Mol Inform. 2024 Oct 15:e202400044. doi: 10.1002/minf.202400044. Online ahead of print.

ABSTRACT

Predicting Protein-Ligand Binding Affinity (PLBA) is pivotal in drug development, as accurate estimations of PLBA expedite the identification of promising drug candidates for specific targets, thereby accelerating the drug discovery process. Despite substantial advancements in PLBA prediction, developing an efficient and more accurate method remains non-trivial. Unlike previous computer-aid PLBA studies which primarily using ligand SMILES and protein sequences represented as strings, this research introduces a Deep Learning-based method, the Enhanced Representation Learning on Protein-Ligand Graph Structured data for Binding Affinity Prediction (ERL-ProLiGraph). The unique aspect of this method is the use of graph representations for both proteins and ligands, intending to learn structural information continued from both to enhance the accuracy of PLBA predictions. In these graphs, nodes represent atomic structures, while edges depict chemical bonds and spatial relationship. The proposed model, leveraging deep-learning algorithms, effectively learns to correlate these graphical representations with binding affinities. This graph-based representations approach enhances the model's ability to capture the complex molecular interactions critical in PLBA. This work represents a promising advancement in computational techniques for protein-ligand binding prediction, offering a potential path toward more efficient and accurate predictions in drug development. Comparative analysis indicates that the proposed ERL-ProLiGraph outperforms previous models, showcasing notable efficacy and providing a more suitable approach for accurate PLBA predictions.

PMID:39404190 | DOI:10.1002/minf.202400044

Lab Chip. 2024 Oct 15. doi: 10.1039/d4lc00567h. Online ahead of print.

ABSTRACT

Quantification of cell growth is central to any study of photoautotrophic microorganisms. However, cellular self-shading and limited CO2 control in conventional photobioreactors lead to heterogeneous conditions that obscure distinct correlations between the environment and cellular physiology. Here we present a microfluidic cultivation platform that enables precise analysis of cyanobacterial growth with spatio-temporal resolution. Since cyanobacteria are cultivated in monolayers, cellular self-shading does not occur, allowing homogeneous illumination and precise knowledge of the photon-flux density at single-cell resolution. A single chip contains multiple channels, each connected to several hundred growth chambers. In combination with an externally applied light gradient, this setup enables high-throughput multi-parameter analysis in short time. In addition, the multilayered microfluidic design allows continuous perfusion of defined gas mixtures. Transversal CO2 diffusion across the intermediate polydimethylsiloxane membrane results in homogeneous CO2 supply, with a unique exchange-surface to cultivation-volume ratio. Three cyanobacterial model strains were examined under various, static and dynamic environmental conditions. Phase-contrast and chlorophyll fluorescence images were recorded by automated time-lapse microscopy. Deep-learning trained cell segmentation was used to efficiently analyse large image stacks, thereby generating statistically reliable data. Cell division was highly synchronized, and growth was robust under continuous illumination but stopped rapidly upon initiating dark phases. CO2-Limitation, often a limiting factor in photobioreactors, was only observed when the device was operated under reduced CO2 between 50 and 0 ppm. Here we provide comprehensive and precise data on cyanobacterial growth at single-cell resolution, accessible for further growth studies and modeling.

PMID:39403985 | DOI:10.1039/d4lc00567h

Adv Sci (Weinh). 2024 Oct 15:e2404277. doi: 10.1002/advs.202404277. Online ahead of print.

ABSTRACT

Microbial data analysis poses significant challenges due to its high dimensionality, sparsity, and compositionality. Recent advances have shown that integrating abundance and phylogenetic information is an effective strategy for uncovering robust patterns and enhancing the predictive performance in microbiome studies. However, existing methods primarily focus on the hierarchical structure of phylogenetic trees, overlooking the evolutionary distances embedded within them. This study introduces DeepPhylo, a novel method that employs phylogeny-aware amplicon embeddings to effectively integrate abundance and phylogenetic information. DeepPhylo improves both the unsupervised discriminatory power and supervised predictive accuracy of microbiome data analysis. Compared to the existing methods, DeepPhylo demonstrates superiority in informing biologically relevant insights across five real-world microbiome use cases, including clustering of skin microbiomes, prediction of host chronological age and gender, diagnosis of inflammatory bowel disease (IBD) across 15 studies, and multilabel disease classification.

