Performance Of Machine Learning Models Research Articles

Exploring the Performance of Linear and Nonlinear Models of Time-of-Flight Secondary Ion Mass Spectrometry Spectra.

Multivariate statistical tools and machine learning (ML) techniques can deconvolute hyperspectral data and control the disparity between the number of samples and features in materials science. Nevertheless, the importance of generating sufficient high-quality sample replicates in training data cannot be overlooked, as it fundamentally affects the performance of ML models. Here, we present a quantitative analysis of time-of-flight secondary ion mass spectrometry (ToF-SIMS) spectra of a simple microarray system of two food dyes using partial least-squares (PLS, linear) and random forest (RF, nonlinear) algorithms. This microarray was generated by a high-throughput sample preparation and analysis workflow for fast and efficient acquisition of quality and reproducible spectra via ToF-SIMS. We drew insights from the bias-variance trade-off, investigated the performances of PLS and RF regression models as a function of training data size, and inferred the amount of data needed to construct accurate and reliable regression models. In addition, we found that the spectral concatenation of positive and negative ToF-SIMS spectra improved the model performances. This study provides an empirical basis for future design of high-throughput microarrays and multicomponent systems, for the purpose of analysis with ToF-SIMS and ML.

Dynamic Image Optimization and Code Generation Platform for Enhanced Data Augmentation

In the rapidly evolving domain of machine learning, the critical role of data quality, particularly image data, cannot be overstated. This research introduces a novel system uniquely designed to significantly improve the preprocessing and augmentation of image data for machine learning applications. At its core, the platform emerges as a comprehensive solution, meticulously bridging the gap between the acquisition of raw image data and its transformation into an optimized form ready for machine learning algorithms. What has been discovered, is a multifaceted system that not only simplifies the enhancement of image data but also elevates the quality of machine learning models by providing access to advanced image optimization techniques. The system distinguishes itself through a highly intuitive user interface that guides users in selecting and applying a variety of optimization strategies. These strategies are meticulously designed to enhance image quality and diversity, which in turn, can significantly improve the performance of machine learning models trained with such data. The platform's backend, powered by Python and leveraging libraries such as OpenCV, Pillow, and scikit-image, coupled with a responsive front end, ensures a seamless user experience and high-quality image processing. The generation of Python code for each processed image is a distinctive feature that enhances the platform's educational value, allowing users to learn, customize, and integrate optimization techniques into their workflows. Moreover, the inclusion of an API extends the platform's utility beyond its web interface, facilitating the automation of data augmentation pipelines and integration with external applications. This platform not only meets the immediate needs of data scientists and machine learning practitioners for data preprocessing and augmentation but also contributes significantly to the field by promoting understanding and application of image optimization techniques.

Transformer-Based Approach to Pathology Diagnosis Using Audio Spectrogram

Early detection of infant pathologies by non-invasive means is a critical aspect of pediatric healthcare. Audio analysis of infant crying has emerged as a promising method to identify various health conditions without direct medical intervention. In this study, we present a cutting-edge machine learning model that employs audio spectrograms and transformer-based algorithms to classify infant crying into distinct pathological categories. Our innovative model bypasses the extensive preprocessing typically associated with audio data by exploiting the self-attention mechanisms of the transformer, thereby preserving the integrity of the audio’s diagnostic features. When benchmarked against established machine learning and deep learning models, our approach demonstrated a remarkable 98.69% accuracy, 98.73% precision, 98.71% recall, and an F1 score of 98.71%, surpassing the performance of both traditional machine learning and convolutional neural network models. This research not only provides a novel diagnostic tool that is scalable and efficient but also opens avenues for improving pediatric care through early and accurate detection of pathologies.

