Machine Learning Classification Models Research Articles

Correction to: Use of Machine Learning Models for Classification of Myographic Diseases

Correction to: Use of Machine Learning Models for Classification of Myographic Diseases

MALrisk: a machne-learning based tool to predict imported malaria in returned travellers with fever.

Early diagnosis is key to reducing the morbi-mortality associated with P. falciparum malaria among international travellers. However, access to microbiological tests can be challenging for some healthcare settings. Artificial Intelligence could improve the management of febrile travellers. Data from a multicentric prospective study of febrile travellers was obtained to build a machine-learning model to predict malaria cases among travellers presenting with fever. Demographic characteristics, clinical and laboratory variables were leveraged as features. Eleven machine-learning classification models were evaluated by 50-fold cross-validation in a Training set. Then, the model with the best performance, defined by the Area Under the Curve (AUC), was chosen for parameter optimization and evaluation in the Test set. Finally, a reduced model was elaborated with those features that contributed most to the model. Out of eleven machine-learning models, XGBoost presented the best performance (mean AUC of 0.98 and a mean F1 score of 0.78). A reduced model (MALrisk) was developed using only six features: Africa as a travel destination, platelet count, rash, respiratory symptoms, hyperbilirubinemia and chemoprophylaxis intake. MALrisk predicted malaria cases with 100% (95%CI 96-100) sensitivity and 72% (95%CI 68-75) specificity. The MALrisk can aid in the timely identification of malaria in non-endemic settings, allowing the initiation of empiric antimalarials and reinforcing the need for urgent transfer in healthcare facilities with no access to malaria diagnostic tests. This resource could be easily scalable to a digital application and could reduce the morbidity associated with late diagnosis.

Early Warning System of Attrition in the BPO Industry Using Machine Learning Classification Models

Employee attrition is one of the factors affecting gross margin erosion in the BPO industry, the fastest-growing industry in the Philippines, due to hiring and training costs. The cost of employee attrition depends on the employee's role and salary/wage level. This study proposed shifting the retention approach from reactive to proactive with the use of an early warning system for employee attrition. The early warning system was powered by Machine Learning Classification Models. The data used in this study are employees hired in 2021 and 2022 from one of the Telco/Communication programs in the BPO Industry. The data attributes considered in this study are composed of Employee status, Employee Performance, Employee Satisfaction, Payroll, Time Off History, Schedule, and employee Observation data. The data is trained and tested in the classification models (Decision Trees, rule-based classification, naïve Bayes, KNN, Logistic Regression, and Random Forest). Models are evaluated using the classification performance metrics (AUC, Accuracy, Precision, Recall, and F1 Score). The model with the highest predictive accuracy is selected and deployed to produce employee classification (Risk of Termination, Neutral, and Positive). This study mainly helps the company reduce turnover and costs and increase gross margin with the help of the early warning system that can predict the status of the employees using significant indicators.

Using Acuity to Predict Oncology Infusion Center Daily Nurse Staffing and Outcomes.

Outpatient oncology infusion centers (OICs) use acuity to quantify the complexity and intensity of care to improve staffing levels and equitable patient assignments. OIC interviews revealed inconsistent measurement of acuity and a mixture of use cases. No publications measured objective operational benefits beyond surveyed nurse satisfaction or compared different models of acuity. This study assessed three acuity models across multiple centers to determine whether acuity was superior to patient volumes or patient hours in predicting the number of nurses needed to care for scheduled patients in an OIC, as well as the effect on objective metrics of missed nurse lunch breaks and patient wait times. A secondary end point was used to identify a superior model. Classification machine learning models were built to assess the predictive value of three acuity models compared to patient hours and patient visits. None of the tested acuity models were found to have statistically significant improvement to the prediction of needed OIC nurse staffing, patient wait times, or missed nurse lunch breaks.

Identifying Predictors of Neck Disability in Patients with Cervical Pain Using Machine Learning Algorithms: A Cross-Sectional Correlational Study.