PMID:39403892 | DOI:10.1002/advs.202404277

Transl Vis Sci Technol. 2024 Oct 1;13(10):24. doi: 10.1167/tvst.13.10.24.

ABSTRACT

PURPOSE: To propose a deep learning-based approach for predicting the most-fixated regions on optical coherence tomography (OCT) reports using eye tracking data of ophthalmologists, assisting them in finding medically salient image regions.

METHODS: We collected eye tracking data of ophthalmology residents, fellows, and faculty as they viewed OCT reports to detect glaucoma. We used a U-Net model as the deep learning backbone and quantized eye tracking coordinates by dividing the input report into an 11 × 11 grid. The model was trained to predict the grids on which fixations would land in unseen OCT reports. We investigated the contribution of different variables, including the viewer's level of expertise, model architecture, and number of eye gaze patterns included in training.

RESULTS: Our approach predicted most-fixated regions in OCT reports with precision of 0.723, recall of 0.562, and f1-score of 0.609. We found that using a grid-based eye tracking structure enabled efficient training and using a U-Net backbone led to the best performance.

CONCLUSIONS: Our approach has the potential to assist ophthalmologists in diagnosing glaucoma by predicting the most medically salient regions on OCT reports. Our study suggests the value of eye tracking in guiding deep learning algorithms toward informative regions when experts may not be accessible.

TRANSLATIONAL RELEVANCE: By suggesting important OCT report regions for a glaucoma diagnosis, our model could aid in medical education and serve as a precursor for self-supervised deep learning approaches to expedite early detection of irreversible vision loss owing to glaucoma.

PMID:39405074 | DOI:10.1167/tvst.13.10.24

Bioinformatics. 2024 Oct 15:btae603. doi: 10.1093/bioinformatics/btae603. Online ahead of print.

ABSTRACT

MOTIVATION: Protein-Protein Interactions (PPIs) are essential for the regulation and facilitation of virtually all biological processes. Computational tools, particularly those based on deep learning, are preferred for the efficient prediction of PPIs. Despite recent progress, two challenges remain unresolved: (i) the imbalanced nature of PPI characteristics is often ignored, and (ii) there exists a high computational cost associated with capturing long-range dependencies within protein data, typically exhibiting quadratic complexity relative to the length of the protein sequence.

RESULT: Here, we propose an anti-symmetric graph learning model, BaPPI, for the balanced prediction of PPIs and extrapolation of the involved patterns in PPI network. In BaPPI, the contextualized information of protein data is efficiently handled by an attention-free mechanism formed by recurrent convolution operator. Anti-symmetric graph convolutional network (GCN) is employed to model the uneven distribution within PPI networks, aiming to learn a more robust and balanced representation of the relationships between proteins. Ultimately, the model is updated using asymmetric loss. The experimental results on classical baseline datasets demonstrate that BaPPI outperforms four state-of-the-art PPI prediction methods. In terms of Micro-F1, BaPPI exceeds the second-best method by 6.5% on SHS27K and 5.3% on SHS148K. Further analysis of the generalization ability and patterns of predicted PPIs also demonstrates our model's generalizability and robustness to the imbalanced nature of PPI datasets.

AVAILABILITY AND IMPLEMENTATION: The source code of this work is publicly available at https://github.com/ttan6729/BaPPI.

PMID:39404784 | DOI:10.1093/bioinformatics/btae603

Bioessays. 2024 Oct 15:e2400155. doi: 10.1002/bies.202400155. Online ahead of print.

