Brief Bioinform. 2024 Mar 27;25(3):bbae112. doi: 10.1093/bib/bbae112.

ABSTRACT

Single-cell RNA sequencing has achieved massive success in biological research fields. Discovering novel cell types from single-cell transcriptomics has been demonstrated to be essential in the field of biomedicine, yet is time-consuming and needs prior knowledge. With the unprecedented boom in cell atlases, auto-annotation tools have become more prevalent due to their speed, accuracy and user-friendly features. However, existing tools have mostly focused on general cell-type annotation and have not adequately addressed the challenge of discovering novel rare cell types. In this work, we introduce scNovel, a powerful deep learning-based neural network that specifically focuses on novel rare cell discovery. By testing our model on diverse datasets with different scales, protocols and degrees of imbalance, we demonstrate that scNovel significantly outperforms previous state-of-the-art novel cell detection models, reaching the most AUROC performance(the only one method whose averaged AUROC results are above 94%, up to 16.26% more comparing to the second-best method). We validate scNovel's performance on a million-scale dataset to illustrate the scalability of scNovel further. Applying scNovel on a clinical COVID-19 dataset, three potential novel subtypes of Macrophages are identified, where the COVID-related differential genes are also detected to have consistent expression patterns through deeper analysis. We believe that our proposed pipeline will be an important tool for high-throughput clinical data in a wide range of applications.

PMID:38555470 | DOI:10.1093/bib/bbae112

J Transl Med. 2024 Mar 30;22(1):321. doi: 10.1186/s12967-024-05127-5.

ABSTRACT

BACKGROUND: Colorectal cancer (CRC) is the third most prevalent cancer globally, and liver metastasis (CRLM) is the primary cause of death. Hence, it is essential to discover novel prognostic biomarkers and therapeutic drugs for CRLM.

METHODS: This study developed two liver metastasis-associated prognostic signatures based on differentially expressed genes (DEGs) in CRLM. Additionally, we employed an interpretable deep learning model utilizing drug sensitivity databases to identify potential therapeutic drugs for high-risk CRLM patients. Subsequently, in vitro and in vivo experiments were performed to verify the efficacy of these compounds.

RESULTS: These two prognostic models exhibited superior performance compared to previously reported ones. Obatoclax, a BCL-2 inhibitor, showed significant differential responses between high and low risk groups classified by prognostic models, and demonstrated remarkable effectiveness in both Transwell assay and CT26 colorectal liver metastasis mouse model.

CONCLUSIONS: This study highlights the significance of developing specialized prognostication approaches and investigating effective therapeutic drugs for patients with CRLM. The application of a deep learning drug response model provides a new drug discovery strategy for translational medicine in precision oncology.

PMID:38555418 | DOI:10.1186/s12967-024-05127-5

Sci Rep. 2024 Mar 30;14(1):7551. doi: 10.1038/s41598-024-58163-y.

ABSTRACT

Transfer learning plays a pivotal role in addressing the paucity of data, expediting training processes, and enhancing model performance. Nonetheless, the prevailing practice of transfer learning predominantly relies on pre-trained models designed for the natural image domain, which may not be well-suited for the medical image domain in grayscale. Recognizing the significance of leveraging transfer learning in medical research, we undertook the construction of class-balanced pediatric radiograph datasets collectively referred to as PedXnets, grounded in radiographic views using the pediatric radiographs collected over 24 years at Asan Medical Center. For PedXnets pre-training, approximately 70,000 X-ray images were utilized. Three different pre-training weights of PedXnet were constructed using Inception V3 for various radiation perspective classifications: Model-PedXnet-7C, Model-PedXnet-30C, and Model-PedXnet-68C. We validated the transferability and positive effects of transfer learning of PedXnets through pediatric downstream tasks including fracture classification and bone age assessment (BAA). The evaluation of transfer learning effects through classification and regression metrics showed superior performance of Model-PedXnets in quantitative assessments. Additionally, visual analyses confirmed that the Model-PedXnets were more focused on meaningful regions of interest.

