Application Of Machine Learning Approaches Research Articles

Nanopore sequencing of intact aminoacylated tRNAs.

Transfer RNAs (tRNA) are decorated during biogenesis with a variety of modifications that modulate their stability, aminoacylation, and decoding potential during translation. The complex landscape of tRNA modification presents significant analysis challenges and to date no single approach enables the simultaneous measurement of important but disparate chemical properties of individual, mature tRNA molecules. We developed a new, integrated approach to analyze the sequence, modification, and aminoacylation state of tRNA molecules in a high throughput nanopore sequencing experiment, leveraging a chemical ligation that embeds the charged amino acid in an adapted tRNA molecule. During nanopore sequencing, the embedded amino acid generates unique distortions in ionic current and translocation speed, enabling application of machine learning approaches to classify charging status and amino acid identity. Specific applications of the method indicate it will be broadly useful for examining relationships and dependencies between tRNA sequence, modification, and aminoacylation.

High-Throughput Approaches to Engineer Fluorescent Nanosensors.

Optical sensors are powerful tools to identify and image (biological) molecules. Because of their optoelectronic properties, nanomaterials are often used as building blocks. To transduce the chemical interaction with the analyte into an optical signal, the interplay between surface chemistry and nanomaterial photophysics has to be optimized. Understanding these aspects promises major opportunities for tailored sensors with optimal performance. However, this requires methods to create and explore the many chemical permutations. Indeed, many current approaches are limited in throughput. This affects the chemical design space that can be studied, the application of machine learning approaches as well as fundamental mechanistic understanding. Here, an overview of selection-limited and synthesis-limited approaches is provided to create and identify molecular nanosensors. Bottlenecks are discussed and opportunities of non-classical recognition strategies are highlighted such as corona phase molecular recognition as well as the requirements for high throughput and scalability. Fluorescent carbon nanotubes are powerful building blocks for sensors and their huge chemical design space makes them an ideal platform for high throughput approaches. Therefore, they are the focus of this article, but the insights are transferable to any nanosensor system. Overall, this perspective aims to provide a fresh perspective to overcome current challenges in the nanosensor field.

Abstract 4138355: Machine Learning for Prediction of All-Cause Mortality in Acute Coronary Syndrome

Background: Acute coronary syndrome (ACS) remains one of the leading causes of death globally. Accurate and reliable mortality risk prediction of ACS patients is essential for developing targeted treatment strategies. Existing traditional models offer moderate discriminative value, and do not incorporate contemporary predictors of ACS prognosis. Machine learning (ML) models have emerged as an alternate method that may offer improved risk assessment. This study aims to compare machine learning models with traditional risk scores for predicting all-cause mortality in patients with ACS. Methods: PubMed, EMBASE, Web of Science and Cochrane databases were searched until 1 st November 2023 for studies comparing ML models with traditional statistical methods for event prediction of ACS patients. The primary outcome was comparative discrimination measured by C-statistics with 95% confidence intervals between ML models and traditional methods in estimating the risk of all-cause mortality. Results: Ten studies were included (239627 patients). The summary C-statistic of all ML models across all endpoints was 0.89 (95% CI, 0.86-0.92), compared to traditional methods 0.82 (95% CI, 0.79-0.85). The difference in C-statistic between all ML models and traditional methods was 0.07 (p<0.05). Three models undertook external validation, and calibration was inconsistently reported. Conclusion: ML models demonstrated superior discrimination of all-cause mortality for ACS patients compared to traditional risk scores. Despite outperforming well-established prognostic tools such as the GRACE and TIMI scores, current clinical applications of ML approaches remain uncertain, particularly in view of the methodological limitations of existing studies and the need for greater model validation.

