Conventional Statistical Models Research Articles

Using Multilevel Models and Generalized Estimating Equation Models to Account for Clustering in Neurology Clinical Research.

In clinical and health services research, clustered data (also known as data with a multilevel or hierarchical structure) are frequently encountered. For example, patients may be clustered or nested within hospitals. Understanding when data have a multilevel structure is important because clustering of individuals can induce a homogeneity in outcomes within clusters, so that, even after adjusting for measured covariates, outcomes for 2 individuals in the same cluster are more likely to be similar than outcomes for 2 individuals from different clusters. Using conventional statistical regression models to analyze clustered data can result in incorrect conclusions being drawn. In particular, estimated CIs may be artificially narrow, and significance levels may be artificially low. As a result, one may conclude that there is a statistically significant association when there is none. To avoid this problem, investigators should ensure that their analyses use techniques that account for clustering of data. Generalized linear models estimated using generalized estimating equation (GEE) methods and multilevel regression models (also known as hierarchical regression models, mixed-effects models, or random-effects models) are two such techniques. We provide an introduction to clustered or multilevel data and describe how GEE models or multilevel models can be used for the analysis of multilevel data.

Machine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta-analysis

Abstract Background Cardiovascular disease (CVD) remains a major cause of mortality in the UK, prompting the need for improved risk predictive models for primary prevention. Machine learning (ML) models utilizing electronic health records (EHR) offer potential enhancements over traditional risk scores like QRISK3 and ASCVD. Objective To systematically evaluate and compare the efficacy of ML models against conventional CVD risk prediction algorithms using EHR data for medium to long-term (5-10 years) CVD risk prediction. Methods A systematic review and random-effect meta-analysis were conducted according to PRISMA guidelines, assessing studies from 2010 to 2024. We retrieved 32 ML models and 26 conventional statistical models from 20 selected studies, focusing on performance metrics such as Area Under the Curve (AUC) and heterogeneity across models. Results ML models, particularly random forest and deep learning, demonstrated superior performance, with the highest recorded pooled AUCs of 0.865 (95% CI: 0.812-0.917) and 0.847 (95% CI: 0.766-0.927), respectively. These significantly outperformed the conventional risk score of 0.765 (95% CI: 0.734-0.796). However, significant heterogeneity (I² > 99%) and potential publication bias were noted across the studies. Conclusion While ML models show enhanced calibration for CVD risk, substantial variability and methodological concerns limit their current clinical applicability. Future research should address these issues by enhancing methodological transparency and standardization to improve the reliability and utility of these models in clinical settings. Implications This study highlights the advanced capabilities of ML models in CVD risk prediction and emphasizes the need for rigorous validation to facilitate their integration into clinical practice. This review was registered with PROSPERO (CRD42021250058).

Abstract B019: A machine learning approach to predicting smoking cessation outcomes among Spanish-speaking smokers who completed a culturally targeted intervention

