PTB-XL+, a comprehensive electrocardiographic feature dataset

Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems. Since then, the field has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildfire science and management. Our overall objective is to improve awareness of ML methods among wildfire researchers and managers, as well as illustrate the diverse and challenging range of problems in wildfire science available to ML data scientists. To that end, we first present an overview of popular ML approaches used in wildfire science to date and then review the use of ML in wildfire science as broadly categorized into six problem domains, including (i) fuels characterization, fire detection, and mapping; (ii) fire weather and climate change; (iii) fire occurrence, susceptibility, and risk; (iv) fire behavior prediction; (v) fire effects; and (vi) fire management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildfires within a data science context. In total, to the end of 2019, we identified 300 relevant publications in which the most frequently used ML methods across problem domains included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent-based learning — in the wildfire sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML models to learn on their own, expertise in wildfire science is necessary to ensure realistic modelling of fire processes across multiple scales, while the complexity of some ML methods such as deep learning requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildfire research and management communities play an active role in providing relevant, high-quality, and freely available wildfire data for use by practitioners of ML methods.

P125. Development of a novel ensemble machine learning algorithm for prediction of complications and readmission after anterior cervical spinal fusion

A urinary tract infection, or UTI, is caused when bacteria get into the urinary tract- kidneys, bladder, or urethra. UTIs cause more than 8.1 million visits to healthcare providers each year. About 60% of women and 12% of men get infected with UTI during their lifetime, therefore being more prominent in females. UTIs can be found by analyzing a urine sample. The urine is examined under a microscope for bacteria or white blood cells that show infection. Healthcare providers may also take a urine culture. This test examines urine to detect and identify bacteria and yeast, which may be causing a UTI. Several models have been proposed to predict urine culture positivity based on urinalysis. Applications of machine learning (ML) methods have been used extensively to solve various complex challenges in recent years in various application areas. ML methods are characterized by their ability to examine data and discover exciting relationships, provide interpretation, and identify patterns. ML can help enhance the reliability, performance, predictability, and accuracy of diagnostic systems for many diseases. This survey provides a comprehensive review of the use of ML in the diagnosis of Urinary Tract infection in human beings. To provide a reliable classification of results assistance of 27 algorithms was tested. Algorithms applied included Logistic regression, Decision tree, Random Forest, and Support Vector Machine. Each model was evaluated by F1-score, AUC-ROC, accuracy, sensitivity, and specificity. Baseline epidemiological factors, previous antimicrobial consumption, medical history, and previous culture results were included as features. Machine learning models such as the Artificial neural network have been used as well for the prediction of the presence of urinary infection. Some specific parameters have been selected with the help of the Analysis of variance technique which gave high accuracy. This survey provides a comprehensive review of the use of ML in the medical field highlighting standard technologies and how they affect medical diagnosis. It provides valuable references and guidance for researchers, practitioners, and decision-makers framing future research and development directions. It is found that Machine Learning models can improve the early prediction of urine culture positivity and UTI by combining automated urinalysis with other clinical information. Clinical utilization of the models can reduce the risk of delayed antimicrobial therapy in patients with nonspecific symptoms of UTI and classify patients with UTI who require further treatment and close monitoring. In conclusion, the paper provides a survey on the machine learning models used with the highest accuracy to detect UTI potential patients.

Cardiovascular diseases (CVDs) remain a leading cause of global mortality, underscoring the urgent need for early and accurate diagnosis. Electrocardiograms (ECGs) are a widely used, noninvasive tool for detecting cardiac abnormalities, but manual interpretation can be time- consuming and prone to error. This study explores advanced machine learning (ML) and deep learning (DL) methods to improve the detection of CVDs from ECG images, leveraging their ability to analyze complex patterns with high precision. Models such as Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and ensemble frameworks are utilized, alongside traditional ML models like XGBoost, CatBoost, and LightGBM. The performance of these models is evaluated based on precision, recall, F1-score, and accuracy. Results show that DL models, particularly an ensemble of CNN and ViT, achieve superior accuracy , outperforming standalone ML methods. Furthermore, an ensemble of XGBoost, CatBoost, and LightGBM achieves competitive results, while Optuna-tuned XGBoost further enhances ML performance. The findings highlight the potential of combining ML and DL techniques for robust and reliable CVD detection in ECG images. This research demonstrates the promise of AI-driven solutions in advancing medical diagnostics and supports the integration of automated systems for early detection of cardiovascular diseases.

Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion. We show that the performance of support vector machines is competitive with that of deep learning methods. Additionally, using a series of numerical experiments, we question the relevance of area under the receiver operating characteristic curve as a metric in virtual screening. We further suggest that area under the precision–recall curve should be used in conjunction with the receiver operating characteristic curve. Our numerical experiments also highlight challenges in estimating the uncertainty in model performance via scaffold-split nested cross validation.

Arsenic, aluminum, iron, lead, chromium, copper, zinc, manganese, and cadmium are some of the heavy metal pollutants in the air that cause severe impacts on the biotic and abiotic environment. This study intended to find the accumulation capacity of the heavy metals on the leaves of tree species such as Terminalia catappa, Syzygium cumini, Saraca asoca, Pongamia glabra, and Ficus religiosa and predict their accuracy by comparing different machine learning (ML) models. The samples were collected at six different locations (likely Vellagate, Cancer Institute, CSI hospital area, Moongilmandapam, Collectorate, and Pallavarmedu) and distributed in a manner within Kanchipuram town, Tamil Nadu, in February and March of 2018 and 2019, respectively. Six ML methods were selected, such as KStar (K*), Lazy IKB, Logistic Regression Algorithm (LR), LogitBoost Classifier (LB), Meta Randomizable Filtered Classifier (MRFC), and Random Tree (RT), for prediction and to compare the efficiency of their predictions. Out of six models, Logistic functions perform well in terms of TP rate when compared to other classifiers (93.21%-99.81% TPR– 0.93–0.99) and Logitboost attained a low TP rate that ranged from 0.76 to 0.82. This study indicates the feasibility of different ML methods in the prediction of species capabilities toward the accumulation of heavy metals.

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

Typhoon‐induced storm surges have been the most destructive disasters in coastal regions. The nowcasting of storm surge, in which the prediction lead time is not greater than 3 hr, is critical to disaster emergency response and recovery, enabling governments to make decisions and take actions according to the latest situation and prediction. Machine learning (ML) methods have been increasingly applied to storm surge predictions, but few ML studies focused on short‐term nowcasts. Moreover, conflicting conclusions often arise regarding the superiority of ML methods and model input variables for storm surge predictions. This study highlights the significance of surge autocorrelation, that is, the correlation of surge height with its local historical values, in the design of ML models for storm surge nowcasts. It is shown in the comparative analyses of model input variables that, independent of the adopted ML methods, models relying solely on historical surge heights as inputs are sufficient to achieve reasonably accurate nowcasts of surge height. Conversely, models without historical surge heights in their inputs yield comparable prediction errors. Involving surge autocorrelation, simple multilayer perceptron models perform even better than sequential‐compatible recurrent neural network category of models. Moreover, it is illustrated that the surge autocorrelation inhibits the performance of Transformer and XGBoost models for storm surge nowcasts. This study shows the possibility to achieve efficient and accurate nowcasts (a lead time under 3 hr) of localized storm surge only based on limited observations by local tide gauge, supporting decision‐making in disaster emergency response and recovery within small‐scale coastal regions.

Coastal aquifers are vital for sustaining ecosystems and providing freshwater for agriculture and domestic use. However, rising groundwater salinity in these regions demands innovative approaches for accurate modeling and prediction. In recent decades, machine learning (ML) and deep learning (DL) techniques have been extensively used across various water resource management fields, often yielding promising outcomes. This review examines the growing usage of ML and DL techniques in modeling groundwater salinity in coastal aquifers. The analysis is based on 104 peer-reviewed journal articles including the review articles indexed in PubMed, ScienceDirect, Google Scholar, Scopus, and SpringerLink using keywords like "saltwater intrusion", "machine learning", “deep learning”, and "groundwater salinity". The review discusses recent advancements, challenges, and future directions for improving ML model accuracy and applicability. Studies reveal an increasing reliance on ML techniques to predict groundwater salinity and manage seawater intrusion across various coastal geological settings. Researchers have employed a range of ML models, from traditional methods like Artificial Neural Networks and Adaptive Neuro Fuzzy Inference Systems to advanced DL-based models like Convolutional Neural Networks and Long Short-Term Memory Networks, often using ensemble methods to enhance accuracy. Key findings include the top-tier output of ensemble and optimized models, including Random Forest and Grasshopper Optimization Algorithm-XGBoost. These studies highlight the importance of model selection, input variable ranking, and computational efficiency, demonstrating ML's global relevance in environmental management. The review highlights the prospects of ML, DL, and ensemble models to redefine groundwater management in coastal aquifers, offering more effective and sustainable solutions to the challenges posed by groundwater salinity and saltwater intrusion. Future advancements will focus on further integrating DL, explainable artificial intelligence, and ensemble approaches, along with other innovative techniques, to explore sparsely studied variables, model new or unique study areas, and apply ML methods for managing groundwater salinity.

