Prediction Model Research Articles

Proactive cervical cancer risk assessment using data-driven analytics

This study introduces a sophisticated predictive model integrating clinical and lifestyle data addressing the critical public health challenge of cervical cancer, particularly in regions lacking routine screenings. Leveraging data driven analytics, the proposed model undergoes comprehensive preprocessing, including exploratory data analysis, missing value imputation, and feature extraction. Feature selection is carried out using the XGBoost classifier to ensure model efficacy. Data normalization and class balance via oversampling techniques are applied, with model validation conducted through stratified cross-validation. The optimized feature vector is then employed to train a LightGBM model. Utilizing a retrospective dataset of 858 patients from the Hospital Universitario de Caracas, Venezuela, comprising demographic, lifestyle, and medical history data, the LightGBM model achieves an impressive accuracy of 98%, outperforming similar existing approaches. The study outcome demonstrates the effectiveness of the proposed data modelling framework and feature selection, along with the choice of LightGBM as a suitable classifier. The proposed predictive framework can efficiently aid healthcare professionals in prioritizing high-risk patients for further evaluation and intervention.

Predicting Rolling Element Bearings’ Deterioration Vibration Trend based on Limited Historical Data for a Desired Confidence Level using Machine Learning Algorithms

Predicting the deterioration trend of bearings and determining the optimal replacement time is crucial for maintenance teams to effectively manage consumable parts, enhance equipment reliability, and prevent potential breakdowns. Given the common practice of periodic condition monitoring based on vibrations in large industries, utilizing this data to forecast future vibration trends is a key focus of this research. Considering the limited availability of data in industrial settings, it is essential for the model used to be capable of working with minimal data. To address these challenges, a run-to-failure test has been conducted on an industrial bearing sample, with its vibration data recorded. Acknowledging the impact of operational variations and uncertainties in vibration behavior even among identical bearings, leveraging the bearing’s vibration history for predictive modeling has been deemed critical. This study proceeds in three distinct phases: selecting the key characteristic for predicting its deterioration trend, identifying the feature to pinpoint the failure onset, and determining the most suitable model for forecasting future bearing vibration states. RMS has emerged as the optimal characteristic for trend prediction, while Peak and Kurtosis have been identified as effective indicators for failure onset detection. The selection of the deterioration estimation model has involved comparing the outcomes of SVR + Bootstrapping and RVR models under various limited data scenarios. Ultimately, the RVR method has proved superior, requiring just three data points for estimation and delivering results with a confidence level leading to an accuracy of approximately 94% for the analyzed bearing.

Predicting Therapeutic Response to Hypoglossal Nerve Stimulation Using Deep Learning.

To develop and validate machine learning (ML) and deep learning (DL) models using drug-induced sleep endoscopy (DISE) images to predict the therapeutic efficacy of hypoglossal nerve stimulator (HGNS) implantation. Patients who underwent DISE and subsequent HGNS implantation at a tertiary care referral center were included. Six DL models and five ML algorithms were trained on images from the base of tongue (BOT) and velopharynx (VP) from patients classified as responders or non-responders as defined by Sher's criteria (50% reduction in apnea-hypopnea index (AHI) and AHI < 15 events/h). Precision, recall, F1 score, and overall accuracy were evaluated as measures of performance. In total, 25,040 images from 127 patients were included, of which 16,515 (69.3%) were from responders and 8,262 (30.7%) from non-responders. Models trained on the VP dataset had greater overall accuracy when compared to BOT alone and combined VP and BOT image sets, suggesting that VP images contain discriminative features for identifying therapeutic efficacy. The VCG-16 DL model had the best overall performance on the VP image set with high training accuracy (0.833), F1 score (0.78), and recall (0.883). Among ML models, the logistic regression model had the greatest accuracy (0.685) and F1 score (0.813). Deep neural networks have potential to predict HGNS therapeutic efficacy using images from DISE, facilitating better patient selection for implantation. Development of multi-institutional data and image sets will allow for development of generalizable predictive models. NA Laryngoscope, 134:5210-5216, 2024.

Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling.

Video Coding for Machines (VCM) aims to compress visual signals for machine analysis. However, existing methods only consider a few machines, neglecting the majority. Moreover, the machine's perceptual characteristics are not leveraged effectively, resulting in suboptimal compression efficiency. To overcome these limitations, this paper introduces Satisfied Machine Ratio (SMR), a metric that statistically evaluates the perceptual quality of compressed images and videos for machines by aggregating satisfaction scores from them. Each score is derived from machine perceptual differences between original and compressed images. Targeting image classification and object detection tasks, we build two representative machine libraries for SMR annotation and create a large-scale SMR dataset to facilitate SMR studies. We then propose an SMR prediction model based on the correlation between deep feature differences and SMR. Furthermore, we introduce an auxiliary task to increase the prediction accuracy by predicting the SMR difference between two images in different quality. Extensive experiments demonstrate that SMR models significantly improve compression performance for machines and exhibit robust generalizability on unseen machines, codecs, datasets, and frame types.