Machine learning for prediction of all-cause mortality in acute coronary syndrome

Abstract Background Acute coronary syndrome (ACS) remains one of the leading causes of death globally. Accurate and reliable mortality risk prediction of ACS patients is essential for developing targeted treatment strategies and improve prognostication. Traditional models for risk stratification such as the Global Registry of Acute Coronary Events (GRACE) and the Thrombolysis In Myocardial Infarction (TIMI) risk scores offer moderate discriminative value, and do not incorporate contemporary predictors of ACS prognosis. Machine learning (ML) models have emerged as an alternate method that may offer improved risk assessment. This study aims to compare machine learning models with traditional risk scores for predicting all-cause mortality in patients with ACS. Methods PubMed, EMBASE, Web of Science and Cochrane databases were searched until 1st November 2023 for studies comparing ML models with traditional statistical methods for event prediction of ACS patients. The primary outcome was comparative discrimination measured by C-statistics with 95% confidence intervals between ML models and traditional methods in estimating the risk of all-cause mortality. Results Ten studies were included (239627 patients). The summary C-statistic of all ML models across all endpoints was 0.89 (95% CI, 0.86-0.92), compared to traditional methods 0.82 (95% CI, 0.79-0.85). The difference in C-statistic between all ML models and traditional methods was 0.07 (p<0.05). Three models undertook external validation, and calibration was inconsistently reported. Conclusion ML models demonstrated superior discrimination of all-cause mortality for ACS patients compared to traditional risk scores. Despite outperforming well-established prognostic tools such as the GRACE and TIMI scores, current clinical applications of ML approaches remain uncertain, particularly in view of the methodological limitations of existing models and the need for greater validation.

Retraction Note: Landscape aesthetic quality assessment of forest lands: an application of machine learning approach

Retraction Note: Landscape aesthetic quality assessment of forest lands: an application of machine learning approach

A Machine Learning Approach to Classifying EEG Data Collected with or without Haptic Feedback during a Simulated Drilling Task.

Artificial Intelligence (AI), computer simulations, and virtual reality (VR) are increasingly becoming accessible tools that can be leveraged to implement training protocols and educational resources. Typical assessment tools related to sensory and neural processing associated with task performance in virtual environments often rely on self-reported surveys, unlike electroencephalography (EEG), which is often used to compare the effects of different types of sensory feedback (e.g., auditory, visual, and haptic) in simulation environments in an objective manner. However, it can be challenging to know which aspects of the EEG signal represent the impact of different types of sensory feedback on neural processing. Machine learning approaches offer a promising direction for identifying EEG signal features that differentiate the impact of different types of sensory feedback during simulation training. For the current study, machine learning techniques were applied to differentiate neural circuitry associated with haptic and non-haptic feedback in a simulated drilling task. Nine EEG channels were selected and analyzed, extracting different time-domain, frequency-domain, and nonlinear features, where 360 features were tested (40 features per channel). A feature selection stage identified the most relevant features, including the Hurst exponent of 13-21 Hz, kurtosis of 21-30 Hz, power spectral density of 21-30 Hz, variance of 21-30 Hz, and spectral entropy of 13-21 Hz. Using those five features, trials with haptic feedback were correctly identified from those without haptic feedback with an accuracy exceeding 90%, increasing to 99% when using 10 features. These results show promise for the future application of machine learning approaches to predict the impact of haptic feedback on neural processing during VR protocols involving drilling tasks, which can inform future applications of VR and simulation for occupational skill acquisition.

Application of machine learning approaches to predict ammonium nitrogen transport in different soil types and evaluate the contribution of control factors

