds. The two hit compounds such as DB06920 and DB08010 resulted excellent binding mechanism with acceptable toxicity properties against MEK. Further, 200 ns of MD simulation combined with MM-GBSA/PBSA calculations confirms that DB06920 may have stable binding conformations with MEK thus step forwarded to the experimental studies in the near future.Communicated by Ramaswamy H. Sarma.

Predictive modeling of consumer purchase behavior on social media: Integrating theory of planned behavior and machine learning for actionable insights

In recent times, it has been observed that social media exerts a favorable influence on consumer purchasing behavior. Many organizations are adopting the utilization of social media platforms as a means to promote products and services. Hence, it is crucial for enterprises to understand the consumer buying behavior in order to thrive. This article presents a novel approach that combines the theory of planned behavior (TPB) with machine learning techniques to develop accurate predictive models for consumer purchase behavior. This study examines three distinct factors of the theory of planned behavior (attitude, social norm, and perceived behavioral control) that provide insights into the primary determinants influencing online purchasing behavior. A total of eight machine learning algorithms, namely K-nearest neighbor, Decision Tree, Random Forest, Logistic Regression, Naive Bayes, Support Vector Machine, AdaBoost, and Gradient Boosting, were utilized in order to forecast consumer purchasing behavior. Empirical findings indicate that gradient boosting demonstrates superior performance in predicting customer buying behavior, with an accuracy rate of 0.91 and a macro F1 score of 0.91. This holds true when all factors, namely attitude (ATTD), social norm (SN), and perceived behavioral control (PBC), are included in the analysis. Furthermore, we incorporated Explainable AI (XAI), specifically LIME (Local Interpretable Model-Agnostic Explanations), to elucidate how the best machine learning model (i.e. gradient boosting) makes its prediction. The findings indicate that LIME has demonstrated a high level of confidence in accurately predicting the influence of low and high behavior. The outcome presented in this article has several implications. For instance, this article presents a novel way to combine the theory of planned behavior with machine learning techniques in order to predict consumer purchase behavior. This integration allows for a comprehensive analysis of factors influencing online purchasing decisions. Also, the incorporation of Explainable AI enhances the transparency and interpretability of the model. This feature is valuable for organizations seeking insights into factors driving predictions and the reasons behind certain outcomes. Moreover, these observations have the potential to offer valuable insights for businesses in customizing their marketing strategies to align with these influential factors.

Accurate Prediction of Soil Heavy Metal Pollution Using an Improved Machine Learning Method: A Case Study in the Pearl River Delta, China

In traditional soil heavy metal (HM) pollution assessment, spatial interpolation analysis is often carried out on the limited sampling points in the study area to get the overall status of heavy metal pollution. Unfortunately, in many machine learning spatial information enhancement algorithms, the additional spatial information introduced fails to reflect the hierarchical heterogeneity of the study area. Therefore, we designed hierarchical regionalization labels based on three interpolation techniques (inverse distance weight, ordinary kriging, and trend surface interpolation) as new spatial covariates for a machine learning (ML) model. It was demonstrated that regional spatial information improved the prediction performance of the model (R2 > 0.7). On the basis of the prediction results, the status of HM pollution in the Pearl River Delta (PRD) region was evaluated: cadmium (Cd) and copper (Cu) were the most serious pollutants in the PRD (the point overstandard rates are 18.77% and 12.95%, respectively). The analysis of index importance and bivariate local indicators of spatial association (LISA) shows that the key factors affecting the spatial distribution of heavy metals are geographical and climatic conditions [namely, altitude, humidity index, and normalized vegetation difference index (NDVI)] and some industrial activities (such as metal processing, printing and dyeing, and electronics industry). This study develops a novel approach to improve existing spatial interpolation techniques, which will enable more precise and scientific soil environmental management.

Predicting drug shortages using pharmacy data and machine learning

Drug shortages are a global and complex issue having negative impacts on patients, pharmacists, and the broader health care system. Using sales data from 22 Canadian pharmacies and historical drug shortage data, we built machine learning models predicting shortages for the majority of the drugs in the most-dispensed interchangeable groups in Canada. When breaking drug shortages into four classes (none, low, medium, high), we were able to correctly predict the shortage class with 69% accuracy and a kappa value of 0.44, one month in advance, without access to any inventory data from drug manufacturers and suppliers. We also predicted 59% of the shortages deemed to be most impactful (given the demand for the drugs and the potential lack of interchangeable options). The models consider many variables, including the average days of a drug supply per patient, the total days of a drug supply, previous shortages, and the hierarchy of drugs within different drug groups and therapeutic classes. Once in production, the models will allow pharmacists to optimize their orders and inventories, and ultimately reduce the impact of drug shortages on their patients and operations.

Ensemble-Learning and Feature Selection Techniques for Enhanced Antisense Oligonucleotide Efficacy Prediction in Exon Skipping

Antisense oligonucleotide (ASO)-mediated exon skipping has become a valuable tool for investigating gene function and developing gene therapy. Machine-learning-based computational methods, such as eSkip-Finder, have been developed to predict the efficacy of ASOs via exon skipping. However, these methods are computationally demanding, and the accuracy of predictions remains suboptimal. In this study, we propose a new approach to reduce the computational burden and improve the prediction performance by using feature selection within machine-learning algorithms and ensemble-learning techniques. We evaluated our approach using a dataset of experimentally validated exon-skipping events, dividing it into training and testing sets. Our results demonstrate that using a three-way-voting approach with random forest, gradient boosting, and XGBoost can significantly reduce the computation time to under ten seconds while improving prediction performance, as measured by R² for both 2'-O-methyl nucleotides (2OMe) and phosphorodiamidate morpholino oligomers (PMOs). Additionally, the feature importance ranking derived from our approach is in good agreement with previously published results. Our findings suggest that our approach has the potential to enhance the accuracy and efficiency of predicting ASO efficacy via exon skipping. It could also facilitate the development of novel therapeutic strategies. This study could contribute to the ongoing efforts to improve ASO design and optimize gene therapy approaches.

