Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence.

Introduction: Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment. Methods: In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects). Results: At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h. Discussion: These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

Uncovering Flat and Hierarchical Topics by Community Discovery on Word Co-occurrence Network.

Topic modeling aims to discover latent themes in collections of text documents. It has various applications across fields such as sociology, opinion analysis, and media studies. In such areas, it is essential to have easily interpretable, diverse, and coherent topics. An efficient topic modeling technique should accurately identify flat and hierarchical topics, especially useful in disciplines where topics can be logically arranged into a tree format. In this paper, we propose Community Topic, a novel algorithm that exploits word co-occurrence networks to mine communities and produces topics. We also evaluate the proposed approach using several metrics and compare it with usual baselines, confirming its good performances. Community Topic enables quick identification of flat topics and topic hierarchy, facilitating the on-demand exploration of sub- and super-topics. It also obtains good results on datasets in different languages.

XRaySwinGen: Automatic medical reporting for X-ray exams with multimodal model.

The importance of radiology in modern medicine is acknowledged for its non-invasive diagnostic capabilities, yet the manual formulation of unstructured medical reports poses time constraints and error risks. This study addresses the common limitation of Artificial Intelligence applications in medical image captioning, which typically focus on classification problems, lacking detailed information about the patient's condition. Despite advancements in AI-generated medical reports that incorporate descriptive details from X-ray images, which are essential for comprehensive reports, the challenge persists. The proposed solution involves a multimodal model utilizing Computer Vision for image representation and Natural Language Processing for textual report generation. A notable contribution is the innovative use of the Swin Transformer as the image encoder, enabling hierarchical mapping and enhanced model perception without a surge in parameters or computational costs. The model incorporates GPT-2 as the textual decoder, integrating cross-attention layers and bilingual training with datasets in Portuguese PT-BR and English. Promising results are noted in the proposed database with ROUGE-L 0.748, METEOR 0.741, and NIH CHEST X-ray with ROUGE-L 0.404 and METEOR 0.393.

Coagulation process for the removal of color and turbidity from wet coffee processing industry wastewater using bio-coagulant: Optimization through central composite design.

The growing problem of industrial pollution in developing countries, especially Ethiopia, has sparked serious issues about the quality of the water, particularly when it comes to the effluent from wet coffee processing industries. In response, this study investigates the potential of utilizing natural coagulants, Acanthus sennii C., Moringa stenopetala B., and Aloe vera L., either individually or in combination, for the treatment of coffee effluent. Methodologically, the study systematically varies operational parameters, including coagulant dose, pH levels, stirring speed, and stirring time, to evaluate their impact on coagulation efficiency. Experimental data undergo statistical analysis, employing ANOVA, while computational optimization techniques are employed using Design Expert software to determine optimal conditions. Notably, the blended form of the three coagulants emerges as particularly promising, yielding optimal conditions of 0.750 g/L coagulant dosage, pH 8.76, agitation speed of 80.73 rpm, and agitation time of 19.23 min. Under these optimized conditions, the blended coagulant achieves remarkable removal efficiencies, approximately 99.99% for color and 98.7% for turbidity. These findings underscore the efficiency of natural coagulants, particularly in blended form, for sustainable wastewater treatment in wet coffee processing.

Exploring driving factors in employing waste reduction tools to alleviate the global food security and sustainability.

To align with the SDG 12.3 target and ensure global food security and sustainability, it is crucial to prioritize the reduction of food loss and waste. This paper aims to synthesize previous research on waste reduction tools like lean manufacturing in the agro-food processing industry and identify areas that require further investigation to assurance worldwide food security and promote sustainability. The study uses a systematic literature review that was proposed by Denyer and Tranfield. This research work provides a descriptive analysis of the evolution of lean manufacturing in agro-food processing and identifies research gaps. The review highlights the importance of demand forecasting, managing variable raw materials and products, increasing management involvement, promoting partnership among supply chain members, and addressing supply and demand seasonality and uncertainty to apply the approach to food waste reduction. Based on the findings, the paper suggests further research areas for future investigation that will help create a more sustainable and equitable food system. Reducing food loss and waste can ensure that everyone has access to safe, nutritious, and affordable food while protecting the planet's resources and reducing greenhouse gas emissions. This study may contribute to the theory of waste minimization, specifically in post-harvest food loss and waste minimization. The findings will help researchers conduct research work interested in minimizing food loss and waste to ensure global food security.

