Int Orthop. 2025 Jan 6. doi: 10.1007/s00264-024-06401-3. Online ahead of print.

ABSTRACT

PURPOSE: Accurate identification of radiographic landmarks is fundamental to characterizing glenohumeral relationships before and sequentially after shoulder arthroplasty, but manual annotation of these radiographs is laborious. We report on the use of artificial intelligence, specifically computer vision and deep learning models (DLMs), in determining the accuracy of DLM-identified and surgeon identified (SI) landmarks before and after anatomic shoulder arthroplasty.

MATERIALS & METHODS: 240 true anteroposterior radiographs were annotated using 11 standard osseous landmarks to train a deep learning model. Radiographs were modified to allow for a training model consisting of 2,260 images. The accuracy of DLM landmarks was compared to manually annotated radiographs using 60 radiographs not used in the training model. In addition, we also performed 14 different measurements of component positioning and compared these to measurements made based on DLM landmarks.

RESULTS: The mean deviation between DLM vs. SI cortical landmarks was 1.9 ± 1.9 mm. Scapular landmarks had slightly lower deviations compared to humeral landmarks (1.5 ± 1.8 mm vs. 2.1 ± 2.0 mm, p < 0.001). The DLM was also found to be accurate with respect to 14 measures of scapular, humeral, and glenohumeral measurements with a mean deviation of 2.9 ± 2.7 mm.

CONCLUSIONS: An accelerated deep learning model using a base of only 240 annotated images was able to achieve low levels of deviation in identifying common humeral and scapular landmarks on preoperative and postoperative radiographs. The reliability and efficiency of this deep learning model represents a powerful tool to analyze preoperative and postoperative radiographs while avoiding human observer bias.

LEVEL OF EVIDENCE: IV.

PMID:39760903 | DOI:10.1007/s00264-024-06401-3

Phys Eng Sci Med. 2025 Jan 6. doi: 10.1007/s13246-024-01512-y. Online ahead of print.

ABSTRACT

Schizophrenia (SZ) is a chronic neuropsychiatric disorder characterized by disturbances in cognitive, perceptual, social, emotional, and behavioral functions. The conventional SZ diagnosis relies on subjective assessments of individuals by psychiatrists, which can result in bias, prolonged procedures, and potentially false diagnoses. This emphasizes the crucial need for early detection and treatment of SZ to provide timely support and minimize long-term impacts. Utilizing the ability of electroencephalogram (EEG) signals to capture brain activity dynamics, this article introduces a novel lightweight modified MobileNetV2- architecture (SchizoLMNet) for efficiently diagnosing SZ using spectrogram images derived from selected EEG channel data. The proposed methodology involves preprocessing of raw EEG data of 81 subjects collected from Kaggle data repository. Short-time Fourier transform (STFT) is applied to transform pre-processed EEG signals into spectrogram images followed by data augmentation. Further, the generated images are subjected to deep learning (DL) models to perform the binary classification task. Utilizing the proposed model, it achieved accuracies of 98.17%, 97.03%, and 95.55% for SZ versus healthy classification in hold-out, subject independent testing, and subject-dependent testing respectively. The SchizoLMNet model demonstrates superior performance compared to various pretrained DL models and state-of-the-art techniques. The proposed framework will be further translated into real-time clinical settings through a mobile edge computing device. This innovative approach will serve as a bridge between medical staff and patients, facilitating intelligent communication and assisting in effective SZ management.

PMID:39760847 | DOI:10.1007/s13246-024-01512-y

Phys Eng Sci Med. 2025 Jan 6. doi: 10.1007/s13246-024-01509-7. Online ahead of print.

