J Transl Med. 2024 Oct 4;22(1):896. doi: 10.1186/s12967-024-05708-4.

ABSTRACT

BACKGROUND: Concurrent chemoradiotherapy (CCRT) is a crucial treatment for non-small cell lung carcinoma (NSCLC). However, the use of deep learning (DL) models for predicting the response to CCRT in NSCLC remains unexplored. Therefore, we constructed a DL model for estimating the response to CCRT in NSCLC and explored the associated biological signaling pathways.

METHODS: Overall, 229 patients with NSCLC were recruited from six hospitals. Based on contrast-enhanced computed tomography (CT) images, a three-dimensional ResNet50 algorithm was used to develop a model and validate the performance in predicting response and prognosis. An associated analysis was conducted on CT image visualization, RNA sequencing, and single-cell sequencing.

RESULTS: The DL model exhibited favorable predictive performance, with an area under the curve of 0.86 (95% confidence interval [CI] 0.79-0·92) in the training cohort and 0.84 (95% CI 0.75-0.94) in the validation cohort. The DL model (low score vs. high score) was an independent predictive factor; it was significantly associated with progression-free survival and overall survival in both the training (hazard ratio [HR] = 0.54 [0.36-0.80], P = 0.002; 0.44 [0.28-0.68], P < 0.001) and validation cohorts (HR = 0.46 [0.24-0.88], P = 0.008; 0.30 [0.14-0.60], P < 0.001). The DL model was also positively related to the cell adhesion molecules, the P53 signaling pathway, and natural killer cell-mediated cytotoxicity. Single-cell analysis revealed that differentially expressed genes were enriched in different immune cells.

CONCLUSION: The DL model demonstrated a strong predictive ability for determining the response in patients with NSCLC undergoing CCRT. Our findings contribute to understanding the potential biological mechanisms underlying treatment responses in these patients.

PMID:39367461 | DOI:10.1186/s12967-024-05708-4

BMC Med Inform Decis Mak. 2024 Oct 4;24(1):285. doi: 10.1186/s12911-024-02699-6.

ABSTRACT

Significant progress has been made recently with the contribution of technological advances in studies on brain cancer. Regarding this, identifying and correctly classifying tumors is a crucial task in the field of medical imaging. The disease-related tumor classification problem, on which deep learning technologies have also become a focus, is very important in the diagnosis and treatment of the disease. The use of deep learning models has shown promising results in recent years. However, the sparsity of ground truth data in medical imaging or inconsistent data sources poses a significant challenge for training these models. The utilization of StyleGANv2-ADA is proposed in this paper for augmenting brain MRI slices to enhance the performance of deep learning models. Specifically, augmentation is applied solely to the training data to prevent any potential leakage. The StyleGanv2-ADA model is trained with the Gazi Brains 2020, BRaTS 2021, and Br35h datasets using the researchers' default settings. The effectiveness of the proposed method is demonstrated on datasets for brain tumor classification, resulting in a notable improvement in the overall accuracy of the model for brain tumor classification on all the Gazi Brains 2020, BraTS 2021, and Br35h datasets. Importantly, the utilization of StyleGANv2-ADA on the Gazi Brains 2020 Dataset represents a novel experiment in the literature. The results show that the augmentation with StyleGAN can help overcome the challenges of working with medical data and the sparsity of ground truth data. Data augmentation employing the StyleGANv2-ADA GAN model yielded the highest overall accuracy for brain tumor classification on the BraTS 2021 and Gazi Brains 2020 datasets, together with the BR35H dataset, achieving 75.18%, 99.36%, and 98.99% on the EfficientNetV2S models, respectively. This study emphasizes the potency of GANs for augmenting medical imaging datasets, particularly in brain tumor classification, showcasing a notable increase in overall accuracy through the integration of synthetic GAN data on the used datasets.

PMID:39367444 | DOI:10.1186/s12911-024-02699-6

BMC Med Inform Decis Mak. 2024 Oct 4;24(1):287. doi: 10.1186/s12911-024-02682-1.

ABSTRACT

BACKGROUND: Hepatocellular Carcinoma (HCC) is a highly aggressive, prevalent, and deadly type of liver cancer. With the advent of deep learning techniques, significant advancements have been made in simplifying and optimizing the feature selection process.

OBJECTIVE: Our scoping review presents an overview of the various deep learning models and algorithms utilized to address feature selection for HCC. The paper highlights the strengths and limitations of each approach, along with their potential applications in clinical practice. Additionally, it discusses the benefits of using deep learning to identify relevant features and their impact on the accuracy and efficiency of diagnosis, prognosis, and treatment of HCC.

