One-step Bayesian example-dependent cost classification: The OsC-MLP method

Example-dependent cost classification problems are those where the decision costs depend not only on the true and the attributed classes but also on the sample features. Discriminative algorithms that carry out such classification tasks must take this dependence into account. In some applications, the decision costs are known for the training set but not in production, which complicates the problem. In this paper, we introduce a new one-step Bayesian formulation to train Neural Networks and solve the above limitation for binary cases with one-step Learning Machines, avoiding the drawbacks that unknown analytical forms of the example-dependent costs create. The formulation is based on defining an artificial likelihood ratio by using the available training classification costs in its definition, and proposes a test that does not require the values of the costs for unseen samples. Furthermore, it also includes Bayesian rebalancing mechanisms to combat the negative effects of class imbalance. Experimental results support the consistency and effectiveness of the corresponding algorithms.

Handling of problematic ion chromatograms with the Automated Target Screening (ATS) workflow for unsupervised analysis of high-resolution mass spectrometry data

Liquid chromatography (LC) or gas chromatography (GC) coupled to high-resolution mass spectrometry (HRMS) is a versatile analytical method for the analysis of thousands of chemical pollutants that can be found in environmental and biological samples. While the tools for handling such complex datasets have improved, there are still no fully automated workflows for targeted screening analysis. Here we present an R-based workflow that is able to cope with challenging data like noisy ion chromatograms, retention time shifts, and multiple peak patterns. The workflow can be applied to batches of HRMS data recorded after GC with electron ionization (GC-EI) and LC coupled to electrospray ionization in both negative and positive mode (LC-ESIneg/LC-ESIpos) to perform peak annotation and quantitation fully unsupervised. We used Orbitrap HRMS data of surface water extracts to compare the Automated Target Screening (ATS) workflow with data evaluations performed with the vendor software TraceFinder and the established semi-automated analysis workflow in the MZmine software. The ATS approach increased the overall evaluation performance of the peak annotation compared to the established MZmine module without the need for any post-hoc corrections. The overall accuracy increased from 0.80 to 0.86 (LC-ESIpos), from 0.77 to 0.83 (LC-ESIneg), and from 0.67 to 0.76 (GC-EI). The mean average percentage errors for quantification of ATS were around 30% compared to the manual quantification with TraceFinder. The ATS workflow enables time-efficient analysis of GC- and LC-HRMS data and accelerates and improves the applicability of target screening in studies with a large number of analytes and sample sizes without the need for manual intervention.

Human-in-the-Loop: Visual Analytics for Building Models Recognizing Behavioral Patterns in Time Series

Detecting complex behavioral patterns in temporal data, such as moving object trajectories, often relies on precise formal specifications derived from vague domain concepts. However, such methods are sensitive to noise and minor fluctuations, leading to missed pattern occurrences. Conversely, machine learning (ML) approaches require abundant labeled examples, posing practical challenges. Our visual analytics approach enables domain experts to derive, test, and combine interval-based features to discriminate patterns and generate training data for ML algorithms. Visual aids enhance recognition and characterization of expected patterns and discovery of unexpected ones. Case studies demonstrate feasibility and effectiveness of the approach, which offers a novel framework for integrating human expertise and analytical reasoning with ML techniques, advancing data analytics.

Harnessing machine learning for EEG signal analysis: Innovations in depth of anaesthesia assessment

Anaesthesia, crucial to surgical practice, is undergoing renewed scrutiny due to the integration of artificial intelligence in its medical use. The precise control over the temporary loss of consciousness is vital to ensure safe, pain-free procedures. Traditional methods of depth of anaesthesia (DoA) assessment, reliant on physical characteristics, have proven inconsistent due to individual variations. In response, electroencephalography (EEG) techniques have emerged, with indices such as the Bispectral Index offering quantifiable assessments. This literature review explores the current scope and frontier of DoA research, emphasising methods utilising EEG signals for effective clinical monitoring. This review offers a critical synthesis of recent advances, specifically focusing on electroencephalography (EEG) techniques and their role in enhancing clinical monitoring. By examining 117 high-impact papers, the review delves into the nuances of feature extraction, model building, and algorithm design in EEG-based DoA analysis. Comparative assessments of these studies highlight their methodological approaches and performance, including clinical correlations with established indices like the Bispectral Index. The review identifies knowledge gaps, particularly the need for improved collaboration for data access, which is essential for developing superior machine learning models and real-time predictive algorithms for patient management. It also calls for refined model evaluation processes to ensure robustness across diverse patient demographics and anaesthetic agents. The review underscores the potential of technological advancements to enhance precision, safety, and patient outcomes in anaesthesia, paving the way for a new standard in anaesthetic care. The findings of this review contribute to the ongoing discourse on the application of EEG in anaesthesia, providing insights into the potential for technological advancement in this critical area of medical practice.

Graph Attention-Based Curriculum Learning for Mental Healthcare Classification

Current research has examined the use of user-generated data from online media to identify and diagnose depression as a serious mental health issue that can significantly impact an individual's daily life. To this end, many studies examined words in personal statements to identify depression. In addition to aiding in the diagnosis and treatment of depression, this study uses and utilizes a Graph Attention Network (GAT) model for the classification of depression from online media. The model is based on masked self-attention layers, that assigns different weight to each node in a neighborhood without costly matrix operations. In addition, an emotion lexicon was extended using hypernyms to improve the model performance. Furthermore, embedding of the model was used to illustrate the contribution of the activated words to each symptom and to obtain qualitative agreement from psychiatrists. This technique uses previously learned embedding to illustrate the contribution of activated words to depressive symptoms in online forums. A significant improvement was observed in the model's performance through the use of the lexicon extension method, resulting in an increase in the ROC performance. The performance was also enhanced by an increase in vocabulary and the adoption of a graph-based curriculum. The lexicon expansion method involves the generation of additional words with similar semantic attributes, utilizing similarity metrics to reinforce lexical features. The graph-based curriculum learning also utilized to handle more challenging training samples, allowing the model to develop increasing expertise in learning complex correlations between input data and output labels.

A Machine Learning Approach to Predict Post-stroke Fatigue. The Nor-COAST study

OBJECTIVE

This study aimed to predict fatigue 18 months post-stroke by utilizing comprehensive data from the acute and sub-acute phases after stroke in a machine-learning set-up.

DESIGN

A prospective multicenter cohort-study with 18-month follow-up.

SETTING

Outpatient clinics at 3 university hospitals and 2 local hospitals.

PARTICIPANTS

474 participants with the diagnosis of acute stroke (mean ± SD age; 70.5 (11.3), 59% male; N=474).

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURES

The primary outcome, fatigue at 18 months, was assessed using the Fatigue Severity Scale (FSS-7). FSS-7≥5 was defined as fatigue. In total, 45 prediction variables were collected, at initial hospital-stay and 3-month post-stroke.

RESULTS

The best performing model, random forest, predicted 69% of all subjects with fatigue correctly with a sensitivity of 0.69 (95% CI: 0.50, 0.86), a specificity of 0.74 (95% CI: 0.66, 0.83), and an Area under the Receiver Operator Characteristic curve of 0.79 (95% CI: 0.69, 0.87) in new unseen data. The proportion of subjects predicted to suffer from fatigue, who truly suffered from fatigue at 18-months was estimated to 0.41 (95% CI: 0.26, 0.57). The proportion of subjects predicted to be free from fatigue who truly did not have fatigue at 18-months was estimated to 0.90 (95% CI: 0.83, 0.96).

CONCLUSIONS

Our findings indicate that the model has satisfactory ability to predict fatigue in the chronic phase post-stroke and may be applicable in clinical settings.

Very Long-Term Functional Outcomes and Dependency in Children With Anti-NMDA Receptor Encephalitis

OBJECTIVES

To assess the daily function of children with anti-N-methyl-d-aspartate receptor encephalitis (NMDARe) after a minimal follow-up of 5 years.

METHODS

Patients 18 years and younger by the time of disease onset, whose serum and CSF were studied in our center between 2013 and 2017, were included in the study. Patients' daily life function was assessed by their physicians using a 15-domain question format (Liverpool Outcome Score).

RESULTS

Of 76 patients, 8 (11%) died and 68 were followed for a mean of 7.1 years (SD 1.5 years, range: 5.0-10.1). Three outcome patterns were identified: full recovery (50; 73%); behavioral and school/working deficits (12; 18%); and multidomain deficits (6; 9%) involving self-care ability, behavioral-cognitive impairment, and seizures. Younger age of disease onset was significantly associated with multidomain deficits (OR 1.6, 95% CI 1.02-2.4, p = 0.04), particularly in children younger than 6 years, among whom 8 of 23 (35%) remained sociofamiliar dependent.