Soil salinity prediction using hybrid machine learning and remote sensing in Ben Tre province on Vietnam's Mekong River Delta

Soil salinization is considered one of the disasters that have significant effects on agricultural activities in many parts of the world, particularly in the context of climate change and sea level rise. This problem has become increasingly essential and severe in the Mekong River Delta of Vietnam. Therefore, soil salinity monitoring and assessment are critical to building appropriate strategies to develop agricultural activities. This study aims to develop a low-cost method based on machine learning and remote sensing to map soil salinity in Ben Tre province, which is located in Vietnam's Mekong River Delta. This objective was achieved by using six machine learning algorithms, including Xgboost (XGR), sparrow search algorithm (SSA), bird swarm algorithm (BSA), moth search algorithm (MSA), Harris hawk optimization (HHO), grasshopper optimization algorithm (GOA), particle swarm optimization algorithm (PSO), and 43 factors extracted from remote sensing images. Various indices were used, namely, root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R²) to estimate the efficiency of the prediction models. The results show that six optimization algorithms successfully improved XGR model performance with an R² value of more than 0.98. Among the proposed models, the XGR-HHO model was better than the other models with a value of R² of 0.99 and a value of RMSE of 0.051, by XGR-GOA (R² = 0.931, RMSE = 0.055), XGR-MSA (R² = 0.928, RMSE = 0.06), XGR-BSA (R² = 0.926, RMSE = 0.062), XGR-SSA (R² = 0.917, 0.07), XGR-PSO (R² = 0.916, RMSE = 0.08), XGR (R² = 0.867, RMSE = 0.1), CatBoost (R² = 0.78, RMSE = 0.12), and RF (R² = 0.75, RMSE = 0.19), respectively. These proposed models have surpassed the reference models (CatBoost and random forest). The results indicated that the soils in the eastern areas of Ben Tre province are more saline than in the western areas. The results of this study highlighted the effectiveness of using hybrid machine learning and remote sensing in soil salinity monitoring. The finding of this study provides essential tools to support farmers and policymakers in selecting appropriate crop types in the context of climate change to ensure food security.

Assessment of data intelligence algorithms in modeling daily reference evapotranspiration under input data limitation scenarios in semi-arid climatic condition

Crop evapotranspiration is essential for planning and designing an efficient irrigation system. The present investigation assessed the capability of four machine learning algorithms, namely, XGBoost linear regression (XGBoost Linear), XGBoost Ensemble Tree, Polynomial Regression (Polynomial Regr), and Isotonic Regression (Isotonic Regr) in modeling daily reference evapotranspiration (ET_o) at IARI, New Delhi. The models were developed considering full and limited dataset scenarios. The efficacy of the constructed models was assessed against the Penman-Monteith (PM56) model estimated daily ET_o. Results revealed the under full and limited dataset conditions, XGBoost Ensemble Tree gave the best results for daily ET_o modeling during the model training period, while in the testing period under scenarios S1(T_max) and S2 (T_max, and T_min), the Isotonic Regr models yielded superior results over other models. In addition, the XGBoost Ensemble Tree models outperformed others for the rest of the input data scenarios. The XGBoost Ensemble Tree algorithms reported the best values of correlation coefficient (r), mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Thus, we recommend applying the XGBoost Ensemble Tree algorithm for precisely modeling daily ET_o in semi-arid climatic conditions.

Estimate earth fissure hazard based on machine learning in the Qa' Jahran Basin, Yemen

Earth fissures are potential hazards that often cause severe damage and affect infrastructure, the environment, and socio-economic development. Owing to the complexity of the causes of earth fissures, the prediction of earth fissures remains a challenging task. In this study, we assess earth fissure hazard susceptibility mapping through four advanced machine learning algorithms, namely random forest (RF), extreme gradient boosting (XGBoost), Naïve Bayes (NB), and K-nearest neighbor (KNN). Using Qa' Jahran Basin in Yemen as a case study area, 152 fissure locations were recorded via a field survey for the creation of an earth fissure inventory and 11 earth fissure conditioning factors, comprising of topographical, hydrological, geological, and environmental factors, were obtained from various data sources. The outputs of the models were compared and analyzed using statistical indices such as the confusion matrix, overall accuracy, and area under the receiver operating characteristics (AUROC) curve. The obtained results revealed that the RF algorithm, with an overall accuracy of 95.65% and AUROC, 0.99 showed excellent performance for generating hazard maps, followed by XGBoost, with an overall accuracy of 92.39% and AUROC of 0.98, the NB model, with overall accuracy, 88.43% and AUROC, 0.96, and KNN model with general accuracy, 80.43% and AUROC, 0.88), respectively. Such findings can assist land management planners, local authorities, and decision-makers in managing the present and future earth fissures to protect society and the ecosystem and implement suitable protection measures.