DESIGN: The review encompasses a comprehensive analysis of the research conducted in the past few years, focusing on the methodologies, datasets, and evaluation metrics adopted by different studies. The paper aims to identify the key trends and advancements in the field, shedding light on the promising areas for future research and development.

RESULTS: The findings of this review indicate that deep learning techniques have shown promising results in simplifying feature selection for HCC. By leveraging large-scale datasets and advanced neural network architectures, these methods have demonstrated improved accuracy and robustness in identifying predictive features.

CONCLUSIONS: We analyze published studies to reveal the state-of-the-art HCC prediction and showcase how deep learning can boost accuracy and decrease false positives. But we also acknowledge the challenges that remain in translating this potential into clinical reality.

PMID:39367397 | DOI:10.1186/s12911-024-02682-1

BMC Musculoskelet Disord. 2024 Oct 4;25(1):788. doi: 10.1186/s12891-024-07884-2.

ABSTRACT

BACKGROUND: Advances in medical imaging have made it possible to classify ankle fractures using Artificial Intelligence (AI). Recent studies have demonstrated good internal validity for machine learning algorithms using the AO/OTA 2018 classification. This study aimed to externally validate one such model for ankle fracture classification and ways to improve external validity.

METHODS: In this retrospective observation study, we trained a deep-learning neural network (7,500 ankle studies) to classify traumatic malleolar fractures according to the AO/OTA classification. Our internal validation dataset (IVD) contained 409 studies collected from Danderyd Hospital in Stockholm, Sweden, between 2002 and 2016. The external validation dataset (EVD) contained 399 studies collected from Flinders Medical Centre, Adelaide, Australia, between 2016 and 2020. Our primary outcome measures were the area under the receiver operating characteristic (AUC) and the area under the precision-recall curve (AUPR) for fracture classification of AO/OTA malleolar (44) fractures. Secondary outcomes were performance on other fractures visible on ankle radiographs and inter-observer reliability of reviewers.

RESULTS: Compared to the weighted mean AUC (wAUC) 0.86 (95%CI 0.82-0.89) for fracture detection in the EVD, the network attained wAUC 0.95 (95%CI 0.94-0.97) for the IVD. The area under the precision-recall curve (AUPR) was 0.93 vs. 0.96. The wAUC for individual outcomes (type 44A-C, group 44A1-C3, and subgroup 44A1.1-C3.3) was 0.82 for the EVD and 0.93 for the IVD. The weighted mean AUPR (wAUPR) was 0.59 vs 0.63. Throughout, the performance was superior to that of a random classifier for the EVD.

CONCLUSION: Although the two datasets had considerable differences, the model transferred well to the EVD and the alternative clinical scenario it represents. The direct clinical implications of this study are that algorithms developed elsewhere need local validation and that discrepancies can be rectified using targeted training. In a wider sense, we believe this opens up possibilities for building advanced treatment recommendations based on exact fracture types that are more objective than current clinical decisions, often influenced by who is present during rounds.

PMID:39367349 | DOI:10.1186/s12891-024-07884-2

BMC Genomics. 2024 Oct 4;25(1):930. doi: 10.1186/s12864-024-10855-5.

ABSTRACT

BACKGROUND: Huntington's disease (HD) is a hereditary neurological disorder caused by mutations in HTT, leading to neuronal degeneration. Traditionally, HD is associated with the misfolding and aggregation of mutant huntingtin due to an extended polyglutamine domain encoded by an expanded CAG tract. However, recent research has also highlighted the role of global transcriptional dysregulation in HD pathology. However, understanding the intricate relationship between mRNA expression and HD at the cellular level remains challenging. Our study aimed to elucidate the underlying mechanisms of HD pathology using single-cell sequencing data.

RESULTS: We used single-cell RNA sequencing analysis to determine differential gene expression patterns between healthy and HD cells. HD cells were effectively modeled using a residual neural network (ResNet), which outperformed traditional and convolutional neural networks. Despite the efficacy of our approach, the F1 score for the test set was 96.53%. Using the SHapley Additive exPlanations (SHAP) algorithm, we identified genes influencing HD prediction and revealed their roles in HD pathobiology, such as in the regulation of cellular iron metabolism and mitochondrial function. SHAP analysis also revealed low-abundance genes that were overlooked by traditional differential expression analysis, emphasizing its effectiveness in identifying biologically relevant genes for distinguishing between healthy and HD cells. Overall, the integration of single-cell RNA sequencing data and deep learning models provides valuable insights into HD pathology.

CONCLUSION: We developed the model capable of analyzing HD at single-cell transcriptomic level.

