Use Of Machine Learning Approaches Research Articles

An ensemble machine learning framework with explainable artificial intelligence for predicting haemoglobin anaemia considering haematological markers

Anaemia is a disorder marked by low blood levels of haemoglobin (HGB), affecting people of all ages and ethnicities and is a major global public health concern. Anaemia must be diagnosed as soon as possible to enable prompt treatment and intervention, which can reduce complications and enhance patient outcomes. With the ability to improve diagnostic precision and expedite patient care procedures, machine learning (ML) has become a potent instrument in the healthcare industry. Hence, we examine the use of ML approaches to predict haemoglobin-like anaemia in this research article. Based on a heterogeneous dataset of blood markars, we investigate the performance of many machine learning techniques such as Logistic Regression, CatBoost, XgBoost Decision Trees, KNN and others. The algorithms are further ensembled using a customized stacking approach. The ML models' judgments are interpreted using explainable artificial intelligence (XAI) methods. The xgboost and the stacking classifier obtained an accuracy, precision and recall of 99% each. Our research shows how ML models can help with the early diagnosis and treatment of anaemia, which will ultimately lead to better patient outcomes and healthcare results. Overall, the research shows how ML emphasizes the value of interdisciplinary cooperation in solving challenging medical problems.

Artificial intelligence-driven predictive framework for early detection of still birth

Predictive modeling is becoming increasingly popular in the context of early disease detection. The use of machine learning approaches for predictive modeling can help early detection of diseases thereby enabling medical experts to appropriate medical treatments. Stillbirth prediction is a similar domain where artificial intelligence-based predictive modeling can alleviate this significant global health challenge. Despite advancements in prenatal care, the prevention of stillbirths remains a complex issue requiring further research and interventions. The cardiotocography (CTG) dataset is used in this research work from the UCI machine learning (ML) repository to investigate the efficiency of the proposed approach regarding stillbirth prediction. This research work adopts the Tabular Prior Data Fitted Network (TabPFN) model which was originally designed to solve small tabular classification. TabPFN is used to predict the still or live birth during pregnancy with 97.91% accuracy. To address this life-saving problem with more accurate results and in-depth analysis of ML models, this research work makes use of 13 renowned ML models for performance comparison with the proposed model. The proposed model is evaluated using precision, recall, F-score, Mathews Correlation Coefficient (MCC), and the area under the curve evaluation parameters and the results are 97.87%, 98.26%, 98.05%, 96.42%, and 98.88%, respectively. The results of the proposed model are further evaluated using k-fold cross-validation and its performance comparison with other state-of-the-art studies indicating the superior performance of TabPFN model.

An Ensemble Method for the Fraud Detection in Transactions

In today's world, bank fraud has become one of the significant threats to the financial stability and security of clients of financial institutions. The development of technologies, in particular in the field of machine learning, opens up wide opportunities for building effective systems for detecting and preventing fraud in the banking sector [1, 2]. Detecting fraudulent transactions is an important task that requires thoughtful and technological solutions. One of these methods is the use of machine learning approaches and methods. This paper proposes the use of an ensemble method that combines several machine learning models at once. This approach will reduce the probability of false positives and increase classification accuracy. In addition, for the optimal operation of the model, preprocessing of the data will be carried out, in particular, their normalization, balancing of classes, as well as the selection of features. During the research, it is important not only to achieve high accuracy, but also to reduce as much as possible the number of fraudulent transactions that will be mistakenly classified as normal [3]. This is related to the business requirements of the banking sector, as each such transaction causes losses to the system's reputation, as well as direct financial losses. Within the framework of the study, it is substantiated that the use of this approach gives better classification results than single models due to the compensation of the shortcomings of each of them. The choice of this approach is also due to high practicality, compatibility with financial systems, as well as ease of integration. This paper analyzes the proposed model, its advantages and disadvantages in comparison with analogues. The ensemble method helps to combine the advantages of simple models and reduce the impact of their shortcomings on the final result. In general, the choice of software should depend on the technical requirements of the project and to obtain better results, different models and approaches should be analyzed.

Challenges Reconciling Theory and Experiments in the Prediction of Lattice Thermal Conductivity: The Case of Cu-Based Sulvanites.