ABSTRACT

The performance of deep Neural Networks (NNs) in the text (ChatGPT) and image (DALL-E2) domains has attracted worldwide attention. Convolutional NNs (CNNs), Large Language Models (LLMs), Denoising Diffusion Probabilistic Models (DDPMs)/Noise Conditional Score Networks (NCSNs), and Graph NNs (GNNs) have impacted computer vision, language editing and translation, automated conversation, image generation, and social network management. Proteins can be viewed as texts written with the alphabet of amino acids, as images, or as graphs of interacting residues. Each of these perspectives suggests the use of tools from a different area of deep learning for protein structural biology. Here, I review how CNNs, LLMs, DDPMs/NCSNs, and GNNs have led to major advances in protein structure prediction, inverse folding, protein design, and small molecule design. This review is primarily intended as a deep learning primer for practicing experimental structural biologists. However, extensive references to the deep learning literature should also make it relevant to readers who have a background in machine learning, physics or statistics, and an interest in protein structural biology.

PMID:39404756 | DOI:10.1002/bies.202400155

Simpl Med Ultrasound (2023). 2023;14337:34-43. doi: 10.1007/978-3-031-44521-7_4. Epub 2023 Oct 1.

ABSTRACT

We propose a novel pipeline for the generation of synthetic ultrasound images via Denoising Diffusion Probabilistic Models (DDPMs) guided by cardiac semantic label maps. We show that these synthetic images can serve as a viable substitute for real data in the training of deep-learning models for ultrasound image analysis tasks such as cardiac segmentation. To demonstrate the effectiveness of this approach, we generated synthetic 2D echocardiograms and trained a neural network for segmenting the left ventricle and left atrium. The performance of the network trained on exclusively synthetic images was evaluated on an unseen dataset of real images and yielded mean Dice scores of 88.6 ±4.91, 91.9 ±4.22, 85.2 ±4.83 % for left ventricular endocardium, epicardium and left atrial segmentation respectively. This represents a relative increase of 9.2, 3.3 and 13.9 % in Dice scores compared to the previous state-of-the-art. The proposed pipeline has potential for application to a wide range of other tasks across various medical imaging modalities.

PMID:39404679 | PMC:PMC7616613 | DOI:10.1007/978-3-031-44521-7_4

IEEE Nucl Sci Symp Conf Rec (1997). 2019 Oct;2019:1-4. doi: 10.1109/nss/mic42101.2019.9059998.

NO ABSTRACT

PMID:39404666 | PMC:PMC7616560 | DOI:10.1109/nss/mic42101.2019.9059998

Clin Image Based Proced Fairness AI Med Imaging Ethical Philos Issues Med Imaging (2023). 2023;14242:225-234. doi: 10.1007/978-3-031-45249-9_22. Epub 2023 Oct 9.

ABSTRACT

Recent research has shown that artificial intelligence (AI) models can exhibit bias in performance when trained using data that are imbalanced by protected attribute(s). Most work to date has focused on deep learning models, but classical AI techniques that make use of hand-crafted features may also be susceptible to such bias. In this paper we investigate the potential for race bias in random forest (RF) models trained using radiomics features. Our application is prediction of tumour molecular subtype from dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) of breast cancer patients. Our results show that radiomics features derived from DCE-MRI data do contain race-identifiable information, and that RF models can be trained to predict White and Black race from these data with 60-70% accuracy, depending on the subset of features used. Furthermore, RF models trained to predict tumour molecular subtype using race-imbalanced data seem to produce biased behaviour, exhibiting better performance on test data from the race on which they were trained.

PMID:39404661 | PMC:PMC7616589 | DOI:10.1007/978-3-031-45249-9_22

Simpl Med Ultrasound (2022). 2022;13565:86-95. doi: 10.1007/978-3-031-16902-1_9. Epub 2022 Sep 15.

ABSTRACT

Accurate geometric quantification of the human heart is a key step in the diagnosis of numerous cardiac diseases, and in the management of cardiac patients. Ultrasound imaging is the primary modality for cardiac imaging, however acquisition requires high operator skill, and its interpretation and analysis is difficult due to artifacts. Reconstructing cardiac anatomy in 3D can enable discovery of new biomarkers and make imaging less dependent on operator expertise, however most ultrasound systems only have 2D imaging capabilities. We propose both a simple alteration to the Pix2Vox++ networks for a sizeable reduction in memory usage and computational complexity, and a pipeline to perform reconstruction of 3D anatomy from 2D standard cardiac views, effectively enabling 3D anatomical reconstruction from limited 2D data. We evaluate our pipeline using synthetically generated data achieving accurate 3D whole-heart reconstructions (peak intersection over union score > 0.88) from just two standard anatomical 2D views of the heart. We also show preliminary results using real echo images.