Forecasting of Flood in the Non-Tidal River of Northern Regions of Bangladesh Using Machine Learning-Based Approach

Forecasting of Flood in the Non-Tidal River of Northern Regions of Bangladesh Using Machine Learning-Based Approach

Cardiovascular disease prediction with machine learning techniques

Cardiovascular disease (CVD) remains the leading cause of death globally. In search of advanced techniques for early detection of CVD, recent research has increasingly focused on using machine learning (ML) methods to improve the accuracy and timeliness of diagnosis. A multifactorial machine learning approach offers a comprehensive solution for cardiovascular disease detection, using vast and diverse datasets to develop predictive models that outperform traditional methods. This paper provides a comprehensive examination of various machine learning approaches and their application in the early detection of cardiovascular abnormalities, with special emphasis on their effectiveness compared to traditional diagnostic methods. The research methodology involves the implementation of several ML models trained and tested using large datasets that provide analysis covering various demographic parameters, lifestyle parameters and health status parameters. Key findings show that ML models significantly outperform traditional statistical methods in detecting early signs of CVD. The superior performance of ML models represents a promising tool for healthcare professionals, potentially leading to better strategies for preventive care and reduction of CVD-related mortality. The ongoing development and refinement of these technologies, along with improvements in data collection and interoperability between healthcare systems, will be critical to realizing their full potential in the clinical setting.

Detecting health misinformation: A comparative analysis of machine learning and graph convolutional networks in classification tasks

In the digital age, the proliferation of health-related information online has heightened the risk of misinformation, posing substantial threats to public well-being. This research conducts a meticulous comparative analysis of classification models, focusing on detecting health misinformation. The study evaluates the performance of traditional machine learning models and advanced graph convolutional networks (GCN) across critical algorithmic metrics. The results comprehensively understand each algorithm's effectiveness in identifying health misinformation and provide valuable insights for combating the pervasive spread of false health information in the digital landscape. GCN with TF-IDF gives the best result, as shown in the result section.•The research method involves a comparative analysis of classification algorithms to detect health misinformation, exploring traditional machine learning models and graph convolutional networks.•This research used algorithms such as Passive Aggressive Classifier, Random Forest, Decision Tree, Logistic Regression, Light GBM, GCN, GCN with BERT, GCN with TF-IDF, and GCN with Word2Vec were employed. Performance Metrics: Accuracy: for Passive Aggressive Classifier: 85.75 %, Random Forest: 86 %, Decision Tree: 81.30 %, Light BGM: 83.29 %, normal GCN: 84.53 %, GCN with BERT: 85.00 %, GCN with TR-IDF: 93.86 % and GCN with word2Vec: 81.00 %•Algorithmic performance metrics, including accuracy, precision, recall, and F1-score, were systematically evaluated to assess the efficacy of each model in detecting health misinformation, focusing on understanding the strengths and limitations of different approaches. The superior performance of Graph Convolutional Networks (GCNs) with TF-IDF embedding, achieving an accuracy of 93.86 %

Combined blood Neurofilament light chain and third ventricle width to differentiate Progressive Supranuclear Palsy from Parkinson's Disease: A machine learning study

IntroductionDifferentiating Progressive Supranuclear Palsy (PSP) from Parkinson's Disease (PD) may be clinically challenging. In this study, we explored the performance of machine learning models based on MR imaging and blood molecular biomarkers in distinguishing between these two neurodegenerative diseases. MethodsTwenty-eight PSP patients, 46 PD patients and 60 control subjects (HC) were consecutively enrolled in the study. Serum concentration of neurofilament light chain protein (Nf-L) was assessed by single molecule array (SIMOA), while an automatic segmentation algorithm was employed for T1-weighted measurements of third ventricle width/intracranial diameter ratio (3rdV/ID). Machine learning (ML) models with Logistic Regression (LR), Random Forest (RF), and XGBoost algorithms based on 3rdV/ID and serum Nf-L levels were tested in distinguishing among PSP, PD and HC. ResultsPSP patients showed higher serum Nf-L levels and larger 3rdV/ID ratio in comparison with both PD and HC groups (p < 0.005). All ML algorithms (LR, RF and XGBoost) showed that the combination of MRI and blood biomarkers had excellent classification performances in differentiating PSP from PD (AUC ≥0.92), outperforming each biomarker used alone (AUC: 0.85–0.90). Among the different algorithms, XGBoost was slightly more powerful than LR and RF in distinguishing PSP from PD patients, reaching AUC of 0.94 ± 0.04. ConclusionOur findings highlight the usefulness of combining blood and simple linear MRI biomarkers to accurately distinguish between PSP and PD patients. This multimodal approach may play a pivotal role in patient management and clinical decision-making, paving the way for more effective and timely interventions in these neurodegenerative diseases.