The exploration of large chemical spaces in search of new thermoelectric materials requires the integration of experiments, theory, simulations, and data science. The development of high-throughput strategies that combine DFT calculations with machine learning has emerged as a powerful approach to discovering new materials. However, experimental validation is crucial to confirm the accuracy of these workflows. This validation becomes especially important in understanding the transport properties that govern the thermoelectric performance of materials since they are highly influenced by synthetic, processing, and operating conditions. In this work, we explore the thermal conductivity of Cu-based sulvanites by using a combination of theoretical and experimental methods. Previous discrepancies and significant variations in reported data for Cu3VS4 and Cu3VSe4 are explained using the Boltzmann Transport Equation for phonons and by synthesizing well-characterized defect-free samples. The use of machine learning approaches for extracting high-order force constants opens doors to charting the lattice thermal conductivity across the entire Cu-based sulvanite family-finding not only materials with κ l values below 2 W m-1 K-1 at moderate temperatures but also rationalizing their thermal transport properties based on chemical composition.

An effective imaging based diagnosis of Solar Photovoltaic System and performance parameters for smart solar power grid

Another of the most attractive power generation sources for residential, corporate, and commercial operations is energy production. Due to this compelling qualities, photovoltaic systems (PV) electricity production have increasingly attracted the attention of researchers and professionals. Nonetheless, the greatest obstacle in generating energy from the sun is the predictable discontinuous output power from photovoltaic (PV) systems, which is largely caused by climate. The power differential of a photovoltaic panels may considerably reduce the financial profit of large scale solar fields. For everyday proper management of electricity supply production, distribution, and storing as well as for judgement on the electricity market, results were consistent prediction of the electricity output of solar PV systems is essential. The 5 subjects mentioned in this article are: The varied faults which might occur in PV panels; internet Photovoltaic panels monitoring; Use of machine learning approaches in Photovoltaic module damage detection; Advantages of fault diagnosis in PV panels and the various motion sensors used for this purpose are discussed. Recommendation for future possible research paths are given in view of the evaluated research.

Virtual screening of drug materials for pharmaceutical tablet manufacturability with reference to sticking

The manufacturing of pharmaceutical solid dosage forms, such as tablets involves a large number of successive processing operations including crystallisation of the drug substance, granulation, drying, milling, mixing of the formulation, and compaction. Each step is fraught with manufacturing problems. Undesired adhesion of powders to the surface of the compaction tooling, known as sticking, is a frequent and highly disruptive problem that occurs at the very end of the process chain when the tablet is formed. As an alternative to the mechanistic approaches to address sticking, we introduce two different machine learning strategies to predict sticking directly from the chemical formula of the drug substance, represented by molecular descriptors. An empirical database for sticking behaviour was developed and used to train the machine learning (ML) algorithms to predict sticking properties from molecular descriptors. The ML model has successfully classified sticking/non-sticking behaviour of powders with 100% separation. Predictions were made for materials in the handbook of Pharmaceutical Excipients and a subset of molecules included in the ChemBL database, demonstrating the potential use of machine learning approaches to screen for sticking propensity early at drug discovery and development stages. This is the first-time molecular descriptors and machine learning were used to predict and screen for sticking behaviour. The method has potential to transform the development of medicines by providing manufacturability information at drug screening stage and is potentially applicable to other manufacturing problems controlled by the chemistry of the drug substance.

INSAFEDARE Project: Innovative Applications of Assessment and Assurance of Data and Synthetic Data for Regulatory Decision Support.

Digital health solutions hold promise for enhancing healthcare delivery and patient outcomes, primarily driven by advancements such as machine learning, artificial intelligence, and data science, which enable the development of integrated care systems. Techniques for generating synthetic data from real datasets are highly advanced and continually evolving. This paper aims to present the INSAFEDARE project's ambition regarding medical devices' regulation and how real and synthetic data can be used to check if devices are safe and effective. The project will consist of three pillars: a) assurance of new state-of-the-art technologies and approaches (such as synthetic data), which will support the validation methods as part of regulatory decision-making; b) technical and scientific, focusing on data-based safety assurance, as well as discovery, integration and use of datasets, and use of machine learning approaches; and c) delivery to practice, through co-production involving relevant stakeholders, dissemination and sustainability of the project's outputs. Finally, INSAFEDARE will develop an open syllabus and training certification for health professionals focused on quality assurance.