PMID:39404657 | PMC:PMC7616561 | DOI:10.1007/978-3-031-16902-1_9

IEEE Trans Radiat Plasma Med Sci. 2024 Aug 1. doi: 10.1109/TRPMS.2024.3436697. Online ahead of print.

ABSTRACT

Pretraining deep convolutional network mappings using natural images helps with medical imaging analysis tasks; this is important given the limited number of clinically-annotated medical images. Many two-dimensional pretrained backbone networks, however, are currently available. This work compared 18 different backbones from 5 architecture groups (pretrained on ImageNet) for the task of assessing [18F]FDG brain Positron Emission Transmission (PET) image quality (reconstructed at seven simulated doses), based on three clinical image quality metrics (global quality rating, pattern recognition, and diagnostic confidence). Using two-dimensional randomly sampled patches, up to eight patients (at three dose levels each) were used for training, with three separate patient datasets used for testing. Each backbone was trained five times with the same training and validation sets, and with six cross-folds. Training only the final fully connected layer (with ~6,000-20,000 trainable parameters) achieved a test mean-absolute-error of ~0.5 (which was within the intrinsic uncertainty of clinical scoring). To compare "classical" and over-parameterized regimes, the pretrained weights of the last 40% of the network layers were then unfrozen. The mean-absolute-error fell below 0.5 for 14 out of the 18 backbones assessed, including two that previously failed to train. Generally, backbones with residual units (e.g. DenseNets and ResNetV2s), were suited to this task, in terms of achieving the lowest mean-absolute-error at test time (~0.45 - 0.5). This proof-of-concept study shows that over-parameterization may also be important for automated PET image quality assessments.

PMID:39404656 | PMC:PMC7616552 | DOI:10.1109/TRPMS.2024.3436697

Radiology. 2024 Oct;313(1):e242705. doi: 10.1148/radiol.242705.

NO ABSTRACT

PMID:39404635 | DOI:10.1148/radiol.242705

Radiology. 2024 Oct;313(1):e240137. doi: 10.1148/radiol.240137.

ABSTRACT

Background Clinical outcome prediction based on acute-phase ischemic stroke data is valuable for planning health care resources, designing clinical trials, and setting patient expectations. Existing methods require individualized features and often involve manually engineered, time-consuming postprocessing activities. Purpose To predict the 90-day modified Rankin Scale (mRS) score with a deep learning (DL) model fusing noncontrast-enhanced CT (NCCT) and clinical information from the acute phase of stroke. Materials and Methods This retrospective study included data from six patient datasets from four multicenter trials and two registries. The DL-based imaging and clinical model was trained by using NCCT data obtained 1-7 days after baseline imaging and clinical data (age; sex; baseline and 24-hour National Institutes of Health Stroke Scale scores; and history of hypertension, diabetes, and atrial fibrillation). This model was compared with models based on either NCCT or clinical information alone. Model-specific mRS score prediction accuracy, mRS score accuracy within 1 point of the actual mRS score, mean absolute error (MAE), and performance in identifying unfavorable outcomes (mRS score, >2) were evaluated. Results A total of 1335 patients (median age, 71 years; IQR, 60-80 years; 674 female patients) were included for model development and testing through sixfold cross validation, with distributions of 979, 133, and 223 patients across training, validation, and test sets in each of the six cross-validation folds, respectively. The fused model achieved an MAE of 0.94 (95% CI: 0.89, 0.98) for predicting the specific mRS score, outperforming the imaging-only (MAE, 1.10; 95% CI: 1.05, 1.16; P < .001) and the clinical information-only (MAE, 1.00; 95% CI: 0.94, 1.05; P = .04) models. The fused model achieved an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.92) for predicting unfavorable outcomes, outperforming the clinical information-only model (AUC, 0.88; 95% CI: 0.87, 0.90; P < .001) and the imaging-only model (AUC, 0.85; 95% CI: 0.84, 0.87; P < .001). Conclusion A fused DL-based NCCT and clinical model outperformed an imaging-only model and a clinical-information-only model in predicting 90-day mRS scores. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Lee in this issue.