PMID:38555414 | DOI:10.1038/s41598-024-58163-y

Clin Breast Cancer. 2024 Mar 13:S1526-8209(24)00079-X. doi: 10.1016/j.clbc.2024.03.006. Online ahead of print.

ABSTRACT

BACKGROUND: To explore whether the combination of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) and nonmono-exponential (NME) model-based diffusion-weighted imaging (DWI) via deep neural network (DNN) can improve the prediction of breast cancer molecular subtypes compared to either imaging technique used alone.

PATIENTS AND METHODS: This prospective study examined 480 breast cancers in 475 patients undergoing DCE-MRI and NME-DWI at 3.0 T. Breast cancers were classified as follows: human epidermal growth factor receptor 2 enriched (HER2-enriched), luminal A, luminal B (HER2-), luminal B (HER2+), and triple-negative subtypes. A total of 20% cases were withheld as an independent test dataset, and the remaining cases were used to train DNN with an 80% to 20% training-validation split and 5-fold cross-validation. The diagnostic accuracies of DNN in 5-way subtype classification between the DCE-MRI, NME-DWI, and their combined multiparametric-MRI datasets were compared using analysis of variance with least significant difference posthoc test. Areas under the receiver-operating characteristic curves were calculated to assess the performances of DNN in binary subtype classification between the 3 datasets.

RESULTS: The 5-way classification accuracies of DNN on both DCE-MRI (0.71) and NME-DWI (0.64) were significantly lower (P < .05) than on multiparametric-MRI (0.76), while on DCE-MRI was significantly higher (P < .05) than on NME-DWI. The comparative results of binary classification between the 3 datasets were consistent with the 5-way classification.

CONCLUSION: The combination of DCE-MRI and NME-DWI via DNN achieved a significant improvement in breast cancer molecular subtype prediction compared to either imaging technique used alone. Additionally, DCE-MRI outperformed NME-DWI in differentiating subtypes.

PMID:38555225 | DOI:10.1016/j.clbc.2024.03.006

Sci Total Environ. 2024 Mar 28:172080. doi: 10.1016/j.scitotenv.2024.172080. Online ahead of print.

ABSTRACT

The perception of structure-borne noise is particularly salient when train passes through the tunnel under the buildings, which has a negative impact on human health. In the process of constructing buildings along metro lines, it is crucial to estimate indoor structure-borne noise levels in order to enhance design and prevent any negative impact on human comfort. This study conducted measurements of structure-borne noise, reverberation time, and train-induced vibrations in Guangzhou, China to investigate the generation, propagation, and dissipation mechanisms of structure-borne noise. An approach based on Short-Time Fourier Transform and Schroeder integral was proposed for obtaining frequency-dependent reverberation time. Additionally, a deep learning-based approach incorporating indoor vibrations, frequency-dependent reverberation time, and room parameters as inputs was proposed based on Genetic Algorithm-Artificial Neural Network. The estimated structure-borne noise levels demonstrated good agreement with measured values, indicating the feasibility of the approach. The finding of this research facilitates a clear comprehension of the generation, distribution, and dissipation mechanisms of indoor structure-borne noise for engineers while also enabling convenient acquisition of indoor structure-borne noise. The estimated noise levels can be effectively utilized during building design processes along metro lines to mitigate adverse impacts on human comfort.

PMID:38554979 | DOI:10.1016/j.scitotenv.2024.172080

Int J Radiat Oncol Biol Phys. 2024 Mar 28:S0360-3016(24)00423-1. doi: 10.1016/j.ijrobp.2024.03.007. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: The dose deposited outside of the treatment field during external photon beam radiotherapy treatment, also known as out-of-field dose, is the subject of extensive study as it may be associated with a higher risk of developing a second cancer, and could have deleterious effects on the immune system which compromise the efficiency of combined radio-immunotherapy treatments. Out-of-field dose estimation tools developed today in research, including Monte Carlo simulations and analytical methods, are not suited to the requirements of clinical implementation because of their lack of versatility and their cumbersome application. We propose a proof of concept based on deep learning for out-of-field dose map estimation that addresses the above limitations.