DISCUSSION

After a minimal follow-up of 5 years, most children with NMDARe had substantial or full functional recovery, but approximately one-fifth remained with behavioral and school/working deficits. The younger the patient at disease onset, the more probable it was to remain with multidomain deficits and dependent on sociofamiliar support.

Magnetoencephalography Decoding Transfer Approach: From Deep Learning Models to Intrinsically Interpretable Models

When decoding neuroelectrophysiological signals represented by Magnetoencephalography (MEG), deep learning models generally achieve high predictive performance but lack the ability to interpret their predicted results. This limitation prevents them from meeting the essential requirements of reliability and ethical-legal considerations in practical applications. In contrast, intrinsically interpretable models, such as decision trees, possess self-evident interpretability while typically sacrificing accuracy. To effectively combine the respective advantages of both deep learning and intrinsically interpretable models, an MEG transfer approach through feature attribution-based knowledge distillation is pioneered, which transforms deep models (teacher) into highly accurate intrinsically interpretable models (student). The resulting models provide not only intrinsic interpretability but also high predictive performance, besides serving as an excellent approximate proxy to understand the inner workings of deep models. In the proposed approach, post-hoc feature knowledge derived from post-hoc interpretable algorithms, specifically feature attribution maps, is introduced into knowledge distillation for the first time. By guiding intrinsically interpretable models to assimilate this knowledge, the transfer of MEG decoding information from deep models to intrinsically interpretable models is implemented. Experimental results demonstrate that the proposed approach outperforms the benchmark knowledge distillation algorithms. This approach successfully improves the prediction accuracy of Soft Decision Tree by a maximum of 8.28%, reaching almost equivalent or even superior performance to deep teacher models. Furthermore, the model-agnostic nature of this approach offers broad application potential.

Spatio-Temporal Graph Representation Learning for Fraudster Group Detection

Motivated by potential financial gain, companies may hire fraudster groups to write fake reviews to either demote competitors or promote their own businesses. Such groups are considerably more successful in misleading customers, as people are more likely to be influenced by the opinion of a large group. To detect such groups, a common model is to represent fraudster groups' static networks, consequently overlooking the longitudinal behavior of a reviewer, thus, the dynamics of coreview relations among reviewers in a group. Hence, these approaches are incapable of excluding outlier reviewers, which are fraudsters intentionally camouflaging themselves in a group and genuine reviewers happen to coreview in fraudster groups. To address this issue, we propose "FGDT," a framework for "fraudster group detection through temporal relations." FGDT first capitalizes on the effectiveness of the HIN-recurrent neural network (RNN) in both reviewers' representation learning while capturing the collaboration between reviewers. The HIN-RNN models the coreview relations of reviewers in a group in a fixed time window of 28 days. We refer to this as spatial relation learning representation to signify the generalizability of this work to other networked scenarios. Then, we use an RNN on the spatial relations to predict the spatio-temporal relations of reviewers in the group. In the third step, a graph convolution network (GCN) refines the reviewers' vector representations using these predicted relations. These refined representations are then used to remove outlier reviewers. The average of the remaining reviewers' representation is then fed to a simple fully connected layer to predict if the group is a fraudster group or not. Exhaustive experiments of FGDT showed a 5% (4%), 12% (5%), and 12% (5%) improvement over three of the most recent approaches on precision, recall, and F1-value over the Yelp (Amazon) dataset, respectively.

The keys of pressing to gain the ball - Characteristics of defensive pressure in elite soccer using tracking data

Recently, the availability of big amounts of data enables analysts to dive deeper into the constraints of performance in various team sports. While offensive analyses in football have been extensively conducted, the evaluation of defensive performance is underrepresented in this sport. Hence, the aim of this study was to analyze successful defensive playing phases by investigating the space and time characteristics of defensive pressure.Therefore, tracking and event data of 153 games of the German Bundesliga (second half of 2020/21 season) were assessed. Defensive pressure was measured in the last 10 seconds of a defensive playing sequence (time characteristic) and it was distinguished between pressure on the ball-carrier, pressure on the group (5 attackers closest to the ball), and pressure on the whole team (space characteristic). A linear mixed model was applied to evaluate the effect of success of a defensive play (ball gain), space characteristic, and time characteristic on defensive pressure.Defensive pressure is higher in successful defensive plays (14.47 ± 16.82[%]) compared to unsuccessful defensive plays (12.87 ± 15.31[%]). The characteristics show that defensive pressure is higher in areas closer to the ball (space characteristic) and the closer the measurement is to the end of a defensive play (time characteristic), which is especially true for successful defensive plays. Defensive pressure is a valuable key performance indicator for defensive play. Further, this study shows that there is an association between the pressing of the ball-carrier and areas close to the ball with the success of defensive play.

A Little Truth Injection But a Big Reward: Label Aggregation With Graph Neural Networks

Various correlations hidden in crowdsourcing annotation tasks bring opportunities to further improve the accuracy of label aggregation. However, these relationships are usually extremely difficult to be modeled. Most existing methods can merely make use of one or two correlations. In this paper, we propose a novel graph neural network model, namely LAGNN, which models five different correlations in crowdsourced annotation tasks by utilizing deep graph neural networks with convolution operations and derives a high label aggregation performance. Utilizing the group of high quality workers through labeling similarity, LAGNN can efficiently revise the preference among workers. Moreover, by injecting a little ground truth in its training stage, the label aggregation performance of LAGNN can be further significantly improved. We evaluate LAGNN on a large number of simulated datasets generated through varying six degrees of freedom and on eight real-world crowdsourcing datasets in both supervised and unsupervised (agnostic) modes. Experiments on data leakage is also contained. Experimental results consistently show that the proposed LAGNN significantly outperforms six state-of-the-art models in terms of label aggregation accuracy.

Building large-scale registries from unstructured clinical notes using a low-resource natural language processing pipeline

Building clinical registries is an important step in clinical research and improvement of patient care quality. Natural Language Processing (NLP) methods have shown promising results in extracting valuable information from unstructured clinical notes. However, the structure and nature of clinical notes are very different from regular text that state-of-the-art NLP models are trained and tested on, and they have their own set of challenges. In this study, we propose Sentence Extractor with Keywords (SE-K), an efficient and interpretable classification approach for extracting information from clinical notes and show that it outperforms more computationally expensive methods in text classification. Following the Institutional Review Board (IRB) approval, we used SE-K and two embedding based NLP approaches (Sentence Extractor with Embeddings (SE-E) and Bidirectional Encoder Representations from Transformers (BERT)) to develop comprehensive registry of anterior cruciate ligament surgeries from 20 years of unstructured clinical data at a multi-site tertiary-care regional children's hospital. The low-resource approach (SE-K) had better performance (average AUROC of 0.94 ± 0.04) than the embedding-based approaches (SE-E: 0.93 ± 0.04 and BERT: 0.87 ± 0.09) for out of sample validation, in addition to minimum performance drop between test and out-of-sample validation. Moreover, the SE-K approach was at least six times faster (on CPU) than SE-E (on CPU) and BERT (on GPU) and provides interpretability. Our proposed approach, SE-K, can be effectively used to extract relevant variables from clinic notes to build large-scale registries, with consistently better performance compared to the more resource-intensive approaches (e.g., BERT). Such approaches can facilitate information extraction from unstructured notes for registry building, quality improvement and adverse event monitoring.

Working memory load recognition with deep learning time series classification

Working memory load (WML) is one of the widely applied signals in the areas of human-machine interaction. The precise evaluation of the WML is crucial for this kind of application. This study aims to propose a deep learning (DL) time series classification (TSC) model for inter-subject WML decoding. We used fNIRS to record the hemodynamic signals of 27 participants during visual working memory tasks. Traditional machine learning and deep time series classification algorithms were respectively used for intra-subject and inter-subject WML decoding from the collected blood oxygen signals. The intra-subject classification accuracy of LDA and SVM were 94.6% and 79.1%. Our proposed TAResnet-BiLSTM model had the highest inter-subject WML decoding accuracy, reaching 92.4%. This study provides a new idea and method for the brain-computer interface application of fNIRS in real-time WML detection.