PMID:39404632 | DOI:10.1148/radiol.240137

ACS Appl Mater Interfaces. 2024 Oct 15. doi: 10.1021/acsami.4c09402. Online ahead of print.

ABSTRACT

Developing a colorimetry-based artificial scent screening system (i.e., an olfactory visual sensing system) with high sensitivity and accurate pattern recognition for detecting fruit ripeness remains challenging. In this work, we construct a flexible dye/CelluMOFs-based sensor array with improved sensitivity for on-site detection of characteristic gases of fruits and integrate a densely connected convolutional network (DenseNet) into the sensor array, enabling it to recognize unique scent fingerprints and categorize the ripeness of fruits. In the system, CelluMOFs are synthesized through in situ growth of γ-cyclodextrin metal-organic frameworks (γ-CD-MOFs) on flexible fiber filter paper to fabricate a uniform, flexible and porous dye/CelluMOFs sensitive membrane. Compared to the pristine filter paper, the CelluMOFs exhibit increased porosity with a 62 times higher specific surface area and a 3-fold increase in dye loading capacity after 12 h of adsorption. The prepared dye/CelluMOFs sensing film shows outstanding mechanical and detection stability with negligible deviation after 100 cycles of rubbing. The colorimetric visualization arrays with multiple colorimetric dye/CelluMOFs chips, enable the sensitive recognition and detection of nine kinds of characteristic fruit odors and achieve a high response at 8-1500 ppm of trans-2-hexenal, showcasing remarkably low gas detection thresholds. On the basis of the ppm-level limit of detection with high sensitivity, the fabricated colorimetric sensor arrays are typically used for in situ assessment of fruit ripeness by integrating DenseNet. This approach achieves a satisfactory classification accuracy of 99.09% on the validation set, enabling high-precision prediction of fruit ripeness levels.

PMID:39403818 | DOI:10.1021/acsami.4c09402

Eur Heart J Imaging Methods Pract. 2024 Jun 25;2(1):qyae064. doi: 10.1093/ehjimp/qyae064. eCollection 2024 Jan.

ABSTRACT

AIMS: This study assessed an artificial intelligence (AI) model's performance in predicting elevated brain natriuretic peptide (BNP) levels from chest radiograms and its effect on diagnostic performance among healthcare professionals.

METHODS AND RESULTS: Patients who underwent chest radiography and BNP testing on the same day were included. Data were sourced from two hospitals: one for model development, and the other for external testing. Two final ensemble models were developed to predict elevated BNP levels of ≥ 200 pg/mL and ≥ 100 pg/mL, respectively. Humans were evaluated to predict elevated BNP levels, followed by the same test, referring to the AI model's predictions. A total of 8390 images were collected for model creation, and 1713 images, for tests. The AI model achieved an accuracy of 0.855, precision of 0.873, sensitivity of 0.827, specificity of 0.882, f1 score of 0.850, and receiver-operating-characteristics area-under-curve of 0.929. The accuracy of the testing by 35 participants significantly improved from 0.708 ± 0.049 to 0.829 ± 0.069 (P < 0.001) with the AI assistance (an accuracy of 0.920). Without the AI assistance, the accuracy of the veterans in the medical career was higher than that of early-career professionals (0.728 ± 0.051 vs. 0.692 ± 0.042, P = 0.030); however, with the AI assistance, the accuracy of the early-career professionals was rather higher than that of the veterans (0.851 ± 0.074 vs. 0.803 ± 0.054, P = 0.033).

