Learning Predictive Models Research Articles

Machine learning-driven predictive modeling of magnetohydrodynamic double diffusion of non-Newtonian hybrid ferrofluids with variable thermophysical properties within corrugated cylinders

This study addresses the complex problem of magnetohydrodynamic (MHD) double diffusion in non-Newtonian hybrid ferrofluids within a concentric corrugated cylinder. Understanding this phenomenon is crucial due to its applications in advanced cooling systems, biomedical drug delivery, and industrial processes where precise control of fluid dynamics and heat transfer is essential. Traditional simulations face challenges in capturing these complexities accurately, making it imperative to explore more efficient modeling approaches. To overcome these challenges, we employed a computational fluid dynamics (CFD) framework combined with machine learning predictive modeling. Four machine learning algorithms – decision tree regression (DT), random forest regression (RF), feed-forward neural networks (FFNN), and 1-dimensional convolutional neural networks (1D-CNN) – were used to analyze the behavior of the fluid under various conditions. The CFD simulations revealed that increasing the power law index (n) results in a decrease in flow rates, with a 20.53% reduction for n from 0.8 to 1 and a 49.04% reduction for n from 1 to 1.4. Significant variations in volume fraction (ϕ) and Hartmann number (Ha) were observed to affect average Nusselt number (Nu¯) and Sherwood number (Sh¯). The machine learning models demonstrated high predictive accuracy, with 1D-CNN achieving R2 values of 0.9996, 0.9994, and 0.9995 for Nu¯, Sh¯, and |Ψ|, respectively. The FFNN achieved R2 values of 0.9995, 0.9984, and 0.9995 for the same metrics. These results confirm that the studied parameters-Rayleigh number (Ra), Hartmann number (Ha), and power law index (n)-significantly influence flow properties. The novelty of this work lies in the integration of machine learning techniques with CFD simulations to model MHD double diffusion in non-Newtonian hybrid ferrofluids. This approach provides a more precise and resource-efficient method for analyzing complex fluid behaviors compared to traditional simulation methods. The findings have significant implications for various applications, including energy systems, biomedical engineering, industrial cooling, and chemical processing. The study not only advances the understanding of MHD phenomena in non-Newtonian fluids but also offers practical insights for designing improved cooling systems and other applications where precise fluid control is essential.

Geometric molecular graph representation learning model for drug-drug interactions prediction.

Drug-drug interaction (DDI) can trigger many adverse effects in patients and has emerged as a threat to medicine and public health. Therefore, it is important to predict potential drug interactions since it can provide combination strategies of drugs for systematic and effective treatment. Existing deep learning-based methods often rely on DDI functional networks, or use them as an important part of the model information source. However, it is difficult to discover the interactions of a new drug. To address the above limitations, we propose a geometric molecular graph representation learning model (Mol-DDI) for DDI prediction based on the basic assumption that structure determines function. Mol-DDI only considers the covalent and non-covalent bond information of molecules, then it uses the pre-training idea of large-scale models to learn drug molecular representations and predict drug interactions during the fine-tuning process. Experimental results show that the Mol-DDI model outperforms others on the three datasets and performs better in predicting new drug interaction experiments.

Machine learning models for diagnosis and risk prediction in eating disorders, depression, and alcohol use disorder.