Machine learning quantification of Amyloid-β deposits in the temporal lobe of 131 brain bank cases

Accurate and scalable quantification of amyloid-β (Aβ) pathology is crucial for deeper disease phenotyping and furthering research in Alzheimer Disease (AD). This multidisciplinary study addresses the current limitations on neuropathology by leveraging a machine learning (ML) pipeline to perform a granular quantification of Aβ deposits and assess their distribution in the temporal lobe. Utilizing 131 whole-slide-images from consecutive autopsied cases at the University of California Davis Alzheimer Disease Research Center, our objectives were threefold: (1) Validate an automatic workflow for Aβ deposit quantification in white matter (WM) and gray matter (GM); (2) define the distributions of different Aβ deposit types in GM and WM, and (3) investigate correlates of Aβ deposits with dementia status and the presence of mixed pathology. Our methodology highlights the robustness and efficacy of the ML pipeline, demonstrating proficiency akin to experts’ evaluations. We provide comprehensive insights into the quantification and distribution of Aβ deposits in the temporal GM and WM revealing a progressive increase in tandem with the severity of established diagnostic criteria (NIA-AA). We also present correlations of Aβ load with clinical diagnosis as well as presence/absence of mixed pathology. This study introduces a reproducible workflow, showcasing the practical use of ML approaches in the field of neuropathology, and use of the output data for correlative analyses. Acknowledging limitations, such as potential biases in the ML model and current ML classifications, we propose avenues for future research to refine and expand the methodology. We hope to contribute to the broader landscape of neuropathology advancements, ML applications, and precision medicine, paving the way for deep phenotyping of AD brain cases and establishing a foundation for further advancements in neuropathological research.

Use of machine learning approaches to predict transition of retention in care among people living with HIV in South Carolina: a real-world data study

ABSTRACT Maintaining retention in care (RIC) for people living with HIV (PLWH) helps achieve viral suppression and reduce onward transmission. This study aims to identify the best machine learning model that predicts the RIC transition over time. Extracting from the enhanced HIV/AIDS reporting system, this study included 9765 PLWH from 2005 to 2020 in South Carolina. Transition of RIC was defined as the change of RIC status in each two–year time window. We applied seven classifiers, such as Random Forest, Support Vector Machine, eXtreme Gradient Boosting and Long–short–term memory, for each lagged response to predict the subsequent year's RIC transition. Classification performance was assessed using balanced prediction accuracy, the area under the curve (AUC), recall, precision and F1 scores. The proportion of the four categories of RIC transition was 13.59%, 29.78%, 9.06% and 47.57%, respectively. Support Vector Machine was the best approach for every lag model based on both the F1 score (0.713, 0.717 and 0.719) and AUC (0.920, 0.925 and 0.928). The findings could facilitate the risk augment of PLWH who are prone to follow–up so that clinicians and policymakers could come up with more specific strategies and relocate resources for intervention to keep them sustained in HIV care.

Altered serum concentrations of IL-8, IL-32 and IL-10 in patients with lung impairment 6 months after COVID-19

Post-COVID symptoms are reported in 10–35 % of patients not requiring hospitalization, and in up to 80 % of hospitalized patients and patients with severe disease. The pathogenesis of post-COVID syndrome remains largely unknown. Some evidence suggests that prolonged inflammation has a key role in the pathogenesis of most post-COVID manifestations. We evaluated a panel of inflammatory and immune-mediated cytokines in individuals with altered HRCT features and in patients without any long-term COVID symptoms. Blood samples of 89 adult patients previously hospitalized with COVID-19 were collected and stratified as patients with and without HRCT evidence of fibrotic lung alterations. Serum analyte concentrations of IL-4, IL-2, CXCL10 (IP-10), IL-1β, TNF-α, CCL2 (MCP-1), IL-17A, IL-6, IL-10, IFN-γ, IL-12p70 and TGF-β1 (free active form) were quantified by bead-based multiplex assay. Clinical and functional data were recorded in a database.With the use of machine learning approach, IL-32, IL-8, and IL-10 proved to be associated with the development of HRCT evidence of lung sequelae at follow-up. Direct comparison of cytokine levels in the two groups showed increased levels of IL-32 and decreased levels of IL-8 in patients with lung impairment. After further stratification of patients by severity (severe versus mild/moderate) during hospitalization, IL-10 emerged as the only cytokine showing decreased levels in severe patients. These findings contribute to a better understanding of the immune response and potential prognostic markers in patients with lung sequelae after COVID-19.

Making the most of AI and machine learning in organizations and strategy research: Supervised machine learning, causal inference, and matching models

AbstractResearch SummaryWe spotlight the use of machine learning in two‐stage matching models to deal with sample selection bias. Recent advances in machine learning have unlocked new empirical possibilities for inductive theorizing. In contrast, the opportunities to use machine learning in regression studies involving large‐scale data with many covariates and a causal claim are still less well understood. Our core contribution is to guide researchers in the use of machine learning approaches to choosing matching variables for enhanced causal inference in propensity score matching models. We use an analysis of real‐world technology invention data of public–private relationships to demonstrate the method and find that machine learning can provide an alternative approach to ad hoc matching. However, as with any method, it is also important to understand its limitations.Managerial SummaryThis article explores the use of machine learning to enhance decision‐making, particularly in addressing sample selection bias in large‐scale datasets. The rapid development of AI and machine learning offers new, powerful tools especially for digital ecosystems where complex data and causal relationships are complex to analyze. We offer managers and stakeholders insight into the effective integration of machine learning for selecting critical variables in propensity score matching models. Through a detailed examination of real‐world data on technology inventions within public–private relationships, we demonstrate the effectiveness of machine learning as a robust alternative to traditional matching methods.