A short- and medium-term forecasting model for roof PV systems with data pre-processing.

This study worked with Chunghwa Telecom to collect data from 17 rooftop solar photovoltaic plants installed on top of office buildings, warehouses, and computer rooms in northern, central and southern Taiwan from January 2021 to June 2023. A data pre-processing method combining linear regression and K Nearest Neighbor (k-NN) was proposed to estimate missing values for weather and power generation data. Outliers were processed using historical data and parameters highly correlated with power generation volumes were used to train an artificial intelligence (AI) model. To verify the reliability of this data pre-processing method, this study developed multilayer perceptron (MLP) and long short-term memory (LSTM) models to make short-term and medium-term power generation forecasts for the 17 solar photovoltaic plants. Study results showed that the proposed data pre-processing method reduced normalized root mean square error (nRMSE) for short- and medium-term forecasts in the MLP model by 17.47% and 11.06%, respectively, and also reduced the nRMSE for short- and medium-term forecasts in the LSTM model by 20.20% and 8.03%, respectively.

Integration of widely targeted metabolomics and the e-tongue reveals the chemical variation and taste quality of Yunnan Arabica coffee prepared using different primary processing methods.

UPLC-Q-TOF-MS and electronic tongue analysis were applied to analyse the metabolic profile and taste quality of Yunnan Arabica coffee under seven primary processing methods. The total phenolic content ranged from 34.44 to 44.42 mg/g DW, the e-tongue results revealed the strongest umami sensor response value in the sample prepared with traditional dry processing, while the samples prepared via honey processing II had the strongest astringency sensor response value. Metabolomics analysis identified 221 differential metabolites, with higher contents of amino acids and derivatives within dry processing II sample, and increased contents of lipids and phenolic acids in the honey processing III sample. The astringency and aftertaste-astringency of the coffee samples positively correlated with the trigonelline, 3,5-di-caffeoylquinic acid and 4-caffeoylquinic acid content. The results contributed to a better understanding of how the primary processing process affects coffee quality, and supply useful information for the enrichment of coffee biochemistry theory.

A chronometric study of the posterior cerebellum's function in emotional processing.

The posterior cerebellum is a recently discovered hub of the affective and social brain, with different subsectors contributing to different social functions. However, very little is known about when the posterior cerebellum plays a critical role in social processing. Due to its location and anatomy, it has been difficult to use traditional approaches to directly study the chronometry of the cerebellum. To address this gap in cerebellar knowledge, here we investigated the causal contribution of the posterior cerebellum to social processing using a chronometric transcranial magnetic stimulation (TMS) approach. We show that the posterior cerebellum is recruited at an early stage of emotional processing (starting from 100 ms after stimulus onset), simultaneously with the posterior superior temporal sulcus (pSTS), a key node of the social brain. Moreover, using a condition-and-perturb TMS approach, we found that the recruitment of the pSTS in emotional processing is dependent on cerebellar activation. Our results are the first to shed light on chronometric aspects of cerebellar function and its causal functional connectivity with other nodes of the social brain.

Identifying signs and symptoms of urinary tract infection from emergency department clinical notes using large language models.

BACKGROUND: Natural language processing (NLP) tools including recently developed large language models (LLMs) have myriad potential applications in medical care and research, including the efficient labeling and classification of unstructured text such as electronic health record (EHR) notes. This opens the door to large-scale projects that rely on variables that are not typically recorded in a structured form, such as patient signs and symptoms. OBJECTIVES: This study is designed to acquaint the emergency medicine research community with the foundational elements of NLP, highlighting essential terminology, annotation methodologies, and the intricacies involved in training and evaluating NLP models. Symptom characterization is critical to urinary tract infection (UTI) diagnosis, but identification of symptoms from the EHR has historically been challenging, limiting large-scale research, public health surveillance, and EHR-based clinical decision support. We therefore developed and compared two NLP models to identify UTI symptoms from unstructured emergency department (ED) notes. METHODS: The study population consisted of patients aged ≥ 18 who presented to an ED in a northeastern U.S. health system between June 2013 and August 2021 and had a urinalysis performed. We annotated a random subset of 1250 ED clinician notes from these visits for a list of 17 UTI symptoms. We then developed two task-specific LLMs to perform the task of named entity recognition: a convolutional neural network-based model (SpaCy) and a transformer-based model designed to process longer documents (Clinical Longformer). Models were trained on 1000 notes and tested on a holdout set of 250 notes. We compared model performance (precision, recall, F1 measure) at identifying the presence or absence of UTI symptoms at the note level. RESULTS: A total of 8135 entities were identified in 1250 notes; 83.6% of notes included at least one entity. Overall F1 measure for note-level symptom identification weighted by entity frequency was 0.84 for the SpaCy model and 0.88 for the Longformer model. F1 measure for identifying presence or absence of any UTI symptom in a clinical note was 0.96 (232/250 correctly classified) for the SpaCy model and 0.98 (240/250 correctly classified) for the Longformer model. CONCLUSIONS: The study demonstrated the utility of LLMs and transformer-based models in particular for extracting UTI symptoms from unstructured ED clinical notes; models were highly accurate for detecting the presence or absence of any UTI symptom on the note level, with variable performance for individual symptoms.