A revision of the dorsal origin of the frontal aslant tract (FAT) in the superior frontal gyrus: a DWI-tractographic study

The frontal aslant tract (FAT) is a white matter tract connecting the superior frontal gyrus (SFG) to the inferior frontal gyrus (IFG). Its dorsal origin is identified in humans in the medial wall of the SFG, in the supplementary motor complex (SM-complex). However, empirical observation shows that many FAT fibres appear to originate from the dorsal, rather than medial, portion of the SFG. We quantitatively investigated the actual origin of FAT fibres in the SFG, specifically discriminating between terminations in the medial wall and in the convexity of the SFG. We analysed data from 105 subjects obtained from the Human Connectome Project (HCP) database. We parcelled the cortex of the IFG, dorsal SFG and medial SFG in several regions of interest (ROIs) ordered in a caudal-rostral direction, which served as seed locations for the generation of streamlines. Diffusion imaging data (DWI) was processed using a multi-shell multi-tissue CSD-based algorithm. Results showed that the number of streamlines originating from the dorsal wall of the SFG significantly exceeds those from the medial wall of the SFG. Connectivity patterns between ROIs indicated that FAT sub-bundles are segregated in parallel circuits ordered in a caudal-rostral direction. Such high degree of coherence in the streamline trajectory allows to establish pairs of homologous cortical parcels in the SFG and IFG. We conclude that the frontal origin of the FAT is found in both dorsal and medial surfaces of the superior frontal gyrus.

Inference of dynamic hypergraph representations in temporal interaction data

A range of systems across the social and natural sciences generate data sets consisting of interactions between two distinct categories of items at various instances in time. Online shopping, for example, generates purchasing events of the form (user, product, time of purchase), and mutualistic interactions in plant-pollinator systems generate pollination events of the form (insect, plant, time of pollination). These data sets can be meaningfully modeled as temporal hypergraph snapshots in which multiple items within one category (i.e., online shoppers) share a hyperedge if they interacted with a common item in the other category (i.e., purchased the same product) within a given time window, allowing for the application of hypergraph analysis techniques. However, it is often unclear how to choose the number and duration of these temporal snapshots, which have a strong influence on the final hypergraph representations. Here we propose a principled nonparametric solution to this problem by extracting temporal hypergraph snapshots that optimally capture structural regularities in temporal event data according to the minimum description length principle. We demonstrate our methods on real and synthetic data sets, finding that they can recover planted artificial hypergraph structure in the presence of considerable noise and reveal meaningful activity fluctuations in human mobility data.

A Comparison of Signals of Designated Medical Events and Non-designated Medical Events: Results from a Scoping Review

INTRODUCTION AND OBJECTIVE

The European Medicines Agency (EMA) maintains a list of designated medical events (DMEs), events that are inherently serious and are prioritized for signal detection, irrespective of statistical criteria. We have analysed the results of our previously published scoping review to determine whether DME signals differ from those of other adverse events in terms of time to communication and characteristics of supporting reports of suspected adverse drug reactions.

METHODS

For all signals, we obtained the launch year of medicinal products from textbooks or regulatory agencies, extracted the year of the first report in VigiBase and calculated the interval between the first report and communication (time to communication, TTC). We further retrieved the average completeness (via vigiGrade) of the reports in each case series in the years before the communication. We categorised as DME signals those concerning an event in the EMA's list. We described the two groups of signals using medians and interquartile ranges (IQR) and compared them using the Brunner-Munzel test, calculating 95% confidence intervals (95% CI) and P values.

RESULTS

Of 4520 signals, 919 concerned DMEs and 3601 concerned non-DMEs. Signals of DMEs were supported by a median of 15 reports (IQR 6-38 reports) with a completeness score of 0.52 (IQR 0.43-0.62) and signals of non-DMEs by 20 reports (IQR 6-84 reports) with a completeness score of 0.46 (IQR 0.38-0.56). The probability that a random DME signal was supported by fewer reports than non-DME signals was 0.56 (95% CI 0.54-0.58, P < 0.001) and that of one having lower average completeness was 0.39 (95% CI 0.36-0.41, P < 0.001). The median TTCs of DME and non-DME signals did not differ (10 years), but the TTC was as low as 2 years when signals (irrespective of classification) were supported by reports whose average completeness was > 0.80.

CONCLUSIONS

Signals of designated medical events were supported by fewer reports and higher completeness scores than signals of other adverse events. Although statistically significant, the differences in effect sizes between the two groups were small. This suggests that listing certain adverse events as DMEs is not having the expected effect of encouraging a focus on reports of the types of suspected adverse reactions that deserve special attention. Further enhancing the completeness of the reports of suspected adverse drug reactions supporting signals of designated medical events might shorten their time to communication and reduce the number of reports required to support them.

Universal Digital High-Resolution Melt Analysis for the Diagnosis of Bacteremia

Fast and accurate diagnosis of bloodstream infection is necessary to inform treatment decisions for septic patients, who face hourly increases in mortality risk. Blood culture remains the gold standard test but typically requires approximately 15 hours to detect the presence of a pathogen. We, therefore, assessed the potential for universal digital high-resolution melt (U-dHRM) analysis to accomplish faster broad-based bacterial detection, load quantification, and species-level identification directly from whole blood. Analytical validation studies demonstrated strong agreement between U-dHRM load measurement and quantitative blood culture, indicating that U-dHRM detection is highly specific to intact organisms. In a pilot clinical study of 17 whole blood samples from pediatric patients undergoing simultaneous blood culture testing, U-dHRM achieved 100% concordance when compared with blood culture and 88% concordance when compared with clinical adjudication. Moreover, U-dHRM identified the causative pathogen to the species level in all cases where the organism was represented in the melt curve database. These results were achieved with a 1-mL sample input and sample-to-answer time of 6 hours. Overall, this pilot study suggests that U-dHRM may be a promising method to address the challenges of quickly and accurately diagnosing a bloodstream infection.

Incremental high average-utility itemset mining: survey and challenges

The High Average Utility Itemset Mining (HAUIM) technique, a variation of High Utility Itemset Mining (HUIM), uses the average utility of the itemsets. Historically, most HAUIM algorithms were designed for static databases. However, practical applications like market basket analysis and business decision-making necessitate regular updates of the database with new transactions. As a result, researchers have developed incremental HAUIM (iHAUIM) algorithms to identify HAUIs in a dynamically updated database. Contrary to conventional methods that begin from scratch, the iHAUIM algorithm facilitates incremental changes and outputs, thereby reducing the cost of discovery. This paper provides a comprehensive review of the state-of-the-art iHAUIM algorithms, analyzing their unique characteristics and advantages. First, we explain the concept of iHAUIM, providing formulas and real-world examples for a more in-depth understanding. Subsequently, we categorize and discuss the key technologies used by varying types of iHAUIM algorithms, encompassing Apriori-based, Tree-based, and Utility-list-based techniques. Moreover, we conduct a critical analysis of each mining method's advantages and disadvantages. In conclusion, we explore potential future directions, research opportunities, and various extensions of the iHAUIM algorithm.

Navigating duplication in pharmacovigilance databases: a scoping review

OBJECTIVES

Pharmacovigilance databases play a critical role in monitoring drug safety. The duplication of reports in pharmacovigilance databases, however, undermines their data integrity. This scoping review sought to provide a comprehensive understanding of duplication in pharmacovigilance databases worldwide.

DESIGN

A scoping review.

DATA SOURCES

Reviewers comprehensively searched the literature in PubMed, Web of Science, Wiley Online Library, EBSCOhost, Google Scholar and other relevant websites.

ELIGIBILITY CRITERIA

Peer-reviewed publications and grey literature, without language restriction, describing duplication and/or methods relevant to duplication in pharmacovigilance databases from inception to 1 September 2023.

DATA EXTRACTION AND SYNTHESIS

We used the Joanna Briggs Institute guidelines for scoping reviews and conformed with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews. Two reviewers independently screened titles, abstracts and full texts. One reviewer extracted the data and performed descriptive analysis, which the second reviewer assessed. Disagreements were resolved by discussion and consensus or in consultation with a third reviewer.

RESULTS

We screened 22 745 unique titles and 156 were eligible for full-text review. Of the 156 titles, 58 (47 peer-reviewed; 11 grey literature) fulfilled the inclusion criteria for the scoping review. Included titles addressed the extent (5 papers), prevention strategies (15 papers), causes (32 papers), detection methods (25 papers), management strategies (24 papers) and implications (14 papers) of duplication in pharmacovigilance databases. The papers overlapped, discussing more than one field. Advances in artificial intelligence, particularly natural language processing, hold promise in enhancing the efficiency and precision of deduplication of large and complex pharmacovigilance databases.

CONCLUSION

Duplication in pharmacovigilance databases compromises risk assessment and decision-making, potentially threatening patient safety. Therefore, efficient duplicate prevention, detection and management are essential for more reliable pharmacovigilance data. To minimise duplication, consistent use of worldwide unique identifiers as the key case identifiers is recommended alongside recent advances in artificial intelligence.

