Force-Driven Graph Learning and Classification

Alcohol consumption tends to increase during the transition from childhood to adolescence, and risk factors at the individual, family, or environmental level, as well as altered brain structure and function have been associated with the likelihood of developing alcohol use disorder (AUD) or binge drinking later in life. Most studies have focused on limited subsets of multilevel or neuroimaging factors, typically emphasizing alcohol initiation, binge drinking, or AUD in cross-sectional designs rather than exploring longitudinal alcohol consumption trajectories. Our study addresses these gaps by examining a comprehensive set of multilevel, multidomain factors and multimodal brain imaging features to prospectively predict early alcohol sipping trajectories over time with large data from the Adolescent Brain Cognitive Development (ABCD) study (baseline N = 11,686, mean age = 9.92 years). We applied machine learning methods to baseline individual, family, and environmental factors as well as structural and functional brain connectivity features, analyzing these predictors separately and in combination. Key findings reveal that functional connectivity features and multilevel factors distinguish individuals with an increasing alcohol sipping trajectory from those who initially experimented with alcohol but reduced their consumption over time. Moreover, we found important structural and functional features that predicted those who increasingly sipped over time versus the ones who did not engage in alcohol experimentation. Stable interactions between age and cortical thickness, surface area and functional connectivity between the amygdala and executive or default networks suggest that accelerated cortical maturation could predict a pattern of increasing alcohol sipping over time. These trends could inform us how individual, family, and environmental factors together with brain imaging features impact the development of different alcohol sipping trajectories over time.

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.

A dose deposition matrix (DDM) prediction method using several voxel features and a machine learning (ML) approach is proposed for plan optimization in radiation therapy. Head and lung cases with the inhomogeneous medium are used as training and testing data. The prediction model is a cascade forward backprop neural network where the input is the features of the voxel, including 1) voxel to body surface distance along the beamlet axis, 2) voxel to beamlet axis distance, 3) voxel density, 4) heterogeneity corrected voxel to body surface distance, 5) heterogeneity corrected voxel to beamlet axis, and (6) the dose of voxel obtained from the pencil beam (PB) algorithm. The output is the predicted voxel dose corresponding to a beamlet. The predicted DDM was used for plan optimization (ML method) and compared with the dose of MC-based plan optimization (MC method) and the dose of pencil beam-based plan optimization (PB method). The mean absolute error (MAE) value was calculated for full volume relative to the dose of the MC method to evaluate the overall dose performance of the final plan. For patient with head tumor, the ML method achieves MAE value 0.49 × 10-4 and PB has MAE 1.86 × 10-4. For patient with lung tumor, the ML method has MAE 1.42 × 10-4 and PB has MAE 3.72 × 10-4. The maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 1.2% for patient with head tumor, while the difference is larger than 10% using the PB method. For patient with lung tumor, the maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 2.1%, while the difference is larger than 16% using the PB method. In this work, a reliable DDM prediction method is established for plan optimization by applying several voxel features and the ML approach. The results show that the ML method based on voxel features can obtain plans comparable to the MC method and is better than the PB method in achieving accurate dose to the patient, which is helpful for rapid plan optimization and accurate dose calculation. Establishment of a new machine learning method based on the relationship between the voxel and beamlet features for dose deposition matrix prediction in radiation therapy.

Generalized anxiety disorder (GAD) is one of common anxiety disorders in adolescents. Although adolescents with GAD are thought to be at high risk for other mental diseases, the disease-specific alterations have not been adequately explored. Recent studies have revealed the abnormal functional connectivity (FC) in adolescents with GAD. Most previous researches have investigated the static FC which ignores the fluctuations of FC over time and focused on the structures of “fear circuit”. To figure out the alterations of dynamic FC caused by GAD and the possibilities of dynamic FC as biomarkers, we propose an effective approach to identify adolescent GAD using temporal features derived from dynamic FC. In our study, the instantaneous synchronization of pairwise signals was estimated as dynamic FC. The Hurst exponent (H) and variance, indicating regularity and variable degree of a time series respectively, were calculated as temporal features of dynamic FC. By leave-one-out cross-validation (LOOCV), a relatively high accuracy of 88.46% could be achieved when H and variance of dynamic FC were combined as features. In addition, we identified the disease-related regions, including regions belonging to default mode (DM) and cerebellar networks. The results suggest that temporal features of dynamic FC could achieve a clinically acceptable diagnostic power and serve as biomarkers of adolescent GAD. Furthermore, our work could be helpful in understanding the pathophysiological mechanism of adolescent GAD.