MATERIALS AND METHODS: For this purpose, a 3D U-Net, considering as inputs the in-field dose, as computed by the treatment planning system, and the patient's anatomy, was trained to predict out-of-field dose maps. The cohort used for learning and performance evaluation included 3151 pediatric patients from the [XXXX] database, treated in 5 clinical centers, whose whole-body dose maps were previously estimated with an empirical analytical method. The test set, composed of 433 patients, was split into 5 subdatasets, each containing patients treated with devices unseen during the training phase. Root mean square deviation (RMSD) evaluated only on non-zero voxels located in the out-of-field areas was computed as performance metric.

RESULTS: RMSD of 0.28 and 0.41 cGy.Gy-1 were obtained for the training and validation datasets, respectively. Values of 0.27, 0.26, 0.28, 0.30 and 0.45 cGy.Gy-1 were achieved for the 6 MV linac, 16 MV linac, Alcyon cobalt irradiator, Mobiletron cobalt irradiator, and betatron devices test sets, respectively.

CONCLUSION: This proof-of-concept approach using a convolutional neural network has demonstrated unprecedented generalizability for this task, although it remains limited, and brings us closer to an implementation compatible with clinical routine.

PMID:38554830 | DOI:10.1016/j.ijrobp.2024.03.007

J Chem Inf Model. 2024 Mar 30. doi: 10.1021/acs.jcim.3c01720. Online ahead of print.

ABSTRACT

In this work, we propose a versatile molecule and reaction encoding binary data format that aims to bridge the gap between the advantages of SMILES, like local stereo- and implicit hydrogen encoding, and block-structured MDL MOL with a 2D layout and explicit bond encoding, while addressing their respective limitations. Our new format introduces a balance between size efficiency, processing speed, and comprehensive representation, making it well-suited for various applications in cheminformatics, including deep learning, data storage, and searching. By offering an explicit approach to store atom connectivity (including implicit hydrogens), electronic state, stereochemistry, and other crucial molecular attributes, our proposal seeks to enhance data storage efficiency and promote interoperability among different software tools.

PMID:38554112 | DOI:10.1021/acs.jcim.3c01720

Microsc Res Tech. 2024 Mar 30. doi: 10.1002/jemt.24557. Online ahead of print.

ABSTRACT

Breast cancer is a major health threat, with early detection crucial for improving cure and survival rates. Current systems rely on imaging technology, but digital pathology and computerized analysis can enhance accuracy, reduce false predictions, and improve medical care for breast cancer patients. The study explores the challenges in identifying benign and malignant breast cancer lesions using microscopic image datasets. It introduces a low-dimensional multiple-channel feature-based method for breast cancer microscopic image recognition, overcoming limitations in feature utilization and computational complexity. The method uses RGB channels for image processing and extracts features using level co-occurrence matrix, wavelet, Gabor, and histogram of oriented gradient. This approach aims to improve diagnostic efficiency and accuracy in breast cancer treatment. The core of our method is the SqE-DDConvNet algorithm, which utilizes a 3 × 1 convolution kernel, SqE-DenseNet module, bilinear interpolation, and global average pooling to enhance recognition accuracy and training efficiency. Additionally, we incorporate transfer learning with pre-trained models, including mVVGNet16, EfficientNetV2B3, ResNet101V2, and CN2XNet, preserving spatial information and achieving higher accuracy under varying magnification conditions. The method achieves higher accuracy compared to baseline models, including texture and deep semantic features. This deep learning-based methodology contributes to more accurate image classification and unique image recognition in breast cancer microscopic images. RESEARCH HIGHLIGHTS: Introduces a low-dimensional multiple-channel feature-based method for breast cancer microscopic image recognition. Uses RGB channels for image processing and extracts features using level co-occurrence matrix, wavelet, Gabor, and histogram of oriented gradient. Employs the SqE-DDConvNet algorithm for enhanced recognition accuracy and training efficiency. Transfer learning with pre-trained models preserves spatial information and achieves higher accuracy under varying magnification conditions. Evaluates predictive efficacy of transfer learning paradigms within microscopic analysis. Utilizes CNN-based pre-trained algorithms to enhance network performance.