Using full-text content to characterize and identify best seller books: A study of early 20th-century literature

Artistic pieces can be studied from several perspectives, one example being their reception among readers over time. In the present work, we approach this interesting topic from the standpoint of literary works, particularly assessing the task of predicting whether a book will become a best seller. Unlike previous approaches, we focused on the full content of books and considered visualization and classification tasks. We employed visualization for the preliminary exploration of the data structure and properties, involving SemAxis and linear discriminant analyses. To obtain quantitative and more objective results, we employed various classifiers. Such approaches were used along with a dataset containing (i) books published from 1895 to 1923 and consecrated as best sellers by the Publishers Weekly Bestseller Lists and (ii) literary works published in the same period but not being mentioned in that list. Our comparison of methods revealed that the best-achieved result-combining a bag-of-words representation with a logistic regression classifier-led to an average accuracy of 0.75 both for the leave-one-out and 10-fold cross-validations. Such an outcome enhances the difficulty in predicting the success of books with high accuracy, even using the full content of the texts. Nevertheless, our findings provide insights into the factors leading to the relative success of a literary work.

A Precise Framework for Rice Leaf Disease Image-Text Retrieval Using FHTW-Net

Cross-modal retrieval for rice leaf diseases is crucial for prevention, providing agricultural experts with data-driven decision support to address disease threats and safeguard rice production. To overcome the limitations of current crop leaf disease retrieval frameworks, we focused on four common rice leaf diseases and established the first cross-modal rice leaf disease retrieval dataset (CRLDRD). We introduced cross-modal retrieval to the domain of rice leaf disease retrieval and introduced FHTW-Net, a framework for rice leaf disease image-text retrieval. To address the challenge of matching diverse image categories with complex text descriptions during the retrieval process, we initially employed ViT and BERT to extract fine-grained image and text feature sequences enriched with contextual information. Subsequently, two-way mixed self-attention (TMS) was introduced to enhance both image and text feature sequences, with the aim of uncovering important semantic information in both modalities. Then, we developed false-negative elimination-hard negative mining (FNE-HNM) strategy to facilitate in-depth exploration of semantic connections between different modalities. This strategy aids in selecting challenging negative samples for elimination to constrain the model within the triplet loss function. Finally, we introduced warm-up bat algorithm (WBA) for learning rate optimization, which improves the model's convergence speed and accuracy. Experimental results demonstrated that FHTW-Net outperforms state-of-the-art models. In image-to-text retrieval, it achieved R@1, R@5, and R@10 accuracies of 83.5%, 92%, and 94%, respectively, while in text-to-image retrieval, it achieved accuracies of 82.5%, 98%, and 98.5%, respectively. FHTW-Net offers advanced technical support and algorithmic guidance for cross-modal retrieval of rice leaf diseases.

Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning

BACKGROUND

Electronic fetal monitoring is used in most US hospital births but has significant limitations in achieving its intended goal of preventing intrapartum hypoxic-ischemic injury. Novel deep learning techniques can improve complex data processing and pattern recognition in medicine.

OBJECTIVE

This study aimed to apply deep learning approaches to develop and validate a model to predict fetal acidemia from electronic fetal monitoring data.

STUDY DESIGN

The database was created using intrapartum electronic fetal monitoring data from 2006 to 2020 from a large, multisite academic health system. Data were divided into training and testing sets with equal distribution of acidemic cases. Several different deep learning architectures were explored. The primary outcome was umbilical artery acidemia, which was investigated at 4 clinically meaningful thresholds: 7.20, 7.15, 7.10, and 7.05, along with base excess. The receiver operating characteristic curves were generated with the area under the receiver operating characteristic assessed to determine the performance of the models. External validation was performed using a publicly available Czech database of electronic fetal monitoring data.

RESULTS

A total of 124,777 electronic fetal monitoring files were available, of which 77,132 had <30% missingness in the last 60 minutes of the electronic fetal monitoring tracing. Of these, 21,041 were matched to a corresponding umbilical cord gas result, of which 10,182 were time-stamped within 30 minutes of the last electronic fetal monitoring reading and composed the final dataset. The prevalence rates of the outcomes in the data were 20.9% with a pH of <7.2, 9.1% with a pH of <7.15, 3.3% with a pH of <7.10, and 1.3% with a pH of <7.05. The best performing model achieved an area under the receiver operating characteristic of 0.85 at a pH threshold of <7.05. When predicting the joint outcome of both pH of <7.05 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.89 was achieved. When predicting both pH of <7.20 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.87 was achieved. At a pH of <7.15 and a positive predictive value of 30%, the model achieved a sensitivity of 90% and a specificity of 48%.

CONCLUSION

The application of deep learning methods to intrapartum electronic fetal monitoring analysis achieves promising performance in predicting fetal acidemia. This technology could help improve the accuracy and consistency of electronic fetal monitoring interpretation.

Participatory Health Cadre Model to Improve Exclusive Breastfeeding Coverage with King's Conceptual System

Objective

The purpose of this research is to develop a participatory health cadre model to enhance exclusive breastfeeding coverage through initial stages using the Imogene King model.

Methods

This study employs a mixed-methods approach with sequential exploratory designs. Qualitative research utilized in-depth interviews with informants including the head of the community health center, nutrition officers from the health center, the coordinator of Maternal and Child Health (MCH) midwives, village midwives, breastfeeding mothers, families of breastfeeding mothers, and health cadres. Quantitative research respondents consist of health cadres. The quantitative study utilizes a quasi-experimental method with a design paradigm known as the one-group pre and post-test design to measure health cadre perception on exclusive breastfeeding.

Results

This study yields elements from Imogene King that form a participatory health cadre model to enhance exclusive breastfeeding coverage, consisting of interaction, perception, communication, transaction, role, growth and development, time, and space. Transactions represent the objective integration of the health cadre participation model, as demonstrated by the behavioral shifts observed in mothers regarding breastfeeding their infants. The t-test results indicate that exclusive breastfeeding monitoring training is effective and successful in enhancing exclusive breastfeeding coverage (Sig. value = 0.000 < 0.05). In addition, the effectiveness of exclusive breastfeeding monitoring training falls within the category of good or high.

Conclusion

The research findings indicate the success of the participatory health cadre model in improving exclusive breastfeeding coverage.

High-Accuracy Tomato Leaf Disease Image-Text Retrieval Method Utilizing LAFANet

Tomato leaf disease control in the field of smart agriculture urgently requires attention and reinforcement. This paper proposes a method called LAFANet for image-text retrieval, which integrates image and text information for joint analysis of multimodal data, helping agricultural practitioners to provide more comprehensive and in-depth diagnostic evidence to ensure the quality and yield of tomatoes. First, we focus on six common tomato leaf disease images and text descriptions, creating a Tomato Leaf Disease Image-Text Retrieval Dataset (TLDITRD), introducing image-text retrieval into the field of tomato leaf disease retrieval. Then, utilizing ViT and BERT models, we extract detailed image features and sequences of textual features, incorporating contextual information from image-text pairs. To address errors in image-text retrieval caused by complex backgrounds, we propose Learnable Fusion Attention (LFA) to amplify the fusion of textual and image features, thereby extracting substantial semantic insights from both modalities. To delve further into the semantic connections across various modalities, we propose a False Negative Elimination-Adversarial Negative Selection (FNE-ANS) approach. This method aims to identify adversarial negative instances that specifically target false negatives within the triplet function, thereby imposing constraints on the model. To bolster the model's capacity for generalization and precision, we propose Adversarial Regularization (AR). This approach involves incorporating adversarial perturbations during model training, thereby fortifying its resilience and adaptability to slight variations in input data. Experimental results show that, compared with existing ultramodern models, LAFANet outperformed existing models on TLDITRD dataset, with top1, top5, and top10 reaching 83.3% and 90.0%, and top1, top5, and top10 reaching 80.3%, 93.7%, and 96.3%. LAFANet offers fresh technical backing and algorithmic insights for the retrieval of tomato leaf disease through image-text correlation.