Survey on Stock Market Prediction using Deep Learning

The share market is a very unpredictable entity that is extremely sensitive to different sorts of criteria. Substantial research has been done in the field of financial markets projection to discover the many characteristics and elements connected with price volatility. The routine movements of the financial markets is exceedingly turbulent and dynamic. It is impacted by a large number of underlying elements and intricate interactions, resulting in a substantial percentage of non linearity. According to certain beliefs on the behavior of the financial markets, stock exchange progression is entirely unpredictable. Therefore, to achieve effective prediction of the stock markets through the use of machine learning approaches a number of related works have been analyzed. This analysis has allowed for the development of a useful and highly effective methodology that will be discussed in the upcoming editions of this research article. Key Words: K Nearest Neighbors, Long Short Term Memory, Stock Market Prediction.

Application of machine learning on hydrate formation prediction of pure components with water and inhibitors solution

AbstractThe present work investigates the use of machine learning approaches for the prediction of hydrate formation pressure (HFP) in gas hydrate systems. Advanced machine learning models, including the decision tree regressor (DTR), random forest regressor (RFR), extreme gradient boosting (XGB), gradient boosting regressor (GBR), histogram gradient boosting regressor (HGBR), and CatBoost regressor (CB), are trained and evaluated on a large dataset consists of 3137 experimental data points. The models are evaluated using R‐squared (R2), mean squared error (MSE), mean absolute error (MAE), and root mean squared error (RMSE). The study indicates that for the intent of HFP prediction, CatBoost outperformed all other machine learning models. It demonstrated high accuracy on the testing set with an R2 value of 0.9922, and with the lowest RMSE (1.61 × 10−3), MAE (7.90 × 10−4), and MSE (2.58 × 10−6), CatBoost strengthened its prediction ability.

Machine Learning-Based Identification of False Profiles

In the current digital era, phony profiles are a problem for social media sites like Instagram. An important problem that has surfaced on these platforms is the increase in phony profiles, which can result in fraud, false information, and privacy violations, among other problems. Because of the huge number of users, manually identifying bogus profiles takes a lot of effort and is frequently ineffective. This study explores the use of machine learning approaches for Instagram false profile detection. The study uses Random Forest methods and artificial neural networks (ANN) to identify patterns suggestive of fraudulent accounts by utilizing a large dataset. The accuracy with which these approaches can identify bogus profiles is evaluated through a thorough process of experimentation and evaluation. The outcomes demonstrate how well ANN and Random Forest work to differentiate between real Keywords - Fake profile detection,Social media fraud detection, Machine learning, ANN.

Transient bending analysis of the graphene nanoplatelets reinforced sandwich concrete building structure validated by machine learning algorithm

This paper demonstrates a thorough examination of the bending behavior of sandwich concrete building structures that are reinforced with graphene nanoplatelets (GPLs). The analysis is confirmed using a machine learning technique. Sandwich structures have notable benefits in terms of strength, longevity, and thermal insulation, making them well-suited for many building applications. Integrating GPLs into the concrete matrix improves the mechanical characteristics and performance of these structures, especially in terms of bending behavior. This study utilizes a machine learning technique to verify the characterization of the temporary bending behavior of a concrete building structure reinforced with graphene nanoplatelets. The approach utilizes a dataset consisting of simulated bending data to create a prediction model that can reliably estimate the temporary bending response of the reinforced structure under different loading situations. The machine learning algorithm’s effectiveness and dependability in optimizing the design and performance of graphene nanoplatelets reinforced sandwich concrete building structures are demonstrated through validation against simulated results. This provides engineers and designers with a powerful tool. This study enhances the comprehension and use of machine learning approaches in analyzing and designing sophisticated structural materials and systems.

Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI

Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.