Machine learning powered predictive modelling of complex residual stress for nuclear fusion reactor design

Fusion In-vessel components, assembled and maintained using laser welding, one of the most promising techniques, exhibit complex distributions of residual stress, microstructures, and material properties. These residual stresses can compromise structural integrity and lifespan of critical components. Although using advanced experimental measurements can evaluate the residual stress for individual case, extending the measurements to massive number of components are costly and time-consuming. Traditional machine learning (ML) models struggle to account for the heterogeneity and anisotropy of these stress distributions. Here, we develop a novel ML framework based on the Eurofer97 steel, the structural material for in-vessel components. The ML framework is trained on high-resolution residual stress data derived from recently-developed evaluation techniques. Combining with microstructures, the model enables prediction of heterogenous and anisotropic residual stress distribution. It successfully predicts the compressive residual stress in fusion zone (∼−200 MPa) balanced by tensile residual stress in heat affected zone (∼300 MPa), aligning closely with experimental results with the R-squared value of 0.989 and the mean square error of 10−4. Unlike experiments that take hours, the ML model provides predictions within seconds. It offers valuable insights into residual stress prediction for various joints, enhancing the reliability and lifetime prediction of in-vessel components.

Variable speed limit control strategy considering traffic flow lane assignment in mixed-vehicle driving environment

To accurately predict traffic flow and optimize the operations of freeway bottleneck areas in a mixed-vehicle driving environment, this paper proposes a traffic prediction model and a variable speed limit (VSL) cooperative control strategy. Firstly, a lane-level short-term traffic prediction model, physics informed Transformer and cell transmission model (PIT-CTM), is constructed by combining the Transformer neural network and lane-level cell transmission model (CTM) based on the physics-informed deep learning framework. On this basis, the accuracy and transferability of PIT-CTM are analysed. Secondly, a lane assignment decision model is presented, which enables the dynamic planning of the optimal traffic distribution across lanes. Furthermore, a lane-level VSL control model is constructed based on the model predictive control (MPC) framework. The model induces vehicles to change lanes earlier by setting the speed limit difference between lanes. By regulating the input flow in the bottleneck area of the freeway, it reduces conflicts between mainline vehicles and ramp vehicles. Finally, the feedback regulation between the lane assignment decision model and the lane-level VSL control model promotes the cooperative optimisation of the lateral and longitudinal flows and adapts the control strategy to the dynamic traffic characteristics. A three-lane freeway merging zone is selected, the numerical experiment is conducted and compared with differential lane-level VSL. The results show that the strategy can effectively optimise the mixed-vehicle traffic state and maintain better control performance under any connected and autonomous vehicle (CAV) penetration rates.

Patterns of Gene Expression Profiles Associated with Colorectal Cancer in Colorectal Mucosa by Using Machine Learning Methods.

Colorectal cancer (CRC) has a very high incidence and lethality rate and is one of the most dangerous cancer types. Timely diagnosis can effectively reduce the incidence of colorectal cancer. Changes in para-cancerous tissues may serve as an early signal for tumorigenesis. Comparison of the differences in gene expression between para-cancerous and normal mucosa can help in the diagnosis of CRC and understanding the mechanisms of development. This study aimed to identify specific genes at the level of gene expression, which are expressed in normal mucosa and may be predictive of CRC risk. A machine learning approach was used to analyze transcriptomic data in 459 samples of normal colonic mucosal tissue from 322 CRC cases and 137 non-CRC, in which each sample contained 28,706 gene expression levels. The genes were ranked using four ranking methods based on importance estimation (LASSO, LightGBM, MCFS, and mRMR) and four classification algorithms (decision tree [DT], K-nearest neighbor [KNN], random forest [RF], and support vector machine [SVM]) were combined with incremental feature selection [IFS] methods to construct a prediction model with excellent performance. The top-ranked genes, namely, HOXD12, CDH1, and S100A12, were associated with tumorigenesis based on previous studies. This study summarized four sets of quantitative classification rules based on the DT algorithm, providing clues for understanding the microenvironmental changes caused by CRC. According to the rules, the effect of CRC on normal mucosa can be determined.