Abstract Introduction: Among the Hispanic/Latinx population in the US, four of five leading causes of death are attributed to smoking. Few evidence-based interventions have been developed to improve smoking cessation for this population. Our team has demonstrated the efficacy of a culturally targeted, extended self-help intervention for Spanish-speaking smokers, estimating a smoking abstinence rate of 33% at 24 months, compared to 24% for usual care. Further efforts are needed to enhance this efficacious, low-cost, scalable intervention approach. Machine learning (ML) is one approach to increase understanding of the predictors of treatment outcomes and inform strategies to improve the intervention. Toward that goal, this secondary data analysis utilized the decision tree (DT) model to predict self-reported 7-day point prevalence abstinence at 18-month follow-up for participants receiving our intervention. Method: Data from participants who reported smoking status at an 18-month follow-up (N=332 of 714 enrolled, 36% abstinent) were randomly split (80:20) into training and test datasets based on smoking status. We entered demographics, psychosocial, and smoking variables collected at baseline as predictors in the model. In addition to handling missing values and normalizing numeric features, we employed the Synthetic Minority Over-sampling Technique (SMOTE) combined with Tomek links (SMOTE-Tomek) to improve inter-class separability. Recursive Feature Elimination (RFE) using DT was implemented to identify the most relevant predictors. The cross-validation (CV) pipeline incorporated preprocessing, feature selection, handling class-imbalance, over-sampling, and model training with a DT as the interpretable classifier. Hyperparameters were tuned using stratified K-fold (K=5) CV to optimize parameters using Grid search. F1 score was selected as the primary metric as it accounts for each class performance by combining the precision and recall metrics. Finally, the performance of the classifier was evaluated in 20% of the unseen dataset. Results: The DT classifier for the CV achieved the F1 score of 0.73 [95% CI 0.66, 0.77], revealing a reasonably good performance in identifying smokers at 18-months. RFE selected familism, age, affect, and confidence as the most relevant predictors of smoking status. Individuals who had lower familism scores (<138), combined with higher age (>50), were more likely to be smokers at 18 months. Individuals who had higher familism scores (>138) combined with higher negative affect (>42) were more likely to be smokers. Conclusion: This study provides the first step toward personalized care for smoking cessation among the Hispanic/Latinx population and demonstrates the potential of DT classifier to predict cessation outcomes among individuals who received and completed a culturally and linguistically targeted smoking cessation intervention. Our future analysis will compare this model with conventional statistical modeling approaches and other ML algorithms to identify the best-performing parsimonious model. Citation Format: Ranjita Poudel, K. Ruwani M. Fernando, Matthew B. Schabath, Steven K. Sutton, Thomas H. Brandon, Issam El Naqa, Vani N. Simmons. A machine learning approach to predicting smoking cessation outcomes among Spanish-speaking smokers who completed a culturally targeted intervention [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr B019.

Factors influencing craniofaciadental changes in skeletal Class III orthognathic surgery by using machine learning

Background/purposeIn skeletal Class III patients, treatment options include camouflage and orthognathic surgery. This study used machine learning to investigate factors influencing dental, skeletal, and soft tissue morphological changes following skeletal Class III orthognathic surgery. Materials and methodsA retrospective analysis was conducted at Taipei Medical University Hospital. The study analyzed the lateral cephalometric radiographs of 58 patients with skeletal Class III who underwent orthognathic surgery. Web-based cephalometric software was used to obtain cephalometric tracing measurements, including dental, skeletal, and soft tissue parameters at pretreatment (T0) and posttreatment (T1), and assess postsurgical changes (T1−T0). Conventional statistical models were used for data analysis, followed by the application of machine learning–based random forest regression to identify influencing factors, as characterized by the feature of importance (FI). ResultsAll cephalometric variables except SNA, A to NP, overbite, and lower lip to E-plane differed significantly between T0 and T1. ANB was significantly influenced by surgery type (P = 0.045), whereas IMPA and lower lip to E-plane were significantly influenced by sex (IMPA P = 0.029; lower lip to E-plane P = 0.033). According to machine learning results on the influence of pretreatment conditions, overjet was a key factor influencing several dependent variables, namely, changes in ANB (FI = 0.226), B to N-Perp (FH) (FI = 0.259), and Pog to N-Perp (FH) (FI = 0.257). ConclusionMachine learning revealed the overjet plays a dominant role in several dependent variables, including changes in ANB, B to N-Perp (FH), and Pog to N-Perp (FH). Future studies should use a larger dataset and three-dimensional data.

Hybrid framework of deep extreme learning machine (DELM) based on sparrow search algorithm for non-stationary wave prediction

Accurate and trustworthy wave height forecast is essential for the efficient exploitation of wave energy. However, the non-linearity and non-stationarity of waves present a challenge task when using the conventional statistical models in the ocean wave forecasting. Aiming at these problems, this paper proposes a short-term wave height prediction method based on the Variational Mode Decomposition (VMD), Deep Extreme Learning Machine (DELM) and Sparrow Search Algorithm (SSA). Specifically, the original wave height data is initially decomposed into numerous sub-series from high to low frequency by VMD technique. Subsequently, the SSA method is employed to optimize the DELM parameters to enhance the functionality of the basic DELM model. Three wave height datasets located in the North Pacific Ocean are employed as cases in this paper. In comparison with other benchmark models, the RMSE parameters of VMD-SSA-DELM model are reduced by 35.59%–73.33% even at 10-h lead time by analyzing different forecast durations, which demonstrate the proposed model's superiority in short-term wave height prediction.

