SHapley Additive exPlanations Research Articles

Global and local interpretability techniques of supervised machine learning black box models for numerical medical data

The most effective machine learning classification techniques, such as artificial neural networks, are not easily interpretable, which limits their usefulness in critical areas, such as medicine, where errors can have severe consequences. Researchers have been working to balance the trade-off between the model performance and interpretability. In this study, seven interpretability techniques (global surrogate, accumulated local effects, local interpretable model-agnostic explanations (LIME), Shapley additive explanations (SHAP), model agnostic post hoc local explanations (MAPLE), local rule-based explanation (LORE), and Contextual Importance and Utility (CIU)) were evaluated to interpret five medical classifiers (multilayer perceptron, support vector machines, random forests, extreme gradient boosting, and naïve bayes) using six model performance metrics and three interpretability technique metrics across six medical numerical datasets. The results confirmed the effectiveness of integrating global and local interpretability techniques, and highlighted the superior performance of global SHAP explainer and local CIU explanations. The quantitative evaluations of explanations emphasised the importance of assessing these interpretability techniques before employing them to interpret black box models.

Deep learning with TabNet: rapid coal ash content estimation via X-ray fluorescence

ABSTRACT As a paramount index of coal quality, the quick and accurate prediction of ash content bears substantial significance for the coal preparation plant. In this study, an innovative approach that integrates SHapley Additive exPlanations with a deep learning model Tabular Networks has been introduced, which efficiently predict the ash content by employing the compositional data obtained from rapid elemental analysis. Pictures of the relationship between elemental and ash content reveal a significant correlation. To further elucidate this relationship, Polynomial regression, Random Forest regression, and eXtreme Gradient Boosting are used as comparison prediction models to verify the accuracy of the deep learning model. The R2 for TabNet, Poly, XGBoost, and RFR are 0.9867, 0.9755, 0.9797, and 0.9714, respectively. The optimization is continued based on SHAP averages, and the best combination of elemental feature contributions obtained is used to continue the prediction of the experiments. The experimental results show that the TabNet model has better predictive performance than other models (RMSE, MAE, and R2 are 1.5126, 1.0953, and 0.9903). An examination and exploration of the contributions and roles of elements to the ash prediction model has been conducted. The case study presented in this paper illustrates that the interpreted deep learning model holds promising prospects for industrial ash fraction prediction.

Explainable AI-driven model for gastrointestinal cancer classification

Although the detection procedure has been shown to be highly effective, there are several obstacles to overcome in the usage of AI-assisted cancer cell detection in clinical settings. These issues stem mostly from the failure to identify the underlying processes. Because AI-assisted diagnosis does not offer a clear decision-making process, doctors are dubious about it. In this instance, the advent of Explainable Artificial Intelligence (XAI), which offers explanations for prediction models, solves the AI black box issue. The SHapley Additive exPlanations (SHAP) approach, which results in the interpretation of model predictions, is the main emphasis of this work. The intermediate layer in this study was a hybrid model made up of three Convolutional Neural Networks (CNNs) (InceptionV3, InceptionResNetV2, and VGG16) that combined their predictions. The KvasirV2 dataset, which comprises pathological symptoms associated to cancer, was used to train the model. Our combined model yielded an accuracy of 93.17% and an F1 score of 97%. After training the combined model, we use SHAP to analyze images from these three groups to provide an explanation of the decision that affects the model prediction.

Protein feature engineering framework for AMPylation site prediction.

AMPylation is a biologically significant yet understudied post-translational modification where an adenosine monophosphate (AMP) group is added toTyrosine and Threonine residues primarily. While recent work has illuminated the prevalence and functional impacts of AMPylation, experimental identification of AMPylation sites remains challenging. Computational prediction techniques provide a faster alternative approach. The predictive performance of machine learning models is highly dependent on the features used to represent the raw amino acid sequences. In this work, we introduce a novel feature extraction pipeline to encode the key properties relevant to AMPylation site prediction. We utilize a recently published dataset of curated AMPylation sites to develop our feature generation framework. We demonstrate the utility of our extracted features by training various machine learning classifiers, on various numerical representations of the raw sequences extracted with the help of our framework. Tenfold cross-validation is used to evaluate the model's capability to distinguish between AMPylated and non-AMPylated sites. The top-performing set of features extracted achieved MCC score of 0.58, Accuracy of 0.8, AUC-ROC of 0.85 and F1 score of 0.73. Further, we elucidate the behaviour of the model on the set of features consisting of monogram and bigram counts for various representations using SHapley Additive exPlanations.