Nondestructive detection of multiple qualities of dried jujube in different storage periods based on hyperspectral imaging combined with deep learning

Moisture content and sugar content are characteristic substances that determine the quality of dried jujubes. In this study, we collected visible/near-infrared and near-infrared hyperspectral data (Vis-NIR and NIR) from three dried jujubes samples with different storage periods, and established recognition models for different storage periods of jujubes using Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Deep Learning Methods (LeNet, ResNet, DenseNet, MobileNet and EfficientNet). Then, we constructed a dried jujubes storage period classification model based on feature bands using Successive projections algorithm (SPA) and Principal component analysis (PCA) methods, the results showed that the classification results based on Vis-NIR were better than those based on NIR, and the classification model based on SPA method was more accurate. In addition, the internal quality attributes of moisture content and total sugar during a single storage period of jujube were also predicted, and a quality prediction model for multiple storage periods was established based on NIR. This study provides a fast and non-destructive method for detecting the storage and quality components of jujube, in order to control the quality of jujube at different storage periods.

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.

Prediction Model for Underweight among Age Under-five Children in Community Health Center of Banjar

Prediction Model for Underweight among Age Under-five Children in Community Health Center of Banjar

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

&lt;p align="center"&gt;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.&lt;/p&gt;

Vibration fatigue of film cooling hole structure of Ni-based single crystal turbine blade: Failure behavior and life prediction

The vibration fatigue failure behavior and fatigue life of the film cooling hole (FCH) structure of Ni-based single crystal superalloy were investigated at high temperature. The vibration fatigue test of the FCH specimens were carried out based on the paired staircase method. The cracks are mostly initiated in the stress concentration area at the edge of the FCH, and may also be initiated in non-stress concentrated areas with large defects. At high temperature, the crack initiation mechanism of the FCH specimens of Ni-based single crystal superalloy is oxidative cracking nucleation in stress concentration area, and the crack propagation mechanism is the competition mechanism of dislocation slip and dislocation climbing. Based on the Fatigue Indicator Parameter (FIP) of the critical plane method, a vibration fatigue life prediction model for FCH structures considering stress concentration and high temperature oxidation damage is proposed. The life prediction model proposed in this paper is applied to the vibration fatigue life prediction of FCH specimens. The deviation between the predicted results and the experimental results is within 2.5 times at 850℃, and the deviation is within 2 times at 980℃. Besides, the life prediction method proposed is compared with other two FIP life prediction methods, and the high accuracy and effectiveness of the proposed life prediction method are verified.

HiMolformer: Integrating graph and sequence representations for predicting liver microsome stability with SMILES

In the initial stages of drug discovery or pre-clinical studies, understanding the metabolic stability of new molecules is crucial. Recently, research on pre-trained deep learning for molecular property prediction has been actively progressing, with various models being made open-source. However, most of these models rely on either 2D graph or 1D sequence for training, and the representation varies depending on the data format used. Consequently, combining multiple representations can broaden the scope of learning and may potentially be a manageable and most effective method to enhance performance.Therefore, we propose a novel hybrid model for predicting metabolic stability, which integrates representations from both graph-based and sequence-based models pre-trained for molecular features. This approach utilizes the combined strengths of 2D topological and 1D sequential information of molecules. HiMol, a graph-based graph neural network (GNN) model, and Molformer, a sequence-based Transformer model, were selected for integration, thus we named it HiMolformer. HiMolformer demonstrated superior performance compared to other models. We also focus on regression task for prediction with a empirical dataset from Korea Chemical Bank (KCB), comprising 3,498 molecules with mouse liver microsome (MLM) and human liver microsome (HLM) data obtained from actual metabolic reaction experiments. To the best of our knowledge, it is the first attempt to develop MLM and HLM prediction models using regression with a single SMILES input. The source code of this model is available at https://github.com/YUNSEOKWOO/HiMolformer.