ABSTRACT

Neointimal coverage and stent apposition, as assessed from intravascular optical coherence tomography (IVOCT) images, are crucial for optimizing percutaneous coronary intervention (PCI). Existing state-of-the-art computer algorithms designed to automate this analysis often treat lumen and stent segmentations as separate target entities, applicable only to a single stent type and overlook automation of preselecting which pullback segments need segmentation, thus limit their practicality. This study aimed for an algorithm capable of intelligently handling the entire IVOCT pullback across different phases of PCI and clinical scenarios, including the presence and coexistence of metal and bioresorbable vascular scaffold (BVS), stent types. We propose a multi-task deep learning model, named TriVOCTNet, that automates image classification/selection, lumen segmentation and stent struts segmentation within a single network by integrating classification, regression and pixel-level segmentation models. This approach allowed a single-network, single-pass implementation with all tasks parallelized for speed and convenience. A joint loss function was specifically designed to optimize each task in situations where each task may or may not be present. Evaluation on 4,746 images achieved classification accuracies of 0.999, 0.997, and 0.998 for lumen, BVS, and metal stent features, respectively. The lumen segmentation performance showed a Euclidean distance error of 21.72 μm and Dice's coefficient of 0.985. For BVS struts segmentation, the Dice's coefficient was 0.896, and for metal stent struts segmentation, the precision was 0.895 and sensitivity was 0.868. TriVOCTNet highlights its clinical potential due to its fast and accurate results, and simplicity in handling all tasks and scenarios through a single system.

PMID:39760844 | DOI:10.1007/s13246-024-01509-7

Curr Opin Neurol. 2025 Feb 1;38(1):40-46. doi: 10.1097/WCO.0000000000001333. Epub 2024 Nov 14.

ABSTRACT

PURPOSE OF REVIEW: Though simple in its fundamental mechanism - a critical disruption of local blood supply - stroke is complicated by the intricate nature of the neural substrate, the neurovascular architecture, and their complex interactions in generating its clinical manifestations. This complexity is adequately described by high-resolution imaging with sensitivity not only to parenchymal macrostructure but also microstructure and functional tissue properties, in conjunction with detailed characterization of vascular topology and dynamics. Such descriptive richness mandates models of commensurate complexity only artificial intelligence could plausibly deliver, if we are to achieve the goal of individually precise, personalized care.

RECENT FINDINGS: Advances in machine vision technology, especially deep learning, are delivering higher fidelity predictive, descriptive, and inferential tools, incorporating increasingly rich imaging information within ever more flexible models. Impact at the clinical front line remains modest, however, owing to the challenges of delivering models robust to the noisy, incomplete, biased, and comparatively small-scale data characteristic of real-world practice.

SUMMARY: The potential benefit of introducing AI to stroke, in imaging and elsewhere, is now unquestionable, but the optimal approach - and the path to real-world application - remain unsettled. Deep generative models offer a compelling solution to current obstacles and are predicted powerfully to catalyse innovation in the field.

PMID:39760722 | DOI:10.1097/WCO.0000000000001333

Turk J Gastroenterol. 2024 Dec 30. doi: 10.5152/tjg.2024.24538. Online ahead of print.

ABSTRACT

Hepatocellular carcinoma (HCC) is a prevalent cancer that significantly contributes to mortality globally, primarily due to its late diagnosis. Early detection is crucial yet challenging. This study leverages the potential of deep learning (DL) technologies, employing the You Only Look Once (YOLO) architecture, to enhance the detection of HCC in computed tomography (CT) images, aiming to improve early diagnosis and thereby patient outcomes. We used a dataset of 1290 CT images from 122 patients, segmented according to a standard 70:20:10 split for training, validation, and testing phases. The YOLO-based DL model was trained on these images, with subsequent phases for validation and testing to assess the model's diagnostic capabilities comprehensively. The model exhibited exceptional diagnostic accuracy, with a precision of 0.97216, recall of 0.919, and an overall accuracy of 95.35%, significantly surpassing traditional diagnostic approaches. It achieved a specificity of 95.83% and a sensitivity of 94.74%, evidencing its effectiveness in clinical settings and its potential to reduce the rate of missed diagnoses and unnecessary interventions. The implementation of the YOLO architecture for detecting HCC in CT scans has shown substantial promise, indicating that DL models could soon become a standard tool in oncological diagnostics. As artificial intelligence technology continues to evolve, its integration into healthcare systems is expected to advance the accuracy and efficiency of diagnostics in oncology, enhancing early detection and treatment strategies and potentially improving patient survival rates.