CHRONIC KIDNEY DISEASE DETECTION USING ENSEMBLE LEARNING TECHNIQUES AND COMPARATIVE STUDY

A common health problem around the globe, chronic kidney disease (CKD) must be identified early in order to be effectively managed. The accuracy of CKD diagnosis may be increased with the use of machine learning approaches, especially ensemble learning. In order to determine which model performs best for CKD detection, this research will compare and contrast several ensemble learning strategies. Ten distinct models are evaluated in the study: Bagging, Random Forest, Gradient Boosting, Ada Boosting, XGBoost, K-Nearest Neighbours (KNN), Decision Tree, Decision Tree after Pruning, Logistic Regression, and Linear Discriminant Analysis. A CKD dataset is used to evaluate these models based on criteria including accuracy, precision score, and recall score. The comparative study results demonstrate how ensemble learning techniques might raise CKD detection accuracy. The findings provide crucial details about the optimal model for CKD detection, which can help with early diagnosis and better patient outcomes. KEYWORDS: Chronic Kidney Disease (CKD), Ensemble Learning, Machine Learning, Accuracy, Early Diagnosis

Machine Learning Approaches of Lung Cancer Image Processing for Detecting and Identifying Various Stages of Analysis

The current paper is aimed at examining the use of machine learning approaches for lung cancer detection and classification using medical imaging data. In order to create the model, we collected a comprehensive dataset of 2400 images of lung cancer at different stages and healthy pictures. These data were preprocessed, and several approaches to the feature extraction were considered, namely Histogram of Oriented Gradients , and Local Binary Patterns . In addition, we attempted to use deep learning representations to determine their usefulness in this case. Moreover, these features were used for four ML models, namely Convolutional Neural Network , ResNet-18, , and VGG-19, to determine the most suitable one. To evaluate the general performance of these models, all the characteristic points were taken into account, such as the precision, recall, F1 score, accuracy, and confusion matrices. The results of the primary analysis indicate that the accuracy of our proposed model was the highest, 96.86%. The other places were taken by other deep learning architectures, which also demonstrate high level performance. In general, we may conclude that the findings show it is possible to use ML algorithms to improve the quality of clinical decisions and make the process of lung cancer detection and classification more accurate. At the same time, we were able to provide a comprehensive evaluation of all these results and the thorough analysis of the general performance of each model. This may serve as the basis for the subsequent improvements and changes that would allow enhancing the general quality of diagnostics and training more advanced models.

Bandgap prediction of non-metallic crystals through machine learning approach.

The determination of bandgap is the heart of electronic structure of any material and is a crucial factor for thermoelectric performance of it. Due to large amount to data (features) that are related to bandgap are now a days available, it is possible to make use of machine learning (ML) approach to predict the bandgap of the material. The study commences by selecting the feature through Pearson correlation study between bandgap and various thermoelectric parameters in non-metallic crystals. Among the 42 parameters available in the dataset, the Seebeck coefficient and its corresponding temperatures show high correlation with the bandgap. With these three selected features we have used different ML models like multilinear regression, polynomial regression, random forest regression and support vector regression to predict the bandgap. Amongst the different ML models considered, random forest regression outperforms the other models to predict the bandgap withR2value of 97.55% between actual bandgap and predicted bandgap.

Application of machine learning for identification of heterotic groups in sunflower through combined approach of phenotyping, genotyping and protein profiling

Application of machine learning in plant breeding is a recent concept, that has to be optimized for precise utilization in the breeding program of high yielding crop plants. Identification and efficient utilization of heterotic grouping pattern aided with machine learning approaches is of utmost importance in hybrid cultivar breeding as it can save time and resources required to breed a new plant hybrid/variety. In the present study, 109 genotypes of sunflower were investigated at morphological, biochemical (SDS-PAGE) and molecular levels (through micro-satellites (SSR) markers) for heterotic grouping. All the three datasets were combined, scaled, and subjected to unsupervised machine learning algorithms, i.e., Hierarchical clustering, K-means clustering and hybrid clustering algorithm (hierarchical + K-means) for assessment of efficiency and resolution power of these algorithms in practical plant breeding for heterotic grouping identification. Following the application of machine learning unsupervised clustering approach, two major groups were identified in the studied sunflower germplasm, and further classification revealed six smaller classes in each major group through hierarchical and hybrid clustering approach. Due to high resolution, obtained in hierarchical clustering, classification achieved through this algorithm was further used for selection of potential parents. One genotype from each smaller group was selected based on the maximum seed yield potential and hybridized in a line × tester mating design producing 36 F1 cross combinations. These F1s along with their parents were studied in open field conditions for validating the efficacy of identified heterotic groups in sunflowers genetic material under study. Data for 11 agronomic and qualitative traits were recorded. These 36 F1 combinations were tested for their combining ability (General/Specific), heterosis, genotypic and phenotypic correlation and path analysis. Results suggested that F1 hybrids performed better for all the traits under investigation than their respective parents. Findings of the study validated the use of machine learning approaches in practical plant breeding; however, more accurate and robust clustering algorithms need to be developed to handle the data noisiness of open field experiments.