The loss of nitrogen in soil damages the environment. Clarifying the mechanism of ammonium nitrogen (NH4+-N) transport in soil and increasing the fixation of NH4+-N after N application are effective methods for improving N use efficiency. However, the main factors are not easily identified because of the complicated transport and retardation factors in different soils. This study employed machine learning (ML) to identify the main influencing factors that contribute to the retardation factor (Rf) of NH4+-N in soil. First, NH4+-N transport in the soil was investigated using column experiments and a transport model. The Rf (1.29 – 17.42) was calculated and used as a proxy for the efficacy of NH4+-N transport. Second, the physicochemical parameters of the soil were determined and screened using lasso and ridge regressions as inputs for the ML model. Third, six machine learning models were evaluated: Adaptive Boosting, Extreme Gradient Boosting (XGB), Random Forest, Gradient Boosting Regression, Multilayer Perceptron, and Support Vector Regression. The optimal ML model of the XGB model with a low mean absolute error (0.81), mean squared error (0.50), and high test r2 (0.97) was obtained by random sampling and five-fold cross-validation. Finally, SHapely Additive exPlanations, entropy-based feature importance, and permutation characteristic importance were used for global interpretation. The cation exchange capacity (CEC), total organic carbon (TOC), and Kaolin had the greatest effects on NH4+-N transport in the soil. The accumulated local effect offered a fundamental insight: When CEC > 6 cmol+ kg−1, and TOC > 40 g kg−1, the maximum resistance to NH4+-N transport within the soil was observed. This study provides a novel approach for predicting the impact of the soil environment on NH4+-N transport and guiding the establishment of an early-warning system of nutrient loss.

Patient-derived organoid biobank identifies epigenetic dysregulation of intestinal epithelial MHC-I as a novel mechanism in severe Crohn’s Disease

ObjectiveEpigenetic mechanisms, including DNA methylation (DNAm), have been proposed to play a key role in Crohn’s disease (CD) pathogenesis. However, the specific cell types and pathways affected as well as...

Revisiting the Application of Machine Learning Approaches in Predicting Aqueous Solubility.

The solubility of chemical substances in water is a critical parameter in pharmaceutical development, environmental chemistry, agrochemistry, and other fields; however, accurately predicting it remains a challenge. This study aims to evaluate and compare the effectiveness of some of the most popular machine learning modeling methods and molecular featurization techniques in predicting aqueous solubility. Although these methods were not implemented in a competitive environment, some of their performance surpassed previous benchmarks, offering gradual but significant improvements. Our results show that methods based on graph convolution and graph attention mechanisms demonstrated exceptional predictive abilities with high-quality data sets, albeit with a sensitivity to data noise and errors. In contrast, models leveraging molecular descriptors not only provided better interpretability but also showed more resilience when dealing with inherent noise and errors in data. Our analysis of over 4000 molecular descriptors used in various models identified that approximately 800 of these descriptors make a significant contribution to solubility prediction. These insights offer guidance and direction for future developments in solubility prediction.

Comparative Study of ANN and SVM Model Network Performance for Predicting Brake Power in SI Engines Using E15 Fuel

Currently, artificial neural networks (ANNs) and support vector machines (SVMs) are the most common applications of machine learning approaches. In this study, a comparative study of ANN and SVM is presented to evaluate the performance of each model in predicting the brake power (BP) of GX35-OHC 4-stroke, air-cooled, single cylinder gasoline engine with E15 (15% ethanol + 85% gasoline) fuel. Two models are compared based on experimental dataset that has single output (BP) and five inputs, engine speed (S), engine torque (T), intake air temperature (Tair), intake air flow (Qair), and fuel consumption (ṁ). The samples were split into three sets: Training set (70%), Validation set (15%), and the Test set (15%) based on 60 samples. The results are compared through different graphs such as target vs actual values, regression plots, histograms of prediction errors, residual plots, learning curves, and error distributions. The results showed that SVM model is indicated to have lower RMSE (0.0044) and higher EVS (0.9953), while ANN is shown to have lower value of MAPE (1.51%). These results have significant implications for the use of ANN and SVM models in real-world applications that need gradual comprehensibility and model generalization. In addition, work done with the models outlined above should try and test them in other engines and operating conditions to demonstrate the model’s and performance.