(1) Background: Neck pain intensity, psychosocial factors, and physical function have been identified as potential predictors of neck disability. Machine learning algorithms have shown promise in classifying patients based on their neck disability status. So, the current study was conducted to identify predictors of neck disability in patients with neck pain based on clinical findings using machine learning algorithms. (2) Methods: Ninety participants with chronic neck pain took part in the study. Demographic characteristics in addition to neck pain intensity, the neck disability index, cervical spine contour, and surface electromyographic characteristics of the axioscapular muscles were measured. Participants were categorised into high disability and low disability groups based on the median value (22.2) of their neck disability index scores. Several regression and classification machine learning models were trained and assessed using a 10-fold cross-validation method; also, MANCOVA was used to compare between the two groups. (3) Results: The multilayer perceptron (MLP) revealed the highest adjusted R2 of 0.768, while linear discriminate analysis showed the highest receiver characteristic operator (ROC) area under the curve of 0.91. Pain intensity was the most important feature in both models with the highest effect size of 0.568 with p < 0.001. (4) Conclusions: The study findings provide valuable insights into pain as the most important predictor of neck disability in patients with cervical pain. Tailoring interventions based on pain can improve patient outcomes and potentially prevent or reduce neck disability.

Research on a synchronised classification method for loose particle detection signals of aerospace-sealed electronic components

Aerospace-sealed electronic components exhibit favourable anti-interference capability and high reliability and are widely utilised in satellites, rockets, and missiles. Loose particle detection is crucial to ensure high reliability. However, the classification problem of loose particle detection signals based on the particle impact noise detection (PIND) method has been a challenge for the high reliability of aerospace-sealed electronic components. To address this issue, this paper systematically proposes a synchronised classification method based on PIND and validates its feasibility. The proposed approach combines a self-developed empirical model (referred to as algorithm 1) with a classical machine learning model (referred to as algorithm 2). The key findings are as follows: this method has a recognition rate for loose particle signals of 91.86%. Compared to a single algorithmic mode, the overall speed improves by 300%. The maximal recognition accuracy rates for component signals, mixed signals, and excessive signals are 90.03%, 81.04%, and 95.17%, respectively. The test results demonstrate that the method effectively balances the accuracy and speed of loose particle detection and leverages the complementary advantages of the two algorithms, thereby addressing the multi-classification issue of loose particle detection signals.

Thermophysical characterization of UFe3B2 and USiNi: An experimental study

In the development for advanced nuclear fuels for LWRs, the focus has traditionally centered on a limited array of materials like doped-UO2, UN, and U3Si2, leaving the vast majority of potential uranium compounds unexplored. To expand the search and expedite the discovery of advanced LWR fuels, we developed a machine learning (ML) classification model dedicated to identifying uranium compounds with excellent thermal conductivity. However, the model's predictive accuracy and the feasibility of such an ML-assisted approach to advanced nuclear fuel discovery have yet to be empirically validated. Therefore, this study examines the thermal properties of two uranium compounds, UFe3B2 and USiNi, that are predicted to outperform UO2 at high temperatures. Our findings confirm that the model precisely predicted the thermal conductivities of both compounds, thereby adding credibility to its reliability. However, the experimental process unveiled several challenges, such as the fabrication of single-phase USiNi and microcrack-free UFe3B2 samples, which our ML model, focused primarily on thermal conductivity, could not anticipate. These challenges underscore the need for a more comprehensive ML framework that considers the intricacies of sample fabrication. This advancement is crucial for the more efficient development of practical, accident-tolerant, advanced LWR fuels.