The relationship between heavy metals and metabolic syndrome using machine learning

BackgroundExposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method.MethodsThe data used in this study are from the national health and nutrition examination survey 2003–2018. According to the demographic information and heavy metal exposure level of participants, a total of 22 variables were included. Lasso was used to screen out the key variables, and 9 commonly used ML models were selected to establish the associations with the 5-fold cross validation method. Finally, we choose the SHapley Additive exPlanations (SHAP) method to explain the prediction results of Adaboost model.Results11,667 eligible individuals were randomly divided into two groups to train and verify the prediction model. Through lasso, characteristic variables were selected from 24 variables as predictors. The AUC (area under curve) of the models selected in this study were all greater than 0.7, and AdaBoost was the best model. The AUC value of AdaBoost was 0.807, the accuracy was 0.720, and the sensitivity was 0.792. It is noteworthy that higher levels of cadmium, body mass index, cesium, being female, and increasing age were associated with an increased probability of MetS. Conversely, lower levels of cobalt and molybdenum were linked to a decrease in the estimated probability of MetS.ConclusionOur study highlights the AdaBoost model proved to be highly effective, precise, and resilient in detecting a correlation between exposure to heavy metals and MetS. Through the use of interpretable methods, we identified cadmium, molybdenum, cobalt, cesium, uranium, and barium as prominent contributors within the predictive model.

Impact of Nature of Medical Data on Machine and Deep Learning for Imbalanced Datasets: Clinical Validity of SMOTE Is Questionable

Dataset imbalances pose a significant challenge to predictive modeling in both medical and financial domains, where conventional strategies, including resampling and algorithmic modifications, often fail to adequately address minority class underrepresentation. This study theoretically and practically investigates how the inherent nature of medical data affects the classification of minority classes. It employs ten machine and deep learning classifiers, ranging from ensemble learners to cost-sensitive algorithms, across comparably sized medical and financial datasets. Despite these efforts, none of the classifiers achieved effective classification of the minority class in the medical dataset, with sensitivity below 5.0% and area under the curve (AUC) below 57.0%. In contrast, the similar classifiers applied to the financial dataset demonstrated strong discriminative power, with overall accuracy exceeding 95.0%, sensitivity over 73.0%, and AUC above 96.0%. This disparity underscores the unpredictable variability inherent in the nature of medical data, as exemplified by the dispersed and homogeneous distribution of the minority class among other classes in principal component analysis (PCA) graphs. The application of the synthetic minority oversampling technique (SMOTE) introduced 62 synthetic patients based on merely 20 original cases, casting doubt on its clinical validity and the representation of real-world patient variability. Furthermore, post-SMOTE feature importance analysis, utilizing SHapley Additive exPlanations (SHAP) and tree-based methods, contradicted established cerebral stroke parameters, further questioning the clinical coherence of synthetic dataset augmentation. These findings call into question the clinical validity of the SMOTE technique and underscore the urgent need for advanced modeling techniques and algorithmic innovations for predicting minority-class outcomes in medical datasets without depending on resampling strategies. This approach underscores the importance of developing methods that are not only theoretically robust but also clinically relevant and applicable to real-world clinical scenarios. Consequently, this study underscores the importance of future research efforts to bridge the gap between theoretical advancements and the practical, clinical applications of models like SMOTE in healthcare.

An Interpretable Machine Learning Approach to Predict Survival Outcomes in Spinal and Sacropelvic Chordomas.