Introducing a novel approach for assessment of groundwater salinity hazard, vulnerability, and risk in a semiarid region

The application of machine learning approaches to improve groundwater salinity risk mapping is limited despite all potential advantages. Therefore, there is an ongoing need for investigations that present new techniques, like machine learning, validated against conventional methods. These advances are particularly important for arid and semiarid regions, such as the Bakhtegan Basin (southern Iran), where groundwater use may far outweigh recharge, but groundwater management improvements are essential. To address these needs, groundwater salinity hazard, vulnerability, and risk maps were investigated using an integrated application of statistical (i.e., frequency ratio and statistical index models), machine learning (i.e., random forest and classification and regression trees algorithms), and decision-making models (fuzzy analytic hierarchy process (FAHP)). Results showed that the risk of groundwater salinity was high in the central areas of the region as well as at the margins of Bakhtegan Lake and irrigated farming lands. Based on the modeling results in the testing phase, it was found that the frequency ratio and random forest models exhibited better performance, with Nash–Sutcliffe efficiency metrics of 0.73 and 0.70, respectively, compared to the classification and regression trees and statistical index models, which had Nash–Sutcliffe efficiency metrics of 0.65 and 0.63, respectively. The innovative techniques developed in the current work accurately identified variables such as normalized difference salinity index, distance from mines, and land use associated with the highest weight values (0.59, 0.14, and 0.11, respectively) compared to other variables to identify groundwater salinity areas of vulnerability. The application of the fuzzy analytic hierarchy process method in developing vulnerability maps, integrating them with hazard maps, and developing groundwater salinity risk maps was innovative in this study. The innovative approach is transferrable for groundwater salinity susceptibility, vulnerability, and risk assessments globally in the study area and similar settings.

Application of machine learning approaches for predicting hemophilia A severity

BackgroundHemophilia A (HA) is an X-linked congenital bleeding disorder, which leads to deficiency of clotting factor (F) VIII. It mostly affects males, and females are considered carriers. However, it is now recognized that variants of F8 in females can result in HA. Nonetheless, most females go undiagnosed and untreated for HA, and their bleeding complications are attributed to other causes. Predicting the severity of HA for female patients can provide valuable insights for treating the conditions associated with the disease, such as heavy bleeding. ObjectivesTo predict the severity of HA based on F8 genotype using a machine learning (ML) approach. MethodsUsing multiple datasets of variants in the F8 and disease severity from various repositories, we derived the sequence for the FVIII protein. Using the derived sequences, we used ML models to predict the severity of HA in female patients. ResultsUtilizing different classification models, we highlight the validity of the datasets and our approach with predictive F1 scores of 0.88, 0.99, 0.93, 0.99, and 0.90 for all the validation sets. ConclusionAlthough with some limitations, ML-based approaches demonstrated the successful prediction of disease severity in female HA patients based on variants in the F8. This study confirms previous research findings that ML can help predict the severity of hemophilia. These results can be valuable for future studies in achieving better treatment and clinical outcomes for female patients with HA, which is an urgent unmet need.

Application of Machine Learning Approaches in Particle Tracking Model to Estimate Sediment Transport in Natural Streams

Application of Machine Learning Approaches in Particle Tracking Model to Estimate Sediment Transport in Natural Streams

Improving structure-based protein-ligand affinity prediction by graph representation learning and ensemble learning.

Predicting protein-ligand binding affinity presents a viable solution for accelerating the discovery of new lead compounds. The recent widespread application of machine learning approaches, especially graph neural networks, has brought new advancements in this field. However, some existing structure-based methods treat protein macromolecules and ligand small molecules in the same way and ignore the data heterogeneity, potentially leading to incomplete exploration of the biochemical information of ligands. In this work, we propose LGN, a graph neural network-based fusion model with extra ligand feature extraction to effectively capture local features and global features within the protein-ligand complex, and make use of interaction fingerprints. By combining the ligand-based features and interaction fingerprints, LGN achieves Pearson correlation coefficients of up to 0.842 on the PDBbind 2016 core set, compared to 0.807 when using the features of complex graphs alone. Finally, we verify the rationalization and generalization of our model through comprehensive experiments. We also compare our model with state-of-the-art baseline methods, which validates the superiority of our model. To reduce the impact of data similarity, we increase the robustness of the model by incorporating ensemble learning.