Predicting intubation for intensive care units patients: A deep learning approach to improve patient management

ObjectiveFor patients in the Intensive Care Unit (ICU), the timing of intubation has a significant association with patients' outcomes. However, accurate prediction of the timing of intubation remains an unsolved challenge due to the noisy, sparse, heterogeneous, and unbalanced nature of ICU data. In this study, our objective is to develop a workflow for pre-processing ICU data and to develop a customized deep learning model to predict the need for intubation. MethodsTo improve the prediction accuracy, we transform the intubation prediction task into a time series classification task. We carefully design a sequence of data pre-processing steps to handle the multimodal noisy data. Firstly, we discretize the sequential data and address missing data using interpolation. Next, we employ a sampling strategy to address data imbalance and standardize the data to facilitate faster model convergence. Furthermore, we employ the feature selection technique and propose an ensemble model to combine features learned by different deep learning models. ResultsThe performance is evaluated on Medical Information Mart for Intensive Care (MIMIC)-III, an ICU dataset. Our proposed Deep Feature Fusion method achieves an area under the curve (AUC) of the receiver operating curve (ROC) of 0.8953, surpassing the performance of other deep learning and traditional machine learning models. ConclusionOur proposed Deep Feature Fusion method proves to be a viable approach for predicting intubation and outperforms other deep learning and classical machine learning models. The study confirms that high-frequency time-varying indicators, particularly Mean Blood Pressure (MeanBP) and peripheral oxygen saturation (SpO2), are significant risk factors for predicting intubation.

Using machine learning with atomistic surface and local water features to predict heterogeneous ice nucleation.

Heterogeneous ice nucleation (HIN) has applications in climate science, nanotechnology, and cryopreservation. Ice nucleation on the earth's surface or in the atmosphere usually occurs heterogeneously involving foreign substrates, known as ice nucleating particles (INPs). Experiments identify good INPs but lack sufficient microscopic resolution to answer the basic question: What makes a good INP? We employ molecular dynamics (MD) simulations in combination with machine learning (ML) to address this question. Often, the large amount of computational cost required to cross the nucleation barrier and observe HIN in MD simulations is a practical limitation. We use information obtained from short MD simulations of atomistic surface and water models to predict the likelihood of HIN. We consider 153 atomistic substrates with some surfaces differing in elemental composition and others only in terms of lattice parameters, surface morphology, or surface charges. A range of water features near the surface (local) are extracted from short MD simulations over a time interval (≤300 ns) where ice nucleation has not initiated. Three ML classification models, Random Forest (RF), support vector machine, and Gaussian process classification are considered, and the accuracies achieved by all three approaches lie within their statistical uncertainties. Including local water features is essential for accurate prediction. The accuracy of our best RF classification model obtained including both surface and local water features is 0.89 ± 0.05. A similar accuracy can be achieved including only local water features, suggesting that the important surface properties are largely captured by the local water features. Some important features identified by ML analysis are local icelike structures, water density and polarization profiles perpendicular to the surface, and the two-dimensional lattice match to ice. We expect that this work, with its strong focus on realistic surface models, will serve as a guide to the identification or design of substrates that can promote or discourage ice nucleation.

Sex Differentiation of Trabecular Bone Structure Based on Textural Analysis of Pelvic Radiographs.

Objectives: The purpose of this paper is to assess the determination of male and female sex from trabecular bone structures in the pelvic region. The study involved analyzing digital radiographs for 343 patients and identifying fourteen areas of interest based on their medical significance, with seven regions on each side of the body for symmetry. Methods: Textural parameters for each region were obtained using various methods, and a thorough investigation of data normalization was conducted. Feature selection approaches were then evaluated to determine a small set of the most representative features, which were input into several classification machine learning models. Results: The findings revealed a sex-dependent correlation in the bone structure observed in X-ray images, with the degree of dependency varying based on the anatomical location. Notably, the femoral neck and ischium regions exhibited distinctive characteristics between sexes. Conclusions: This insight is crucial for medical professionals seeking to estimate sex dependencies from such image data. For these four specific areas, the balanced accuracy exceeded 70%. The results demonstrated symmetry, confirming the genuine dependencies in the trabecular bone structures.