Retrospective, population-based cohort study. This study aimed to develop machine learning (ML) models to predict five-year and 10-year mortality in spinal and sacropelvic chordoma patients and integrate them into a web application for enhanced prognostication. Past research has uncovered factors influencing survival in spinal chordoma patients. While identifying individual predictors is important, personalized survival predictions are equally vital. Though prior efforts have resulted in nomograms aiming to serve this purpose, they cannot capture complex interactions within data and rely on statistical assumptions that may not fit real-world data. Adult spinal and sacropelvic chordoma patients were identified from the National Cancer Database. Sociodemographic, clinicopathologic, diagnostic, and treatment-related variables were utilized as predictive features. Five supervised ML algorithms (TabPFN, CatBoost, XGBoost, LightGBM, and Random Forest) were implemented to predict mortality at five and 10 years postdiagnosis. Model performance was primarily evaluated using the area under the receiver operating characteristic (AUROC). SHapley Additive exPlanations (SHAP) values and partial dependence plots provided feature importance and interpretability. The top models were integrated into a web application. From the NCDB, 1206 adult patients diagnosed with histologically confirmed spinal and sacropelvic chordomas were retrieved for the five-year mortality outcome [423 (35.1%) with five-year mortality] and 801 patients for the 10-year mortality outcome [588 (73.4%) with 10-year mortality]. Top-performing models for both of the outcomes were the models created with the CatBoost algorithm. The CatBoost model for five-year mortality predictions displayed a mean AUROC of 0.801, and the CatBoost model predicting 10-year mortality yielded a mean AUROC of 0.814. This study developed ML models that can accurately predict five-year to 10-year survival probabilities in spinal chordoma patients. Integrating these interpretable, personalized prognostic models into a web application provides quantitative survival estimates for a given patient. The local interpretability enables transparency into how predictions are influenced. Further external validation is warranted to support generalizability and clinical utility.

Application of deep learning model incorporating domain knowledge in international migration forecasting

PurposeForecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.Design/methodology/approachThis study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.FindingsThe model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R2 values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.Originality/valueThis study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

Toward Precision Diagnosis: Machine Learning in Identifying Malignant Orbital Tumors With Multiparametric 3 T MRI.

Orbital tumors present a diagnostic challenge due to their varied locations and histopathological differences. Although recent advancements in imaging have improved diagnosis, classification remains a challenge. The integration of artificial intelligence in radiology and ophthalmology has demonstrated promising outcomes. This study aimed to evaluate the performance of machine learning models in accurately distinguishing malignant orbital tumors from benign ones using multiparametric 3 T magnetic resonance imaging (MRI) data. In this single-center prospective study, patients with orbital masses underwent presurgery 3 T MRI scans between December 2015 and May 2021. The MRI protocol comprised multiparametric imaging including dynamic contrast-enhanced (DCE), diffusion-weighted imaging (DWI), intravoxel incoherent motion (IVIM), as well as morphological imaging acquisitions. A repeated nested cross-validation strategy using random forest classifiers was used for model training and evaluation, considering 8 combinations of explanatory features. Shapley additive explanations (SHAP) values were used to assess feature contributions, and the model performance was evaluated using multiple metrics. One hundred thirteen patients were analyzed (57/113 [50.4%] were women; average age was 51.5 ± 17.5 years, range: 19-88 years). Among the 8 combinations of explanatory features assessed, the performance on predicting malignancy when using the most comprehensive model, which is the most exhaustive one incorporating all 46 explanatory features-including morphology, DWI, DCE, and IVIM, achieved an area under the curve of 0.9 [0.73-0.99]. When using the streamlined "10-feature signature" model, performance reached an area under the curve of 0.88 [0.71-0.99]. Random forest feature importance graphs measured by the mean of SHAP values pinpointed the 10 most impactful features, which comprised 3 quantitative IVIM features, 4 quantitative DCE features, 1 quantitative DWI feature, 1 qualitative DWI feature, and age. Our findings demonstrate that a machine learning approach, integrating multiparametric MRI data such as DCE, DWI, IVIM, and morphological imaging, offers high-performing models for differentiating malignant from benign orbital tumors. The streamlined 10-feature signature, with a performance close to the comprehensive model, may be more suitable for clinical application.