PMID:39760649 | DOI:10.5152/tjg.2024.24538

Microsc Res Tech. 2025 Jan 6. doi: 10.1002/jemt.24775. Online ahead of print.

ABSTRACT

Reactive lymphocytes are an important type of leukocytes, which are morphologically transformed from lymphocytes. The increase in these cells is usually a sign of certain virus infections, so their detection plays an important role in the fight against diseases. Manual detection of reactive lymphocytes is undoubtedly time-consuming and labor-intensive, requiring a high level of professional knowledge. Therefore, it is highly necessary to conduct research into computer-assisted diagnosis. With the development of deep learning technology in the field of computer vision, more and more models are being applied in the field of medical imaging. We aim to propose an advanced multi-object detection network and apply it to practical medical scenarios of reactive lymphocyte detection and other leukocyte detection. First, we introduce a space-to-depth convolution (SPD-Conv), which enhances the model's ability to detect dense small objects. Next, we design a dynamic large kernel attention (DLKA) mechanism, enabling the model to better model the context of various cells in clinical scenarios. Lastly, we introduce a brand-new feature fusion network, the asymptotic feature pyramid network (AFPN), which strengthens the model's ability to fuse multi-scale features. Our model ultimately achieves mAP50 of 0.918 for reactive lymphocyte detection and 0.907 for all leukocytes, while also demonstrating good interpretability. In addition, we propose a new peripheral blood cell dataset, providing data support for subsequent related work. In summary, our work takes a significant step forward in the detection of reactive lymphocytes.

PMID:39760201 | DOI:10.1002/jemt.24775

Data Brief. 2024 Nov 29;57:111187. doi: 10.1016/j.dib.2024.111187. eCollection 2024 Dec.

ABSTRACT

We present a comprehensive dataset comprising head- and eye-centred video recordings from human participants performing a search task in a variety of Virtual Reality (VR) environments. Using a VR motion platform, participants navigated these environments freely while their eye movements and positional data were captured and stored in CSV format. The dataset spans six distinct environments, including one specifically for calibrating the motion platform, and provides a cumulative playtime of over 10 h for both head- and eye-centred perspectives. The data collection was conducted in naturalistic VR settings, where participants collected virtual coins scattered across diverse landscapes such as grassy fields, dense forests, and an abandoned urban area, each characterized by unique ecological features. This structured and detailed dataset offers substantial reuse potential, particularly for machine learning applications. The richness of the dataset makes it an ideal resource for training models on various tasks, including the prediction and analysis of visual search behaviour, eye movement and navigation strategies within VR environments. Researchers can leverage this extensive dataset to develop and refine algorithms requiring comprehensive and annotated video and positional data. By providing a well-organized and detailed dataset, it serves as an invaluable resource for advancing machine learning research in VR and fostering the development of innovative VR technologies.

PMID:39760008 | PMC:PMC11699299 | DOI:10.1016/j.dib.2024.111187

Data Brief. 2024 Dec 3;57:111194. doi: 10.1016/j.dib.2024.111194. eCollection 2024 Dec.

ABSTRACT

Effective data representation in machine learning and deep learning is paramount. For an algorithm or neural network to capture patterns in data and be able to make reliable predictions, the data must appropriately describe the problem domain. Although there exists much literature on data preprocessing for machine learning and data science applications, novel data representation methods for enhancing machine learning model performance remain highly absent within the literature. This dataset is a compilation of convolutional neural network model performance trained and tested on a wide range of numerical base representations of the MNIST and MNIST-C datasets. This performance data can be further analysed by the research community to uncover trends in model performance against the numerical base of its data. This dataset can be used to produce more research of the same nature, testing cross-base data encoding on machine learning training and testing data for a wide range of real-world applications.