Background Safety issues for fluoroquinolones have been provided by regulatory agencies. This study was conducted to identify signals of fluoroquinolones reported in the Korea Adverse Event Reporting System (KAERS) using tree-based machine learning (ML) methods. Research design and methods All adverse events (AEs) associated with the target drugs reported in the KAERS from 2013 to 2017 were matched with drug label information. A dataset containing label-positive and -negative AEs was arbitrarily divided into training and test sets. Decision tree, random forest (RF), bagging, and gradient boosting machine (GBM) were fitted on the training set with hyperparameters tuned using five-fold cross-validation and applied to the test set. The ML method with the highest area under the curve (AUC) scores was selected as the final ML model. Results Bagging was selected as the final ML model for gemifloxacin (AUC score: 1) and levofloxacin (AUC: 0.9987). RF was selected in ciprofloxacin, moxifloxacin, and ofloxacin (AUC scores: 0.9859, 0.9974, and 0.9999 respectively). We found that the final ML methods detected additional signals that were not detected using the disproportionality analysis (DPA) methods. Conclusions The bagging-or-RF-based ML methods performed better than DPA and detected novel AE signals previously unidentified using the DPA methods.

Machine learning (ML) techniques have been researched and used in various environmental monitoring applications. Few studies have reported the long-term evaluation of such applications. Discussions regarding the risks and regulatory frameworks of ML applications in environmental monitoring have been rare. We monitored the performance of six predictive models developed using ML and statistical methods for 28 months. The six models used to predict NOx emissions were developed using six different algorithms. The model developed with a moderate complexity algorithm, adaptive boosting, had the best performance in long-term monitoring, with a root mean square error (RMSE) of 0.48 kg/hr in the 28-month monitoring period, and passed two of the three relative accuracy test audits. High complexity models based on gradient boosting and neural network algorithms had the best training performance, with a minimum RMSE of 0.23 kg/hr and 0.26 kg/hr, but also had the worst RMSE scores, of 0.51 kg/hr and 0.57 kg/hr, during the monitoring period. In addition, all six models failed all three relative accuracy test audits. The following problems were observed: (1) Complex ML models tended to have overfitting problems, thus indicating the importance of the trade-off between model accuracy and complexity. (2) Model input sensor drift or out of high-frequency ranges from the training data resulted in inaccurate predictions or an accuracy lower than the minimum allowed by regulators. (3) Existing regulatory frameworks must be modernized to keep pace with current machine learning practices. Some statistical tests are unsuitable for applications developed by using ML methods.

Introduction: The utility of ECG to diagnose left ventricular (LV) dilation in patients with left bundle branch block (LBBB) is not known. We sought to compare the diagnostic yield of ECG using (i) QRS duration, (ii) published LVH criteria, and (iii) machine learning (ML) models to detect increased left ventricular end diastolic volume indexed (LVEDVi) in the setting of LBBB. Hypothesis: ML is superior to QRS duration and LVH criteria to detect increased LVEDVi among LBBB. Methods: 12-lead ECGs were processed to reconstruct orthogonal X, Y, Z leads using Kors’s matrix and obtain root-mean-squared (3D) ECG. R wave, S wave and overall amplitudes, voltage-time-integrals (VTIs), and other ECG features were extracted from all ECG leads. ML algorithms [logistic regression (LR), support vector classifier (SVC), decision trees (DT), random forest (RF), gradient boosted machine (GBM) and boosted trees (BT)] were trained to predict increased LVEDVi (women >61 mL/m 2 , men >74 mL/m 2 ) from ECG features on a training set of 2668 ECGs with typical LBBB and echocardiogram within 45 days before or after ECG. LVEDV was measured using ASE biplane method of discs. We obtained ROC AUCs for prediction of increased LVEDVi by (i) QRS duration, (ii) published LVH criteria, and (iii) ML models in a separate validation set of adults with typical LBBB. Results: Among the validation set of 413 adults (53% women, age 73±12 yr) with LBBB, QRS duration alone had a higher AUC (women 0.668, men 0.699) for diagnosing increased LVMi compared to standard LVH criteria (Table). The best ML model (RF with overall AUC 0.694) did not substantially outperform QRS duration alone. Conclusions: In patients with LBBB, QRS duration ≥150 in women and ≥160 in men is a superior predictor of LV dilation than traditional ECG-based LVH criteria, with no additional value added by ML methods.