Comparison of machine learning and conventional statistical modeling for predicting readmission following acute heart failure hospitalization

IntroductionDeveloping accurate models for predicting the risk of 30-day readmission is a major healthcare interest. Evidence suggests that models developed using machine learning (ML) may have better discrimination than conventional statistical models (CSM), but the calibration of such models is unclear. ObjectivesTo compare models developed using ML with those developed using CSM to predict 30-day readmission for cardiovascular and non-cardiovascular causes in HF patients. MethodsWe retrospectively enrolled 10,919 patients with HF (> 18 years) discharged alive from a hospital or emergency department (2004-2007) in Ontario, Canada. The study sample was randomly divided into training and validation sets in a 2:1 ratio. CSMs to predict 30-day readmission were developed using Fine-Gray subdistribution hazards regression (treating death as a competing risk), and the ML algorithm employed random survival forests for competing risks (RSF-CR). Models were evaluated in the validation set using both discrimination and calibration metrics. ResultsIn the validation sample of 3602 patients, RSF-CR (c-statistic=0.620) showed similar discrimination to the Fine-Gray competing risk model (c-statistic=0.621) for 30-day cardiovascular readmission. In contrast, for 30-day non-cardiovascular readmission, the Fine-Gray model (c-statistic=0.641) slightly outperformed the RSF-CR model (c-statistic=0.632). For both outcomes, The Fine-Gray model displayed better calibration than RSF-CR using calibration plots of observed vs. predicted risks across the deciles of predicted risk. ConclusionsFine-Gray models had similar discrimination but superior calibration to the RSF-CR model, highlighting the importance of reporting calibration metrics for ML-based prediction models. The discrimination was modest in all readmission prediction models regardless of the methods used.

Integrating Machine Learning for Improved Prediction of Temperature and Moisture in Pavement Granular Layers

Abstract Pavement temperature and moisture content within the base and subgrade layers affect the load-bearing capacity of the pavement and dominate the pavement performance in cold regions. Accurately predicting pavement temperature and moisture content can improve pavement design and management. Conventional approaches, including numerical and statistical models, have been implemented to predict pavement temperature and soil moisture content. However, they have weaknesses, such as being only suitable for warm regions or only for predicting pavement temperature within the asphalt layer. Furthermore, none of them can simultaneously predict the pavement temperature and moisture content. To address this issue, data collected from an instrumented test road in Alberta, Canada, were used to train a model to predict the daily average pavement temperature and moisture content at various depths through three parameters, namely depth, day of the year, and air temperature. The MATLAB toolbox, Neural Net Fitting, was used, and the performance of three built-in algorithms, Levenberg–Marquardt, Bayesian regularization, and Scaled conjugate gradient backpropagation, was compared. The model with Bayesian regularization showed the highest accuracy, with an R2 value of 0.99 and a root mean square error (RMSE) of 1.49°C for pavement temperature prediction, and an R2 value of 0.95 and an RMSE of 0.025 m3/m3 for moisture content prediction. The model developed in this research is the first to simultaneously estimate pavement temperature and moisture content, so its performance was separately compared with two existing models in the literature. The artificial neural network (ANN) model shows higher accuracy than the two existing models, so it was found that the ANN could be a robust method for pavement temperature and moisture content prediction at various depths.

Adaptive two-dimensional subspace identification for monitoring batch processes with limited batch data

Data-driven based batch process monitoring is of critical importance in ensuring stable operating processes and consistent product quality. For long-duration batch processes, it is unrealistic to involve expensive data to train a statistical model for monitoring. To model the inherently batch-wise and variable-wise dynamics, nonlinearity, and time-varying characteristics, this paper proposes a local learning-based two-dimensional subspace identification (LL-2D-SID) scheme based on the similarity between the ongoing batch and the previous batches. The similarity is estimated by the extended extrapolative time-warping. Unlike the conventional statistical models using rich batch data, LL-2D-SID through online optimizing mechanism using limited batch data still has good prediction performance. The application of the sintering process in the polytetrafluoroethylene production has demonstrated that the LL-2D-SID based process monitoring scheme can not only accurately track temperature changes but also timely give fault alarms with a lower error alarm rate than the other SID-based process monitoring schemes.