PMID:39760007 | PMC:PMC11697575 | DOI:10.1016/j.dib.2024.111194

Int J Gen Med. 2024 Dec 31;17:6585-6594. doi: 10.2147/IJGM.S486189. eCollection 2024.

ABSTRACT

PURPOSE: Papillary thyroid carcinoma (PTC) is the most common thyroid malignancy. Although its mortality rate is low, some patients experience cancer recurrence during follow-up. In this study, we investigated the accuracy of a novel multimodal model by simultaneously analyzing numeric and time-series data to predict recurrence in patients with PTC after thyroidectomy.

PATIENTS AND METHODS: We analyzed patients with thyroid carcinoma who underwent thyroidectomy at the Chungbuk National University Hospital between January 2006 and December 2021. The proposed model used numerical data, including clinical information at the time of surgery, and time-series data, including postoperative thyroid function test results. For the model training with unbalanced data, we employed weighted binary cross-entropy with weights of 0.8 for the positive (recurrence) group and 0.2 for the negative (nonrecurrence) group. We performed four-fold cross-validation of the dataset to evaluate the model performance.

RESULTS: Our dataset comprised 1613 patients who underwent thyroidectomy, including 1550 and 63 patients with nonrecurrent and recurrent PTC, respectively. Patients with recurrence had a larger tumor size, more tumor multiplicity, and a higher male-to-female ratio than those without recurrence. The proposed model achieved an average area under the curve of 0.9622, F1-score of 0.4603, sensitivity of 0.9042, and specificity of 0.9077.

CONCLUSION: When applying our proposed model, the experimental results showed that it could predict recurrence at least 1 year before occurrence. The multimodal model for predicting PTC recurrence after thyroidectomy showed good performance. In clinical practice, it may help with the early detection of recurrence during the follow-up of patients with PTC after thyroidectomy.

PMID:39759893 | PMC:PMC11699832 | DOI:10.2147/IJGM.S486189

Heliyon. 2024 Nov 23;10(23):e40684. doi: 10.1016/j.heliyon.2024.e40684. eCollection 2024 Dec 15.

ABSTRACT

Label-free imaging is routinely used during cell culture because of its minimal interference with intracellular biology and capability of observing cells over time. However, label-free image analysis is challenging due to the low contrast between foreground signals and background. So far various deep learning tools have been developed for label-free image analysis and their performance depends on the quality of training data. In this study, we developed a simple computational pipeline that requires no training data and is suited to run on images generated using high-content microscopy equipment. By combining classical image processing functions, Voronoi segmentation, Gaussian mixture modeling and automatic parameter optimization, our pipeline can be used for cell number quantification and spatial distribution characterization based on a single label-free image. We demonstrated the applicability of our pipeline in four morphologically distinct cell types with various cell densities. Our pipeline is implemented in R and does not require excessive computational power, providing novel opportunities for automated label-free image analysis for large-scale or repeated cell culture experiments.

PMID:39759864 | PMC:PMC11700677 | DOI:10.1016/j.heliyon.2024.e40684

Heliyon. 2024 Nov 26;10(23):e40689. doi: 10.1016/j.heliyon.2024.e40689. eCollection 2024 Dec 15.

ABSTRACT

[This corrects the article DOI: 10.1016/j.heliyon.2024.e31730.].

PMID:39759858 | PMC:PMC11700673 | DOI:10.1016/j.heliyon.2024.e40689

Front Neuroinform. 2024 Dec 20;18:1459970. doi: 10.3389/fninf.2024.1459970. eCollection 2024.

ABSTRACT

INTRODUCTION: Modeling multi-channel electroencephalographic (EEG) time-series is a challenging tasks, even for the most recent deep learning approaches. Particularly, in this work, we targeted our efforts to the high-fidelity reconstruction of this type of data, as this is of key relevance for several applications such as classification, anomaly detection, automatic labeling, and brain-computer interfaces.