Enhancing accuracy and convenience of golf swing tracking with a wrist-worn single inertial sensor

In this study, we address two technical challenges to enhance golf swing trajectory accuracy using a wrist-worn inertial sensor: orientation estimation and drift error mitigation. We extrapolated consistent sensor orientation from specific address-phase signal segments and trained the estimation with a convolutional neural network. We then mitigated drift error by applying a constraint on wrist speed at the address, backswing top, and finish, and ensuring that the wrist's finish displacement aligns with a virtual circle on the 3D swing plane. To verify the proposed methods, we gathered data from twenty male right-handed golfers, including professionals and amateurs, using a driver and a 7-iron. The orientation estimation error was about 60% of the baseline, comparable to studies requiring additional sensor information or calibration poses. The drift error was halved and the single-inertial-sensor tracking performance across all swing phases was about 17 cm, on par with multimodal approaches. This study introduces a novel signal processing method for tracking rapid, wide-ranging motions, such as a golf swing, while maintaining user convenience. Our results could impact the burgeoning field of daily motion monitoring for health care, especially with the increasing prevalence of wearable devices like smartwatches.

Prototype Learning for Medical Time Series Classification via Human-Machine Collaboration

Deep neural networks must address the dual challenge of delivering high-accuracy predictions and providing user-friendly explanations. While deep models are widely used in the field of time series modeling, deciphering the core principles that govern the models' outputs remains a significant challenge. This is crucial for fostering the development of trusted models and facilitating domain expert validation, thereby empowering users and domain experts to utilize them confidently in high-risk decision-making contexts (e.g., decision-support systems in healthcare). In this work, we put forward a deep prototype learning model that supports interpretable and manipulable modeling and classification of medical time series (i.e., ECG signal). Specifically, we first optimize the representation of single heartbeat data by employing a bidirectional long short-term memory and attention mechanism, and then construct prototypes during the training phase. The final classification outcomes (i.e., normal sinus rhythm, atrial fibrillation, and other rhythm) are determined by comparing the input with the obtained prototypes. Moreover, the proposed model presents a human-machine collaboration mechanism, allowing domain experts to refine the prototypes by integrating their expertise to further enhance the model's performance (contrary to the human-in-the-loop paradigm, where humans primarily act as supervisors or correctors, intervening when required, our approach focuses on a human-machine collaboration, wherein both parties engage as partners, enabling more fluid and integrated interactions). The experimental outcomes presented herein delineate that, within the realm of binary classification tasks-specifically distinguishing between normal sinus rhythm and atrial fibrillation-our proposed model, albeit registering marginally lower performance in comparison to certain established baseline models such as Convolutional Neural Networks (CNNs) and bidirectional long short-term memory with attention mechanisms (Bi-LSTMAttns), evidently surpasses other contemporary state-of-the-art prototype baseline models. Moreover, it demonstrates significantly enhanced performance relative to these prototype baseline models in the context of triple classification tasks, which encompass normal sinus rhythm, atrial fibrillation, and other rhythm classifications. The proposed model manifests a commendable prediction accuracy of 0.8414, coupled with macro precision, recall, and F1-score metrics of 0.8449, 0.8224, and 0.8235, respectively, achieving both high classification accuracy as well as good interpretability.

COVID-19 Hierarchical Classification Using a Deep Learning Multi-Modal

Coronavirus disease 2019 (COVID-19), originating in China, has rapidly spread worldwide. Physicians must examine infected patients and make timely decisions to isolate them. However, completing these processes is difficult due to limited time and availability of expert radiologists, as well as limitations of the reverse-transcription polymerase chain reaction (RT-PCR) method. Deep learning, a sophisticated machine learning technique, leverages radiological imaging modalities for disease diagnosis and image classification tasks. Previous research on COVID-19 classification has encountered several limitations, including binary classification methods, single-feature modalities, small public datasets, and reliance on CT diagnostic processes. Additionally, studies have often utilized a flat structure, disregarding the hierarchical structure of pneumonia classification. This study aims to overcome these limitations by identifying pneumonia caused by COVID-19, distinguishing it from other types of pneumonia and healthy lungs using chest X-ray (CXR) images and related tabular medical data, and demonstrate the value of incorporating tabular medical data in achieving more accurate diagnoses. Resnet-based and VGG-based pre-trained convolutional neural network (CNN) models were employed to extract features, which were then combined using early fusion for the classification of eight distinct classes. We leveraged the hierarchal structure of pneumonia classification within our approach to achieve improved classification outcomes. Since an imbalanced dataset is common in this field, a variety of versions of generative adversarial networks (GANs) were used to generate synthetic data. The proposed approach tested in our private datasets of 4523 patients achieved a macro-avg F1-score of 95.9% and an F1-score of 87.5% for COVID-19 identification using a Resnet-based structure. In conclusion, in this study, we were able to create an accurate deep learning multi-modal to diagnose COVID-19 and differentiate it from other kinds of pneumonia and normal lungs, which will enhance the radiological diagnostic process.

Improving Graph Convolutional Network with Learnable Edge Weights and Edge-Node Co-Embedding for Graph Anomaly Detection

The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it poses significant challenges due to the ubiquity of anomalies and the difficulty in identifying them accurately. This paper aims to enhance the performance of the current Graph Convolutional Network (GCN)-based Graph Anomaly Detection (GAD) algorithm on datasets with extremely low proportions of anomalous labels. This goal is achieved through modifying the GCN network structure and conducting feature extraction, thus fully utilizing three types of information in the graph: node label information, node feature information, and edge information. Firstly, we theoretically demonstrate the relationship between label propagation and feature convolution, indicating that the Label Propagation Algorithm (LPA) can serve as a regularization penalty term for GCN, aiding in training and enabling learnable edge weights, providing a basis for incorporating node label information into GCN networks. Secondly, we introduce a method to aggregate node and edge features, thereby incorporating edge information into GCN networks. Finally, we design different GCN trainable weights for node features and co-embedding features. This design allows different features to be projected into different spaces, greatly enhancing model expressiveness. Experimental results on the DGraph dataset demonstrate superior AUC performance compared to baseline models, highlighting the feasibility and efficacy of the proposed approach in addressing GAD tasks in the scene with extremely low proportions of anomalous data.

Reviewing the essential roles of remote phenotyping, GWAS and explainable AI in practical marker-assisted selection for drought-tolerant winter wheat breeding

Marker-assisted selection (MAS) plays a crucial role in crop breeding improving the speed and precision of conventional breeding programmes by quickly and reliably identifying and selecting plants with desired traits. However, the efficacy of MAS depends on several prerequisites, with precise phenotyping being a key aspect of any plant breeding programme. Recent advancements in high-throughput remote phenotyping, facilitated by unmanned aerial vehicles coupled to machine learning, offer a non-destructive and efficient alternative to traditional, time-consuming, and labour-intensive methods. Furthermore, MAS relies on knowledge of marker-trait associations, commonly obtained through genome-wide association studies (GWAS), to understand complex traits such as drought tolerance, including yield components and phenology. However, GWAS has limitations that artificial intelligence (AI) has been shown to partially overcome. Additionally, AI and its explainable variants, which ensure transparency and interpretability, are increasingly being used as recognised problem-solving tools throughout the breeding process. Given these rapid technological advancements, this review provides an overview of state-of-the-art methods and processes underlying each MAS, from phenotyping, genotyping and association analyses to the integration of explainable AI along the entire workflow. In this context, we specifically address the challenges and importance of breeding winter wheat for greater drought tolerance with stable yields, as regional droughts during critical developmental stages pose a threat to winter wheat production. Finally, we explore the transition from scientific progress to practical implementation and discuss ways to bridge the gap between cutting-edge developments and breeders, expediting MAS-based winter wheat breeding for drought tolerance.

Distinction of Chaos from Randomness Is Not Possible from the Degree Distribution of the Visibility and Phase Space Reconstruction Graphs

We investigate whether it is possible to distinguish chaotic time series from random time series using network theory. In this perspective, we selected four methods to generate graphs from time series: the natural, the horizontal, the limited penetrable horizontal visibility graph, and the phase space reconstruction method. These methods claim that the distinction of chaos from randomness is possible by studying the degree distribution of the generated graphs. We evaluated these methods by computing the results for chaotic time series from the 2D Torus Automorphisms, the chaotic Lorenz system, and a random sequence derived from the normal distribution. Although the results confirm previous studies, we found that the distinction of chaos from randomness is not generally possible in the context of the above methodologies.