Utilization of frequency ratio method for the production of landslide susceptibility maps: Karaburun Peninsula case, Turkey

Geographical information systems (GIS) facilitate both current landslide mapping processes and the prediction of potential landslides that may be experienced in the future. Within the scope of the study, landslide susceptibility maps were created to reduce the damage of possible landslides in the Karaburun Peninsula of İzmir province. A landslide inventory map was produced from related databases in the first place, followed by the creation of parameter maps (elevation, aspect, slope, curvature, land use, vegetation cover, lithology, distance to roads, distance to rivers, and distance to fault lines). The frequency ratio (FR) method was utilized for producing the landslide susceptibility maps on a 5-level risk scale ranging from very low to very high-risk categories. Receiver operating characteristic (ROC) analysis was performed for accuracy testing. The resulting landslide susceptibility map revealed that 3% and 46% of the study area had high- and medium-risk categories, and the low landslide risk areas comprised 47% of the region. These results provide important inputs to guide sustainable strategic and physical planning processes in the region, which has been declared a special protection area and is a popular destination for tourism activities and energy facilities.

Identifying sensitivity of factor cluster based gully erosion susceptibility models

The present study has attempted to address the issue of sensitivity of different clusters of factors towards gully erosion in the Mayurakshi river basin. Firstly, the gully erosion susceptibility of the basin area has been mapped by integrating using 18 parameters divided into four factor-cluster, viz. erodibility, erosivity, resistance, and topographical cluster, with the help of four machine learning (ML) models such as random forest (RF), gradient boost (GBM), extreme gradient boost (XGB), and support vector machine (SVM). Results show that almost 20% and 25% of the upper catchment of the basin belongs to extreme and high gully erosion susceptibility. Among the applied algorithms, RF is appeared as the best performing model. The spatial association of factor cluster-based models with the final susceptibility model is found the highest for the erosivity cluster, followed by the erodibility cluster. From the sensitivity analysis, it becomes clear that geology and soil texture are dominant contributing factors to gully erosion susceptibility. The geological formation of unclassified granite gneiss and geomorphological formation of denudational origin pediment-pediplain complex is dominant over the entire upper catchment of the basin, and therefore, can be considered regional factors of importance. Since the study has figured out the different grades of susceptible areas with dominant factors and factor cluster, it would be useful for devising planning for gully erosion check measures. From economic particularly food security purpose, it is very essential since it is concerned with precious soil loss and negative effects on agriculture.

Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Natural disasters always have a damaging effect on our way of life. Landslides  cause serious damage to both human and natural resources around the world. In this paper, the prediction accuracy of five hybrid models for landslide occurrence in the Uttarkashi, Uttarakhand (India) was evaluated and compared. In this approach, the Rough Set theory coupled with five different models namely Bayesian Network (HBNRS), Backpropagation Neural Network (HBPNNRS), Bagging (HBRS), XGBoost (HXGBRS), and Random Forest (HRFRS) were taken into account. The database for the models development was prepared using fifteen conditioning factors that had 373 landslide and 181 non-landslide locations that were then randomly divided into training and testing locations with a ratio of 75%:25%. The appropriateness and predictability of these conditioning factors were assessed using the multi-collinearity test and the least absolute shrinkage and selection operator approach. The accuracy, sensitivity, specificity, precision, and F-Measures, and the area under the curve (AUC)-receiver operating characteristics curve, were used to evaluate and compare the performance of the individual and hybrid created models. The findings indicate that the constructed hybrid model HXGBRS (AUC = 0.937, Precision = 0.946, F1-score = 0.926 and Accuracy = 89.92%) is the most accurate model for predicting landslides when compared to other models (HBPNNRS, HBNRS, HBRS, and HRFRS). Importantly, when the fusion is performed with the rough set method, the prediction capability of each model is improved. Simultaneously, the HXGBRS model proposed shows superior stability and can effectively avoid overfitting. After the core modules were developed, the user-friendly platform was designed as an integrated GIS environment using dynamic maps for effective landslide prediction in large prone areas. Users can predict the probability of landslide occurrence for selected region by changing the values of a conditioning factors. The created approach could be beneficial for predicting the impact of landslides on slopes and tracking landslides along national routes.

Predictive Modeling for the Diagnosis of Gestational Diabetes Mellitus Using Epidemiological Data in the United Arab Emirates

Gestational diabetes mellitus (GDM) is a common condition with repercussions for both the mother and her child. Machine learning (ML) modeling techniques were proposed to predict the risk of several medical outcomes. A systematic evaluation of the predictive capacity of maternal factors resulting in GDM in the UAE is warranted. Data on a total of 3858 women who gave birth and had information on their GDM status in a birth cohort were used to fit the GDM risk prediction model. Information used for the predictive modeling were from self-reported epidemiological data collected at early gestation. Three different ML models, random forest (RF), gradient boosting model (GBM), and extreme gradient boosting (XGBoost), were used to predict GDM. Furthermore, to provide local interpretation of each feature in GDM diagnosis, features were studied using Shapley additive explanations (SHAP). Results obtained using ML models show that XGBoost, which achieved an AUC of 0.77, performed better compared to RF and GBM. Individual feature importance using SHAP value and the XGBoost model show that previous GDM diagnosis, maternal age, body mass index, and gravidity play a vital role in GDM diagnosis. ML models using self-reported epidemiological data are useful and feasible in prediction models for GDM diagnosis amongst pregnant women. Such data should be periodically collected at early pregnancy for health professionals to intervene at earlier stages to prevent adverse outcomes in pregnancy and delivery. The XGBoost algorithm was the optimal model for identifying the features that predict GDM diagnosis.