PMID:38553901 | DOI:10.1002/jemt.24557

NPJ Precis Oncol. 2024 Mar 29;8(1):80. doi: 10.1038/s41698-024-00575-0.

ABSTRACT

This review delves into the most recent advancements in applying artificial intelligence (AI) within neuro-oncology, specifically emphasizing work on gliomas, a class of brain tumors that represent a significant global health issue. AI has brought transformative innovations to brain tumor management, utilizing imaging, histopathological, and genomic tools for efficient detection, categorization, outcome prediction, and treatment planning. Assessing its influence across all facets of malignant brain tumor management- diagnosis, prognosis, and therapy- AI models outperform human evaluations in terms of accuracy and specificity. Their ability to discern molecular aspects from imaging may reduce reliance on invasive diagnostics and may accelerate the time to molecular diagnoses. The review covers AI techniques, from classical machine learning to deep learning, highlighting current applications and challenges. Promising directions for future research include multimodal data integration, generative AI, large medical language models, precise tumor delineation and characterization, and addressing racial and gender disparities. Adaptive personalized treatment strategies are also emphasized for optimizing clinical outcomes. Ethical, legal, and social implications are discussed, advocating for transparency and fairness in AI integration for neuro-oncology and providing a holistic understanding of its transformative impact on patient care.

PMID:38553633 | DOI:10.1038/s41698-024-00575-0

Sci Rep. 2024 Mar 29;14(1):7523. doi: 10.1038/s41598-024-58131-6.

ABSTRACT

Myocardial scar (MS) and left ventricular ejection fraction (LVEF) are vital cardiovascular parameters, conventionally determined using cardiac magnetic resonance (CMR). However, given the high cost and limited availability of CMR in resource-constrained settings, electrocardiograms (ECGs) are a cost-effective alternative. We developed computer vision-based multi-task deep learning models to analyze 12-lead ECG 2D images, predicting MS and LVEF < 50%. Our dataset comprises 14,052 ECGs with clinical features, utilizing ground truth labels from CMR. Our top-performing model achieved AUC values of 0.838 (95% CI 0.812-0.862) for MS and 0.939 (95% CI 0.921-0.954) for LVEF < 50% classification, outperforming cardiologists. Moreover, MS predictions in a prevalence-specific test dataset recorded an AUC of 0.812 (95% CI 0.810-0.814). Extracted 1D signals from ECG images yielded inferior performance, compared to the 2D approach. In conclusion, our results demonstrate the potential of computer-based MS and LVEF < 50% classification from ECG scan images in clinical screening offering a cost-effective alternative to CMR.

PMID:38553581 | DOI:10.1038/s41598-024-58131-6

Sci Rep. 2024 Mar 29;14(1):7501. doi: 10.1038/s41598-024-58251-z.

ABSTRACT

Coherent beam combination offers a solution to the challenges associated with the power handling capacity of individual fibres, however, the combined intensity profile strongly depends on the relative phase of each fibre. Optimal combination necessitates precise control over the phase of each fibre channel, however, determining the required phase compensations is challenging because phase information is typically not available. Additionally, the presence of continuously varying phase noise in fibre laser systems means that a single-step and high-speed correction process is required. In this work, we use a spatial light modulator to demonstrate coherent combination in a seven-beam system. Deep learning is used to identify the relative phase offsets for each beam directly from the combined intensity pattern, allowing real-time correction. Furthermore, we demonstrate that the deep learning agent can calculate the phase corrections needed to achieve user-specified target intensity profiles thus simultaneously achieving both beam combination and beam shaping.

PMID:38553568 | DOI:10.1038/s41598-024-58251-z

J Cardiovasc Comput Tomogr. 2024 Mar 28:S1934-5925(24)00071-6. doi: 10.1016/j.jcct.2024.03.012. Online ahead of print.

NO ABSTRACT

PMID:38553402 | DOI:10.1016/j.jcct.2024.03.012

J Med Imaging Radiat Sci. 2024 Mar 28:S1939-8654(24)00054-7. doi: 10.1016/j.jmir.2024.02.024. Online ahead of print.