Quantification of play behaviour in calves using automated ultra-wideband location data and its association with age, weaning and health status

Play behaviour can act as an indicator of positive animal welfare. Previous attempts to predict play behaviour in farmed calves are limited because of the classification methods used, which lead to overestimation, and the short time periods that calves are observed. The study aimed to automatically classify and quantify play behaviour in farmed calves using location data from ultra-wide band sensors and to investigate factors associated with play behaviour. Location data were collected from 46 calves in three cohorts for a period of 18 weeks. Behavioural observations from video footage were merged with location data to obtain a total of 101.36 h of labelled data. An AdaBoost ensemble learning algorithm was implemented to classify play behaviour. To account for overestimation, generally seen in low-prevalence behaviours, an adjusted count technique was applied to the outputs of the classifier. Two generalized linear mixed models were fitted to investigate factors (e.g. age, health) associated with duration of play and number of play instances per day. Our algorithm identified play behaviour with > 94% accuracy when evaluated on the test set with no animals used for training, and 16% overestimation, which was computed based on the predicted number of samples of play versus the number of samples labelled as play on the test set. The instances and duration of play behaviour per day significantly decreased with age and sickness, whilst play behaviour significantly increased during and after weaning. The instances of play also significantly decreased as mean temperature increased. We suggest that the quantification method that we used could be used to detect and monitor other low prevalence behaviours (e.g. social grooming) from location data, including indicators of positive welfare.

Enhancing volleyball training: empowering athletes and coaches through advanced sensing and analysis

Modern sensing technologies and data analysis methods usher in a new era for sports training and practice. Hidden insights can be uncovered and interactive training environments can be created by means of data analysis. We present a system to support volleyball training which makes use of Inertial Measurement Units, a pressure sensitive display floor, and machine learning techniques to automatically detect relevant behaviours and provides the user with the appropriate information. While working with trainers and amateur athletes, we also explore potential applications that are driven by automatic action recognition, that contribute various requirements to the platform. The first application is an automatic video-tagging protocol that marks key events (captured on video) based on the automatic recognition of volleyball-specific actions with an unweighted average recall of 78.71% in the 10-fold cross-validation setting with convolution neural network and 73.84% in leave-one-subject-out cross-validation setting with active data representation method using wearable sensors, as an exemplification of how dashboard and retrieval systems would work with the platform. In the context of action recognition, we have evaluated statistical functions and their transformation using active data representation besides raw signal of IMUs sensor. The second application is the "bump-set-spike" trainer, which uses automatic action recognition to provide real-time feedback about performance to steer player behaviour in volleyball, as an example of rich learning environments enabled by live action detection. In addition to describing these applications, we detail the system components and architecture and discuss the implications that our system might have for sports in general and for volleyball in particular.

Motif-based community detection in heterogeneous multilayer networks

Multilayer networks composed of intralayer edges and interlayer edges are an important type of complex networks. Considering the heterogeneity of nodes and edges, it is necessary to design more reasonable and diverse community detection methods for multilayer networks. Existing research on community detection in multilayer networks mainly focuses on multiplexing networks (where the nodes are homogeneous and the edges are heterogeneous), but few studies have focused on heterogeneous multilayer networks where both nodes and edges represent different semantics. In this paper, we studied community detection on heterogeneous multilayer networks and proposed a motif-based detection algorithm. First, the communities and motifs of multilayer networks are defined, especially the interlayer motifs. Then, the modularity of multilayer networks based on these motifs is designed, and the community structure of the multilayer network is detected by maximizing the modularity of multilayer networks. Finally, we verify the effectiveness of the detection algorithm on synthetic networks. In the experiments on synthetic networks, comparing with the classical community detection algorithms (without considering interlayer heterogeneity), the motif-based modularity community detection algorithm can obtain better results under different evaluation indexes, and we found that there exists a certain relationship between motifs and communities. In addition, the proposed algorithm is applied in the empirical network, which shows its practicability in the real world. This study provides a solution for the investigation of heterogeneous information in multilayer networks.

Non-invasive biomarkers for detecting progression toward hypovolemic cardiovascular instability in a lower body negative pressure model

Occult hemorrhages after trauma can be present insidiously, and if not detected early enough can result in patient death. This study evaluated a hemorrhage model on 18 human subjects, comparing the performance of traditional vital signs to multiple off-the-shelf non-invasive biomarkers. A validated lower body negative pressure (LBNP) model was used to induce progression towards hypovolemic cardiovascular instability. Traditional vital signs included mean arterial pressure (MAP), electrocardiography (ECG), plethysmography (Pleth), and the test systems utilized electrical impedance via commercial electrical impedance tomography (EIT) and multifrequency electrical impedance spectroscopy (EIS) devices. Absolute and relative metrics were used to evaluate the performance in addition to machine learning-based modeling. Relative EIT-based metrics measured on the thorax outperformed vital sign metrics (MAP, ECG, and Pleth) achieving an area-under-the-curve (AUC) of 0.99 (CI 0.95-1.00, 100% sensitivity, 87.5% specificity) at the smallest LBNP change (0-15 mmHg). The best vital sign metric (MAP) at this LBNP change yielded an AUC of 0.6 (CI 0.38-0.79, 100% sensitivity, 25% specificity). Out-of-sample predictive performance from machine learning models were strong, especially when combining signals from multiple technologies simultaneously. EIT, alone or in machine learning-based combination, appears promising as a technology for early detection of progression toward hemodynamic instability.

Detecting Leadership Opportunities in Group Discussions Using Off-the-Shelf VR Headsets

The absence of some forms of non-verbal communication in virtual reality (VR) can make VR-based group discussions difficult even when a leader is assigned to each group to facilitate discussions. In this paper, we discuss if the sensor data from off-the-shelf VR devices can be used to detect opportunities for facilitating engaging discussions and support leaders in VR-based group discussions. To this end, we focus on the detection of suppressed speaking intention in VR-based group discussions by using personalized and general models. Our extensive analysis of experimental data reveals some factors that should be considered to enable effective feedback to leaders. In particular, our results show the benefits of combining the sensor data from leaders and low-engagement participants, and the usefulness of specific HMD sensor features.

Determinants of multimodal fake review generation in China's E-commerce platforms

This paper develops a theoretical model of determinants influencing multimodal fake review generation using the theories of signaling, actor-network, motivation, and human-environment interaction hypothesis. Applying survey data from users of China's three leading E-commerce platforms (Taobao, Jingdong, and Pinduoduo), we adopt structural equation modeling, machine learning technique, and Bayesian complex networks analysis to perform factor identification, path analysis, feature factor importance ranking, regime division, and network centrality analysis of full sample, male sample, and female sample to reach the following conclusions: (1) platforms' multimodal recognition and governance capabilities exert significant negative moderating effects on merchants' information behavior, while it shows no apparent moderating effect on users' information behavior; users' emotional venting, perceived value, reward mechanisms, and subjective norms positively influence multimodal fake review generation through perceptual behavior control; (2) feature factors of multimodal fake review generation can be divided into four regimes, i.e., regime 1 includes reward mechanisms and perceived social costs, indicating they are key feature factors of multimodal fake review generation; merchant perception impact is positioned in regime 2, signifying its pivotal role in multimodal fake review generation; regime 3 includes multimodal recognition and governance capabilities, supporting/disparaging merchants, and emotional venting; whereas user perception impact is positioned in regime 4, indicating its weaker influence on multimodal fake review generation; (3) both in full sample, male sample, and female sample, reward mechanisms play a crucial role in multimodal fake review generation; perceived value, hiring review control agency, multimodal recognition and governance capabilities exhibit a high degree of correlation; however, results of network centrality analysis also exhibit heterogeneity between male and female samples, i.e., male sample has different trends in closeness centrality values and betweenness centrality values than female sample. This indicates that determinants influencing multimodal fake review generation are complex and interconnected.

Subgraph Isomorphic Decision Tree to Predict Radical Thermochemistry with Bounded Uncertainty Estimation

Detailed chemical kinetic models offer valuable mechanistic insights into industrial applications. Automatic generation of reliable kinetic models requires fast and accurate radical thermochemistry estimation. Kineticists often prefer hydrogen bond increment (HBI) corrections from a closed-shell molecule to the corresponding radical for their interpretability, physical meaning, and facilitation of error cancellation as a relative quantity. Tree estimators, used due to limited data, currently rely on expert knowledge and manual construction, posing challenges in maintenance and improvement. In this work, we extend the subgraph isomorphic decision tree (SIDT) algorithm originally developed for rate estimation to estimate HBI corrections. We introduce a physics-aware splitting criterion, explore a bounded weighted uncertainty estimation method, and evaluate aleatoric uncertainty-based and model variance reduction-based prepruning methods. Moreover, we compile a data set of thermochemical parameters for 2210 radicals involving C, O, N, and H based on quantum chemical calculations from recently published works. We leverage the collected data set to train the SIDT model. Compared to existing empirical tree estimators, the SIDT model (1) offers an automatic approach to generating and extending the tree estimator for thermochemistry, (2) has better accuracy and R2, (3) provides significantly more realistic uncertainty estimates, and (4) has a tree structure much more advantageous in descent speed. Overall, the SIDT estimator marks a great leap in kinetic modeling, offering more precise, reliable, and scalable predictions for radical thermochemistry.