CONCLUSION: The AI model can predict elevated BNP levels from chest radiograms and has the potential to improve human performance. The gap in utilizing new tools represents one of the emerging issues.

PMID:39403705 | PMC:PMC11472749 | DOI:10.1093/ehjimp/qyae064

Front Plant Sci. 2024 Sep 30;15:1469685. doi: 10.3389/fpls.2024.1469685. eCollection 2024.

ABSTRACT

Fruits and vegetables are among the most nutrient-dense cash crops worldwide. Diagnosing diseases in fruits and vegetables is a key challenge in maintaining agricultural products. Due to the similarity in disease colour, texture, and shape, it is difficult to recognize manually. Also, this process is time-consuming and requires an expert person. We proposed a novel deep learning and optimization framework for apple and cucumber leaf disease classification to consider the above challenges. In the proposed framework, a hybrid contrast enhancement technique is proposed based on the Bi-LSTM and Haze reduction to highlight the diseased part in the image. After that, two custom models named Bottleneck Residual with Self-Attention (BRwSA) and Inverted Bottleneck Residual with Self-Attention (IBRwSA) are proposed and trained on the selected datasets. After the training, testing images are employed, and deep features are extracted from the self-attention layer. Deep extracted features are fused using a concatenation approach that is further optimized in the next step using an improved human learning optimization algorithm. The purpose of this algorithm was to improve the classification accuracy and reduce the testing time. The selected features are finally classified using a shallow wide neural network (SWNN) classifier. In addition to that, both trained models are interpreted using an explainable AI technique such as LIME. Based on this approach, it is easy to interpret the inside strength of both models for apple and cucumber leaf disease classification and identification. A detailed experimental process was conducted on both datasets, Apple and Cucumber. On both datasets, the proposed framework obtained an accuracy of 94.8% and 94.9%, respectively. A comparison was also conducted using a few state-of-the-art techniques, and the proposed framework showed improved performance.

PMID:39403618 | PMC:PMC11471556 | DOI:10.3389/fpls.2024.1469685

Heliyon. 2024 Sep 27;10(19):e38510. doi: 10.1016/j.heliyon.2024.e38510. eCollection 2024 Oct 15.

ABSTRACT

The attention and sentiment of the public are crucial for better implementation of waste sorting behaviors and moving towards green living. In this study, web scraping technology was used to collect 367,856 Weibo posts related to waste sorting from Sina Weibo. Utilizing text co-occurrence networks, Latent Dirichlet Allocation (LDA) topic modeling, and a deep learning model combining the Affective Cognitive Model (OCC) with Long Short-Term Memory Model (LSTM) (referred to as OCC-LSTM), we comprehensively understand the text at both micro and macro levels, analyzing the attention and sentiment of the public towards waste sorting behaviors on the Sina Weibo platform. Several important findings emerged from the empirical results. First, highly engaging posts were predominantly published by users with a large following, and the number of posts fluctuated over time. This reflects the influence of social hot topics and the timeliness of information dissemination. Second, there was heterogeneity in the user groups and their locations, often influenced by cultural differences due to geographical location. Third, positive sentiment towards waste sorting behavior was higher than negative sentiment on the Weibo platform. Moreover, public attention varied under different emotional influences concerning the topic of waste sorting behavior. The innovation of this study lies in the development of a research framework combining co-occurrence networks and deep learning, expanding the analysis on both micro and macro levels. This framework broadens the research paradigms and dimensions of public perception in waste sorting. This study is significant for promoting waste sorting behaviors and implementing climate policies.

PMID:39403487 | PMC:PMC11471487 | DOI:10.1016/j.heliyon.2024.e38510

Heliyon. 2024 Sep 24;10(19):e38316. doi: 10.1016/j.heliyon.2024.e38316. eCollection 2024 Oct 15.