Machine learning-based prediction model for late recurrence after surgery in patients with renal cell carcinoma

Background

Renal cell carcinoma is characterized by a late recurrence that occurs 5 years after surgery; hence, continuous monitoring and follow-up is necessary. Prognosis of late recurrence of renal cell carcinoma can only be improved if it is detected early and treated appropriately. Therefore, tools for rapid and accurate renal cell carcinoma prediction are essential.

Methods

This study aimed to develop a prediction model for late recurrence after surgery in patients with renal cell carcinoma that can be used as a clinical decision support system for the early detection of late recurrence. We used the KOrean Renal Cell Carcinoma database that contains large-scale cohort data of patients with renal cell carcinoma in Korea. From the collected data, we constructed a dataset of 2956 patients for the analysis. Late recurrence and non-recurrence were classified by applying eight machine learning models, and model performance was evaluated using the area under the receiver operating characteristic curve.

Results

Of the eight models, the AdaBoost model showed the highest performance. The developed algorithm showed a sensitivity of 0.673, specificity of 0.807, accuracy of 0.799, area under the receiver operating characteristic curve of 0.740, and F1-score of 0.609.

Conclusions

To the best of our knowledge, we developed the first algorithm to predict the probability of a late recurrence 5 years after surgery. This algorithm may be used by clinicians to identify patients at high risk of late recurrence that require long-term follow-up and to establish patient-specific treatment strategies.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01964-w.

Cardiovascular Disease Detection using Ensemble Learning

One of the most challenging tasks for clinicians is detecting symptoms of cardiovascular disease as earlier as possible. Many individuals worldwide die each year from cardiovascular disease. Since heart disease is a major concern, it must be dealt with timely. Multiple variables affecting health, such as excessive blood pressure, elevated cholesterol, an irregular pulse rate, and many more, make it challenging to diagnose cardiac disease. Thus, artificial intelligence can be useful in identifying and treating diseases early on. This paper proposes an ensemble-based approach that uses machine learning (ML) and deep learning (DL) models to predict a person’s likelihood of developing cardiovascular disease. We employ six classification algorithms to predict cardiovascular disease. Models are trained using a publicly available dataset of cardiovascular disease cases. We use random forest (RF) to extract important cardiovascular disease features. The experiment results demonstrate that the ML ensemble model achieves the best disease prediction accuracy of 88.70%.

A Machine Learning Approach for Predicting Readmission Charges Billed by Hospitals

Background

The Centers for Medicare and Medicaid Services projects that health care costs will continue to grow over the next few years. Rising readmission costs contribute significantly to increasing health care costs. Multiple areas of health care, including readmissions, have benefited from the application of various machine learning algorithms in several ways.

Objective

We aimed to identify suitable models for predicting readmission charges billed by hospitals. Our literature review revealed that this application of machine learning is underexplored. We used various predictive methods, ranging from glass-box models (such as regularization techniques) to black-box models (such as deep learning–based models).

Methods

We defined readmissions as readmission with the same major diagnostic category (RSDC) and all-cause readmission category (RADC). For these readmission categories, 576,701 and 1,091,580 individuals, respectively, were identified from the Nationwide Readmission Database of the Healthcare Cost and Utilization Project by the Agency for Healthcare Research and Quality for 2013. Linear regression, lasso regression, elastic net, ridge regression, eXtreme gradient boosting (XGBoost), and a deep learning model based on multilayer perceptron (MLP) were the 6 machine learning algorithms we tested for RSDC and RADC through 10-fold cross-validation.

Results

Our preliminary analysis using a data-driven approach revealed that within RADC, the subsequent readmission charge billed per patient was higher than the previous charge for 541,090 individuals, and this number was 319,233 for RSDC. The top 3 major diagnostic categories (MDCs) for such instances were the same for RADC and RSDC. The average readmission charge billed was higher than the previous charge for 21 of the MDCs in the case of RSDC, whereas it was only for 13 of the MDCs in RADC. We recommend XGBoost and the deep learning model based on MLP for predicting readmission charges. The following performance metrics were obtained for XGBoost: (1) RADC (mean absolute percentage error [MAPE]=3.121%; root mean squared error [RMSE]=0.414; mean absolute error [MAE]=0.317; root relative squared error [RRSE]=0.410; relative absolute error [RAE]=0.399; normalized RMSE [NRMSE]=0.040; mean absolute deviation [MAD]=0.031) and (2) RSDC (MAPE=3.171%; RMSE=0.421; MAE=0.321; RRSE=0.407; RAE=0.393; NRMSE=0.041; MAD=0.031). The performance obtained for MLP-based deep neural networks are as follows: (1) RADC (MAPE=3.103%; RMSE=0.413; MAE=0.316; RRSE=0.410; RAE=0.397; NRMSE=0.040; MAD=0.031) and (2) RSDC (MAPE=3.202%; RMSE=0.427; MAE=0.326; RRSE=0.413; RAE=0.399; NRMSE=0.041; MAD=0.032). Repeated measures ANOVA revealed that the mean RMSE differed significantly across models with P<.001. Post hoc tests using the Bonferroni correction method indicated that the mean RMSE of the deep learning/XGBoost models was statistically significantly (P<.001) lower than that of all other models, namely linear regression/elastic net/lasso/ridge regression.