PMID:39367331 | DOI:10.1186/s12864-024-10855-5

BMC Bioinformatics. 2024 Oct 4;25(1):322. doi: 10.1186/s12859-024-05940-1.

ABSTRACT

PURPOSE: More accurate prediction of phenotype traits can increase the success of genomic selection in both plant and animal breeding studies and provide more reliable disease risk prediction in humans. Traditional approaches typically use regression models based on linear assumptions between the genetic markers and the traits of interest. Non-linear models have been considered as an alternative tool for modeling genomic interactions (i.e. non-additive effects) and other subtle non-linear patterns between markers and phenotype. Deep learning has become a state-of-the-art non-linear prediction method for sound, image and language data. However, genomic data is better represented in a tabular format. The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports successful results on various datasets. Tabular deep learning applications in genome-wide prediction (GWP) are still rare. In this work, we perform an overview of the main families of recent deep learning architectures for tabular data and apply them to multi-trait regression and multi-class classification for GWP on real gene datasets.

METHODS: The study involves an extensive overview of recent deep learning architectures for tabular data learning: NODE, TabNet, TabR, TabTransformer, FT-Transformer, AutoInt, GANDALF, SAINT and LassoNet. These architectures are applied to multi-trait GWP. Comprehensive benchmarks of various tabular deep learning methods are conducted to identify best practices and determine their effectiveness compared to traditional methods.

RESULTS: Extensive experimental results on several genomic datasets (three for multi-trait regression and two for multi-class classification) highlight LassoNet as a standout performer, surpassing both other tabular deep learning models and the highly efficient tree based LightGBM method in terms of both best prediction accuracy and computing efficiency.

CONCLUSION: Through series of evaluations on real-world genomic datasets, the study identifies LassoNet as a standout performer, surpassing decision tree methods like LightGBM and other tabular deep learning architectures in terms of both predictive accuracy and computing efficiency. Moreover, the inherent variable selection property of LassoNet provides a systematic way to find important genetic markers that contribute to phenotype expression.

PMID:39367318 | DOI:10.1186/s12859-024-05940-1

Sci Rep. 2024 Oct 4;14(1):23065. doi: 10.1038/s41598-024-74276-w.

ABSTRACT

Distinguishing between pathologic complete response and residual cancer after neoadjuvant chemotherapy (NAC) is crucial for treatment decisions, but the current imaging methods face challenges. To address this, we developed deep-learning models using post-NAC dynamic contrast-enhanced MRI and clinical data. A total of 852 women with human epidermal growth factor receptor 2 (HER2)-positive or triple-negative breast cancer were randomly divided into a training set (n = 724) and a validation set (n = 128). A 3D convolutional neural network model was trained on the training set and validated independently. The main models were developed using cropped MRI images, but models using uncropped whole images were also explored. The delayed-phase model demonstrated superior performance compared to the early-phase model (area under the receiver operating characteristic curve [AUC] = 0.74 vs. 0.69, P = 0.013) and the combined model integrating multiple dynamic phases and clinical data (AUC = 0.74 vs. 0.70, P = 0.022). Deep-learning models using uncropped whole images exhibited inferior performance, with AUCs ranging from 0.45 to 0.54. Further refinement and external validation are necessary for enhanced accuracy.

PMID:39367159 | DOI:10.1038/s41598-024-74276-w

Sci Rep. 2024 Oct 4;14(1):23069. doi: 10.1038/s41598-024-74733-6.

ABSTRACT

A smart grid (SG) is a cutting-edge electrical grid that utilizes digital communication technology and automation to effectively handle electricity consumption, distribution, and generation. It incorporates energy storage systems, smart meters, and renewable energy sources for bidirectional communication and enhanced energy flow between grid modules. Due to their cyberattack vulnerability, SGs need robust safety measures to protect sensitive data, ensure public safety, and maintain a reliable power supply. Robust safety measures, comprising intrusion detection systems (IDSs), are significant to protect against malicious manipulation, unauthorized access, and data breaches in grid operations, confirming the electricity supply chain's integrity, resilience, and reliability. Deep learning (DL) improves intrusion recognition in SGs by effectually analyzing network data, recognizing complex attack patterns, and adjusting to dynamic threats in real-time, thereby strengthening the reliability and resilience of the grid against cyber-attacks. This study develops a novel Mountain Gazelle Optimization with Deep Ensemble Learning based intrusion detection (MGODEL-ID) technique on SG environment. The MGODEL-ID methodology exploits ensemble learning with metaheuristic approaches to identify intrusions in the SG environment. Primarily, the MGODEL-ID approach utilizes Z-score normalization to convert the input data into a uniform format. Besides, the MGODEL-ID approach employs the MGO model for feature subset selection. Meanwhile, the detection of intrusions is performed by an ensemble of three classifiers such as long short-term memory (LSTM), deep autoencoder (DAE), and extreme learning machine (ELM). Eventually, the dung beetle optimizer (DBO) is utilized to tune the hyperparameter tuning of the classifiers. A widespread simulation outcome is made to demonstrate the improved security outcomes of the MGODEL-ID model. The experimental values implied that the MGODEL-ID model performs better than other models.