A machine learning approach for evaluating Southern Ocean cloud radiative biases in a global atmosphere model

Abstract. The evaluation and quantification of Southern Ocean cloud–radiation interactions simulated by climate models are essential in understanding the sources and magnitude of the radiative bias that persists in climate models for this region. To date, most evaluation methods focus on specific synoptic or cloud-type conditions that do not consider the entirety of the Southern Ocean's cloud regimes at once. Furthermore, it is difficult to directly quantify the complex and non-linear role that different cloud properties have on modulating cloud radiative effect. In this study, we present a new method of model evaluation, using machine learning that can at once identify complexities within a system and individual contributions. To do this, we use an XGBoost (eXtreme Gradient Boosting) model to predict the radiative bias within a nudged version of the Australian Community Climate and Earth System Simulator – Atmosphere-only model, using cloud property biases as predictive features. We find that the XGBoost model can explain up to 55 % of the radiative bias from these cloud properties alone. We then apply SHAP (SHapley Additive exPlanations) feature importance analysis to quantify the role each cloud property bias plays in predicting the radiative bias. We find that biases in the liquid water path are the largest contributor to the cloud radiative bias over the Southern Ocean, though important regional and cloud-type dependencies exist. We then test the usefulness of this method in evaluating model perturbations and find that it can clearly identify complex responses, including cloud property and cloud-type compensating errors.

Pseudo datasets explain artificial neural networks

AbstractMachine learning enhances predictive ability in various research compared to conventional statistical approaches. However, the advantage of the regression model is that it can effortlessly interpret the effect of each predictor. Therefore, interpretable machine-learning models are desirable as the deep-learning technique advances. Although many studies have proposed ways to explain neural networks, this research suggests an intuitive and feasible algorithm to interpret any set of input features of artificial neural networks at the population-mean level changes. The new algorithm provides a novel concept of generating pseudo datasets and evaluating the impact due to changes in the input features. Our approach can accurately obtain the effect estimate from single to multiple input neurons and depict the association between the predictive and outcome variables. According to computer simulation studies, the explanatory effects of the predictors derived by the neural network as a particular case could approximate the general linear model estimates. Besides, we applied the new method to three real-life analyzes. The results demonstrated that the new algorithm could obtain similar effect estimates from the neural networks and regression models. Besides, it yields better predictive errors than the conventional regression models. Again, it is worth noting that the new pipeline is much less computationally intensive than the SHapley Additive exPlanations (SHAP), which could not simultaneously measure the impact due to two or more inputs while adjusting for other features.

Association of Performance on Multiple Cognitive Domains with Sarcopenia Among Middle-aged and Older Adults.

The relationship between cognitive function and subsequent sarcopenia remains unclear. Therefore, this study aimed to examine the associations of performance on multiple cognitive domains with sarcopenia in the middle-aged and older adults. This longitudinal analysis (wave 2011-2013) included 2934 participants from the CHARLS study. Sarcopenia was defined by the Asian Sarcopenia Working Group 2019 criteria. Cognitive function was measured by the Chinese version of the Mini-Mental State Examination (MMSE). Three interpretable techniques, namely SHapley Additive exPlanations (SHAP) and two built-in methods (coefficients of logistic regression and Gini importance of random forest), were used to assess the relationship between MMSE, its components (orientation, attention, episodic memory, and visuospatial ability) and sarcopenia. In addition, the association of MMSE score and its components with sarcopenia was further validated using stepwise regression. All interpretable methods showed that MMSE score was important predictors for sarcopenia, especially for SHAP (MMSE score ranked top one). For its components, episodic memory, visuospatial ability, and attention showed high predictive value compared with orientation. Stepwise regression analyses showed that MMSE score and its components of episodic memory and visuospatial ability were correlated with sarcopenia, with their odds ratios of 0.93 (95% CI: 0.91-0.96, p<0.001), 0.87 (95% CI: 0.82-0.93, p<0.001), and 1.32 (95% CI: 1.05-1.65, p=0.016), respectively. Better cognitive function especially episodic memory and visuospatial ability was negatively associated with incident sarcopenia among community middle-aged and older adults.

Game-theoretic optimization of landslide susceptibility mapping: a comparative study between Bayesian-optimized basic neural network and new generation neural network models.