Construction and validation of machine learning algorithm for predicting depression among home-quarantined individuals during the large-scale COVID-19 outbreak: based on Adaboost model

ObjectivesCOVID-19 epidemics often lead to elevated levels of depression. To accurately identify and predict depression levels in home-quarantined individuals during a COVID-19 epidemic, this study constructed a depression prediction model based on multiple machine learning algorithms and validated its effectiveness.MethodsA cross-sectional method was used to examine the depression status of individuals quarantined at home during the epidemic via the network. Characteristics included variables on sociodemographics, COVID-19 and its prevention and control measures, impact on life, work, health and economy after the city was sealed off, and PHQ-9 scale scores. The home-quarantined subjects were randomly divided into training set and validation set according to the ratio of 7:3, and the performance of different machine learning models were compared by 10-fold cross-validation, and the model algorithm with the best performance was selected from 15 models to construct and validate the depression prediction model for home-quarantined subjects. The validity of different models was compared based on accuracy, precision, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC), and the best model suitable for the data framework of this study was identified.ResultsThe prevalence of depression among home-quarantined individuals during the epidemic was 31.66% (202/638), and the constructed Adaboost depression prediction model had an ACC of 0.7917, an accuracy of 0.7180, and an AUC of 0.7803, which was better than the other 15 models on the combination of various performance measures. In the validation sets, the AUC was greater than 0.83.ConclusionsThe Adaboost machine learning algorithm developed in this study can be used to construct a depression prediction model for home-quarantined individuals that has better machine learning performance, as well as high effectiveness, robustness, and generalizability.

NOx Emission Predictions in Gas Turbines Through Integrated Data-Driven Machine Learning Approaches

Abstract The reduction of NOx emissions is a paramount endeavor in contemporary engineering and energy production, as these emissions are closely linked to adverse environmental and health impacts. The prediction of NOx emission from gas turbines through several integrated data-driven machine learning methods has been evaluated in study. The study compares the performance of ensemble and conventional machine learning models, demonstrating superior accuracy achieved by the ensemble models. Specifically, the Random Forest model achieved an accuracy rate of 91.68%, XGBoost yielded an accuracy of 91.54%, and CATBoost exhibited the highest accuracy at 92.76%. These findings highlight the capability of data-driven machine learning techniques in enhancing NOx emission predictions in gas turbines. The improved prediction by ensembles can be utilized in the development and implementation of more effective control and mitigation strategies in practical applications. Through the application of these advanced machine learning approaches, the gas turbine industry can play a pivotal role in minimizing its environmental impact while optimizing operational efficiency. This study also provides valuable insights into the effectiveness of ensemble machine learning models, advancing our understanding of their capabilities in addressing the critical issue of NOx emissions from gas turbines.

Improving the performance of machine learning model predicting phase and crystal structure of high entropy alloys by the synthetic minority oversampling technique

It is critical to select the suitable integration of elements that has an influence on phase formation when selecting the proper High Entropy Alloys (HEAs) with desired qualities. Machine Learning (ML) models were used to predict the phase and crystal structure of HEAs in this study. Trained on extensive experimental datasets, the set of input characteristics includes Atomic size difference, Mixing Enthalpy, Mixing Entropy, Valence Electron concentration, Electronegativity difference, Ω and Average Melting Temperature. The phase is divided into three categories: Solid solution (S), Dual phase (D), and Intermetallic (Im). Crystal structure classifications include BCC, FCC, and FCC+BCC. For phase and crystal structure prediction, five ML algorithms were used: Decision Tree (DT), K Nearest Neighbour (KNN), Random Forest (RF), Gradient Boosting (GB) and eXtreme Gradient Boosting (XG Boosting), The classification of the HEAs phase has been predicted with great accuracy using an XG Boosting (80 %) and Random Forest exhibits the highest accuracy (94 %) for crystal structure prediction when model is trained on an experimental dataset. Even though the ML model predicts the classes with a better degree of accuracy (>80 %), the F1 value of each class varies more dramatically. This issue has arisen as a result of an imbalance in the dataset's class distribution. To boost performance, this work uses an ML model in conjunction with the Synthetic Minority Oversampling Technique (SMOTE). According to this approach, XG boosting identified the crystal structure with 93 % accuracy and predicted the phase of HEAs with 84 % accuracy. Additionally, it has been noted that each class's F1 score improved and the difference between them was reduced after using the SMOTE technique. It is evident that the SMOTE approach has improved the ML model's ability to differentiate between the various classes.