Dynamic Bayesian network structure learning based on an improved bacterial foraging optimization algorithm

With the rapid development of artificial intelligence and data science, Dynamic Bayesian Network (DBN), as an effective probabilistic graphical model, has been widely used in many engineering fields. And swarm intelligence algorithm is an optimization algorithm based on natural selection with the characteristics of distributed, self-organization and robustness. By applying the high-performance swarm intelligence algorithm to DBN structure learning, we can fully utilize the algorithm's global search capability to effectively process time-based data, improve the efficiency of network generation and the accuracy of network structure. This study proposes an improved bacterial foraging optimization algorithm (IBFO-A) to solve the problems of random step size, limited group communication, and the inability to maintain a balance between global and local searching. The IBFO-A algorithm framework comprises four layers. First, population initialization is achieved using a logistics-sine chaotic mapping strategy as the basis for global optimization. Second, the activity strategy of a colony foraging trend is constructed by combining the exploration phase of the Osprey optimization algorithm. Subsequently, the strategy of bacterial colony propagation is improved using a "genetic" approach and the Multi-point crossover operator. Finally, the elimination-dispersal activity strategy is employed to escape the local optimal solution. To solve the problem of complex DBN learning structures due to the introduction of time information, a DBN structure learning method called IBFO-D, which is based on the IBFO-A algorithm framework, is proposed. IBFO-D determines the edge direction of the structure by combining the dynamic K2 scoring function, the designed V-structure orientation rule, and the trend activity strategy. Then, according to the improved reproductive activity strategy, the concept of "survival of the fittest" is applied to the network candidate solution while maintaining species diversity. Finally, the global optimal network structure with the highest score is obtained based on the elimination-dispersal activity strategy. Multiple tests and comparison experiments were conducted on 10 sets of benchmark test functions, two non-temporal and temporal data types, and six data samples of two benchmark 2T-BN networks to evaluate and analyze the optimization performance and structure learning ability of the proposed algorithm under various data types. The experimental results demonstrated that IBFO-A exhibits good convergence, stability, and accuracy, whereas IBFO-D is an effective approach for learning DBN structures from data and has practical value for engineering applications.

Multi-View Gait Analysis by Temporal Geometric Features of Human Body Parts

A gait is a walking pattern that can help identify a person. Recently, gait analysis employed a vision-based pose estimation for further feature extraction. This research aims to identify a person by analyzing their walking pattern. Moreover, the authors intend to expand gait analysis for other tasks, e.g., the analysis of clinical, psychological, and emotional tasks. The vision-based human pose estimation method is used in this study to extract the joint angles and rank correlation between them. We deploy the multi-view gait databases for the experiment, i.e., CASIA-B and OUMVLP-Pose. The features are separated into three parts, i.e., whole, upper, and lower body features, to study the effect of the human body part features on an analysis of the gait. For person identity matching, a minimum Dynamic Time Warping (DTW) distance is determined. Additionally, we apply a majority voting algorithm to integrate the separated matching results from multiple cameras to enhance accuracy, and it improved up to approximately 30% compared to matching without majority voting.

Human-centred explanations for artificial intelligence systems

As Artificial Intelligence (AI) systems increase in capability, so there are growing concerns over the ways in which the recommendations they provide can affect people's everyday life and decisions. The field of Explainable AI (XAI) aims to address such concerns but there is often a neglect of the human in this process. We present a formal definition of human-centred XAI and illustrate the application of this formalism to the design of a user interface. The user interface supports users in indicating their preferences relevant to a situation and to compare their preferences with those of a computer recommendation system. A user trial is conducted to evaluate the resulting user interface. From the user trial, we believe that users are able to appreciate how their preferences can influence computer recommendations, and how these might contrast with the preferences used by the computer. We provide guidelines of implementing human-centred XAI.

Reconstructing the evolution history of networked complex systems

The evolution processes of complex systems carry key information in the systems' functional properties. Applying machine learning algorithms, we demonstrate that the historical formation process of various networked complex systems can be extracted, including protein-protein interaction, ecology, and social network systems. The recovered evolution process has demonstrations of immense scientific values, such as interpreting the evolution of protein-protein interaction network, facilitating structure prediction, and particularly revealing the key co-evolution features of network structures such as preferential attachment, community structure, local clustering, degree-degree correlation that could not be explained collectively by previous theories. Intriguingly, we discover that for large networks, if the performance of the machine learning model is slightly better than a random guess on the pairwise order of links, reliable restoration of the overall network formation process can be achieved. This suggests that evolution history restoration is generally highly feasible on empirical networks.

Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images

Purpose

To develop and validate a deep learning system (DLS) for estimation of vertical cup-to-disc ratio (vCDR) in ultra-widefield (UWF) and smartphone-based fundus images.

Methods

A DLS consisting of two sequential convolutional neural networks (CNNs) to delineate optic disc (OD) and optic cup (OC) boundaries was developed using 800 standard fundus images from the public REFUGE data set. The CNNs were tested on 400 test images from the REFUGE data set and 296 UWF and 300 smartphone-based images from a teleophthalmology clinic. vCDRs derived from the delineated OD/OC boundaries were compared with optometrists' annotations using mean absolute error (MAE). Subgroup analysis was conducted to study the impact of peripapillary atrophy (PPA), and correlation study was performed to investigate potential correlations between sectoral CDR (sCDR) and retinal nerve fiber layer (RNFL) thickness.

Results

The system achieved MAEs of 0.040 (95% CI, 0.037-0.043) in the REFUGE test images, 0.068 (95% CI, 0.061-0.075) in the UWF images, and 0.084 (95% CI, 0.075-0.092) in the smartphone-based images. There was no statistical significance in differences between PPA and non-PPA images. Weak correlation (r = -0.4046, P < 0.05) between sCDR and RNFL thickness was found only in the superior sector.

Conclusions

We developed a deep learning system that estimates vCDR from standard, UWF, and smartphone-based images. We also described anatomic peripapillary adversarial lesion and its potential impact on OD/OC delineation.

Translational Relevance

Artificial intelligence can estimate vCDR from different types of fundus images and may be used as a general and interpretable screening tool to improve community reach for diagnosis and management of glaucoma.

Strategically Acquired Gradient Echo (STAGE) Imaging, part IV: Constrained Reconstruction of White Noise (CROWN) Processing as a Means to Improve Signal-to-Noise in STAGE Imaging at 3 Tesla

Increasing the signal-to-noise ratio (SNR) has always been of critical importance for magnetic resonance imaging. Although increasing field strength provides a linear increase in SNR, it is more and more costly as field strength increases. Therefore, there is a major effort today to use signal processing methods to improve SNR since it is more efficient and economical. There are a variety of methods to improve SNR such as averaging the data at the expense of imaging time, or collecting the data with a lower resolution, all of these methods, including imaging processing methods, usually come at the expense of loss of image detail or image blurring. Therefore, we developed a new mathematical approach called CROWN (Constrained Reconstruction of White Noise) to enhance SNR without loss of structural detail and without affecting scanning time. In this study, we introduced and tested the concept behind CROWN specifically for STAGE (strategically acquired gradient echo) imaging. The concept itself is presented first, followed by simulations to demonstrate its theoretical effectiveness. Then the SNR improvement on proton spin density (PSD) and R2⁎ maps was investigated using brain STAGE data acquired from 10 healthy controls (HCs) and 10 patients with Parkinson's disease (PD). For the PSD and R2* maps, the SNR and CNR between white matter and gray matter were improved by a factor of 1.87 ± 0.50 and 1.72 ± 0.88, respectively. The white matter hyperintensity lesions in PD patients were more clearly defined after CROWN processing. Using these improved maps, simulated images for any repeat time, echo time or flip angle can be created with improved SNR. The potential applications of this technology are to trade off the increased SNR for higher resolution images and/or faster imaging.

Lifestyle and health changes in wheelchair users with a chronic disability after 12 weeks of using the WHEELS mHealth application

PURPOSE

The aim of this study was to determine changes in physical activity, nutrition, sleep behaviour and body composition in wheelchair users with a chronic disability after 12 weeks of using the WHEELS mHealth application (app).

METHODS

A 12-week pre-post intervention study was performed, starting with a 1-week control period. Physical activity and sleep behaviour were continuously measured with a Fitbit charge 3. Self-reported nutritional intake, body mass and waist circumference were collected. Pre-post outcomes were compared with a paired-sample t-test or Wilcoxon signed-rank test. Fitbit data were analysed with a mixed model or a panel linear model. Effect sizes were determined and significance was accepted at p < .05.