Application of machine learning approach (artificial neural network) and shrinking core model in cobalt (II) and copper (II) leaching process

The leaching laboratory experiment uses the artificial neural network (ANN) to predict and evaluate copper and cobalt recovery. This study aimed to evaluate the efficacy of using the shrinking core model in conjunction with an artificial neural network (ANN) as part of a machine learning strategy to improve the leaching process of cobalt (II) and copper (II). The numerous factors in the leaching process, such as acid concentration, leaching time, temperature, soil-to-solution ratio, and stirring speed, are adjusted using an ANN with several layers, feed-forward, and back-propagation learning methods. These variables are in charge of the high cobalt recovery during the reduced sulfuric acid leaching procedure. The ANN algorithm has 10 hidden layers, 5 input variables describing the leaching parameters, and two neurons as output layers corresponding to copper and cobalt leaching recovery. The optimum conditions were found to be acid concentration of 100 g/L, leaching duration 120 min, temperature 55 °C, soil-to-solution ratio of 1:40 g/mL, and stirring speed 300 rpm. The optimized trained neural networks tested, trained, and validated steps are represented by R 2 values of 0.94, 0.99, 0.97, and 0.97, respectively, equating to 97.5% copper recovery and 95.4% cobalt recovery.

Application of machine learning approach for iron deficiency anaemia detection in children using conjunctiva images

Iron deficiency is commonly referred to as anaemia which is a general public health problem that normally occurs as a result of a reduction in red blood cells which is common in developing countries such as Africa. In this study, machine learning algorithms such as CNN, k-NN, Naïve Bayes, Decision Tree and SVM were utilized for the study to detect anaemia in children using conjunctiva images. The images were segmented into their various CIELAB colour space components and the ROI from each image was retrieved. The dataset was split randomly into 70:10:20, which were then used to train, validate, and test the models, as appropriate. The CNN achieved the highest accuracy (98.45 %). The findings of this study demonstrate that non-invasive techniques are essential for detecting anaemia in children. This study deploys a cost-effective mechanism, and result-orientated, to detect anaemia in developing communities where health facilities, resources, and personnel are scarce.

Deep Brain Stimulation (DBS) in Treatment-Resistant Depression (TRD): Hope and Concern.

In this chapter, we explore the historical evolution, current applications, and future directions of Deep Brain Stimulation (DBS) for Treatment-Resistant Depression (TRD). We begin by highlighting the early efforts of neurologists and neurosurgeons who laid the foundations for today's DBS techniques, moving from controversial lobotomies to the precision of stereotactic surgery. We focus on the advent of DBS, emphasizing its emergence as a significant breakthrough for movement disorders and its extension to psychiatric conditions, including TRD. We provide an overview of the neural networks implicated in depression, detailing the rationale for the choice of common DBS targets. We also cover the technical aspects of DBS, from electrode placement to programming and parameter selection. We then critically review the evidence from clinical trials and open-label studies, acknowledging the mixed outcomes and the challenges posed by placebo effects and trial design. Safety and ethical considerations are also discussed. Finally, we explore innovative directions for DBS research, including the potential of closed-loop systems, dual stimulation strategies, and noninvasive alternatives like ultrasound neuromodulation. In the last section, we outline recommendations for future DBS studies, including the use of alternative designs for placebo control, the collection of neural and behavioral recordings, and the application of machine-learning approaches.