Predictive modeling for early detection of biliary atresia in infants with cholestasis: Insights from a machine learning study

Cholestasis, characterized by the obstruction of bile flow, poses a significant concern in neonates and infants. It can result in jaundice, inadequate weight gain, and liver dysfunction. However, distinguishing between biliary atresia (BA) and non-biliary atresia in these young patients presenting with cholestasis poses a formidable challenge, given the similarity in their clinical manifestations. To this end, our study endeavors to construct a screening model aimed at prognosticating outcomes in cases of BA. Within this study, we introduce a wrapper feature selection model denoted as bWFMVO-SVM-FS, which amalgamates the water flow-based multi-verse optimizer (WFMVO) and support vector machine (SVM) technology. Initially, WFMVO is benchmarked against eleven state-of-the-art algorithms, with its efficiency in searching for optimized feature subsets within the model validated on IEEE CEC 2017 and IEEE CEC 2022 benchmark functions. Subsequently, the developed bWFMVO-SVM-FS model is employed to analyze a cohort of 870 consecutively registered cases of neonates and infants with cholestasis (diagnosed as either BA or non-BA) from Xinhua Hospital and Shanghai Children's Hospital, both affiliated with Shanghai Jiao Tong University. The results underscore the remarkable predictive capacity of the model, achieving an accuracy of 92.639 % and specificity of 88.865 %. Gamma-glutamyl transferase, triangular cord sign, weight, abnormal gallbladder, and stool color emerge as highly correlated with early symptoms in BA infants. Furthermore, leveraging these five significant features enhances the interpretability of the machine learning model's performance outcomes for medical professionals, thereby facilitating more effective clinical decision-making.

Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non-interventional study in Kenya.

Hypertension and diabetes mellitus (DM) are major causes of morbidity and mortality, with growing burdens in low-income countries where they are underdiagnosed and undertreated. Advances in machine learning may provide opportunities to enhance diagnostics in settings with limited medical infrastructure. A non-interventional study was conducted to develop and validate a machine learning algorithm to estimate cardiovascular clinical and laboratory parameters. At two sites in Kenya, digital retinal fundus photographs were collected alongside blood pressure (BP), laboratory measures and medical history. The performance of machine learning models, originally trained using data from the UK Biobank, were evaluated for their ability to estimate BP, glycated haemoglobin, estimated glomerular filtration rate and diagnoses from fundus images. In total, 301 participants were enrolled. Compared with the UK Biobank population used for algorithm development, participants from Kenya were younger and would probably report Black/African ethnicity, with a higher body mass index and prevalence of DM and hypertension. The mean absolute error was comparable or slightly greater for systolic BP, diastolic BP, glycated haemoglobin and estimated glomerular filtration rate. The model trained to identify DM had an area under the receiver operating curve of 0.762 (0.818 in the UK Biobank) and the hypertension model had an area under the receiver operating curve of 0.765 (0.738 in the UK Biobank). In a Kenyan population, machine learning models estimated cardiovascular parameters with comparable or slightly lower accuracy than in the population where they were trained, suggesting model recalibration may be appropriate. This study represents an incremental step toward leveraging machine learning to make early cardiovascular screening more accessible, particularly in resource-limited settings.

Protein feature engineering framework for AMPylation site prediction

AMPylation is a biologically significant yet understudied post-translational modification where an adenosine monophosphate (AMP) group is added to Tyrosine and Threonine residues primarily. While recent work has illuminated the prevalence and functional impacts of AMPylation, experimental identification of AMPylation sites remains challenging. Computational prediction techniques provide a faster alternative approach. The predictive performance of machine learning models is highly dependent on the features used to represent the raw amino acid sequences. In this work, we introduce a novel feature extraction pipeline to encode the key properties relevant to AMPylation site prediction. We utilize a recently published dataset of curated AMPylation sites to develop our feature generation framework. We demonstrate the utility of our extracted features by training various machine learning classifiers, on various numerical representations of the raw sequences extracted with the help of our framework. Tenfold cross-validation is used to evaluate the model’s capability to distinguish between AMPylated and non-AMPylated sites. The top-performing set of features extracted achieved MCC score of 0.58, Accuracy of 0.8, AUC-ROC of 0.85 and F1 score of 0.73. Further, we elucidate the behaviour of the model on the set of features consisting of monogram and bigram counts for various representations using SHapley Additive exPlanations.