METHODS: We analyzed the most recent works finding that high-fidelity reconstruction is seriously challenged by the complex dynamics of the EEG signals and the large inter-subject variability. So far, previous works provided good results in either high-fidelity reconstruction of single-channel signals, or poor-quality reconstruction of multi-channel datasets. Therefore, in this paper, we present a novel deep learning model, called hvEEGNet, designed as a hierarchical variational autoencoder and trained with a new loss function. We tested it on the benchmark Dataset 2a (including 22-channel EEG data from 9 subjects).

RESULTS: We show that it is able to reconstruct all EEG channels with high-fidelity, fastly (in a few tens of epochs), and with high consistency across different subjects. We also investigated the relationship between reconstruction fidelity and the training duration and, using hvEEGNet as an anomaly detector, we spotted some data in the benchmark dataset that are corrupted and never highlighted before.

DISCUSSION: Thus, hvEEGNet could be very useful in several applications where automatic labeling of large EEG dataset is needed and time-consuming. At the same time, this work opens new fundamental research questions about (1) the effectiveness of deep learning models training (for EEG data) and (2) the need for a systematic characterization of the input EEG data to ensure robust modeling.

PMID:39759760 | PMC:PMC11695360 | DOI:10.3389/fninf.2024.1459970

Int J Clin Health Psychol. 2024 Oct-Dec;24(4):100526. doi: 10.1016/j.ijchp.2024.100526. Epub 2024 Dec 12.

ABSTRACT

OBJECTIVE: College students with subclinical depression often experience sleep disturbances and are at high risk of developing major depressive disorder without early intervention. Clinical guidelines recommend non-pharmacotherapy as the primary option for subclinical depression with comorbid sleep disorders (sDSDs). However, the neuroimaging mechanisms and therapeutic responses associated with these treatments are poorly understood. Additionally, the lack of an early diagnosis and therapeutic effectiveness prediction model hampers the clinical promotion and acceptance of non-pharmacological interventions for subclinical depression.

METHODS: This study involved pre- and post-treatment resting-state functional Magnetic Resonance Imaging (rs-fMRI) and clinical data from a multicenter, single-blind, randomized clinical trial. The trial included 114 first-episode, drug-naïve university students with subclinical depression and comorbid sleep disorders (sDSDs; Mean age=22.8±2.3 years; 73.7% female) and 93 healthy controls (HCs; Mean age=22.2±1.7 years; 63.4% female). We examined altered functional connectivity (FC) and brain network connective mode related to subregions of Default Mode Network (sub-DMN) using seed-to-voxel analysis before and after six weeks of non-pharmacological antidepressant treatment. Additionally, we developed an individualized diagnosing and therapeutic effect predicting model to realize early recognition of subclinical depression and provide objective suggestions to select non-pharmacological therapy by using the newly proposed Hierarchical Functional Brain Network (HFBN) with advanced deep learning algorithms within the transformer framework.

RESULTS: Neuroimaging responses to non-pharmacologic treatments are characterized by alterations in functional connectivity (FC) and shifts in brain network connectivity patterns, particularly within the sub-DMN. At baseline, significantly increased FC was observed between the sub-DMN and both Executive Control Network (ECN) and Dorsal Attention Network (DAN). Following six weeks of non-pharmacologic intervention, connectivity patterns primarily shifted within the sub-DMN and ECN, with a predominant decrease in FCs. The HFBN model demonstrated superior performance over traditional deep learning models, accurately predicting therapeutic outcomes and diagnosing subclinical depression, achieving cumulative scores of 80.47% for sleep quality prediction and 84.67% for depression prediction, along with an overall diagnostic accuracy of 82.34%.