Landslide susceptibility mapping is essential for reducing the risk of landslides and ensuring the safety of people and infrastructure in landslide-prone areas. However, little research has been done on the development of well-optimized Elman neural networks (ENN), deep neural networks (DNN), and artificial neural networks (ANN) for robust landslide susceptibility mapping (LSM). Additionally, there is a research gap regarding the use of Bayesian optimization and the derivation of SHapley Additive exPlanations (SHAP) values from optimized models. Therefore, this study aims to optimize DNN, ENN, and ANN models using Bayesian optimization for landslide susceptibility mapping and derive SHAP values from these optimized models. The LSM models have been validated using the receiver operating characteristics curve, confusion matrix, and other twelve error matrices. The study used six machine learning-based feature selection techniques to identify the most important variables for predicting landslide susceptibility. The decision tree, random forest, and bagging feature selection models showed that slope, elevation, DFR, annual rainfall, LD, DD, RD, and LULC are influential variables, while geology and soil texture have less influence. The DNN model outperformed the other two models, covering 7839.54 km2 under the very low landslide susceptibility zone and 3613.44 km2 under the very high landslide susceptibility zone. The DNN model is better suited for generating landslide susceptibility maps, as it can classify areas with higher accuracy. The model identified several key factors that contribute to the initiation of landslides, including high elevation, built-up and agricultural land use, less vegetation, aspect (north and northwest), soil depth less than 140 cm, high rainfall, high lineament density, and a low distance from roads. The study's findings can help stakeholders make informed decisions to reduce the risk of landslides and ensure the safety of people and infrastructure in landslide-prone areas.

Prediction of Torque Capacity in Circular Concrete-Filled Double-Skin Tubular Members under Pure Torsion via Machine Learning and Shapley Additive Explanations Interpretation

The prediction of torque capacity in circular Concrete-Filled Double-Skin Tubular (CFDST) members under pure torsion is considered vital for structural design and analysis. In this study, torque capacity is predicted using machine learning (ML) algorithms, such as Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Random Forest (RF), and Decision Tree (DT), which are employed. The interpretation of the results is conducted using Shapley Additive Explanations (SHAPs). The performance of these ML models is evaluated against two traditional analytical formulas that have been proposed and are available in the literature. Through comprehensive analysis, it is shown that superior predictive capabilities are possessed by the CatBoost and XGBoost models, characterized by high R2 values and minimal mean errors. Additionally, insights into the influence of input features are provided by SHAP interpretation, with an emphasis on key parameters such as concrete compressive strength and steel tube dimensions. The gap between empirical models and ML techniques is bridged by this study, offering engineers a more accurate and efficient tool for CFDST structural design. Significant implications for optimizing CFDST column designs and advancing structural engineering practices are presented by these findings. Directions for future research include the further refinement of ML models and the integration of probabilistic analyses for enhanced structural resilience. Overall, the transformative potential of ML and SHAP interpretation in advancing the field of structural engineering is showcased by this study.

An Improved Deep Learning Approach Considering Spatiotemporal Heterogeneity for PM2.5 Prediction: A Case Study of Xinjiang, China

Prediction of fine particulate matter with particle size less than 2.5 µm (PM2.5) is an important component of atmospheric pollution warning and control management. In this study, we propose a deep learning model, namely, a spatiotemporal weighted neural network (STWNN), to address the challenge of poor long-term PM2.5 prediction in areas with sparse and uneven stations. The model, which is based on convolutional neural network–bidirectional long short-term memory (CNN–Bi-LSTM) and attention mechanisms and uses a geospatial data-driven approach, considers the spatiotemporal heterogeneity effec It is correct.ts of PM2.5. This approach effectively overcomes instability caused by sparse station data in forecasting daily average PM2.5 concentrations over the next week. The effectiveness of the STWNN model was evaluated using the Xinjiang Uygur Autonomous Region as the study area. Experimental results demonstrate that the STWNN exhibits higher performance (RMSE = 10.29, MAE = 6.4, R2 = 0.96, and IA = 0.81) than other models in overall prediction and seasonal clustering. Furthermore, the SHapley Additive exPlanations (SHAP) method was introduced to calculate the contribution and spatiotemporal variation of feature variables after the STWNN prediction model. The SHAP results indicate that the STWNN has significant potential in improving the performance of long-term PM2.5 prediction at the regional station level. Analyzing spatiotemporal differences in key feature variables that influence PM2.5 provides a scientific foundation for long-term pollution control and supports emergency response planning for heavy pollution events.