Carbon emissions trading price forecasts by multi-perspective fusion

<p>The precise prediction of carbon emissions trading prices is the foundation for the stable and sustainable development of the carbon financial market. In recent years, influenced by a combination of factors such as the pandemic, trading regulations, and policies, carbon prices have exhibited strong random volatility and clear non-stationary characteristics. Traditional single-perspective prediction methods based on conventional statistical models are increasingly inadequate due to the homogenization of features and are struggling to adapt to China's regional carbon emissions trading market. Therefore, this paper proposes a multi-perspective fusion-based prediction method tailored to the Chinese market. It leverages carbon emissions trading information from key cities as relevant features to predict the price changes in individual cities. Inspired by the development of artificial intelligence, this paper implements various time series models based on deep neural networks. The effectiveness of the multi-perspective approach is validated through multiple metrics. It provides scientific decision-making tools for domestic carbon emissions trading investors, making a significant contribution to strengthening carbon market risk management and promoting the establishment and rational development of a unified carbon market in China.</p>

Python code for modeling ARIMA-LSTM architecture with random forest algorithm

Over conventional statistical models, machine learning mechanisms are establishing themselves as a potential area for modeling and forecasting complex time series. Because it can integrate several forecasting methodologies’ capabilities, hybrid time series models are fundamental in data science. Here, we present a Python script that builds a combined architecture of the ARIMA-LSTM model with random forest technique to generate a high-accuracy prediction. This script is a step-by-step process to create a statistical and then machine learning model through statistical assumption.

Interpretable Trend Analysis Neural Networks for Longitudinal Data Analysis

Cohort study is one of the most commonly used study methods in medical and public health researches, which result in longitudinal data. Conventional statistical models and machine learning methods are not capable of modeling the evolution trend of the variables in longitudinal data. In this article, we propose a Trend Analysis Neural Networks (TANN), which models the evolution trend of the variables by adaptive feature learning. TANN was tested on dataset of Kaiuan research. The task was to predict occurrence of cardiovascular events within 2 and 5 years, with three repeated medical examinations during 2008 and 2013. For 2-year prediction, The AUC of the TANN is 0.7378, which is a significant improvement than that of conventional methods, while that of TRNS, RNN, DNN, GBDT, RF, and LR are 0.7222, 0.7034, 0.7054, 0.7136, 0.7160, and 0.7024, respectively. For 5-year prediction, TANN also shows improvement. The experimental results show that the proposed TANN achieves better prediction performance on cardiovascular events prediction than conventional models. Furthermore, by analyzing the weights of TANN, we could find out important trends of the indicators, which are ignored by conventional machine learning models. The trend discovery mechanism interprets the model well. TANN is an appropriate balance between high performance and interpretability.

Intelligent Deep Adaptive Intuitionistic Fuzzy Classifier Based Dyslexia Prediction Among Children at its Early Stage

The inability of standard linear research to clearly define the role of cognitive abilities in reading difficulties is most likely due to the fact that reading and the components that are related to reading are both part of a system of factors. There are numerous interrelated and mitigating elements that conventional statistical models are unable to deal effectively. This work aims to increase dyslexia prediction accuracy by introducing two stage non-linear methodology which incorporate both deep learning and uncertainty theory. In the first stage, the pattern of dyslexic symptoms is learned by introducing deep adaptive neural network. During the training phase, the hyperparameters weight and learning rate are optimized using a metaheuristic algorithm called the fruit fly optimization algorithm. This algorithm imitates the behavior of fruit flies to search for the best set of values. The acquired knowledge is infused in the uncertainty inference model known as intuitionistic inference classifier. Each characteristic that defines an instance as dyslexic or non-dyslexic is represented in tristate degrees to precisely address the inconsistent or vague instance which neither or nor exhibit dyslexic symptoms by introducing the hesitancy factor. The simulation results support the proposed intuitionistic fuzzy rules prominently improves the accuracy rate of dyslexia prediction compared to the other existing state of arts.