Local privacy‐friendly verification of customer participation in frequency regulation services using smart meter data

AbstractThe delivery of flexibility from distributed assets guarantees the stable operation of the power system as increasing volumes of renewable energy are deployed. Nevertheless, verifying the adequate provision is challenging when considering behind‐the‐meter resources. A cost‐effective alternative to dedicated metring is using measurements from smart meters. However, flexibility activations must be discerned from the rest of the loads in the household. Furthermore, privacy issues arise since electricity consumption contains personal data. The authors tackle both issues by developing a data‐driven privacy‐friendly verification algorithm for participation in frequency containment reserves (FCRs). Our methodology evaluated three machine learning (ML) classification models, deployed locally, and fed with total consumption measurements and activation set points to verify users' participation. The amount of information that leaves the premises was reduced from low‐granularity power measurements to simple compliance indicators. The models were trained and evaluated using a real dataset of households, where FCR was delivered by behind‐the‐meter batteries, resulting in an accuracy close to 0.90. A proof‐of‐concept setup was employed to test the algorithms under real circumstances. Even with several background loads, an accuracy of up to 0.83 was observed, promising results considering the privacy‐friendly features, use of simple ML models, and embedded deployment.

Deep learning on pre-procedural computed tomography and clinical data predicts outcome following stroke thrombectomy

BackgroundDeep learning using clinical and imaging data may improve pre-treatment prognostication in ischemic stroke patients undergoing endovascular thrombectomy (EVT).MethodsDeep learning models were trained and tested on baseline clinical and imaging...

Machine learning-aided search for ligands of P2Y6 and other P2Y receptors.

The P2Y6 receptor, activated by uridine diphosphate (UDP), is a target for antagonists in inflammatory, neurodegenerative, and metabolic disorders, yet few potent and selective antagonists are known to date. This prompted us to use machine learning as a novel approach to aid ligand discovery, with pharmacological evaluation at three P2YR subtypes: initially P2Y6 and subsequently P2Y1 and P2Y14. Relying on extensive published data for P2Y6R agonists, we generated and validated an array of classification machine learning model using the algorithms deep learning (DL), adaboost classifier (ada), Bernoulli NB (bnb), k-nearest neighbors (kNN) classifier, logistic regression (lreg), random forest classifier (rf), support vector classification (SVC), and XGBoost (XGB) classifier models, and the common consensus was applied to molecular selection of 21 diverse structures. Compounds were screened using human P2Y6R-induced functional calcium transients in transfected 1321N1 astrocytoma cells and fluorescent binding inhibition at closely related hP2Y14R expressed in CHO cells. The hit compound ABBV-744, an experimental anticancer drug with a 6-methyl-7-oxo-6,7-dihydro-1H-pyrrolo[2,3-c]pyridine scaffold, had multifaceted interactions with the P2YR family: hP2Y6R inhibition in a non-surmountable fashion, suggesting that noncompetitive antagonism, and hP2Y1R enhancement, but not hP2Y14R binding inhibition. Other machine learning-selected compounds were either weak (experimental anti-asthmatic drug AZD5423 with a phenyl-1H-indazole scaffold) or inactive in inhibiting the hP2Y6R. Experimental drugs TAK-593 and GSK1070916 (100µM) inhibited P2Y14R fluorescent binding by 50% and 38%, respectively, and all other compounds by < 20%. Thus, machine learning has led the way toward revealing previously unknown modulators of several P2YR subtypes that have varied effects.

Data Disparity and Temporal Unavailability Aware Asynchronous Federated Learning for Predictive Maintenance on Transportation Fleets

Predictive maintenance has emerged as a critical application in modern transportation, leveraging sensor data to forecast potential damages proactively using machine learning. However, privacy concerns limit data sharing, making Federated learning an appealing approach to preserve data privacy. Nevertheless, challenges arise due to disparities in data distribution and temporal unavailability caused by individual usage patterns in transportation. In this paper, we present a novel asynchronous federated learning approach to address system heterogeneity and facilitate machine learning for predictive maintenance on transportation fleets. The approach introduces a novel data disparity aware aggregation scheme and a federated early stopping method for training. To validate the effectiveness of our approach, we evaluate it on two independent real-world datasets from the transportation domain: 1) oil dilution prediction of car combustion engines and 2) remaining lifetime prediction of plane turbofan engines. Our experiments show that we reliably outperform five state-of-the-art baselines, including federated and classical machine learning models. Moreover, we show that our approach generalises to various prediction model architectures.