ABSTRACT

State of the art of cardiac SPECT imaging continues to advance. Contemporary clinical applications of cardiac SPECT are reviewed and illustrated. Beyond traditional stress and rest myocardial perfusion imaging, the role of digital SPECT technology, ultra low dose imaging with efficient stress first / stress only if normal imaging, deep learning algorithms relative to coronary angiography and SPECT CT, sourceless emission attenuation correction, myocardial blood flow and blood flow reserve to assess ischemic jeopardy, culprit ischemic territories, and cardiac allograft vasculopathy, advanced methods of SPECT detection of amyloid cardiomyopathy, resting MPI to define pre-operative regional scar prior to operative ablation, parametric radionuclide ventriculography to quantify dyssynchrony and benefit of biventricular pacing, assessment of treatment response of RV and LV function in patients with pulmonary hypertension, dual isotope MIBG imaging to assess cardiac risk, and the value proposition of real world effectiveness of SPECT cardiac imaging are illustrated.

PMID:38553298 | DOI:10.1016/j.jmir.2024.02.024

Radiol Clin North Am. 2024 May;62(3):473-488. doi: 10.1016/j.rcl.2024.01.002. Epub 2024 Feb 7.

ABSTRACT

Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.

PMID:38553181 | DOI:10.1016/j.rcl.2024.01.002

Artif Intell Med. 2024 Apr;150:102830. doi: 10.1016/j.artmed.2024.102830. Epub 2024 Mar 4.

ABSTRACT

The full acceptance of Deep Learning (DL) models in the clinical field is rather low with respect to the quantity of high-performing solutions reported in the literature. End users are particularly reluctant to rely on the opaque predictions of DL models. Uncertainty quantification methods have been proposed in the literature as a potential solution, to reduce the black-box effect of DL models and increase the interpretability and the acceptability of the result by the final user. In this review, we propose an overview of the existing methods to quantify uncertainty associated with DL predictions. We focus on applications to medical image analysis, which present specific challenges due to the high dimensionality of images and their variable quality, as well as constraints associated with real-world clinical routine. Moreover, we discuss the concept of structural uncertainty, a corpus of methods to facilitate the alignment of segmentation uncertainty estimates with clinical attention. We then discuss the evaluation protocols to validate the relevance of uncertainty estimates. Finally, we highlight the open challenges for uncertainty quantification in the medical field.

PMID:38553168 | DOI:10.1016/j.artmed.2024.102830

Artif Intell Med. 2024 Apr;150:102822. doi: 10.1016/j.artmed.2024.102822. Epub 2024 Feb 27.

ABSTRACT

BACKGROUND: Stroke is a prevalent disease with a significant global impact. Effective assessment of stroke severity is vital for an accurate diagnosis, appropriate treatment, and optimal clinical outcomes. The National Institutes of Health Stroke Scale (NIHSS) is a widely used scale for quantitatively assessing stroke severity. However, the current manual scoring of NIHSS is labor-intensive, time-consuming, and sometimes unreliable. Applying artificial intelligence (AI) techniques to automate the quantitative assessment of stroke on vast amounts of electronic health records (EHRs) has attracted much interest.

OBJECTIVE: This study aims to develop an automatic, quantitative stroke severity assessment framework through automating the entire NIHSS scoring process on Chinese clinical EHRs.

METHODS: Our approach consists of two major parts: Chinese clinical named entity recognition (CNER) with a domain-adaptive pre-trained large language model (LLM) and automated NIHSS scoring. To build a high-performing CNER model, we first construct a stroke-specific, densely annotated dataset "Chinese Stroke Clinical Records" (CSCR) from EHRs provided by our partner hospital, based on a stroke ontology that defines semantically related entities for stroke assessment. We then pre-train a Chinese clinical LLM coined "CliRoberta" through domain-adaptive transfer learning and construct a deep learning-based CNER model that can accurately extract entities directly from Chinese EHRs. Finally, an automated, end-to-end NIHSS scoring pipeline is proposed by mapping the extracted entities to relevant NIHSS items and values, to quantitatively assess the stroke severity.