ABSTRACT

In agriculture, specifically livestock monitoring, drones' ability to track multiple targets is essential for advancing the field. However, limited computing resources and unpredictable drone movements often cause issues like ambiguous video frames, object obstructions, and size deviations. These inconsistencies reduce tracking accuracy, making traditional algorithms inadequate for handling drone footage. This study introduces an enhanced deep learning-based multi-target drone tracker framework that enables real-time processing. The proposed method combines object detection and tracking by leveraging consecutive frame pairs to extract and share features, enhancing computational efficiency. It employs diverse loss functions to address class and sample distribution imbalances and includes a composite deblurring module to enhance detection accuracy. Object association utilizes a dual regress bounding box technique, aiding in object identification verification and predictive motion. Live tracking is achieved by predicting object locations in subsequent frames, enabling real-time tracking. Evaluation against leading benchmarks shows that the system improves precision and speed, achieving a 4.3 % increase in Multi-Object Tracking Accuracy (MOTA) and a 7.7 % boost in F1 score.

PMID:39403468 | PMC:PMC11471501 | DOI:10.1016/j.heliyon.2024.e38316

Basic Clin Neurosci. 2024 May-Jun;15(3):393-402. doi: 10.32598/bcn.2023.5138.2. Epub 2024 May 1.

ABSTRACT

INTRODUCTION: Emotion recognition by electroencephalogram (EEG) signals is one of the complex methods because the extraction and recognition of the features hidden in the signal are sophisticated and require a significant number of EEG channels. Presenting a method for feature analysis and an algorithm for reducing the number of EEG channels fulfills the need for research in this field.

METHODS: Accordingly, this study investigates the possibility of utilizing deep learning to reduce the number of channels while maintaining the quality of the EEG signal. A stacked autoencoder network extracts optimal features for emotion classification in valence and arousal dimensions. Autoencoder networks can extract complex features to provide linear and non- linear features which are a good representative of the signal.

RESULTS: The accuracy of a conventional emotion recognition classifier (support vector machine) using features extracted from SAEs was obtained at 75.7% for valence and 74.4% for arousal dimensions, respectively.

CONCLUSION: Further analysis also illustrates that valence dimension detection with reduced EEG channels has a different composition of EEG channels compared to the arousal dimension. In addition, the number of channels is reduced from 32 to 12, which is an excellent development for designing a small-size EEG device by applying these optimal features.

PMID:39403356 | PMC:PMC11470895 | DOI:10.32598/bcn.2023.5138.2

J Multidiscip Healthc. 2024 Oct 10;17:4731-4739. doi: 10.2147/JMDH.S487511. eCollection 2024.

ABSTRACT

BACKGROUND: Percutaneous coronary intervention (PCI) is the primary treatment for acute myocardial infarction (AMI). However, in-stent restenosis (ISR) remains a significant limitation to the efficacy of PCI. The cholesterol-to-lymphocyte ratio (CLR), a novel biomarker associated with inflammation and dyslipidemia, may have predictive value for ISR. Deep learning-based models, such as the multilayer perceptron (MLP), can aid in establishing predictive models for ISR using CLR.

METHODS: A retrospective analysis was conducted on clinical and laboratory data from 1967 patients. The Boruta algorithm was employed to identify key features associated with ISR. An MLP model was developed and divided into training and validation sets. Model performance was evaluated using ROC curves and calibration plots.

RESULTS: Patients in the ISR group exhibited significantly higher levels of CLR and low-density lipoprotein (LDL) compared to the non-ISR group. The Boruta algorithm identified 21 important features for subsequent modeling. The MLP model achieved an AUC of 0.95 on the validation set and 0.63 on the test set, indicating good predictive performance. Calibration plots demonstrated good agreement between predicted and observed outcomes. Feature importance analysis revealed that the number of initial stent implants, hemoglobin levels, Gensini score, CLR, and white blood cell count were significant predictors of ISR. Partial dependence plots (PDP) confirmed CLR as a key predictor for ISR.

CONCLUSION: The CLR, as a biomarker that integrates lipid metabolism and inflammation, shows significant potential in predicting coronary ISR. The MLP model, based on deep learning, demonstrated robust predictive capabilities, offering new insights and strategies for clinical decision-making.

PMID:39403292 | PMC:PMC11472739 | DOI:10.2147/JMDH.S487511