Early diagnosis and treatment of mental illnesses is hampered by the lack of reliable markers. This study used machine learning models to uncover diagnostic and risk prediction markers for eating disorders (EDs), major depressive disorder (MDD), and alcohol use disorder (AUD). Case-control samples (aged 18-25 years), including participants with Anorexia Nervosa (AN), Bulimia Nervosa (BN), MDD, AUD, and matched controls, were used for diagnostic classification. For risk prediction, we used a longitudinal population-based sample (IMAGEN study), assessing adolescents at ages 14, 16 and 19. Regularized logistic regression models incorporated broad data domains spanning psychopathology, personality, cognition, substance use, and environment. The classification of EDs was highly accurate, even when excluding body mass index from the analysis. The area under the receiver operating characteristic curves (AUC-ROC [95 % CI]) reached 0.92 [0.86-0.97] for AN and 0.91 [0.85-0.96] for BN. The classification accuracies for MDD (0.91 [0.88-0.94]) and AUD (0.80 [0.74-0.85]) were also high. The models demonstrated high transdiagnostic potential, as those trained for EDs were also accurate in classifying AUD and MDD from healthy controls, and vice versa (AUC-ROCs, 0.75-0.93). Shared predictors, such as neuroticism, hopelessness, and symptoms of attention-deficit/hyperactivity disorder, were identified as reliable classifiers. In the longitudinal population sample, the models exhibited moderate performance in predicting the development of future ED symptoms (0.71 [0.67-0.75]), depressive symptoms (0.64 [0.60-0.68]), and harmful drinking (0.67 [0.64-0.70]). Our findings demonstrate the potential of combining multi-domain data for precise diagnostic and risk prediction applications in psychiatry.

Exploring deep learning models for roadside landslide prediction: Insights and implications from comparative analysis

This study undertakes a comparative analysis of four distinct deep learning models, i.e., Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), in the context of roadside landslide prediction, aiming to provide comprehensive insights into their strengths and weaknesses. A geospatial dataset from the Lai Châu province, Vietnam, with thirteen environmental factors (elevation, aspect, slope, curvature, topographic wetness index, stream power index, flow accumulation, geology, normalized difference vegetation index, maximum rainfall, average annual rainfall, and proximity to faults and rivers) and 284 road-along landslides was considered for analysis. Our modeling efforts yielded invaluable insights into the performance of these models during both training and validation phases. The DNN model emerged as the frontrunner in the training phase, boasting the highest area under the curve (AUC) of 0.94, accuracy of 87.47%, kappa of 0.748, and lowest RMSE of 0.125. However, during validation, the CNN model outshone others, exhibiting the highest AUC of 0.88 and overall accuracy of 80.00%. Despite variations in performance metrics across phases, CNN consistently demonstrated robust predictive prowess. The findings of this study underscore the significance of selecting appropriate machine learning models tailored to specific contexts and objectives. Moreover, they contribute valuable insights for decision-makers and researchers alike, ultimately aiming to enhance the safety and resilience of communities inhabiting landslide-prone areas. Moving forward, future research directions may explore ensemble methods, novel architectures, and interpretability techniques to further advance predictive accuracy and applicability in roadside landslide susceptibility modeling.

Pediatric cardiac surgery: machine learning models for postoperative complication prediction.

Managing children undergoing cardiac surgery with cardiopulmonary bypass (CPB) presents a significant challenge for anesthesiologists. Machine Learning (ML)-assisted tools have the potential to enhance the recognition of patients at risk of complications and predict potential issues, ultimately improving outcomes. We evaluated the prediction capacity of six models, ranging from logistic regression to support vector machine, using a dataset comprising 33 variables and 1364 subjects. TheArea Under the Curve (AUC)and theF1 scoreserved as the primary evaluation metrics. Our primary objectives were twofold: first, to develop aneffective prediction model, and second, to create auser-friendly comprehensive modelfor identifying high-risk patients. Thelogistic regression model demonstrated the highest effectiveness, achieving anAUC of 83.65%, and an F1 score of 0.7296, with balanced sensitivity and specificity of77.94%and76.47%, respectively. In comparison, thecomprehensive three-layer decision tree modelachieved anAUC of 72.84%, with sensitivity (79.41%) comparable to more complex models. Our machine learning-assisted tools provide an additional perspective and enhance the predictive capabilities of traditional scoring methods. These tools can assist anesthesiologists in making well-informed decisions. Furthermore, we have successfully demonstrated the feasibility of creating a practical white-box model. The next steps involve conducting clinical validation and multicenter cross-validation. NCT05537168.