Machine learning for monitoring hobbing tool health in CNC hobbing machine

Utilizing Machine Learning (ML) to oversee the status of hobbing cutters aims to enhance the gear manufacturing process’s effectiveness, output, and quality. Manufacturers can proactively enact measures to optimize tool performance and minimize downtime by conducting precise real-time assessments of hobbing cutter conditions. This proactive approach contributes to heightened product quality and decreased production costs. This study introduces an innovative condition monitoring system utilizing a Machine Learning approach. A Failure Mode and Effect Analysis (FMEA) were executed to gauge the severity of failures in hobbing cutters of Computer Numerical Control (CNC) Hobbing Machine, and the Risk Probability Number (RPN) was computed. This numerical value aids in prioritizing preventive measures by concentrating on failures with the most substantial potential impact. Failures with high RPN numbers were considered to implement the Machine Learning approach and artificial faults were induced in the hobbing cutter. Vibration signals (displacement, velocity, and acceleration) were then measured using a commercial high-capacity and high-frequency range Data Acquisition System (DAQ). The analysis covered operating parameters such as speed (ranging from 35 to 45 rpm), feed (ranging from 0.6 to 1 mm/rev), and depth of cut (6.8 mm). MATLAB code and script were employed to extract statistical features. These features were subsequently utilized to train seven algorithms (Decision Tree, Naive Bayes, Support Vector Machine (SVM), Efficient Linear, Kernel, Ensemble and Neural Network) as well as the application of Bayesian optimization for hyperparameter tuning and model evaluation were done. Amongst these algorithms, J48 Decision tree (DT) algorithm demonstrated impeccable accuracy, correctly classifying 100% of instances in the provided dataset. These algorithms stand out for their accuracy and efficiency in building, making them well-suited for this purpose. Based on ML model performance, it is recommended to employ J48 Decision Tree Model for the condition monitoring of a CNC hobbing cutter. The emerging confusion matrix was crucial in creating a condition monitoring system. This system can analyze statistical features extracted from vibration signals to assess the health of the cutter and classify it accordingly. The system alerts the operator when a hobbing cutter approaches a worn or damaged condition, enabling timely replacement before any issues arise.

Toward Precision Diagnosis: Machine Learning in Identifying Malignant Orbital Tumors With Multiparametric 3 T MRI.

Orbital tumors present a diagnostic challenge due to their varied locations and histopathological differences. Although recent advancements in imaging have improved diagnosis, classification remains a challenge. The integration of artificial intelligence in radiology and ophthalmology has demonstrated promising outcomes. This study aimed to evaluate the performance of machine learning models in accurately distinguishing malignant orbital tumors from benign ones using multiparametric 3 T magnetic resonance imaging (MRI) data. In this single-center prospective study, patients with orbital masses underwent presurgery 3 T MRI scans between December 2015 and May 2021. The MRI protocol comprised multiparametric imaging including dynamic contrast-enhanced (DCE), diffusion-weighted imaging (DWI), intravoxel incoherent motion (IVIM), as well as morphological imaging acquisitions. A repeated nested cross-validation strategy using random forest classifiers was used for model training and evaluation, considering 8 combinations of explanatory features. Shapley additive explanations (SHAP) values were used to assess feature contributions, and the model performance was evaluated using multiple metrics. One hundred thirteen patients were analyzed (57/113 [50.4%] were women; average age was 51.5 ± 17.5 years, range: 19-88 years). Among the 8 combinations of explanatory features assessed, the performance on predicting malignancy when using the most comprehensive model, which is the most exhaustive one incorporating all 46 explanatory features-including morphology, DWI, DCE, and IVIM, achieved an area under the curve of 0.9 [0.73-0.99]. When using the streamlined "10-feature signature" model, performance reached an area under the curve of 0.88 [0.71-0.99]. Random forest feature importance graphs measured by the mean of SHAP values pinpointed the 10 most impactful features, which comprised 3 quantitative IVIM features, 4 quantitative DCE features, 1 quantitative DWI feature, 1 qualitative DWI feature, and age. Our findings demonstrate that a machine learning approach, integrating multiparametric MRI data such as DCE, DWI, IVIM, and morphological imaging, offers high-performing models for differentiating malignant from benign orbital tumors. The streamlined 10-feature signature, with a performance close to the comprehensive model, may be more suitable for clinical application.