Shear viscosity, though being a fundamental property of all fluids, is computationally expensive to calculate from equilibrium molecular dynamics simulations. Recently, machine learning (ML) methods have been used to augment molecular simulations in many contexts, thus showing promise to estimate viscosity too in a relatively inexpensive manner. However, ML methods face significant challenges—such as overfitting, when the size of the data set is small, as is the case with viscosity. In this work, we train seven ML models to predict the shear viscosity of a Lennard–Jones fluid, with particular emphasis on addressing issues arising from a small data set. Specifically, the issues related to model selection, performance estimation and uncertainty quantification were investigated. First, we show that the widely used performance estimation procedure of using a single unseen data set shows a wide variability—in estimating the errors on—small data sets. In this context, the common practice of using cross validation (CV) to select the hyperparameters (model selection) can be adapted to estimate the generalization error (performance estimation) as well. We compare two simple CV procedures for their ability to do both model selection and performance estimation, and find that k-fold CV based procedure shows a lower variance of error estimates. Also, these CV procedures naturally lead to an ensemble of trained ML models. We discuss the role of performance metrics in training and evaluation and propose a method to rank the ML models based on multiple metrics. Finally, two methods for uncertainty quantification—Gaussian process regression (GPR) and ensemble method—were used to estimate the uncertainty on individual predictions. The uncertainty estimates from GPR were also used to construct an applicability domain using which the ML models provided even more reliable predictions on an independent viscosity data set generated in this work. Overall, the procedures prescribed in this work, together, lead to robust ML models for small data sets.

This paper presents a systematic literature review with respect to application of data science and machine learning (ML) to heart failure (HF) datasets with the intention of generating both a synthesis of relevant findings and a critical evaluation of approaches, applicability and accuracy in order to inform future work within this field. This paper has a particular intention to consider ways in which the low uptake of ML techniques within clinical practice could be resolved. Literature searches were performed on Scopus (2014-2021), ProQuest and Ovid MEDLINE databases (2014-2021). Search terms included ‘heart failure’ or ‘cardiomyopathy’ and ‘machine learning’, ‘data analytics’, ‘data mining’ or ‘data science’. 81 out of 1688 articles were included in the review. The majority of studies were retrospective cohort studies. The median size of the patient cohort across all studies was 1944 (min 46, max 93260). The largest patient samples were used in readmission prediction models with the median sample size of 5676 (min. 380, max. 93260). Machine learning methods focused on common HF problems: detection of HF from available dataset, prediction of hospital readmission following index hospitalization, mortality prediction, classification and clustering of HF cohorts into subgroups with distinctive features and response to HF treatment. The most common ML methods used were logistic regression, decision trees, random forest and support vector machines. Information on validation of models was scarce. Based on the authors’ affiliations, there was a median 3:1 ratio between IT specialists and clinicians. Over half of studies were co-authored by a collaboration of medical and IT specialists. Approximately 25% of papers were authored solely by IT specialists who did not seek clinical input in data interpretation. The application of ML to datasets, in particular clustering methods, enabled the development of classification models assisting in testing the outcomes of patients with HF. There is, however, a tendency to over-claim the potential usefulness of ML models for clinical practice. The next body of work that is required for this research discipline is the design of randomised controlled trials (RCTs) with the use of ML in an intervention arm in order to prospectively validate these algorithms for real-world clinical utility.

PurposeInjuries are common in sports and can have significant physical, psychological and financial consequences. Machine learning (ML) methods could be used to improve injury prediction and allow proper approaches to injury prevention. The aim of our study was therefore to perform a systematic review of ML methods in sport injury prediction and prevention.MethodsA search of the PubMed database was performed on March 24th 2020. Eligible articles included original studies investigating the role of ML for sport injury prediction and prevention. Two independent reviewers screened articles, assessed eligibility, risk of bias and extracted data. Methodological quality and risk of bias were determined by the Newcastle–Ottawa Scale. Study quality was evaluated using the GRADE working group methodology.ResultsEleven out of 249 studies met inclusion/exclusion criteria. Different ML methods were used (tree-based ensemble methods (n = 9), Support Vector Machines (n = 4), Artificial Neural Networks (n = 2)). The classification methods were facilitated by preprocessing steps (n = 5) and optimized using over- and undersampling methods (n = 6), hyperparameter tuning (n = 4), feature selection (n = 3) and dimensionality reduction (n = 1). Injury predictive performance ranged from poor (Accuracy = 52%, AUC = 0.52) to strong (AUC = 0.87, f1-score = 85%). ConclusionsCurrent ML methods can be used to identify athletes at high injury risk and be helpful to detect the most important injury risk factors. Methodological quality of the analyses was sufficient in general, but could be further improved. More effort should be put in the interpretation of the ML models.