Light conditions and the evolution of the visual system in birds.

Despite vision is an essential sense for many animals, the intuitively appealing notion that the visual system has been shaped by environmental light conditions is backed by insufficient evidence. Based on a comprehensive phylogenetic comparative analysis of birds, we investigate if exposure to different light conditions might have triggered evolutionary divergence in the visual system through pressures on light sensitivity, visual acuity, and neural processing capacity. Our analyses suggest that birds that have adopted nocturnal habits evolved eyes with larger corneal diameters and, to a lesser extent, longer axial length than diurnal species. However, we found no evidence that sensing and processing organs were selected together, as observed in diurnal birds. Rather than enlarging the processing centers, we found a tendency among nocturnal species to either reduce or maintain the size of the two main brain centers involved in vision -the optic tectum and the wulst. These results suggest a mosaic pattern of evolution, wherein optimization of the eye optics for efficient light capture in nocturnal species may have compromised visual acuity and central processing capacity.

Impact of Otitis Media With Effusion in Early Age on Auditory Processing Abilities in Children: A Systematic Review and Meta-Analysis.

Objective: Early-onset otitis media with effusion (OME) can affect the development of the auditory nervous system and thus lead to auditory processing abnormalities. This study aims to review the effect of childhood OME on auditory processing abilities in children. Methods: A systematic review of the literature, restricted to the English language from 1990 to 2022 was conducted using search engines like PubMed, Embase, and Google Scholar. After selecting the articles following predefined inclusion and exclusion criteria, the data were extracted and meta-analysis was performed. Results: A total of 10 articles met the inclusion criteria. Children with a history of OME had poorer performance in most behavioral and electrophysiological tests. Pooled analysis of various tests such as the gap in noise test, frequency pattern test (verbal and nonverbal), and latencies of auditory brainstem response-I, V, I to III, and I to V showed a difference between the 2 groups. Conclusion: Childhood OME can significantly affect auditory processing abilities in children.

Milk processing systems of the Mongolian nomadic Khalkha groups in eastern Mongolia and technique transmission from West Asia.

The purpose of this paper is to understand the milk processing system practiced in the Mongolian nomadic Khalkha groups of Su'qbaatar and Dornod Provinces in eastern Mongolia through a field survey, to compare it with surrounding areas of Qentiy and Dundgowi Provinces, and then to analyze the transmission of processing techniques by further comparison with those of Syria, Jordan, Iran and Iraq in West Asia. The milk processing techniques of fermentation, cream separation and additive coagulation are all used in Su'qbaatar and Dornod Provinces. In fermentation processes, the technique of alcohol fermentation with churning is mainly used for cow milk to process alcoholic sour milk, followed by further processing to spirit, butter oil and non-matured dry cheese. In cream separation processes, the technique of heating/cream separation is used, in which cream is first separated from milk and non-matured dry cheese is processed from skim milk. In additive coagulation processes, the technique of fermented milk coagulation which utilizes lactic acid fermented whey as a coagulant is used to process non-matured dry cheese. These techniques are widely shared in the eastern part of Mongolia. It is characteristic of Su'qbaatar Province that the processing of cow milk is dominated by the technique of fermentation processes, mainly alcohol fermentation with churning. It is presumed that the technique of churning sour milk transmitted from West Asia to eastern Mongolia, and then the function of churning originally for butter processing was converted to allow for alcohol fermentation under the cooler environment in North Asia.