Comparison of different machine learning classification models for predicting deep vein thrombosis in lower extremity fractures

Deep vein thrombosis (DVT) is a common complication in patients with lower extremity fractures. Once it occurs, it will seriously affect the quality of life and postoperative recovery of patients. Therefore, early prediction and prevention of DVT can effectively improve the prognosis of patients. This study constructed different machine learning models to explore their effectiveness in predicting DVT. Five prediction models were applied to the study, including Extreme Gradient Boosting (XGBoost) model, Logistic Regression (LR) model, RandomForest (RF) model, Multilayer Perceptron (MLP) model, and Support Vector Machine (SVM) model. Afterwards, the performance of the obtained prediction models was evaluated by area under the curve (AUC), accuracy, sensitivity, specificity, F1 score, and Kappa. The prediction performances of the models based on machine learning are as follows: XGBoost model (AUC = 0.979, accuracy = 0.931), LR model (AUC = 0.821, accuracy = 0.758), RF model (AUC = 0.970, accuracy = 0.921), MLP model (AUC = 0.830, accuracy = 0.756), SVM model (AUC = 0.713, accuracy = 0.661). On our data set, the XGBoost model has the best performance. However, the model still needs external verification research before clinical application.

Cancer Risk Identification using Machine Learning

In this comprehensive study, we explore the SEER (Surveillance, Epidemiology, and End Result) dataset to meticulously craft a predictive model aimed at understanding patient survivability, focusing keenly on outcomes like patient survival diagnosis and treatments. Employing a good approach involving rigorous data cleaning, intricate feature extraction, and detailed correlation analysis, we identify the dominant attributes that significantly influence patient outcomes. Our methodology integrates classical machine learning models, including decision trees and random forests, with modern techniques such as neural networks. This mix of methodologies allows us to accurately predict patient survivability. Furthermore, our study delves into the intricate relationships between attributes, models, and algorithms, aiming to identify the dominant factors that influence the outcomes. Our groundbreaking findings underscore the enormous potential of integrating these dominant attributes, paving the way for the creation of exceptionally robust predictive models. These models will substantially enhance medical decision-making processes and, in turn, elevate the overall quality of patient care. Keywords - SEER dataset, patient survivability, machine learning, decision trees, random forests, neural networks, data cleaning, feature extraction, clinical data, medical decision-making.

A Semantic-Spatial Aware Data Conflation Approach for Place Knowledge Graphs

Recent advances in knowledge graphs show great promise to link various data together to provide a semantic network. Place is an important part in the big picture of the knowledge graph since it serves as a powerful glue to link any data to its georeference. A key technical challenge in constructing knowledge graphs with location nodes as geographical references is the matching of place entities. Traditional methods typically rely on rule-based matching or machine-learning techniques to determine if two place names refer to the same location. However, these approaches are often limited in the feature selection of places for matching criteria, resulting in imbalanced consideration of spatial and semantic features. Deep feature-based methods such as deep learning methods show great promise for improved place data conflation. This paper introduces a Semantic-Spatial Aware Representation Learning Model (SSARLM) for Place Matching. SSARLM liberates the tedious manual feature extraction step inherent in traditional methods, enabling an end-to-end place entity matching pipeline. Furthermore, we introduce an embedding fusion module designed for the unified encoding of semantic and spatial information. In the experiment, we evaluate the approach to named places from Guangzhou and Shanghai cities in GeoNames, OpenStreetMap (OSM), and Baidu Map. The SSARLM is compared with several classical and commonly used binary classification machine learning models, and the state-of-the-art large language model, GPT-4. The results demonstrate the benefit of pre-trained models in data conflation of named places.