RESULTS

Thirty participants completed the study. No significant changes in physical activity (+1.5 √steps) and sleep quality (-9.7 sleep minutes; -1.2% sleep efficiency) were found. Significant reduction in energy (-1022 kJ, d = 0.71), protein (-8.3 g, d = 0.61) and fat (-13.1 g, d = 0.87) intake, body mass (-2.2 kg, d = 0.61) and waist circumference (-3.3 cm, d = 0.80) were found.

CONCLUSION

Positive changes were found in nutritional behaviour and body composition, but not in physical activity and sleep quality. The WHEELS app seems to partly support healthy lifestyle behaviour.Implications for RehabilitationHealthy lifestyle promotion is crucial, especially for wheelchair users as they tend to show poorer lifestyle behaviour despite an increased risk of obesity and comorbidity.The WHEELS lifestyle app seems to be a valuable tool to support healthy nutrition choices and weight loss and to improve body satisfaction, mental health and vitality.

Dopamine and serotonin in human substantia nigra track social context and value signals during economic exchange

Dopamine and serotonin are hypothesized to guide social behaviours. In humans, however, we have not yet been able to study neuromodulator dynamics as social interaction unfolds. Here, we obtained subsecond estimates of dopamine and serotonin from human substantia nigra pars reticulata during the ultimatum game. Participants, who were patients with Parkinson's disease undergoing awake brain surgery, had to accept or reject monetary offers of varying fairness from human and computer players. They rejected more offers in the human than the computer condition, an effect of social context associated with higher overall levels of dopamine but not serotonin. Regardless of the social context, relative changes in dopamine tracked trial-by-trial changes in offer value-akin to reward prediction errors-whereas serotonin tracked the current offer value. These results show that dopamine and serotonin fluctuations in one of the basal ganglia's main output structures reflect distinct social context and value signals.

Multimodal-based machine learning approach to classify features of internet gaming disorder and alcohol use disorder: A sensor-level and source-level resting-state electroencephalography activity and neuropsychological study

OBJECTIVES

Addictions have recently been classified as substance use disorder (SUD) and behavioral addiction (BA), but the concept of BA is still debatable. Therefore, it is necessary to conduct further neuroscientific research to understand the mechanisms of BA to the same extent as SUD. The present study used machine learning (ML) algorithms to investigate the neuropsychological and neurophysiological aspects of addictions in individuals with internet gaming disorder (IGD) and alcohol use disorder (AUD).

METHODS

We developed three models for distinguishing individuals with IGD from those with AUD, individuals with IGD from healthy controls (HCs), and individuals with AUD from HCs using ML algorithms, including L1-norm support vector machine, random forest, and L1-norm logistic regression (LR). Three distinct feature sets were used for model training: a unimodal-electroencephalography (EEG) feature set combined with sensor- and source-level feature; a unimodal-neuropsychological feature (NF) set included sex, age, depression, anxiety, impulsivity, and general cognitive function, and a multimodal (EEG + NF) feature set.

RESULTS

The LR model with the multimodal feature set used for the classification of IGD and AUD outperformed the other models (accuracy: 0.712). The important features selected by the model highlighted that the IGD group had differential delta and beta source connectivity between right intrahemispheric regions and distinct sensor-level EEG activities. Among the NFs, sex and age were the important features for good model performance.

CONCLUSIONS

Using ML techniques, we demonstrated the neurophysiological and neuropsychological similarities and differences between IGD (a BA) and AUD (a SUD).

Reconstructing brain functional networks through identifiability and deep learning

We propose a novel approach for the reconstruction of functional networks representing brain dynamics based on the idea that the coparticipation of two brain regions in a common cognitive task should result in a drop in their identifiability, or in the uniqueness of their dynamics. This identifiability is estimated through the score obtained by deep learning models in supervised classification tasks and therefore requires no a priori assumptions about the nature of such coparticipation. The method is tested on EEG recordings obtained from Alzheimer's and Parkinson's disease patients, and matched healthy volunteers, for eyes-open and eyes-closed resting-state conditions, and the resulting functional networks are analysed through standard topological metrics. Both groups of patients are characterised by a reduction in the identifiability of the corresponding EEG signals, and by differences in the patterns that support such identifiability. Resulting functional networks are similar, but not identical to those reconstructed by using a correlation metric. Differences between control subjects and patients can be observed in network metrics like the clustering coefficient and the assortativity in different frequency bands. Differences are also observed between eyes open and closed conditions, especially for Parkinson's disease patients.

Thermoplastic clear dental aligners under cyclic compression loading: A mechanical performance analysis using acoustic emission technique

The objective of this work is to analyse the performance of clear aligners made of thermoplastic materials. Within this framework, the damage evolution stages and damage states of the aligners at different cycles of the compressive loading are evaluated using the Acoustic Emission (AE) technique. Three different clear aligner systems were prepared: thermoformed PET-g (polyethylene terephthalate glycol) and PU (polyurethane), and additively manufactured PU. Cyclic compression tests are performed to simulate 22500 swallows. The mechanical results show that the energy absorbed by the thermoformed PET-g aligner remains stable around 4 Nmm throughout the test. Although the PU-based aligners show a higher energy absorption of about 7 Nmm during the initial phase of the cyclic loading, this gradually decreases after 12500 cycles. The time-domain based, and frequency-based parameters of the stress wave acoustic signals generated by the aligners under compression loading are used to identify the damage evolution stages. The machine learning-based AE results reveal the initiation and termination of the different damage states in the aligners and the frequency-based results distinguish the different damage sources. Finally, the microscopy results validated the damage occurrences in the aligners identified by the AE results. The mechanical test results indicate that the thermoformed PET-g has the potential to match the performance and requirements of the dentistry of the popular Invisalign (additively manufactured PU). The AE results have the potential to identify at which cycles the aligners may start losing their functionality.

Predicting network congestion by extending betweenness centrality to interacting agents

We present a simple model to predict network activity at the edge level by extending a known approximation method to compute betweenness centrality with a repulsive mechanism to prevent unphysical densities. By taking into account the strong interaction effects often observed in real phenomena, we aim to obtain an improved measure of edge usage during rush hours as traffic congestion patterns emerge in urban networks. In this approach, the network is iteratively populated by agents following dynamically evolving fastest paths who are progressively attracted towards uncongested parts of the network as the global traffic volume increases. Following the transition of the network state from empty to saturated, we study the emergence of congestion and the progressive disruption of global connectivity due to a relatively small fraction of crowded edges. We assess the predictive power of our model by comparing the speed distribution against a large experimental data set for the London area with remarkable results, which also translate into a qualitative similarity of the congestion maps. Also, percolation analysis confirms the quantitative agreement of the model with the real data for London. We perform simulations for seven other topologically different cities to obtain the Fisher critical exponent τ that shows no common functional dependence on the traffic level. The critical exponent γ, studied to assess the power-law decay of spatial correlation, is found to be inversely proportional to the number of vehicles for both real and simulated traffic. This simulation approach seems particularly fit to describe qualitative and quantitative properties of the network loading process, culminating in peak-hour congestion, by using only topological and geographical network features.

Network Representation of fMRI Data Using Visibility Graphs: The Impact of Motion and Test-Retest Reliability

Visibility graphs provide a novel approach for analysing time-series data. Graph theoretical analysis of visibility graphs can provide new features for data mining applications in fMRI. However, visibility graphs features have not been used widely in the field of neuroscience. This is likely due to a lack of understanding of their robustness in the presence of noise (e.g., motion) and their test-retest reliability. In this study, we investigated visibility graph properties of fMRI data in the human connectome project (N = 1010) and tested their sensitivity to motion and test-retest reliability. We also characterised the strength of connectivity obtained using degree synchrony of visibility graphs. We found that strong correlation (r > 0.5) between visibility graph properties, such as the number of communities and average degrees, and motion in the fMRI data. The test-retest reliability (Intraclass correlation coefficient (ICC)) of graph theoretical features was high for the average degrees (0.74, 95% CI = [0.73, 0.75]), and moderate for clustering coefficient (0.43, 95% CI = [0.41, 0.44]) and average path length (0.41, 95% CI = [0.38, 0.44]). Functional connectivity between brain regions was measured by correlating the visibility graph degrees. However, the strength of correlation was found to be moderate to low (r < 0.35). These findings suggest that even small movement in fMRI data can strongly influence robustness and reliability of visibility graph features, thus, requiring robust motion correction strategies prior to data analysis. Further studies are necessary for better understanding of the potential application of visibility graph features in fMRI.