Multi-head learning models for power consumption prediction of unmanned ground vehicles

Multi-head learning models for power consumption prediction of unmanned ground vehicles

Implementation of machine learning classification models considering the optimum data ratio in predicting soil liquefaction susceptibility

Abstract Soil Liquefaction has a disastrous impact on structures and underground infrastructure. Therefore, an appropriate liquefaction vulnerability assessment strategy can help reduce the detrimental consequences of this hazard. In recent decades, machine learning has been studied more frequently to solve geotechnical issues, such as determining liquefaction susceptibility. Intending to improve the model’s learning ability to identify liquefaction vulnerability and to find the optimum training and testing data ratio, this research attempts to develop a machine learning model for liquefaction prediction utilizing relatively more varied data in different data ratios. In this study, liquefaction prediction models were developed using four supervised learning-based algorithms: Random Forest (RF), Naïve Bayes Classifier (NBC), Decision Tree (DT), and K-Nearest Neighbor (k-NN). Seven parameters were utilized to train the model using historical data on liquefaction. The model’s performance in predicting liquefaction was compared with various training and testing data ratios and validated using 5-fold cross-validation. The capability of the model was assessed using performance metrics. The results show that the RF model has the highest accuracy in predicting liquefaction among all the algorithms used. RF achieved an overall accuracy of 90.28%, followed by the k-NN (86.11%) and the DT (81.94%) on a training and testing data ratio of 80:20. The NBC algorithm obtained the highest accuracy of 78.44% on the 75:25 data ratio. In general, the machine learning approach is capable of predicting liquefaction susceptibility.

Automatic kidney disease prediction using deep learning techniques

The kidneys play an energetic role in eliminating excess products and fluids from the body, by a complex mechanism which is crucial for upholding a stable balance of body chemicals. Chronic kidney disease (CKD) is considered by an unhurried weakening in renal function that may eventually result in kidney injury or failure. The difficulty of diagnosing the illness rises as it worsens. However, using data from normal medical visits to evaluate the various phases of CKD could help with early detection and prompt care. Researchers suggest a classification strategy for CKD along with optimization strategies used in the learning process. The incorporation of artificial intelligence offers promise because it may often astonish with its skills and enable seemingly difficult undertakings. Modern machine learning techniques have been developed to detect renal illness in light of this. In the current study, a new deep learning model for CKD initial recognition and prediction is introduced. The main objective of the project is to build a strong deep neural network (DNN) and estimate its result outcomes in comparison to other leading-edge machine learning techniques. The outcomes demonstrate that the proposed strategy outperforms current approaches and has promise as a useful tool for CKD detection.

Empirical Evaluation of Machine Learning Models for Fuel Consumption, Driver Identification, and Behavior Prediction

Empirical Evaluation of Machine Learning Models for Fuel Consumption, Driver Identification, and Behavior Prediction

Deep Learning Model for Prediction of Dementia Severity based on EEG Signals

This study aimed to determine variations in the electroencephalograms (EEGs) of 15 individuals who were diagnosed with mild cognitive impairment (MCI) following stroke, 5 individuals suffering from vascular dementia (VD) and 15 healthy normal control (NC) individuals who performed a working memory task. Conventional filters including notch and bandpass filters were utilised to remove noise from the EEG data. The proposed method comprises computing the estimates of the attention entropy (AttEn), bubble entropy (BubbEn) and symbolic dynamic entropy (SyDyEn) of univariate data sequence features. The long short-term memory (LSTM) deep learning neural network was used to automatically classify dementia severity through noninvasive EEG-based recordings. The LSTM classification result with AttEn exceeds an average of 88.9% than BubbEn and SyDyEn, with classification results of 69.2% and 77.7%, respectively. The analysis of the brain EEG-based dementia severity dataset suggests that AttEn could potentially serve as a biomarker for detecting dementia severity. AttEn can capture relevant patterns and features in the EEG data and may be indicative of the severity of dementia with LSTM RNN to differentiate patients with VD, patients with MCI and NC individuals.