CONCLUSIONS: Two-scale neuroimaging signatures related to the sub-DMN underlying the antidepressant mechanisms of non-pharmacological treatments for subclinical depression. The HFBN model exhibited supreme capability in early diagnosing and predicting non-pharmacological treatment outcomes for subclinical depression, thereby promoting objective clinical psychological treatment decision-making.

PMID:39759571 | PMC:PMC11699106 | DOI:10.1016/j.ijchp.2024.100526

Phys Imaging Radiat Oncol. 2024 Nov 22;32:100677. doi: 10.1016/j.phro.2024.100677. eCollection 2024 Oct.

ABSTRACT

BACKGROUND AND PURPOSE: With the increasing amount of in-house created deep learning models in radiotherapy, it is important to know how to minimise the risks associated with the local clinical implementation prior to clinical use. The goal of this study is to give an example of how to identify the risks and find mitigation strategies to reduce these risks in an implemented workflow containing a deep learning based planning tool for breast Volumetric Modulated Arc Therapy.

MATERIALS AND METHODS: The deep learning model ran on a private Google Cloud environment for adequate computational capacity and was integrated into a workflow that could be initiated within the clinical Treatment Planning System (TPS). A proactive Failure Mode and Effect Analysis (FMEA) was conducted by a multidisciplinary team, including physicians, physicists, dosimetrists, technologists, quality managers, and the research and development team. Failure modes categorised as 'Not acceptable' and 'Tolerable' on the risk matrix were further examined to find mitigation strategies.

RESULTS: In total, 39 failure modes were defined for the total workflow, divided over four steps. Of these, 33 were deemed 'Acceptable', five 'Tolerable', and one 'Not acceptable'. Mitigation strategies, such as a case-specific Quality Assurance report, additional scripted checks and properties, a pop-up window, and time stamp analysis, reduced the failure modes to two 'Tolerable' and none in the 'Not acceptable' region.

CONCLUSIONS: The pro-active risk analysis revealed possible risks in the implemented workflow and led to the implementation of mitigation strategies that decreased the risk scores for safer clinical use.

PMID:39759485 | PMC:PMC11697787 | DOI:10.1016/j.phro.2024.100677

Front Artif Intell. 2024 Dec 20;7:1452563. doi: 10.3389/frai.2024.1452563. eCollection 2024.

ABSTRACT

BACKGROUND: Detecting programmed death ligand 1 (PD-L1) expression based on immunohistochemical (IHC) staining is an important guide for the treatment of lung cancer with immune checkpoint inhibitors. However, this method has problems such as high staining costs, tumor heterogeneity, and subjective differences among pathologists. Therefore, the application of deep learning models to segment and quantitatively predict PD-L1 expression in digital sections of Hematoxylin and eosin (H&E) stained lung squamous cell carcinoma is of great significance.

METHODS: We constructed a dataset comprising H&E-stained digital sections of lung squamous cell carcinoma and used a Transformer Unet (TransUnet) deep learning network with an encoder-decoder design to segment PD-L1 negative and positive regions and quantitatively predict the tumor cell positive score (TPS).

RESULTS: The results showed that the dice similarity coefficient (DSC) and intersection overunion (IoU) of deep learning for PD-L1 expression segmentation of H&E-stained digital slides of lung squamous cell carcinoma were 80 and 72%, respectively, which were better than the other seven cutting-edge segmentation models. The root mean square error (RMSE) of quantitative prediction TPS was 26.8, and the intra-group correlation coefficients with the gold standard was 0.92 (95% CI: 0.90-0.93), which was better than the consistency between the results of five pathologists and the gold standard.

CONCLUSION: The deep learning model is capable of segmenting and quantitatively predicting PD-L1 expression in H&E-stained digital sections of lung squamous cell carcinoma, which has significant implications for the application and guidance of immune checkpoint inhibitor treatments. And the link to the code is https://github.com/Baron-Huang/PD-L1-prediction-via-HE-image.

PMID:39759385 | PMC:PMC11695341 | DOI:10.3389/frai.2024.1452563

Front Artif Intell. 2024 Dec 20;7:1509179. doi: 10.3389/frai.2024.1509179. eCollection 2024.