A hierarchy of visual processing deficits in body dysmorphic disorder: a conceptual review and empirical investigation.

OBJECTIVE: Abnormal visual processing has been proposed as a mechanism underlying excessive focus on minor appearance flaws in body dysmorphic disorder (BDD). Existing BDD research has not differentiated the various stages of face processing (featural, first-order configural, holistic and second-order configural) that are required for higher-order processes such as emotion recognition. This study investigated a hierarchical visual processing model to examine the nature of abnormalities in face processing in BDD. METHOD: Thirty BDD participants and 27 healthy controls completed the Navon task, a featural and configural face processing task and a facial emotion labelling task. RESULTS: BDD participants performed similarly to controls when processing global and local non-face stimuli on the Navon task, when detecting subtle changes in the features and spacing of a target face, and when labelling emotional faces. However, BDD participants displayed poorer performance when viewing inverted faces, indicating difficulties in configural processing. CONCLUSIONS: The findings only partially support prior work. However, synthesis of results with previous findings indicates that heterogenous task methodologies may contribute to inconsistent findings. Recommendations are provided regarding the task parameters that appear most sensitive to abnormalities in BDD.

Establishing a reference focal plane using convolutional neural networks and beads for brightfield imaging.

Repeatability of measurements from image analytics is difficult, due to the heterogeneity and complexity of cell samples, exact microscope stage positioning, and slide thickness. We present a method to define and use a reference focal plane that provides repeatable measurements with very high accuracy, by relying on control beads as reference material and a convolutional neural network focused on the control bead images. Previously we defined a reference effective focal plane (REFP) based on the image gradient of bead edges and three specific bead image features. This paper both generalizes and improves on this previous work. First, we refine the definition of the REFP by fitting a cubic spline to describe the relationship between the distance from a bead's center and pixel intensity and by sharing information across experiments, exposures, and fields of view. Second, we remove our reliance on image features that behave differently from one instrument to another. Instead, we apply a convolutional regression neural network (ResNet 18) trained on cropped bead images that is generalizable to multiple microscopes. Our ResNet 18 network predicts the location of the REFP with only a single inferenced image acquisition that can be taken across a wide range of focal planes and exposure times. We illustrate the different strategies and hyperparameter optimization of the ResNet 18 to achieve a high prediction accuracy with an uncertainty for every image tested coming within the microscope repeatability measure of 7.5 µm from the desired focal plane. We demonstrate the generalizability of this methodology by applying it to two different optical systems and show that this level of accuracy can be achieved using only 6 beads per image.

BioBBC: a multi-feature model that enhances the detection of biomedical entities.

The rapid increase in biomedical publications necessitates efficient systems to automatically handle Biomedical Named Entity Recognition (BioNER) tasks in unstructured text. However, accurately detecting biomedical entities is quite challenging due to the complexity of their names and the frequent use of abbreviations. In this paper, we propose BioBBC, a deep learning (DL) model that utilizes multi-feature embeddings and is constructed based on the BERT-BiLSTM-CRF to address the BioNER task. BioBBC consists of three main layers; an embedding layer, a Long Short-Term Memory (Bi-LSTM) layer, and a Conditional Random Fields (CRF) layer. BioBBC takes sentences from the biomedical domain as input and identifies the biomedical entities mentioned within the text. The embedding layer generates enriched contextual representation vectors of the input by learning the text through four types of embeddings: part-of-speech tags (POS tags) embedding, char-level embedding, BERT embedding, and data-specific embedding. The BiLSTM layer produces additional syntactic and semantic feature representations. Finally, the CRF layer identifies the best possible tag sequence for the input sentence. Our model is well-constructed and well-optimized for detecting different types of biomedical entities. Based on experimental results, our model outperformed state-of-the-art (SOTA) models with significant improvements based on six benchmark BioNER datasets.

Results of an interlaboratory study on the working curve in vat photopolymerization.