Functional connectivity, reflecting synchronized brain activity across distinct regions, is crucial for understanding cognitive processes. Despite the recent interest in exploring the relationship between functional connectivity and structural brain features, understanding the precise link remains challenging. We propose a novel analysis method that integrates structural factors-such as anatomical morphology summaries, voxel intensity, diffusion-weighted information, and geographic distance to explain variation in functional connectivity. Our method employs generalized additive model (GAM), leveraging region-pair or vertex-pair information, while accommodating individual subject differences in both template and subject spaces. Furthermore, we assess repeatability via the so called discriminability of subjects under our approach, quantifying the probability of similarities between measurements for the same subject versus different subjects. Utilizing data from the Human Connectome Project, we analyze brain connectivity in twin pairs and non-twin pairs to evaluate the repeatability of model-based connectivity patterns estimated via GAMs. Our findings suggest that direct structure/function regression models enhances our understanding of functional connectivity variation, providing insights into underlying mechanisms and discriminability of brain connections.

Developing Theory Using Machine Learning Methods

How Magic a Bullet Is Machine Learning for Credit Analysis? An Exploration with FinTech Lending Data

Using electroencephalogram (EEG) signals to control intelligent wheelchairs is one of the new control methods for controlling intelligent wheelchairs. The most serious problem in the control process is recognition and classification of EEG signals, especially a variety of EEG signals. To improve the accuracy of EEG classification, improved-common spatial patterns and a deep-belief network algorithm are proposed and used for recognition and classification of EEG signals. A variety of different EEG signals were collected by an Emotiv EPOC+ EEG collector, and the characteristic signals were extracted by improved-common spatial patterns and identified and classified by a deep-belief network algorithm. Simulation results show that the classification accuracy of improved-common spatial patterns and the deep-belief network algorithm is higher than that of the traditional classification method, and a research perspective is provided for the classification of various EEG signals in the future.

Parameter importance assessment improves efficacy of machine learning methods for predicting snow avalanche sites in Leh-Manali Highway, India

Machine learning guided design of functional materials with targeted properties

The optimum location of signal sensors in actual buildings to determine the structural damage condition using machine learning is discussed in this study. The target buildings are a local government office and a Fire Station in Japan, with two acceleration sensors located on the ground and the roof level of the buildings. An additional sensor location is considered in this study. The structural damage condition is evaluated by machine learning (ML) methods from the sensor signals for five cases of single and multiple sensor locations. The maximum story drift is used as an identifier of the structural damage condition. Seven ML methods are developed, and their accuracy is compared. Several intensity measures (IM) obtained from each sensor signal are used as input features for the ML models, and the prediction importance level of each IM is evaluated in order to establish its usefulness. Finally, the results are compared to the methodology using wavelet power spectrum and convolutional neural network to predict the damage condition of buildings.

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

Machine learning (ML) methods are attracting considerable attention among academics in the field of finance. However, it is commonly believed that ML has not transformed the asset management industry to the same extent as other sectors. This survey focuses on the ML methods and empirical results available in the literature that matter most for active portfolio management. ML has asset management applications for signal generation, portfolio construction, and trade execution, and promising findings have been reported. Reinforcement learning (RL), in particular, is expected to play a more significant role in the industry. Nevertheless, the performance of a sample of active exchange-traded funds (ETF) that use ML in their investments tends to be mixed. Overall, ML techniques show great promise for active portfolio management, but investors should be cautioned against their main potential pitfalls. 
\n
\n

IntroductionThe current diagnosis of Parkinson's disease (PD) comorbidity with depression (DPD) largely depends on clinical evaluation. However, the modality may tend to lack precision in detecting PD with depression. A radiomic approach that combines functional connectivity and activity with clinical scores has the potential to achieve accurate and differential diagnosis between PD and DPD.MethodsIn this study, we aimed to employ the radiomic approach to extract large‐scale features of functional connectivity and activity for differentiating among DPD, PD with no depression (NDPD), and healthy controls (HC). We extracted 6,557 features of five types from all subjects including clinical characteristics, resting‐state functional connectivity (RSFC), amplitude of low‐frequency fluctuation (ALFF), regional homogeneity (ReHo), and voxel‐mirrored homotopic connectivity (VMHC). Lasso, random forest, and support vector machine (SVM) were implemented for feature selection and dimension reduction based on the training sets, and the prediction performance for different methods in the testing sets was compared.ResultsThe results showed that nineteen features were selected for the group of DPD versus HC, 34 features were selected for the group of NDPD versus HC, and 17 features were retained for the group of DPD versus NDPD. In the testing sets, Lasso prediction achieved the accuracies of 0.95, 0.96, and 0.85 for distinguishing between DPD and HC, NDPD and HC, and DPD and NDPD, respectively. Random forest achieved the accuracies of 0.90, 0.82, and 0.90 for distinguishing between DPD and HC, NDPD and HC, and DPD and NDPD, respectively, while SVM yielded the accuracies of 1, 0.86 and 0.65 for distinguishing between DPD and HC, NDPD and HC, and DPD and NDPD, respectively.ConclusionsBy identifying aberrant functional connectivity and activity as potential biomarkers, the radiomic approach facilitates a deeper understanding and provides new insights into the pathophysiology of DPD to support the clinical diagnosis with high prediction accuracy.

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.