Effectiveness of Three Machine Learning Models for Prediction of Daily Streamflow and Uncertainty Assessment

Effectiveness of Three Machine Learning Models for Prediction of Daily Streamflow and Uncertainty Assessment

Machine learning predictive model to estimate the photo-degradation performance of stannates and hydroxystannates photocatalysts on a variety of waterborne contaminants

In this work, a comprehensive machine learning (ML) methodology was used to predict the degradation efficiency of different stannate and hydroxystannate photocatalysts on a wide range of waterborne pollutants. The structural, atomic features along with molecular fingerprints (MF) were used as descriptors of the crystalline phase of the photocatalysts and the organic compounds, respectively. The encoded features of the photocatalysts and contaminants along with the experimental variables of the degradation process are input to two ML models, named as RF (random forest) and KNN (K nearest neighbor). The RF model has achieved a very good prediction of the photocatalytic degradation efficiency (%) by different photocatalysts over a wide range of organic contaminants. The RF model performance was investigated by applying two different training strategies. The effects of different factors on photocatalytic degradation performance are further evaluated by feature importance analyses. Two illustrative applications on the use of the ML model for optimal photocatalyst selection and for assessing other types of photocatalysts for different environmental applications were provided.

How important are climate change risks for predicting clean energy stock prices? Evidence from machine learning predictive modeling and interpretation

How important are climate change risks for predicting clean energy stock prices? Evidence from machine learning predictive modeling and interpretation

A machine learning-based method for predicting the shear behaviors of rock joints

In this study, machine learning prediction models (MLPMs), including artificial neural network (ANN), support vector regression (SVR), K-nearest neighbors (KNN), and random forest (RF) algorithms, were developed to predict the peak shear stress values and shear stress-displacement curves of rock joints. The database used contained 693 records of peak shear stress and 162 original shear stress-displacement curves derived from direct shear tests. The results demonstrated that the MLPMs provided reliable predictions for shear stress, with the mean squared errors (MSEs) between their predicted and measured shear stress varying from 0.003 to 0.069 and the coefficients of determination (R2 values) varying from 0.964 to 0.998. The feature importance values indicate that the joint surface roughness coefficient (JRC) is the most important influential factor in determining the peak shear stress, followed by the joint wall compressive strength (JCS), basic friction angle (φb), and shear surface area (As). Similarly, for the shear stress-displacement curve, the JRC is the dominant factor, followed by As, φb, and JCS. Additional direct shear tests were conducted for model validation. The validation shows that the MLPM predictions demonstrate improved consistency with the experimental results in relation to both the peak shear stress and peak shear displacement.

Machine Learning Prediction of Quality of Life: Insight from Property Crime and Tropical Climate Analysis

<p align="center">This study delves into predicting the quality of life, a widely researched concept spanning various domains, employing mixed methodologies and indicators. Common predictors of overall quality of life encompass health status, socioeconomic factors, subjective well-being, and environmental conditions. Consequently, this research investigates the potential of utilizing machine learning prediction models for quality-of-life prediction, focusing on two key indicators.Five machine learning algorithms—Generalized Linear Model, Random Forest, Decision Tree, Gradient Boosted Tree, and Support Vector Machine—are empirically compared. Their performance in predicting quality of life is assessed based on property crime and tropical climate (temperature) attributes. Despite an initially low correlation value, temperature yields valuable insights for specific algorithms, enhancing predictive accuracy. This underscores the intricate and nuanced impact of seemingly unrelated factors in machine learning. The Support Vector Machine emerges as the top-performing algorithm, followed by Random Forest and Decision Tree. This paper offers a foundational research framework to aid educators and researchers in exploring quality of life prediction in-depth, utilizing property crime and temperature as key factors.</p>

Risk of intraoperative hemorrhage during cesarean scar ectopic pregnancy surgery: development and validation of an interpretable machine learning prediction model