Impact of SUSAN Denoising and ComBat Harmonization on Machine Learning Model Performance for Malignant Brain Neoplasms.

Feature variability in radiomics studies due to technical and magnet strength parameters is well-known and may be addressed through various preprocessing methods. However, very few studies have evaluated the downstream impact of variable preprocessing on model classification performance in a multiclass setting. We sought to evaluate the impact of Smallest Univalue Segment Assimilating Nucleus (SUSAN) denoising and Combining Batches harmonization on model classification performance. A total of 493 cases (410 internal and 83 external data sets) of glioblastoma, intracranial metastatic disease, and primary CNS lymphoma underwent semiautomated 3D-segmentation post-baseline image processing (BIP) consisting of resampling, realignment, coregistration, skull-stripping, and image normalization. Post-BIP, 2 sets were generated, one with and another without SUSAN denoising. Radiomics features were extracted from both data sets and batch-corrected to produce 4 data sets: (a) BIP, (b) BIP with SUSAN denoising, (c) BIP with Combining Batches, and (d) BIP with both SUSAN denoising and Combining Batches harmonization. Performance was then summarized for models using a combination of 6 feature-selection techniques and 6 machine learning models across 4 mask-sequence combinations with features derived from 1 to 3 (multiparametric) MRI sequences. Most top-performing models on the external test set used BIP+SUSAN denoising-derived features. Overall, the use of SUSAN denoising and Combining Batches harmonization led to a slight but generally consistent improvement in model performance on the external test set. The use of image-preprocessing steps such as SUSAN denoising and Combining Batches harmonization may be more useful in a multi-institutional setting to improve model generalizability. Models derived from only T1 contrast-enhanced images showed comparable performance to models derived from multiparametric MRI.

Assessing Column Stability: A Comparative Study of Machine Learning Regression Models for Shear Strength Prediction

This research presents a comprehensive investigation into the accurate estimation of shear strength in rectangular reinforced concrete columns through advanced machine learning (ML) models. The study addresses the intricate challenge posed by shear strength complexity, which is crucial for evaluating column stability and ensuring structural integrity. Building upon a substantial dataset comprising 545 experimental observations sourced from diverse literature, this research establishes a robust foundation for predictive modeling. Four distinct ML regression models, Random Forest, Decision Tree, XGBoost, and LightGBM, are meticulously evaluated for their performance. The evaluation employs established metrics, including R2, RMSE, MAE, and MAPE to quantify their predictive capabilities. The outcomes highlight the models' robustness in capturing nuanced variations in shear strength, with impressive R2 values ranging from 93.6% to 93.9%, showcasing their exceptional ability to elucidate intricate shear behaviors. Furthermore, comparative analysis indicates the slightly superior performance of the Random Forest over the Decision Tree, highlighting the efficacy of ensemble methods in this context. Extending the exploration to include XGBoost and LightGBM, the study showcases their potential as accurate shear strength predictors. The performance of the models is validated through scatter plots and error distribution plots, confirming accurate shear strength predictions across various scenarios. This research contributes significantly to the advancement of structural engineering methodologies by highlighting the potential of ML to improve the accuracy of shear strength estimation. The findings not only underscore the exceptional performance of ML models but also provide valuable insights into their comparative effectiveness, paving the way for enhanced structural assessments in columns.

Diagnosis and classification of portosystemic shunts: a machine learning retrospective case-control study.