Conclusions

Models built using XGBoost and MLP are suitable for predicting readmission charges billed by hospitals. The MDCs allow models to accurately predict hospital readmission charges.

Highway Proneness Appraisal to Landslides along Taiping to Ipoh Segment Malaysia, Using MCDM and GIS Techniques

Landslides are geological hazards that claim lives and affect socio-economic growth. Despite increased slope failure, some constructions, such as road constructions, are still being performed without proper investigation of the susceptibility of slope mass movement. This study researches the susceptibility of landslides in a study area encompassing a major highway that extends from Taiping to Ipoh, Malaysia. After a comprehensive literature review, 10 landslide conditioning factors were considered for this study. As novel research in this study area, multi-criteria decision-making (MCDM) models such as AHP and fuzzy AHP were used to rank the conditioning factors before generating the final landslide susceptibility mapping using Geographical Information System (GIS) software. The landslide susceptibility map has five classes ranging from very low (9.20%) and (32.97%), low (18.09%) and (25.60%), moderate (24.46%) and (21.36%), high (27.57%) and (13.26%), to very high (20.68%) and (6.81%) susceptibility for the FAHP and AHP models, respectively. It was recorded that the area is mainly covered with moderate to very high landslide risk, which requires proper intervention, especially for subsequent construction or renovation processes. The highway was overlayed on the susceptibility map, which concludes that the highway was constructed on a terrain susceptible to slope instability. Therefore, decision-makers should consider further investigation and landslide susceptibility mapping before construction.

Landslide Susceptibility Mapping of Landslides with Artificial Neural Networks: Multi-Approach Analysis of aBackpropagation Algorithm Applying the Neuralnet Package in Cuenca, Ecuador

Natural hazards generate disasters and huge losses in several aspects, with landslides being one of the natural risks that have caused great impacts worldwide. The aim of this research was to explore a method based on machine learning to evaluate susceptibility to rotational landslides in an area near Cuenca city, Ecuador, which has a high incidence of these phenomena, mainly due to its environmental conditions, and in which, however, such studies are scarce. The implemented method consisted of an artificial neural network multilayer perceptron (ANN MLP), generated with the neuralnet R package, with which, by means of different backpropagation algorithms (RPROP+, RPROP−, SLR, SAG, and Backprop), five landslide susceptibility maps (LSMs) were generated for the study area. A landslide inventory updated to 2019 and 10 conditioning factors, mainly topographical, geological, land cover, and hydrological, were considered. The results obtained, which were validated through the AUC-ROC value and statistical parameters of precision, recall, accuracy, and F-Score, showed a good degree of adjustment and an acceptable predictive capacity. The resulting maps showed that the area has mostly sectors of moderate, high, and very high susceptibility, whose landslide occurrence percentages vary between approximately 63% and 80%. In this research, different variants of the backpropagation algorithm were implemented to verify which one gave the best results. With the implementation of additional methodologies and correct zoning, future analyses could be developed, contributing to adequate territorial planning and better disaster risk management in the area.

Designing grazing susceptibility to land degradation index (GSLDI) in hilly areas

Evaluation of grazing impacts on land degradation processes is a difficult task due to the heterogeneity and complex interacting factors involved. In this paper, we designed a new methodology based on a predictive index of grazing susceptibility to land degradation index (GSLDI) built on artificial intelligence to assess land degradation susceptibility in areas affected by small ruminants (SRs) of sheep and goats grazing. The data for model training, validation, and testing consisted of sampling points (erosion and no-erosion) taken from aerial imagery. Seventeen environmental factors (e.g., derivatives of the digital elevation model, small ruminants' stock), and 55 subsequent attributes (e.g., classes/features) were assigned to each sampling point. The impact of SRs stock density on the land degradation process has been evaluated and estimated with two extreme SRs' density scenarios: absence (no stock), and double density (overstocking). We applied the GSLDI methodology to the Curvature Subcarpathians, a region that experiences the highest erosion rates in Romania, and found that SRs grazing is not the major contributor to land degradation, accounting for only 4.6%. This methodology could be replicated in other steep slope grazing areas as a tool to assess and predict susceptible to land degradation, and to establish common strategies for sustainable land-use practices.

A Prehospital Triage System to Detect Traumatic Intracranial Hemorrhage Using Machine Learning Algorithms

IMPORTANCE

An adequate system for triaging patients with head trauma in prehospital settings and choosing optimal medical institutions is essential for improving the prognosis of these patients. To our knowledge, there has been no established way to stratify these patients based on their head trauma severity that can be used by ambulance crews at an injury site.

OBJECTIVES

To develop a prehospital triage system to stratify patients with head trauma according to trauma severity by using several machine learning techniques and to evaluate the predictive accuracy of these techniques.

DESIGN, SETTING, AND PARTICIPANTS

This single-center retrospective cohort study was conducted by reviewing the electronic medical records of consecutive patients who were transported to Tokyo Medical and Dental University Hospital in Japan from April 1, 2018, to March 31, 2021. Patients younger than 16 years with cardiopulmonary arrest on arrival or with a significant amount of missing data were excluded.

MAIN OUTCOMES AND MEASURES

Machine learning-based prediction models to detect the presence of traumatic intracranial hemorrhage were constructed. The predictive accuracy of the models was evaluated with the area under the receiver operating curve (ROC-AUC), area under the precision recall curve (PR-AUC), sensitivity, specificity, and other representative statistics.