Current models for predicting intraoperative hemorrhage in cesarean scar ectopic pregnancy (CSEP) are constrained by known risk factors and conventional statistical methods. Our objective is to develop an interpretable prediction model using machine learning (ML) techniques to assess the risk of intraoperative hemorrhage during CSEP in women, followed by external validation and clinical application. This multicenter retrospective study utilized electronic medical record (EMR) data from four tertiary medical institutions. The model was developed using data from 1680 patients with CSEP diagnosed and treated at Qilu Hospital of Shandong University, Chongqing Health Center for Women and Children, and Dezhou Maternal and Child Health Care Hospital between January 1, 2008, and December 31, 2023. External validation data were obtained from Liao Cheng Dong Chang Fu District Maternal and Child Health Care Hospital between January 1, 2021, and December 31, 2023. Random forest (RF), Lasso, Boruta, and Extreme Gradient Boosting (XGBoost) were employed to identify the most influential variables in the model development data set; the best variables were selected based on reaching the λmin value. Model development involved eight machine learning methods with ten-fold cross-validation. Accuracy and decision curve analysis (DCA) were used to assess model performance for selection of the optimal model. Internal validation of the model utilized area under the receiver operating characteristic curve (AUC), sensitivity, specificity, Matthews correlation coefficient, and F1 score. These same indicators were also applied to evaluate external validation performance of the model. Finally, visualization techniques were used to present the optimal model which was then deployed for clinical application via network applications. Setting λmin at the value of 0.003, the optimal variable combination containing 9 variables was selected for model development. The optimal prediction model (Bayes) had an accuracy of 0.879 (95% CI: 0.857-0.901) an AUC of 0.882 (95% CI: 0.860-0.904), a DCA curve maximum threshold probability of 0.41, and a maximum return of 7.86%. The internal validation accuracy was 0.869 (95% CI: 0.847-0.891), an AUC of 0.822 (95% CI: 0.801-0.843), a sensitivity of 0.938, a specificity of 0.422, a Matthews correlation coefficient of 0.392, and an F1 score of 0.925. In the external validation, the accuracy was 0.936 (95% CI: 0.913-0.959), an AUC of 0.853 (95% CI: 0.832-0.874), a sensitivity of 0.954, a specificity of 0.5, a Matthews correlation coefficient of 0.365, and an F1 score of 0.966. This indicates that the prediction model performed well in both internal and external validation. The developed prediction model, deployed in the network application, is capable of forecasting the risk of intraoperative hemorrhage during CSEP. This tool can facilitate targeted preoperative assessment and clinical decision-making for clinicians. Prospective data should be utilized in future studies to further validate the extended applicability of the model. Natural Science Foundation of Shandong Province; Qilu Hospital of Shandong University.

Multi-stain deep learning prediction model of treatment response in lupus nephritis based on renal histopathology.

The response of the kidney after induction treatment is one of the determinants of prognosis in lupus nephritis, but effective predictive tools are lacking. Here, we sought to apply deep learning approaches on kidney biopsies for treatment response prediction in lupus nephritis. Patients who received cyclophosphamide or mycophenolate mofetil as induction treatment were included and the primary outcome was 12-month treatment response, complete response defined as 24h urinary protein under 0.5 g with normal estimated glomerular filtration rate or within 10% of normal range. The model development cohort included 245 patients (880 digital slides), and the external test cohort had 71 patients (258 digital slides). Deep learning models were trained independently on hematoxylin and eosin, periodic acid-Schiff, periodic Schiff-methenamine silver and Masson's trichrome stained slides at multiple magnifications and integrated to predict the primary outcome of complete response to therapy at 12 months. Single-stain models showed area under the curves of 0.813, 0.841, 0.823, and 0.862, respectively. Further, integration of the four models into a multi-stain model achieved area under the curves of 0.901 and 0.840 on internal validation and external testing, respectively, which outperformed conventional clinicopathologic parameters including estimated glomerular filtration rate, chronicity index and reduction in proteinuria at three months. Decisive features uncovered by visualization uncovered for model prediction included tertiary lymphoid structures, glomerulosclerosis, interstitial fibrosis and tubular atrophy. Our study demonstrated the feasibility of utilizing deep learning on kidney pathology to predict treatment response for lupus patients. Further validation is required before the model could be implemented for risk stratification and to aid in making therapeutic decisions in clinical practice.