The application of machine learning approaches to determine the predictors of anemia among under five children in Ethiopia

Health professionals need a strong prediction system to reach appropriate disease diagnosis, particularly for under-five child with health problems like anemia. Diagnosis and treatment delay can potentially lead to devastating disease complications resulting in childhood mortality. However, the application of machine learning techniques using a large data set provides scientifically sounded information to solve such palpable critical health and health-related problems. Therefore, this study aimed to determine the predictors of anemia among under-5 year’s age children in Ethiopia using a machine learning approach. A cross-sectional study design was done using the Ethiopian Demographic and Health Survey 2016 data set. A two-stage stratified cluster sampling technique was employed to select the samples. The data analysis was conducted using Statistical Package for Social Sciences/SPSS version 25 and R-software. Data were derived from Ethiopian Demographic and Health Survey. Boruta algorism was applied to select the features and determine the predictors of anemia among under-5 years-old children in Ethiopia. The machine learning algorism showed that number of children, distance to health facilities, health insurance coverage, youngest child’s stool disposal, residence, mothers’ wealth index, type of cooking fuel, number of family members, mothers’ educational status and receiving rotavirus vaccine were the top ten important predictors for anemia among under-five children. Machine-learning algorithm was applied to determine the predictors of anemia among under- 5 year’s age children in Ethiopia. We have identified the determinant factors by conducting a feature importance analysis with the Boruta algorithm. The most significant predictors were number of children, distance to health facility, health insurance coverage, youngest child’s stool disposal, residence, mothers’ wealth index, and type of cooking fuel. Machine learning model plays a paramount role for policy and intervention strategies related to anemia prevention and control among under-five children.

Fault detection in beam structure using adaptive immune based approach

Different structural and machine elements are used over the ages. These are subjected to various loads like static and dynamic load, temperature, corrosion etc. Due to the above-mentioned reasons, ageing of the structural elements occur. So, to enhance the designed lifetime of any structure continuous maintenance is required. One such method has been proposed in this research work and the proposed method can be employed as an online tool for the fault identification. Here dynamic analysis of structure has been conducted as the forward method to find out the modal natural frequencies related with the damage. Recently with the application of machine learning approaches and the soft computing, the damage can be detected easily. In this methodology, Clonal Section Algorithm (CSA) has been applied to find out the faults (crack locations and depth) in the structure initially. Later one such method has been developed in the concepts of adaptive immune based technique (Adaptive Clonal Section Algorithm-ACSA) which is the combination of an artificial immune (Clonal Selection Algorithm) and Regression Analysis (RA). The use of regression analysis makes the proposed method more adaptive and the residual error in the collection of vibration data is reduced. The mechanism and various steps involved in CSA, RA and ACSA are analyzed here in a precise manner. The key endeavor of this study is the development of ACSA and its implementation to condition monitoring of structure. To authenticate and check the accuracy of both the methods (CSA and ACSA), laboratory tests are carried out. The results obtained from each method are corroborated with other and found to be convergent.

Machine Learning in Cardio-Oncology: New Insights from an Emerging Discipline.

A growing body of evidence on a wide spectrum of adverse cardiac events following oncologic therapies has led to the emergence of cardio-oncology as an increasingly relevant interdisciplinary specialty. This also calls for better risk-stratification for patients undergoing cancer treatment. Machine learning (ML), a popular branch discipline of artificial intelligence that tackles complex big data problems by identifying interaction patterns among variables, has seen increasing usage in cardio-oncology studies for risk stratification. The objective of this comprehensive review is to outline the application of ML approaches in cardio-oncology, including deep learning, artificial neural networks, random forest and summarize the cardiotoxicity identified by ML. The current literature shows that ML has been applied for the prediction, diagnosis and treatment of cardiotoxicity in cancer patients. In addition, role of ML in gender and racial disparities for cardiac outcomes and potential future directions of cardio-oncology are discussed. It is essential to establish dedicated multidisciplinary teams in the hospital and educate medical professionals to become familiar and proficient in ML in the future.