RESULTS

A total of 2123 patients (1527 male patients [71.9%]; mean [SD] age, 57.6 [19.8] years) with head trauma were enrolled in this study. Traumatic intracranial hemorrhage was detected in 258 patients (12.2%). Among several machine learning algorithms, extreme gradient boosting (XGBoost) achieved the mean (SD) highest ROC-AUC (0.78 [0.02]) and PR-AUC (0.46 [0.01]) in cross-validation studies. In the testing set, the ROC-AUC was 0.80, the sensitivity was 74.0% (95% CI, 59.7%-85.4%), and the specificity was 74.9% (95% CI, 70.2%-79.3%). The prediction model using the National Institute for Health and Care Excellence (NICE) guidelines, which was calculated after consultation with physicians, had a sensitivity of 72.0% (95% CI, 57.5%-83.8%) and a specificity of 73.3% (95% CI, 68.7%-77.7%). The McNemar test revealed no statistically significant differences between the XGBoost algorithm and the NICE guidelines for sensitivity or specificity (P = .80 and P = .55, respectively).

CONCLUSIONS AND RELEVANCE

In this cohort study, the prediction model achieved a comparatively accurate performance in detecting traumatic intracranial hemorrhage using only the simple pretransportation information from the patient. Further validation with a prospective multicenter data set is needed.

A Comparative Assessment of Machine Learning Models for Landslide Susceptibility Mapping in the Rugged Terrain of Northern Pakistan

This study investigated the performances of different techniques, including random forest (RF), support vector machine (SVM), maximum entropy (maxENT), gradient-boosting machine (GBM), and logistic regression (LR), for landslide susceptibility mapping (LSM) in the rugged terrain of northern Pakistan. Initially, a landslide inventory of 200 samples was produced along with an additional 200 samples indicating nonlandslide areas and divided into training (70%) and validation (30%) groups using a stratified loop-based random sampling approach. Then, a geospatial database of 12 possible landslide influencing factors (LIFs) was generated, including elevation, slope, aspect, topographic wetness index (TWI), topographic position index (TPI), distance to drainage, distance to fault, distance to road, normalized difference vegetation index (NDVI), rainfall, land cover/land use (LCLU), and a geological map of the study area. None of the LIFs were redundant for the modeling, as indicated by the multicollinearity test (tolerance > 0.1) and information gain ratio (IGR > 0). We extended the evaluation measures of each algorithm from area-under-the-curve (AUC) analysis to the calculation of performance overall (POA) with the help of precision, recall, F1 score, accuracy (ACC), and Matthew’s correlation coefficient (MCC). The results showed that the SVM was the most promising model (AUC = 0.969, POA = 2669) for the LSM, followed by RF (AUC = 0.967, POA = 2656), GBM (AUC = 0.967, POA = 2623), maxENT (AUC = 0.872, POA = 1761), and LR (AUC = 0.836, POA = 1299). It is important to note that the SVM, RF, and GBM were the top performers, with almost similar accuracy. Thus, each of these could be equally effective for LSM and can be used for risk reduction and mitigation measures in the rugged terrain of Pakistan and other regions with similar topography.

EEG-Driven Prediction Model of Oxcarbazepine Treatment Outcomes in Patients With Newly-Diagnosed Focal Epilepsy

Objective: Antiseizure medicine (ASM) is the first choice for patients with epilepsy. The choice of ASM is determined by the type of epilepsy or epileptic syndrome, which may not be suitable for certain patients. This initial choice of a particular drug affects the long-term prognosis of patients, so it is critical to select the appropriate ASMs based on the individual characteristics of a patient at the early stage of the disease. The purpose of this study is to develop a personalized prediction model to predict the probability of achieving seizure control in patients with focal epilepsy, which will help in providing a more precise initial medication to patients.

Methods: Based on response to oxcarbazepine (OXC), enrolled patients were divided into two groups: seizure-free (52 patients), not seizure-free (NSF) (22 patients). We created models to predict patients' response to OXC monotherapy by combining Electroencephalogram (EEG) complexities and 15 clinical features. The prediction models were gradient boosting decision tree-Kolmogorov complexity (GBDT-KC) and gradient boosting decision tree-Lempel-Ziv complexity (GBDT-LZC). We also constructed two additional prediction models, support vector machine-Kolmogorov complexity (SVM-KC) and SVM-LZC, and these two models were compared with the GBDT models. The performance of the models was evaluated by calculating the accuracy, precision, recall, F1-score, sensitivity, specificity, and area under the curve (AUC) of these models.

Results: The mean accuracy, precision, recall, F1-score, sensitivity, specificity, AUC of GBDT-LZC model after five-fold cross-validation were 81%, 84%, 91%, 87%, 91%, 64%, 81%, respectively. The average accuracy, precision, recall, F1-score, sensitivity, specificity, AUC of GBDT-KC model with five-fold cross-validation were 82%, 84%, 92%, 88%, 83%, 92%, 83%, respectively. We used the rank of absolute weights to separately calculate the features that have the most significant impact on the classification of the two models.

Conclusion: (1) The GBDT-KC model has the potential to be used in the clinic to predict seizure-free with OXC monotherapy. (2). Electroencephalogram complexity, especially Kolmogorov complexity (KC) may be a potential biomarker in predicting the treatment efficacy of OXC in newly diagnosed patients with focal epilepsy.