Radiographic Imaging for the Diagnosis and Treatment of Patients with Skeletal Class III Malocclusion.

Skeletal Class III malocclusion is one type of dentofacial deformity that significantly affects patients' facial aesthetics and oral health. The orthodontic treatment of skeletal Class III malocclusion presents challenges due to uncertainties surrounding mandibular growth patterns and treatment outcomes. In recent years, disease-specific radiographic features have garnered interest from researchers in various fields including orthodontics, for their exceptional performance in enhancing diagnostic precision and treatment effect predictability. The aim of this narrative review is to provide an overview of the valuable radiographic features in the diagnosis and management of skeletal Class III malocclusion. Based on the existing literature, a series of analyses on lateral cephalograms have been concluded to identify the significant variables related to facial type classification, growth prediction, and decision-making for tooth extractions and orthognathic surgery in patients with skeletal Class III malocclusion. Furthermore, we summarize the parameters regarding the inter-maxillary relationship, as well as different anatomical structures including the maxilla, mandible, craniofacial base, and soft tissues from conventional and machine learning statistical models. Several distinct radiographic features for Class III malocclusion have also been preliminarily observed using cone beam computed tomography (CBCT) and magnetic resonance imaging (MRI).

Novel Neural Network Models for Predicting Mental Health Outcomes in the U.S. Youth Population

Anxiety and depression are two of the most pressing mental health issues, particularly among young adults. Given the success of neural networks for predictive modeling, we developed novel neural network models for classifying anxiety and depression using Substance Abuse and Mental Health Services Administration’s Mental Health Client- Level Data (SAMHSA MH-CLD) on 382,174 young adults (15 to 24 years old). The SAMHSA MH-CLD included mental health and general background data collected in 2020 for individuals reporting to state-accredited hospital service centers across the United States. The neural networks were trained on 10% randomized k-folds of the dataset and tested on the remaining 90% for each fold. We found that neural network models predicted anxiety and depression with high accuracy (91.5% to 94.2% accuracy, 8.4% to 3.1% loss), outperforming conventional statistical models. Additionally, for all tested variable sets, our neural network model outperformed expectations for the average therapist consultation (46% to 50% accuracy), as reported previously. For the optimal neural network model with the highest accuracy, the variables most correlated with anxiety and depression were age, education, gender, race, employment, marital status, and stressor events, not accounting for redundant and minimally correlated variables. The effectiveness of our neural network model indicates that it can be implemented alongside therapists in clinical environments to improve psychiatric diagnosis among young adults.

Anomalous kaon correlations measured in Pb-Pb collisions at the LHC as evidence for the melting and refreezing of the QCD vacuum

Measurements of the dynamical correlations between neutral and charged kaons in central Pb-Pb collisions at √SNN = 2.76 TeV by the ALICE Collaboration display anomalous behavior relative to conventional heavy-ion collision simulators. We consider other conventional statistical models, none of which can reproduce the magnitude and centrality dependence of the correlations. The data can be reproduced by coherent emission from domains which grow in number and volume with increasing centrality. We study the dynamical evolution of the strange quark condensate and show that the energy released during the expansion and cooling of the system may be sufficient to explain the anomaly.

Biomass@MOF nanohybrid materials for competitive drug adsorption: analysis by conventional macroscopic models and statistical physical models

This study discloses the design of nanohybrid Biomass@MOF resulting from the functionalization of a hydrochar (HC) through hydrothermal treatment (HT) of corn cob residues and MIL-53(Al).

Predicting waitlist dropout in hepatocellular carcinoma: a narrative review.