RESULTS: Results obtained on a benchmark dataset CCKS2019 and our newly created CSCR dataset demonstrate the superior performance of our domain-adaptive pre-trained LLM and the CNER model, compared with the existing benchmark LLMs and CNER models. The high F1 score of 0.990 ensures the reliability of our model in accurately extracting the entities for the subsequent automatic NIHSS scoring. Subsequently, our automated, end-to-end NIHSS scoring approach achieved excellent inter-rater agreement (0.823) and intraclass consistency (0.986) with the ground truth and significantly reduced the processing time from minutes to a few seconds.

CONCLUSION: Our proposed automatic and quantitative framework for assessing stroke severity demonstrates exceptional performance and reliability through directly scoring the NIHSS from diagnostic notes in Chinese clinical EHRs. Moreover, this study also contributes a new clinical dataset, a pre-trained clinical LLM, and an effective deep learning-based CNER model. The deployment of these advanced algorithms can improve the accuracy and efficiency of clinical assessment, and help improve the quality, affordability and productivity of healthcare services.

PMID:38553162 | DOI:10.1016/j.artmed.2024.102822

Artif Intell Med. 2024 Apr;150:102820. doi: 10.1016/j.artmed.2024.102820. Epub 2024 Feb 23.

ABSTRACT

Due to the constant increase in cancer rates, the disease has become a leading cause of death worldwide, enhancing the need for its detection and treatment. In the era of personalized medicine, the main goal is to incorporate individual variability in order to choose more precisely which therapy and prevention strategies suit each person. However, predicting the sensitivity of tumors to anticancer treatments remains a challenge. In this work, we propose two deep neural network models to predict the impact of anticancer drugs in tumors through the half-maximal inhibitory concentration (IC50). These models join biological and chemical data to apprehend relevant features of the genetic profile and the drug compounds, respectively. In order to predict the drug response in cancer cell lines, this study employed different DL methods, resorting to Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs). In the first stage, two autoencoders were pre-trained with high-dimensional gene expression and mutation data of tumors. Afterward, this genetic background is transferred to the prediction models that return the IC50 value that portrays the potency of a substance in inhibiting a cancer cell line. When comparing RSEM Expected counts and TPM as methods for displaying gene expression data, RSEM has been shown to perform better in deep models and CNNs model can obtain better insight in these types of data. Moreover, the obtained results reflect the effectiveness of the extracted deep representations in the prediction of the IC50 value that portrays the potency of a substance in inhibiting a tumor, achieving a performance of a mean squared error of 1.06 and surpassing previous state-of-the-art models.

PMID:38553160 | DOI:10.1016/j.artmed.2024.102820

J Neurosurg. 2024 Mar 29:1-12. doi: 10.3171/2024.1.JNS232280. Online ahead of print.

ABSTRACT

OBJECTIVE: The relationships between immediate bleeding severity, postoperative complications, and long-term functional outcomes in patients with aneurysmal subarachnoid hemorrhage (aSAH) remain uncertain. Here, the authors apply their recently developed automated deep learning technique to quantify total bleeding volume (TBV) in patients with aSAH and investigate associations between quantitative TBV and secondary complications, adverse long-term functional outcomes, and death.

METHODS: Electronic health record data were extracted for adult patients admitted to a single institution within 72 hours of aSAH onset between 2018 and 2021. An automatic deep learning model was used to fully segment and quantify TBV on admission noncontrast head CT images. Patients were subgrouped by TBV quartile, and multivariable logistic regression, restricted cubic splines, and subgroup analysis were used to explore the relationships between TBV and each clinical outcome.