Predicting Heavy Metal Adsorption on Soil with Machine Learning and Mapping Global Distribution of Soil Adsorption Capacities

Studying heavy metal adsorption on soil is important for understanding the fate of heavy metals and properly assessing the related environmental risks. Existing experimental methods and traditional models for quantifying adsorption, however, are time-consuming and ineffective. In this study, we developed machine learning models for the soil adsorption of six heavy metals (Cd(II), Cr(VI), Cu(II), Pb(II), Ni(II), and Zn(II)) using 4420 data points (1105 soils) extracted from 150 journal articles. After a comprehensive comparison, our results showed that the gradient boosting decision tree had the best performance for a combined model based on all the data. The Shapley additive explanation method was used to identify the feature importance and the effects of these features on the adsorption, based on which six independent models were developed for the six metals to achieve better model performance than the combined model. Using these independent models, the global distribution of heavy metal adsorption capacities on soils was predicted with known soil properties. Reversed models, including one combined model for all the six metals and six independent models, were also built using the same data sets to predict the heavy metal concentration in water when the adsorbed amount is known for a soil/sediment.

Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models

Gully erosion is the most severe type of water erosion and is a major land degradation process. Gully erosion susceptibility mapping (GESM)’s efficiency and interpretability remains a challenge, especially in complex terrain areas. In this study, a WoE-MLC model was used to solve the above problem, which combines machine learning classification algorithms and the statistical weight of evidence (WoE) model in the Loess Plateau. The three machine learning (ML) algorithms utilized in this research were random forest (RF), gradient boosted decision trees (GBDT), and extreme gradient boosting (XGBoost). The results showed that: (1) GESM were well predicted by combining both machine learning regression models and WoE-MLC models, with the area under the curve (AUC) values both greater than 0.92, and the latter was more computationally efficient and interpretable; (2) The XGBoost algorithm was more efficient in GESM than the other two algorithms, with the strongest generalization ability and best performance in avoiding overfitting (averaged AUC = 0.947), followed by the RF algorithm (averaged AUC = 0.944), and GBDT algorithm (averaged AUC = 0.938); and (3) slope gradient, land use, and altitude were the main factors for GESM. This study may provide a possible method for gully erosion susceptibility mapping at large scale.

The accuracy versus interpretability trade-off in fraud detection model

Like a hydra, fraudsters adapt and circumvent increasingly sophisticated barriers erected by public or private institutions. Among these institutions, banks must quickly take measures to avoid losses while guaranteeing the satisfaction of law-abiding customers. Facing an expanding flow of operations, effective banking relies on data analytics to support established risk control processes, but also on a better understanding of the underlying fraud mechanism. In addition, fraud being a criminal offence, the evidential aspect of the process must also be considered. These legal, operational, and strategic constraints lead to compromises on the means to be implemented for fraud management. This paper first focuses on the translation of practical questions raised in the banking industry at each step of the fraud management process into performance evaluation required to design a fraud detection model. Secondly, it considers a range of machine learning approaches that address these specificities: the imbalance between fraudulent and nonfraudulent operations, the lack of fully trusted labels, the concept-drift phenomenon, and the unavoidable trade-off between accuracy and interpretability of detection. This state-of-the-art review sheds some light on a technology race between black box machine learning models improved by post-hoc interpretation and intrinsic interpretable models boosted to gain accuracy. Finally, it discusses how concrete and promising hybrid approaches can provide pragmatic, short-term answers to banks and policy makers without swallowing up stakeholders with economical and ethical stakes in this technological race.

The Predictive Capability of a Novel Ensemble Tree-Based Algorithm for Assessing Groundwater Potential

Understanding the potential groundwater resource distribution is critical for sustainable groundwater development, conservation, and management strategies. This study analyzes and maps the groundwater potential in Busan Metropolitan City, South Korea, using random forest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGB) methods. Fourteen groundwater conditioning factors were evaluated for their contribution to groundwater potential assessment using an elastic net. Curvature, the stream power index, the distance from drainage, lineament density, and fault density were excluded from the subsequent analysis, while nine other factors were used to create groundwater potential maps (GMPs) using the RF, GBM, and XGB models. The accuracy of the resultant GPMs was tested using receiver operating characteristic curves and the seed cell area index, and the results were compared. The analysis showed that the three models used in this study satisfactorily predicted the spatial distribution of groundwater in the study area. In particular, the XGB model showed the highest prediction accuracy (0.818), followed by the GBM (0.802) and the RF models (0.794). The XGB model, which is the most recently developed technique, was found to best contribute to improving the accuracy of the GPMs. These results contribute to the establishment of a sustainable management plan for groundwater resources in the study area.

BOW-GBDT: A GBDT Classifier Combining With Artificial Neural Network for Identifying GPCR-Drug Interaction Based on Wordbook Learning From Sequences

Background: As a class of membrane protein receptors, G protein-coupled receptors (GPCRs) are very important for cells to complete normal life function and have been proven to be a major drug target for widespread clinical application. Hence, it is of great significance to find GPCR targets that interact with drugs in the process of drug development. However, identifying the interaction of the GPCR–drug pairs by experimental methods is very expensive and time-consuming on a large scale. As more and more database about GPCR–drug pairs are opened, it is viable to develop machine learning models to accurately predict whether there is an interaction existing in a GPCR–drug pair.