The working curve informs resin properties and print parameters for stereolithography, digital light processing, and other photopolymer additive manufacturing (PAM) technologies. First demonstrated in 1992, the working curve measurement of cure depth vs radiant exposure of light is now a foundational measurement in the field of PAM. Despite its widespread use in industry and academia, there is no formal method or procedure for performing the working curve measurement, raising questions about the utility of reported working curve parameters. Here, an interlaboratory study (ILS) is described in which 24 individual laboratories performed a working curve measurement on an aliquot from a single batch of PAM resin. The ILS reveals that there is enormous scatter in the working curve data and the key fit parameters derived from it. The measured depth of light penetration Dp varied by as much as 7x between participants, while the critical radiant exposure for gelation Ec varied by as much as 70x. This significant scatter is attributed to a lack of common procedure, variation in light engines, epistemic uncertainties from the Jacobs equation, and the use of measurement tools with insufficient precision. The ILS findings highlight an urgent need for procedural standardization and better hardware characterization in this rapidly growing field.

Harnessing the power of resistant starch: a narrative review of its health impact and processing challenges.

Starch is a primary energy storage for plants, making it an essential component of many plant-based foods consumed today. Resistant starch (RS) refers to those starch fractions that escape digestion in the small intestine and reach the colon where they are fermented by the microflora. RS has been repeatedly reported as having benefits on health, but ensuring that its content remains in food processing may be challenging. The present work focuses on the impact RS on health and explores the different processes that may influence its presence in foods, thus potentially interfering with these effects. Clinical evidence published from 2010 to 2023 and studying the effect of RS on health parameters in adult populations, were identified, using PUBMED/Medline and Cochrane databases. The search focused as well on observational studies related to the effect of food processes on RS content. While processes such as milling, fermentation, cooking and heating seem to have a deleterious influence on RS content, other processes, such as cooling, cooking time, storage time, or water content, may positively impact its presence. Regarding the influence on health parameters, there is a body of evidence suggesting an overall significant beneficial effect of RS, especially type 1 and 2, on several health parameters such as glycemic response, insulin resistance index, bowel function or inflammatory markers. Effects are more substantiated in individuals suffering from metabolic diseases. The effects of RS may however be exerted differently depending on the type. A better understanding of the influence of food processes on RS can guide the development of dietary intake recommendations and contribute to the development of food products rich in RS.

Advanced methods to mechanically isolate stromal vascular fraction: A concise review.

Adipose tissue is a highly attractive reservoir of stem cells due to its accessibility and abundance, and the SVF within it holds great promise for stem cell-based therapies. The use of mechanical methods for SVF isolation from adipose tissue is preferred over enzymatic methods, as it can be readily applied in clinical settings without additional processing steps. However, there is a lack of consensus on the optimal approach for mechanically isolating SVF. This comprehensive review aims to present and compare the latest mechanical isolation methods for SVF from adipose tissue, including centrifugation, filtration/washing, emulsification, vibration, and mincing/adiponizing. Each of these methods possesses unique advantages and limitations, and yet, no conclusive evidence has emerged demonstrating the superiority of one approach over the others, primarily due to the dearth of well-controlled prospective studies in this field.

Examining the effects of pleasantness ratings on correct and false recognition in the DRM paradigm: accuracy, recollection and familiarity estimates.

Distinctive encoding usually increases correct recognition while also producing a reduction in false recognition. In the Deese-Roediger-McDermott (DRM) illusion this phenomenon, called the mirror effect, occurs when participants focus on unique features of each of the words in the study list. In previous studies, the pleasantness rating task, used to foster distinctive encoding, generated different patterns of results. The main aim of our research is to examine under what circumstances this task can produce the mirror effect in the DRM paradigm, based on evidence from recognition accuracy and subjective retrieval experience. In Experiment 1, a standard version (word pleasantness rating on a 5-point Likert-type scale) was used for comparison with two other encoding conditions: shallow processing (vowel identification) and a read-only control. The standard task, compared to the other conditions, increased correct recognition, but did not reduce false recognition, and this result may be affected by the number of lists presented for study. Therefore, in experiment 2, to minimize the possible effect of the so-called retention size, the number of studied lists was reduced. In addition, the standard version was compared with a supposedly more item-specific version (participants rated the pleasantness of words while thinking of a single reason for this), also including the read-only control condition. In both versions of the pleasantness rating task, more correct recognition is achieved compared to the control condition, with no differences between the two versions. In the false recognition observed here, only the specific pleasantness rating task achieved a reduction relative to the control condition. On the other hand, the subjective retrieval experience accompanied correct and false recognition in the various study conditions. Although the standard pleasantness rating task has been considered to perform item-specific processing, our results challenge that claim. Furthermore, we propose a possible boundary condition of the standard task for the reduction of false recognition in the DRM paradigm.