Liver transplantation is the gold standard treatment for patients with hepatocellular carcinoma (HCC). Current allocation systems face a complex issue due to the imbalance between available organs and recipients. The prioritization of HCC patients remains controversial, leading to potential disparities in access to transplantation. Factors such as tumor size, alpha-fetoprotein (AFP) levels, Model of End-Stage Liver Disease (MELD) score, and response to locoregional therapy (LRT) contribute to determining waitlist dropout risk in HCC patients. Several statistical and machine learning (ML) models have been proposed to predict waitlist dropout, incorporating variables related to tumor and patient factors, underlying liver disease, and waitlist time. This narrative review aims to summarize the evidence regarding different prediction models of HCC waitlist dropout. All published articles up to December 25, 2023, were considered. Articles not based on prediction models using conventional statistical methods or ML models were excluded. Factors such as tumor size, AFP levels, MELD score, and LRT response have been shown to impact disease progression in these patients, influencing waitlist dropout. Most articles in the literature are based on statistical models. Both ML and statistical models may offer promising results, but their application is currently limited. Several attempts have been made to find the best model to stratify the risk of waitlist dropout in HCC patients. However, to date, none of the explored models have been implemented. The allocation of HCC recipients is still based on supplementary scoring systems or geographical criteria. Improving methodology and databases in future research is essential to obtain accurate and reliable models for clinicians. This is the only way to achieve real applicability.

Parametric seasonal-trend autoregressive neural network for long-term crop price forecasting.

Crop price forecasting is difficult in that supply is not as elastic as demand, therefore, supply and demand should be stabilized through long-term forecasting and pre-response to the price. In this study, we propose a Parametric Seasonal-Trend Autoregressive Neural Network (PaSTANet), which is a hybrid model that includes both a multi-kernel residual convolution neural network model and a Gaussian seasonality-trend model. To compare the performance of the PaSTANet, we used daily data from the Garak market for four crops: onion, radish, Chinese cabbage, and green onion, and performed long-term price forecasts for one year in 2023. The PaSTANet shows good performance on all four crops compared to other conventional statistical and deep learning-based models. In particular, for onion, the (mean absolute error (MAE) for the long-term forecast of 2023 is 107, outperforming the second-best Prophet (152) by 29.6%. Chinese cabbage, radish, and green onion all outperform the existing models with MAE of 2008, 3703, and 557, respectively. Moreover, using the confidence interval, the predicted price was categorized into three intervals: probability, caution, and warning. Comparing the percentage of classified intervals about the true prices in our test set, we found that they accurately detect the large price volatility.

A hybrid model to overcome landslide inventory incompleteness issue for landslide susceptibility prediction

Landslide inventory incompleteness (LII) may significantly affect the model performance in landslide susceptibility mapping (LSM). However, traditional methods, including heuristic, statistical and deterministic models, cannot address LII issue. In this work, we introduce a novel hybrid LEO-MAHP model, blending landslide frequency, empirical adjustments, optimization functions, and multi-participated analytic hierarchy process to address it by taking Badong County as the study area. This hybrid model mitigates the drawbacks of data-heavy statistical approaches and subjective heuristic models by incorporating LII into weight determination. The findings show that the LEO-MAHP model demonstrates superior performance (AUROC = 0.809 and 0.805) over conventional statistical (AUROC = 0.714 and 0.770) and heuristic models (AUROC = 0.738 and 0.741) across different LII levels. We further discuss alternative LII solutions, proposing an updated landslide management strategy that accounts for climate change and human activities. Our findings underscore the necessity of evaluating LII before applying statistical or machine learning methods in LSM.

A Quantile Generalized Additive Approach for Compound Climate Extremes: Pan‐Atlantic Extremes as a Case Study

AbstractWe present an application of quantile generalized additive models (QGAMs) to study spatially compounding climate extremes, namely extremes that occur (near‐) simultaneously in geographically remote regions. We take as an example wintertime cold spells in North America and co‐occurring wet or windy extremes in Western Europe, which we collectively term Pan‐Atlantic compound extremes. QGAMS are largely novel in climate science applications and present a number of key advantages over conventional statistical models of weather extremes. Specifically, they remove the need for a direct identification and parametrization of the extremes themselves, since they model all quantiles of the distributions of interest. They thus make use of all information available, and not only of a small number of extreme values. Moreover, they do not require any a priori knowledge of the functional relationship between the predictors and the dependent variable. Here, we use QGAMs to both characterize the co‐occurrence statistics and investigate the role of possible dynamical drivers of the Pan‐Atlantic compound extremes. We find that cold spells in North America are a useful predictor of subsequent wet or windy extremes in Western Europe, and that QGAMs can predict those extremes more accurately than conventional peak‐over‐threshold models.