Concordance analysis between deep learning model predictions and electrocardiography thresholds from cardiology guidelines

Abstract Deep learning models for the classification of electrocardiograms (ECGs) are able to learn disease-specific patterns, but they are rarely implemented in medical practice due to their "black box" nature. Post-hoc explainable artificial intelligence (XAI) methods compute regions of interest (ROI) which are of importance for a model’s decision making. However, it needs to be further analyzed whether a model focuses on the morphological or rhythmical information within the ROIs. We evaluate a pre-trained ResNet for sinus bradycardia (SB) and sinus tachycardia (ST) classification on the PTBXL dataset using the XAI method Integrated Gradients. We compare the confidence of the model predictions to ECG features used by clinicians using correlation analysis. Correlation is highest for RR intervals (SB: 0.44) and atrial as well as ventricular heart rates (ST: 0.51), with the majority exceeding clinical thresholds for both disorders, indicating that the model learned rhythmical features. Except for QT intervals in ST classification, morphological features such as duration and amplitudes of P-/T-waves do not show any correlation.

A Machine Learning Model for Prostate Cancer Prediction in Korean Men

Purpose: Unnecessary prostate biopsies for detecting prostate cancer (PCa) should be minimized. Therefore, this study developed a machine learning (ML) model to predict PCa in Korean men and evaluated its usability.Materials and Methods: We retrospectively analyzed clinical data from 928 patients who underwent prostate biopsies at Kangwon National University Hospital between May 2013 and May 2023. Of these, 377 (41.6%) were diagnosed with PCa, and 551 (59.4%) did not have cancer. For external validation, clinical data from 385 patients aged 48–89 years who underwent prostate biopsies from September 2005 to September 2023 at Wonju Severance Christian Hospital were also included. Twenty-two clinical features were used to develop an ML model to predict PCa. Features were selected based on their contributions to model performance, leading to the inclusion of 15 features. A meta-learner was constructed using logistic regression to predict the probability of PCa, and the classifier was trained and validated on randomly extracted training and test sets at an 8:2 ratio.Results: The prostate health index, prostate volume, age, nodule on digital rectal examination, and prostate-specific antigen were the top 5 features for predicting PCa. The area under the receiver operating characteristic curve (AUC) of the meta-learner logistic regression model was 0.89, and the accuracy, sensitivity, and specificity were 0.828, 0.711, and 0.909, respectively. Our model also showed excellent prediction performance for high-grade PCa, with a Gleason score of 7 or higher and an AUC of 0.903. Furthermore, we evaluated the performance of the model using external cohort clinical data and achieved an AUC of 0.863.Conclusions: Our ML model excelled in predicting PCa, specifically clinically significant PCa. Although extensive cross-validation in other clinical cohorts is needed, this ML model is a promising option for future diagnostics.

Deep-Learning Model for Mortality Prediction of ICU Patients with Paralytic Ileus.

Paralytic Ileus (PI) patients in the Intensive Care Unit (ICU) face a significant risk of death. Current predictive models for PI are often complex and rely on many variables, resulting in unreliable outcomes for such a serious health condition. Predicting mortality in ICU patients with PI is particularly challenging due to the vast amount of data and numerous features involved. To address this issue, a deep-learning predictive framework was developed using the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset, which includes data from 1017 ICU patients with PI. By employing SHAP (SHapley Additive exPlanations) analysis, we were able to narrow down the features to six distinct clinical lab items. The proposed framework, called DLMP (Deep Learning Model for Mortality Prediction of ICU Patients with PI), utilizes these six unique clinical lab items: Anion gap, Platelet, PTT, BUN, Total Bilirubin, and Bicarbonate, along with one demographic variable as inputs to a neural network consisting of only two neuron layers. DLMP achieved an outstanding prediction performance with an AUC score of 0.887, outperforming existing predictive models for ICU patients with PI. The DLMP framework significantly enhances the prediction of mortality for PI patients compared to traditional process mining and machine learning models. This model holds considerable potential for prognosis, enabling families to be better informed about the severity of a patient's condition and to prepare accordingly. Furthermore, the model is valuable for research purposes and clinical trials.