ABSTRACT

Social media platforms, including X, Facebook, and Instagram, host millions of daily users, giving rise to bots automated programs disseminating misinformation and ideologies with tangible real-world consequences. While bot detection in platform X has been the area of many deep learning models with adequate results, most approaches neglect the graph structure of social media relationships and often rely on hand-engineered architectures. Our work introduces the implementation of a Neural Architecture Search (NAS) technique, namely Deep and Flexible Graph Neural Architecture Search (DFG-NAS), tailored to Relational Graph Convolutional Neural Networks (RGCNs) in the task of bot detection in platform X. Our model constructs a graph that incorporates both the user relationships and their metadata. Then, DFG-NAS is adapted to automatically search for the optimal configuration of Propagation and Transformation functions in the RGCNs. Our experiments are conducted on the TwiBot-20 dataset, constructing a graph with 229,580 nodes and 227,979 edges. We study the five architectures with the highest performance during the search and achieve an accuracy of 85.7%, surpassing state-of-the-art models. Our approach not only addresses the bot detection challenge but also advocates for the broader implementation of NAS models in neural network design automation.

PMID:39759384 | PMC:PMC11695282 | DOI:10.3389/frai.2024.1509179

Brief Bioinform. 2024 Nov 22;26(1):bbae672. doi: 10.1093/bib/bbae672.

ABSTRACT

Identifying phage-host interactions (PHIs) is a crucial step in developing phage therapy, which is the promising solution to addressing the issue of antibiotic resistance in superbugs. However, the lifestyle of phages, which strongly depends on their host for life activities, limits their cultivability, making the study of predicting PHIs time-consuming and labor-intensive for traditional wet lab experiments. Although many deep learning (DL) approaches have been applied to PHIs prediction, most DL methods are predominantly based on sequence information, failing to comprehensively model the intricate relationships within PHIs. Moreover, most existing approaches are limited for sub-optimal performance, due to the potential risk of overfitting induced by the highly data sparsity in the task of PHIs prediction. In this study, we propose a novel approach called MI-RGC, which introduces mutual information for feature augmentation and employs regional graph convolution to learn meaningful representations. Specifically, MI-RGC treats the presence status of phages in environmental samples as random variables, and derives the mutual information between these random variables as the dependency relationships among phages. Consequently, a mutual information-based heterogeneous network is construted as feature augmentation for sequence information of phages, which is utilized for building a sequence information-based heterogeneous network. By considering the different contributions of neighboring nodes at varying distances, a regional graph convolutional model is designed, in which the neighboring nodes are segmented into different regions and a regional-level attention mechanism is employed to derive node embeddings. Finally, the embeddings learned from these two networks are aggregated through an attention mechanism, on which the prediction of PHIs is condcuted accordingly. Experimental results on three benchmark datasets demonstrate that MI-RGC derives superior performance over other methods on the task of PHIs prediction.

PMID:39756070 | DOI:10.1093/bib/bbae672

Adv Sci (Weinh). 2025 Jan 4:e2410722. doi: 10.1002/advs.202410722. Online ahead of print.

ABSTRACT

Powder X-ray diffraction (PXRD) is a prevalent technique in materials characterization. While the analysis of PXRD often requires extensive human manual intervention, and most automated method only achieved at coarse-grained level. The more difficult and important task of fine-grained crystal structure prediction from PXRD remains unaddressed. This study introduces XtalNet, the first equivariant deep generative model for end-to-end crystal structure prediction from PXRD. Unlike previous crystal structure prediction methods that rely solely on composition, XtalNet leverages PXRD as an additional condition, eliminating ambiguity and enabling the generation of complex organic structures with up to 400 atoms in the unit cell. XtalNet comprises two modules: a Contrastive PXRD-Crystal Pretraining (CPCP) module that aligns PXRD space with crystal structure space, and a Conditional Crystal Structure Generation (CCSG) module that generates candidate crystal structures conditioned on PXRD patterns. Evaluation on two MOF datasets (hMOF-100 and hMOF-400) demonstrates XtalNet's effectiveness. XtalNet achieves a top-10 Match Rate of 90.2% and 79% for hMOF-100 and hMOF-400 in conditional crystal structure prediction task, respectively. XtalNet enables the direct prediction of crystal structures from experimental measurements, eliminating the need for manual intervention and external databases. This opens up new possibilities for automated crystal structure determination and the accelerated discovery of novel materials.