Performance prediction of a pump as a turbine using energy loss analysis

As interest in renewable energy sources grows, interest in small-scale hydropower development and utilization increases. The development of micro- and small-scale hydropower plants is challenging, mainly due to the high cost of hydraulic turbines. If the turbine mode performance can be predicted accurately before installation, pumps as turbines (PATs) are an excellent alternative for small-scale hydropower generation. In this study, a theoretical procedure using a detailed energy loss analysis to determine PAT's energy losses is developed, and a non-dimensional performance prediction model is presented. The models were implemented to determine the pressure, head, torque, power, and efficiency across a wide range of flow rates. This work clearly characterizes the effects of individual losses, thereby acknowledging their influence. The prediction results were tested at ten different flow rates, ranging from 50 % to 180 %. The model result was validated through experiments using a hydro-pump test rig developed at the Bahir Dar Institute of Technology at Bahir Dar University. The numerical and model results have good agreement with the experimental results. at BEP The experimental result gives a 1.6 flow rate, 1.72 head ratios, and an efficiency of 76.53 %, 78.09 %, and 74.04 % using analytical, numerical, and experimental methods, respectively. The PAT off-design efficiency decreases sharply below BEP and smoothly above BEP. At BEP, the CFD and analytical results deviated by −2.04 % and 3.08 %, respectively, from the experimental results. Further, the detailed energy loss analysis revealed that the volute frictional (12.1 %), the throat frictional (11.9 %), the inlet pipe frictional (11.2 %), the impeller frictional (9.4 %), and the volute diffusion (8.9 %) losses take the major energy losses sequentially. This provides full insight for applying performance optimization measures.

Predicting Electricity Consumption using an Innovative Deep Energy Predictor Model for Enhanced Accuracy and Efficiency

Accurate forecasting of electricity consumption is crucial for efficient energy management and planning. Traditional models often struggle to capture the complex, nonlinear relationships inherent in energy consumption data, leading to less reliable predictions. In the quest to improve the accuracy and efficiency of electricity consumption predictions, we introduce the Deep Energy Predictor Model (DEPM). This innovative hybrid model combines the strengths of XGBoost for classification and Deep Neural Networks (DNN) for deep learning (DL) capabilities. The model leverages advanced feature extraction techniques using Cascaded ResNet, ensuring the capture of intricate patterns within the data. Implemented in Python, the DEPM highlights an impressive accuracy of 98%, with a precision of 0.97, recall of 0.99, and an F1-score of 0.98, setting a new standard for predictive models in the energy sector. This study elaborates on the model architecture, implementation details, and the evaluation metrics that underscore the model's superior performance. Our results demonstrate the potential of DEPM to significantly enhance the reliability of electricity consumption forecasts, providing a robust tool for energy management and planning.

Associations between volatile organic compounds exposure and multiple oxidative damage biomarkers: Method development, human exposure, and application for e-waste pollution prediction

Atmospheric monitoring studies reveal substantial health risks from exposure to volatile organic compounds (VOCs) for workers and nearby children in e-waste recycling areas (ERA), yet internal exposure risks are seldom examined. To address this, we developed a method to simultaneously analyze 12 urinary VOC metabolites (mVOCs) and oxidative damage biomarkers (ODBs) in workers and children from ERA and general adults from control areas using ultrahigh performance liquid chromatography coupled with quadrupole/orbitrap high-resolution mass spectrometry (UPLC-Orbitrap-HRMS). The results showed that e-waste workers exhibited significantly higher levels of VOC exposure and ODBs than e-waste children and control adults. Exceeding 91.1 %, 69.1 %, 20.8 %, 19.7 %, and 3.26 % of e-waste workers faced non-carcinogenic risk from exposure to acrolein, acrylonitrile, acrylamide, 1,3-butadiene, and 1,2-dichloroethane, respectively. The weighted quantile sum, quantile g-computation, and Bayesian kernel machine regression models consistently indicated significant positive associations between these VOC mixtures and cholesterol ODB levels (i.e., glycocholic acid, cholic acid, and glycochenodeoxycholic acid), highlighting the necessity for improved protective measures for occupational workers. Interestingly, cholesterol ODBs significantly mediated the association between VOCs exposure and nucleic acid ODBs, accounting for 12.0–26.0 % of the association with 8-hydroxy-2′-deoxyguanosine (an oxidative DNA damage biomarker) and 25.4–53.4 % with 8-hydroxyguanosine (an oxidative RNA damage biomarker). This suggests that cholesterol ODBs potentially serve as better indicators of health risks from VOC exposure than nucleic acid ODBs. Additionally, the combination of mVOCs and ODBs (Mean AUC: 0.906, ACC: 0.821) as exposure fingerprints outperformed either mVOCs (Mean AUC: 0.878, ACC: 0.802) or ODBs (Mean AUC: 0.843, ACC: 0.768) alone in predicting the presence of e-waste pollution, underscoring the importance of integrating exposure and effect biomarker fingerprints to accurately capture e-waste pollution characteristic. Our findings offer a novel approach for screening e-waste pollution in unknow e-waste recycling sites and provide a foundation for developing high-precision prediction models for other polluting industries.