Unlocking maintenance insights in industrial text through semantic search

Maintenance records in Computerized Maintenance Management Systems (CMMS) contain valuable human knowledge on maintenance activities. These records primarily consist of noisy and unstructured texts written by maintenance experts. The technical nature of the text, combined with a concise writing style and frequent use of abbreviations, makes it difficult to be processed through classical Natural Language Processing (NLP) pipelines. Due to these complexities, this text must be normalized before feeding to classical machine learning models. Developing these custom normalization pipelines requires manual labor and domain expertise and is a time-consuming process that demands constant updates. This leads to the under-utilization of this valuable source of information to generate insights to help with maintenance decision support. This study proposes a Technical Language Processing (TLP) pipeline for semantic search in industrial text using BERT (Bidirectional Encoder Representations), a transformer-based Large Language Model (LLM). The proposed pipeline can automatically process complex unstructured industrial text and does not require custom preprocessing. To adapt the BERT model for the target domain, three unsupervised domain fine-tuning techniques are compared to identify the best strategy for leveraging available tacit knowledge in industrial text. The proposed approach is validated on two industrial maintenance records from the mining and aviation domains. Semantic search results are analyzed from a quantitative and qualitative perspective. Analysis shows that TSDAE, a state-of-the-art unsupervised domain fine-tuning technique, can efficiently identify intricate patterns in the industrial text regardless of associated complexities. BERT model fine-tuned with TSDAE on industrial text achieved a precision of 0.94 and 0.97 for mining excavators and aviation maintenance records, respectively.

Probing polymorph binding preference of CaCO3 biomineralization peptides through machine learning

Abstract An exploratory machine learning (ML) classification model that seeks to examine CaCO3 polymorph selection is presented. The ML model can distinguish if a given peptide sequence binds with calcite or aragonite, polymorphs of CaCO3. The classifier, which was created using SVM and amino acid chemical composition as the input descriptors, yielded satisfactory performance in the classification task, as characterized by AUC = 0.736 and F1 = 0.800 in the test set. Model optimization revealed that tiny, aliphatic, aromatic, acidic, and basic residues are essential descriptors for discriminating aragonite biomineralization peptides from calcite. The presented model offers valuable insights on the significant chemical attributes of biomineralization peptides involved in polymorph binding preference. This can deepen our understanding about the biomineralization phenomenon and may be deployed in the future for the creation biomimetic materials.

Exploring the Feasibility of Applying Deep Learning for the Early Prediction of Arthritis

Introduction: Arthritis is one of the most common chronic diseases. Early detection of arthritis and its progression can facilitate early intervention measures, lowering disease severity in patients. As electronic health records (EHR) become more accessible, this study assesses whether general health information and arthritis-related questionnaires can be used in arthritis diagnosis, without the involvement of costly imaging methods. Therefore, we created deep learning (DL) and machine learning (ML) models to explore the feasibility of combining EHR and modern computational tools to diagnose arthritis. Methods: A total of 782 arthritis patients and 4014 control patients were identified from the Osteoarthritis Initiative (OAI) – a ten-year-long observational study that included patient EHR in five time points. Six hundred variables were filtered by random forest classifier followed by manual filtering. Data were split properly to training, testing and validation set, and the training set was balanced. Sequential, nonsequential DL models, and five independent DL models for each time points were used. The accuracy, positive prevalence value (PPV), negative prevalence value (NPV), and area under curve (AUC), were assessed and compared with four classical ML models. SHAP (SHapley Additive exPlanations) summary analysis was also conducted. Results: Sequential and non-sequential deep learning models showed accuracies of ~ 0.97, and the four classical machine learning approaches showed accuracies of above 0.9. High positive and negative predicted values (&gt; 0.90) for all of the models suggested the potential clinical applicability of the model, while the SHAP analysis demonstrated its interpretability. Discussion: We tested various models and showed the ability to use machine learning methods for early diagnosis of arthritis with EHR. The models can be used as a screening tool to select susceptible patients for confirmatory tests such as X-ray and MRI. Identification of early disease states could facilitate protective measures that slow disease progression.