Development of a novel continuum damage mechanics‐based machine learning approach for vibration fatigue assessment of fastener clip subjected to high‐frequency vibration

AbstractThis paper proposes a novel method based on continuum damage mechanics (CDM) and machine learning (ML) models to evaluate the vibration fatigue behavior of W1‐type railway fastener clips subjected to high‐frequency vibration. Firstly, static and fatigue tests are conducted on 60Si2Mn spring steel to acquire elastic modulus, tensile strength, and P‐S‐N curves. Subsequently, a CDM model is established, and numerical simulations are performed under various working conditions to obtain the fatigue characteristics of the clips. Finally, the ML model is trained using numerical simulation results, thereby establishing a mapping model between the working conditions and fatigue characteristics. The developed ML model demonstrates high accuracy in predicting the vibration fatigue life of the clips. Moreover, the Shapley Additive Explanations (SHAP) algorithm is employed to elucidate the ML model, revealing that the vibration frequency has a greater impact on the fatigue life of the clips compared to the vibration displacement.

Automated real-time prediction of geological formation tops during drilling operations: an applied machine learning solution for the Norwegian Continental Shelf

AbstractAccurate prediction of geological formation tops is a crucial task for optimizing hydrocarbon exploration and production activities. This research investigates and conducts a comprehensive comparative analysis of several advanced machine learning approaches tailored for the critical application of geological formation top prediction within the complex Norwegian Continental Shelf (NCS) region. The study evaluates and benchmarks the performance of four prominent machine learning models: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest ensemble method, and Multi-Layer Perceptron (MLP) neural network. To facilitate a rigorous assessment, the models are extensively evaluated across two distinct datasets - a dedicated test dataset and a blind dataset independent for validation. The evaluation criteria revolve around quantifying the models' predictive accuracy in successfully classifying multiple geological formation top types. Additionally, the study employs the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm as a baseline benchmarking technique to contextualize the relative performance of the machine learning models against a conventional clustering approach. Leveraging two model-agnostic feature importance analysis techniques - Permutation Feature Importance (PFI) and Shapley Additive exPlanations (SHAP), the investigation identifies and ranks the most influential input variables driving the predictive capabilities of the models. The comprehensive analysis unveils the MLP neural network model as the top-performing approach, achieving remarkable predictive accuracy with a perfect score of 0.99 on the blind validation dataset, surpassing the other machine learning techniques as well as the DBSCAN benchmark. However, the SVM model attains superior performance on the initial test dataset, with an accuracy of 0.99. Intriguingly, the PFI and SHAP analyses converge in consistently pinpointing depth (DEPT), revolution per minute (RPM), and Hook-load (HKLD) as the three most impactful parameters influencing model predictions across the different algorithms. These findings underscore the potential of sophisticated machine learning methodologies, particularly neural network-based models, to significantly enhance the accuracy of geological formation top prediction within the geologically complex NCS region. However, the study emphasizes the necessity for further extensive testing on larger datasets to validate the generalizability of the high performance observed. Overall, this research delivers an exhaustive comparative evaluation of state-of-the-art machine learning techniques, offering critical insights to guide the optimal selection, development, and real-world deployment of accurate and reliable predictive modeling strategies tailored for hydrocarbon exploration and reservoir characterization endeavors in the NCS. Graphical abstract

Development and validation of a machine learning-based postoperative prognostic model for plasma cell neoplasia with spinal lesions as initial clinical manifestations: a single-center cohort study.