Diagnosis of portosystemic shunts (PSS) in dogs often requires multiple diagnostic tests, and available clinicopathologic tests have limitations in sensitivity and specificity. The objective of this study was to train and validate a machine learning model (MLM) that can accurately predict the presence of a PSS utilizing routinely collected demographic data and clinicopathologic features. Dogs diagnosed with PSS or control dogs tested for PSS but had the condition ruled out (non-PSS) were identified. Dogs were included if a complete blood count and serum chemistry panel were available from PSS diagnostic testing. Dogs with a PSS were subcategorized as having a single intrahepatic PSS, a single extrahepatic PSS, or multiple extrahepatic PSS. An extreme gradient boosting (XGboost) MLM was trained with data from 70% of the cases, and MLM performance was determined on the test set, comprising the remaining 30% of the case data. Two MLMs were created. The first was designed to predict the presence of any PSS (PSS MLM), and the second to predict the PSS subcategory (PSS SubCat MLM). The trained PSS MLM had a sensitivity of 94.3% (95% CI 90.1-96.8%) and specificity of 90.5% (95% CI 85.32-94.0%) for dogs in the test set. The area under the receiver operator characteristic curve (AUC) was 0.976 (95% CI; 0.964-0.989). The mean corpuscular hemoglobin, lymphocyte count, and serum globulin concentration were most important in prediction classification. The PSS SubCat MLM had an accuracy of 85.7% in determining the subtype of PSS of dogs in the test set, with variable sensitivity and specificity depending on PSS subtype. These MLMs have a high accuracy for diagnosing PSS; however, the prediction of PSS subclassification is less accurate. The MLMs can be used as a screening tool to increase or decrease the index of suspicion for PSS before confirmatory diagnostics such as advanced imaging are pursued.

Dynamic Data Scaling Techniques for Streaming Machine Learning

This research delves into innovative dynamic data scaling techniques designed for streaming machine learning environments. In the realm of real-time data streams, conventional static scaling methods may encounter challenges in adapting to evolving data distributions. To overcome this hurdle, our study explores dynamic scaling approaches capable of adjusting and optimizing scaling parameters dynamically as the characteristics of incoming data shift over time. The objective is to augment the performance and adaptability of machine learning models in streaming scenarios by ensuring that the scaling process remains responsive to changing patterns in the data. Through empirical evaluations and comparative analyses, the study aims to showcase the efficacy of the proposed dynamic data scaling techniques in enhancing predictive accuracy and sustaining model relevance in dynamic and fast-paced streaming environments. This research contributes to the advancement of scalable and adaptive machine learning methodologies, particularly in applications where timely and accurate insights from streaming data are crucial.

Predictive modeling of skin permeability for molecules: Investigating FDA-approved drug permeability with various AI algorithms.

The transdermal route of drug administration has gained popularity for its convenience and bypassing the first-pass metabolism. Accurate skin permeability prediction is crucial for successful transdermal drug delivery (TDD). In this study, we address this critical need to enhance TDD. A dataset comprising 441 records for 140 molecules with diverse LogKp values was characterized. The descriptor calculation yielded 145 relevant descriptors. Machine learning models, including MLR, RF, XGBoost, CatBoost, LGBM, and ANN, were employed for regression analysis. Notably, LGBM, XGBoost, and gradient boosting models outperformed others, demonstrating superior predictive accuracy. Key descriptors influencing skin permeability, such as hydrophobicity, hydrogen bond donors, hydrogen bond acceptors, and topological polar surface area, were identified and visualized. Cluster analysis applied to the FDA-approved drug dataset (2326 compounds) revealed four distinct clusters with significant differences in molecular characteristics. Predicted LogKp values for these clusters offered insights into the permeability variations among FDA-approved drugs. Furthermore, an investigation into skin permeability patterns across 83 classes of FDA-approved drugs based on the ATC code showcased significant differences, providing valuable information for drug development strategies. The study underscores the importance of accurate skin permeability prediction for TDD, emphasizing the superior performance of nonlinear machine learning models. The identified key descriptors and clusters contribute to a nuanced understanding of permeability characteristics among FDA-approved drugs. These findings offer actionable insights for drug design, formulation, and prioritization of molecules with optimum properties, potentially reducing reliance on costly experimental testing. Future research directions include offering promising applications in pharmaceutical research and formulation within the burgeoning field of computer-aided drug design.