RESULTS: A total of 819 patients were included in the study. Sixty-six (8.1%) patients developed hydrocephalus, while 43 (5.3%) experienced rebleeding, 141 (17.2%) had delayed cerebral ischemia, 88 (10.7%) died in the 12 months after discharge, and 208 (25.7%) had a modified Rankin Scale score ≥ 3 12 months after discharge. On multivariable analysis, patients in the highest TBV quartile (> 37.94 ml) had an increased risk of hydrocephalus (adjusted OR [aOR] 4.38, 95% CI 1.61-11.87; p = 0.004), rebleeding (aOR 3.26, 95% CI 1.03-10.33; p = 0.045), death (aOR 6.92, 95% CI 1.89-25.37; p = 0.004), and 12-month disability (aOR 3.30, 95% CI 1.62-6.72; p = 0.001) compared with the lowest TBV quantile (< 8.34 ml). The risks of hydrocephalus (nonlinear, p = 0.025), rebleeding, death, and disability (linear, p > 0.05) were positively associated with TBV by restricted cubic splines. In subgroup analysis, TBV had a stronger effect on 12-month outcome in female than male patients (p for interaction = 0.0499) and on rebleeding prevalence in patients with endovascular coiling than those with surgical clipping (p for interaction = 0.008).

CONCLUSIONS: Elevated TBV is associated with a greater risk of hydrocephalus, rebleeding, death, and poor prognosis.

PMID:38552240 | DOI:10.3171/2024.1.JNS232280

J Chem Inf Model. 2024 Mar 29. doi: 10.1021/acs.jcim.3c01559. Online ahead of print.

ABSTRACT

Water molecules are integral to the structural stability of proteins and vital for facilitating molecular interactions. However, accurately predicting their precise position around protein structures remains a significant challenge, making it a vibrant research area. In this paper, we introduce HydraProt (deep Hydration of Proteins), a novel methodology for predicting precise positions of water molecule oxygen atoms around protein structures, leveraging two interconnected deep learning architectures: a 3D U-net and a Multi-Layer Perceptron (MLP). Our approach starts by introducing a coarse voxel-based representation of the protein, which allows for rapid sampling of candidate water positions via the 3D U-net. These water positions are then assessed by embedding the water-protein relationship in the Euclidean space by means of an MLP. Finally, a postprocessing step is applied to further refine the MLP predictions. HydraProt surpasses existing state-of-the-art approaches in terms of precision and recall and has been validated on large data sets of protein structures. Notably, our method offers rapid inference runtime and should constitute the method of choice for protein structure studies and drug discovery applications. Our pretrained models, data, and the source code required to reproduce these results are accessible at https://github.com/azamanos/HydraProt.

PMID:38552195 | DOI:10.1021/acs.jcim.3c01559

Medicine (Baltimore). 2024 Mar 29;103(13):e37347. doi: 10.1097/MD.0000000000037347.

ABSTRACT

BACKGROUND: Diabetic macular edema (DME) is the main cause of irreversible vision loss in patients with diabetes mellitus (DM), resulting in a certain burden to patients and society. With the increasing incidence of DME, more and more researchers are focusing on it.

METHODS: The papers related to DME between 2012 and 2022 from the Web of Science core Collection were searched in this study. Based on CiteSpace and VOS viewer, these publications were analyzed in terms of spatiotemporal distribution, author distribution, subject classification, topic distribution, and citations.

RESULTS: A total of 5165 publications on DME were included. The results showed that the research on DME is on a steady growth trend. The country with the highest number of published documents was the US. Wong Tien Yin from Tsinghua University was the author with the most published articles. The journal of Retina, the Journal of Retinal and Vitreous Diseases had a large number of publications. The article "Mechanisms of macular edema: Beyond the surface" was the highly cited literature and "Aflibercept, bevacizumab, or ranibizumab for diabetic macular edema" had the highest co-citation frequency. The treatment, diagnosis, pathogenesis, as well as etiology and epidemiological investigation of DME, have been the current research direction. Deep learning has been widely used in the medical field for its strong feature representation ability.

CONCLUSIONS: The study revealed the important authoritative literature, journals, institutions, scholars, countries, research hotspots, and development trends in in the field of DME. This indicates that communication and cooperation between disciplines, universities, and countries are crucial. It can advance research in DME and even ophthalmology.

PMID:38552080 | DOI:10.1097/MD.0000000000037347