PMID:39755935 | DOI:10.1002/advs.202410722

Adv Sci (Weinh). 2025 Jan 4:e2407812. doi: 10.1002/advs.202407812. Online ahead of print.

ABSTRACT

β-secretase (BACE1) is instrumental in amyloid-β (Aβ) production, with overexpression noted in Alzheimer's disease (AD) neuropathology. The interaction of Aβ with the receptor for advanced glycation endproducts (RAGE) facilitates cerebral uptake of Aβ and exacerbates its neurotoxicity and neuroinflammation, further augmenting BACE1 expression. Given the limitations of previous BACE1 inhibition efforts, the study explores reducing BACE1 expression to mitigate AD pathology. The research reveals that the anticancer agent 6-thioguanosine (6-TG) markedly diminishes BACE1 expression without eliciting cytotoxicity while enhancing microglial phagocytic activity, and ameliorate cognitive impairments with reducing Aβ accumulation in AD mice. Leveraging advanced deep learning-based tool for target identification, and corroborating with surface plasmon resonance assays, it is elucidated that 6-TG directly interacts with RAGE, modulating BACE1 expression through the JAK2-STAT1 pathway and elevating soluble RAGE (sRAGE) levels in the brain. The findings illuminate the therapeutic potential of 6-TG in ameliorating AD manifestations and advocate for small molecule strategies to increase brain sRAGE levels, offering a strategic alternative to the challenges posed by the complexity of AD.

PMID:39755927 | DOI:10.1002/advs.202407812

Int J Med Inform. 2024 Dec 26;195:105754. doi: 10.1016/j.ijmedinf.2024.105754. Online ahead of print.

ABSTRACT

BACKGROUND: Ischemic stroke affects 15 million people worldwide, causing five million deaths annually. Despite declining mortality rates, stroke incidence and readmission risks remain high, highlighting the need for preventing readmission to improve the quality of life of survivors. This study developed a machine-learning model to predict 90-day stroke readmission using electronic medical records converted to the common data model (CDM) from the Regional Accountable Care Hospital in Gangwon state in South Korea.

METHODS: We retrospectively analyzed data from 1,136 patients with ischemic stroke admitted between August 2003 and August 2021 after excluding cases with missing blood test values. Demographics, blood test results, treatments, and comorbidities were used as key features. Six machine learning models and three deep learning models were used to predict 90-day readmission using the synthetic minority over-sampling technique to address class imbalance. Models were evaluated using threefold cross-validation, and SHapley Additive exPlanations (SHAP) values were calculated to interpret feature importance.

RESULTS: Among 1,136 patients, 196 (17.2 %) were readmitted within 90 days. Male patients were significantly more likely to experience readmission (p = 0.02). LightGBM achieved an area under the curve of 0.94, demonstrating that analyzing stroke and stroke-related conditions provides greater predictive accuracy than predicting stroke alone or all-cause readmissions. SHAP analysis highlighted renal and metabolic variables, including creatinine, blood urea nitrogen, calcium, sodium, and potassium, as key predictors of readmission.

CONCLUSION: Machine-learning models using electronic health record-based CDM data demonstrated strong predictive performance for 90-day stroke readmission. These results support personalized post-discharge management and lay the groundwork for future multicenter studies.

PMID:39755003 | DOI:10.1016/j.ijmedinf.2024.105754