The generation mechanism of cutting heat and the theoretical prediction model for temperature on the rake face of the cutting tool in Zirconia ceramics

Cutting temperature and its distribution are crucial factors influencing tool strength and wear rate, due to the hardness and brittleness of Zirconia (ZrO2) ceramics, significant challenges arise in both direct temperature measurement in the cutting zone and theoretical analysis of cutting heat. Thus, focusing on the turning characteristics of ZrO2 ceramics, this study analyzes the mechanism of cutting heat generation and proposes utilizing thermodynamic state equations to determine the cutting heat source on rake face of tool. Based on the heat source method, a theoretically prediction model for temperature distribution on rake face is established. This model considers primary cutting parameters, workpiece material properties, crack fracture characteristics of the machined surface, and thermal characterizations of the tool material. The relationship between tool wear and cutting temperature is experimentally analyzed to determine the characteristic temperature that indicates the initial stage of tool wear. The validity of the theoretical model is verified, as the predicted results show high consistency with experimental results within the range of experimental parameters, with a relative error within 15.2 %.The results reveal the highest temperature during brittle cutting occurs within the cutting layer area, with the highest temperature occurring approximately 50 μm from the tool tip, followed by a gradual decrease beyond 150-200 μm. This study also demonstrates that cutting heat in ceramic turning does not solely originate from friction heat between tool flank-workpiece but also includes impact heat from tool rake face-workpiece, which under certain cutting parameters exerts a more significant influence on cutting temperature. This model can facilitate the selection and optimization of cutting process parameters for brittle materials and provide a theoretical basis for analyzing the relationship between tool thermal damage, thermophysical properties, and tool wear.

The interaction between incentive and opportunity in corporate tax planning: Evidence from financially constrained firms

Prior studies document that incentive factors (i.e., equity compensation, shareholder activism, financial constraints, etc.) motivate managers to avoid more taxes, which suggests that managers overlook tax planning opportunities (TPOs) in the absence of incentives. In this study, I use a prediction model to capture TPOs and find that the positive association between financial constraints (my proxy for incentive) and tax avoidance is stronger for firms with higher levels of TPOs. My results are robust to a variety of identification strategies. To shed light on a possible source of tax uncertainty, I show moderate evidence that firms with lower levels of TPOs adopt risky tax planning strategies under financial constraints to increase tax avoidance. Overall, my study contributes to the literature by demonstrating corporate tax planning as an incentive-opportunity story and identifying an important cross-section in which the connection between incentive and tax avoidance is more prominent.

Development, Validation, and Clinical Utility of Electronic Patient-Reported Outcome Measure-Enhanced Prediction Models for Overall Survival in Patients With Advanced Non-Small Cell Lung Cancer Receiving Immunotherapy.

Electronic patient-reported outcome measures (ePROMs) are increasingly collected routinely in clinical practice and may be prognostic for survival in adults with advanced non-small cell lung cancer (NSCLC) in addition to clinical data. This study developed ePROM-enhanced models for predicting 1-year overall survival in patients with advanced NSCLC at the start of immunotherapy. This is a single-center study using consecutive patients from a tertiary cancer hospital in England. Using Cox proportional hazards models, we developed one clinical factor-only model and three ePROM-enhanced models, each including one of the following factors: quality of life (as measured by EuroQoL five-dimension five-level utility score) and overall symptom burden and number of moderate-to-severe symptoms (as measured by patient-reported version of Common Terminology Criteria for Adverse Events). Predictive performance was evaluated and compared through bootstrapping internal validation, and clinical utility was determined via decision curve analysis. The clinical factor-only model contained age, histology, performance status, and neutrophile-to-lymphocyte ratio. While calibration was similar between the clinical factor-only and ePROM-enhanced models, the latter showed improved discrimination by 0.020 (95% CI, 0.011 to 0.024), 0.024 (95% CI, 0.016 to 0.031), and 0.024 (95% CI, 0.014 to 0.029) when enhanced with ePROMs on quality of life, overall symptom burden, and number of moderate-to-severe symptoms, respectively. If care decisions are to be made at risk thresholds between 25% and 75%, the ePROM-enhanced models led to higher net benefit than the clinical factor-only model and the default strategies of intervention for all and intervention for none. The ePROM-enhanced models outperformed the clinical factor-only model in predicting 1-year overall survival for patients with advanced NSCLC receiving immunotherapy and showed potential clinical utility for informing decisions in this population. Future studies should focus on validating the models in external data sets.

Mechanical performance and strength prediction model of demountable RC columns with a novel bolts-flange connection

Mechanical performance and strength prediction model of demountable RC columns with a novel bolts-flange connection