Methods: In this paper, the proposed model aims to improve the accuracy of predicting the interactions of GPCR–drug pairs. For GPCRs, the work extracts protein sequence features based on a novel bag-of-words (BOW) model improved with weighted Silhouette Coefficient and has been confirmed that it can extract more pattern information and limit the dimension of feature. For drug molecules, discrete wavelet transform (DWT) is used to extract features from the original molecular fingerprints. Subsequently, the above-mentioned two types of features are contacted, and SMOTE algorithm is selected to balance the training dataset. Then, artificial neural network is used to extract features further. Finally, a gradient boosting decision tree (GBDT) model is trained with the selected features. In this paper, the proposed model is named as BOW-GBDT.

Results: D92M and Check390 are selected for testing BOW-GBDT. D92M is used for a cross-validation dataset which contains 635 interactive GPCR–drug pairs and 1,225 non-interactive pairs. Check390 is used for an independent test dataset which consists of 130 interactive GPCR–drug pairs and 260 non-interactive GPCR–drug pairs, and each element in Check390 cannot be found in D92M. According to the results, the proposed model has a better performance in generation ability compared with the existing machine learning models.

Conclusion: The proposed predictor improves the accuracy of the interactions of GPCR–drug pairs. In order to facilitate more researchers to use the BOW-GBDT, the predictor has been settled into a brand-new server, which is available at http://www.jci-bioinfo.cn/bowgbdt.

Risk Assessment of Resources Exposed to Rainfall Induced Landslide with the Development of GIS and RS Based Ensemble Metaheuristic Machine Learning Algorithms

Disastrous natural hazards, such as landslides, floods, and forest fires cause a serious threat to natural resources, assets and human lives. Consequently, landslide risk assessment has become requisite for managing the resources in future. This study was designed to develop four ensemble metaheuristic machine learning algorithms, such as grey wolf optimized based artificial neural network (GW-ANN), grey wolf optimized based random forest (GW-RF), particle swarm optimization optimized based ANN (PSO-ANN), and PSO optimized based RF for modeling rainfall-induced landslide susceptibility (LS) in Aqabat Al-Sulbat, Asir region, Saudi Arabia, which observes landslide frequently. To obtain very high precision and robust prediction from machine learning algorithms, the grey wolf and PSO optimization algorithms were integrated to develop new ensemble machine learning techniques. Subsequently, LS maps produced by training dataset were validated using the receiver operating characteristics (ROC) curve based on the testing dataset. Based on the area under curve (AUC) value of ROC curve, the best method for LS modeling was selected. We developed ROC curve-based sensitivity analysis to investigate the influence of the parameters for LS modeling. The Gumble extreme value distribution was employed to estimate the rainfall at 2, 5, 10, 20, 50, and 100 year return periods. Then, the landslide hazard maps were prepared at different return periods by integrating the best LS model and estimated rainfall at different return periods. The theory of danger pixels was employed to prepare a final risk assessment of the resources, which have been exposed to the landslide. The results showed that 27–42 and 6–15 km2 were predicted as the very high and high LS zones using four ensemble metaheuristic machine learning algorithms. Based on the area under curve (AUC) of ROC, GR-ANN (AUC-0.905) appeared as the best model for LS modeling. The areas under high and very high landslide hazard were gradually increased over the progression of time (26 km2 at the 2 year return period and 40 km2 at the 100 year return period for the high landslide hazard zone, and 6 km2 at the 2 year return period and 20 km2 at the 100 year return period for the very high landslide hazard zone). Similarly, the areas of danger pixel also increased gradually from the 2 to 100 year return periods (37 km2 to 62 km2). Various natural resources, such as scrubland, built up, and sparse vegetation, were identified under risk zone due to landslide hazards. In addition, these resources would be exposed extensively to landslides over the advancement of return periods. Therefore, the outcome of the present study will help planners and scientists to propose high precision management plans for protecting natural resources, which have been exposed to landslides.

Mapping Landslide Susceptibility Using Machine Learning Algorithms and GIS: A Case Study in Shexian County, Anhui Province, China

In this study, Logistics Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Machine (GBM), and Multilayer Perceptron (MLP) machine learning algorithms are combined with GIS techniques to map landslide susceptibility in Shexian County, China. By using satellite images and various topographic and geological maps, 16 landslide susceptibility factor maps of Shexian County were initially constructed. In total, 502 landslide and random safety points were then using the “Extract Multivalues To Points” tool in ArcGIS, parameters for the 16 factors were extracted and imported into models for the five algorithms, of which 70% of samples were used for training and 30% of samples were used for verification, which makes sense for date symmetry. The Shexian grid was converted into 260130 vector points and imported into the five models, and the natural breakpoint method was used to divide the grid into four levels: low, moderate, high, and very high. Finally, by using column results gained using Area Under Curve (AUC) analysis and a grid chart, susceptibility results for mapping landslide prediction in Shexian County was compared using the five methods. Results indicate that the ratio of landslide points of high or very high levels from LR, SVM, RF, GBM, and MLP was 1.52, 1.77, 1.95, 1.83, and 1.64, and the ratio of very high landslide points to grade area was 1.92, 2.20, 2.98, 2.62, and 2.14, respectively. The success rate of training samples for the five methods was 0.781, 0.824, 0.853, 0.828, and 0.811, and prediction accuracy was 0.772, 0.803, 0.821, 0.815, and 0.803, respectively; the order of accuracy of the five algorithms was RF > SVM > MLP > GBM > LR. Our results indicate that the five machine learning algorithms have good effect on landslide susceptibility evaluation in Shexian area, with Random Forest having the best effect.