Spinal multiple myeloma (MM) and solitary plasmacytoma of bone (SPB), both plasma cell neoplasms, greatly affect patients' quality of life due to spinal involvement. Accurate prediction of surgical outcomes is crucial for personalized patient care, but systematic treatment guidelines and predictive models are lacking. This study aimed to develop and validate a machine learning (ML)-based model to predict postoperative outcomes and identify prognostic factors for patients with spinal MM and SPB. A retrospective analysis was conducted on patients diagnosed with MM or SPB from 2011 to 2015, followed by prospective data collection from 2016 to 2017. Patient demographics, tumor characteristics, clinical treatments, and laboratory results were analyzed as input features. Four types of ML algorithms were employed for model development. The performance was assessed using discrimination and calibration measures, and the Shapley Additive exPlanations (SHAP) method was applied for model interpretation. A total of 169 patients were included, with 119 for model training and 50 for validation. The Gaussian Naïve Bayes (GNB) model exhibited superior predictive accuracy and stability. Prospective validation on the 50 patients revealed an area under the curve (AUC) of 0.863, effectively distinguishing between 5-year survivors and non-survivors. Key prognostic factors identified included International Staging System (ISS) stage, Durie-Salmon (DS) stage, targeted therapy, and age. The GNB model has the best performance and high reliability in predicting postoperative outcomes. Variables such as ISS stage and DS stage were significant in influencing patient prognosis. This study enhances the ability to identify patients at risk of poor outcomes, thereby aiding clinical decision-making.

Predicting the mechanical properties of plastic concrete: An optimization method by using genetic programming and ensemble learners

This study presents a comparative analysis of individual and ensemble learning algorithms (ELAs) to predict the compressive strength (CS) and flexural strength (FS) of plastic concrete. Multilayer perceptron neuron network (MLPNN), Support vector machine (SVM), random forest (RF), and decision tree (DT) were used as base learners, which were then combined with bagging and Adaboost methods to improve the predictive performance. In addition, gene expression programming (GEP) was used to develop computational equations that can be used to predict the CS and FS of plastic concrete. An extensive database containing 357 and 125 data points was obtained from the literature, and the eight most impactful ingredients were used in the model’s development. The accuracy of all models was assessed using several statistical measures, including an error matrix, Akaike information criterion (AIC), K-fold cross-validation, and other external validation equations. Furthermore, sensitivity and SHAP analysis were performed to evaluate input variables' relative significance and impact on the anticipated CS and FS. Based on statistical measures and other validation criteria, GEP outpaces all other individual models, whereas, in ELAs, the SVR ensemble with Adaboost and RF modified with the Bagging technique demonstrated superior performance. SHapley Additive exPlanations (SHAP) and sensitivity analysis reveal that plastic, cement, water, and the age of the specimens have the highest influence, while superplasticizer has the lowest impact, which is consistent with experimental studies. Moreover, GUI and GEP-based simple mathematical correlation can enhance the practical scope of this study and be an effective tool for the pre-mix design of plastic concrete.

Interpretable machine learning scheme for predicting bridge pier scour depth

Predicting scour depth around bridge piers is challenging due to the involvement of various uncertain factors and complex processes, making it difficult to obtain accurate results using traditional deterministic models. Recently, nonlinear analysis and prediction using machine learning (ML) techniques that glean statistical structures from input/output data have received substantial attention. With the use of ML, however, interpretation becomes difficult with increased complexity and diversity of the analysis parameters. The study herein proposes a local scour depth prediction model around piers using interpretable ML.A scour depth prediction model was constructed using the state-of-the-art eXtreme Gradient Boositng (XGB) model, and Shapley additive explanations (SHAP) based on the cooperative game theory. The ML model demonstrated excellent prediction accuracy (R2: 0.75, RMSE: 0.23) compared with existing empirical formulas used for assessment of pier scour. Model analysis results demonstrated that for each input variable, the distribution of SHAP values for scour depth is consistent with the general theoretical knowledge about the factors influencing scour depth, suggesting that the predictions of the XGB model are reasonable. Considering accuracy and conservatism, design recommendations using two statistical parameters: mean absolute percentage error (MAPE) and the percentage of predicted scour depth exceeding measured scour depth, referred to as the “level of conservatism” were proposed as a means of providing the flexibility of including a target level of accuracy and conservatism in the computed scour depth.