PMID:39367158 | DOI:10.1038/s41598-024-74733-6

PLoS One. 2024 Oct 4;19(10):e0308664. doi: 10.1371/journal.pone.0308664. eCollection 2024.

ABSTRACT

This study aims at improving the lower-limb muscle segmentation accuracy of deep learning approaches based on Magnetic Resonance Imaging (MRI) scans, crucial for the diagnostic and therapeutic processes in musculoskeletal diseases. In general, segmentation methods such as U-Net deep learning neural networks can achieve good Dice Similarity Coefficient (DSC) values, e.g. around 0.83 to 0.91 on various cohorts. Some generic post-processing strategies have been studied to incorporate connectivity constraints into the resulting masks for the purpose of further improving the segmentation accuracy. In this paper, a novel mean shape (MS) based post-processing method is proposed, utilizing Statistical Shape Modelling (SSM) to fine-tune the segmentation output, taking into consideration the muscle anatomical shape. The methodology was compared to existing post-processing techniques and a commercial semi-automatic tool on MRI scans from two cohorts of post-menopausal women (10 Training, 8 Testing, voxel size 1.0x1.0x1.0 mm3). The MS based method obtained a mean DSC of 0.83 across the different analysed muscles and the best performance for the Hausdorff Distance (HD, 20.6 mm) and the Average Symmetric Surface Distance (ASSD, 2.1 mm). These findings highlight the feasibility and potential of using anatomical mean shape in post-processing of human lower-limb muscle segmentation task and indicate that the proposed method can be popularized to other biological organ segmentation mission.

PMID:39365764 | DOI:10.1371/journal.pone.0308664

Bioinformatics. 2024 Oct 4:btae594. doi: 10.1093/bioinformatics/btae594. Online ahead of print.

ABSTRACT

MOTIVATION: Accurately predicting the drug-target binding affinity (DTA) is crucial to drug discovery and repurposing. Although deep learning has been widely used in this field, it still faces challenges with insufficient generalization performance, inadequate use of three-dimensional (3D) information and poor interpretability.

RESULTS: To alleviate these problems, we developed the PocketDTA model. This model enhances the generalization performance by pre-trained models ESM-2 and GraphMVP. It ingeniously handles the first three (top-3) target binding pockets and drug 3D information through customized GVP-GNN Layers and GraphMVP-Decoder. Additionally, it employs a bilinear attention network to enhance interpretability. Comparative analysis with state-of-the-art (SOTA) methods on the optimized Davis and KIBA datasets reveals that the PocketDTA model exhibits significant performance advantages. Further, ablation studies confirm the effectiveness of the model components, whereas cold-start experiments illustrate its robust generalization capabilities. In particular, the PocketDTA model has shown significant advantages in identifying key drug functional groups and amino acid residues via molecular docking and literature validation, highlighting its strong potential for interpretability.

AVAILABILITY AND IMPLEMENTATION: Code and data are available at: Https://github.com/zhaolongNCU/PocketDTA.

PMID:39365726 | DOI:10.1093/bioinformatics/btae594

IEEE Trans Med Imaging. 2024 Oct 4;PP. doi: 10.1109/TMI.2024.3473970. Online ahead of print.

ABSTRACT

Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image, leading to considerable radiation exposure. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. While recent advances, including deep learning and neural rendering algorithms, have made strides in this area, these methods either produce unsatisfactory results or suffer from time inefficiency of individual optimization. In this paper, we introduce a novel geometry-aware encoder-decoder framework to solve this problem. Our framework starts by encoding multi-view 2D features from various 2D X-ray projections with a 2D CNN encoder. Leveraging the geometry of CBCT scanning, it then back-projects the multi-view 2D features into the 3D space to formulate a comprehensive volumetric feature map, followed by a 3D CNN decoder to recover 3D CBCT image. Importantly, our approach respects the geometric relationship between 3D CBCT image and its 2D X-ray projections during feature back projection stage, and enjoys the prior knowledge learned from the data population. This ensures its adaptability in dealing with extremely sparse view inputs without individual training, such as scenarios with only 5 or 10 X-ray projections. Extensive evaluations on two simulated datasets and one real-world dataset demonstrate exceptional reconstruction quality and time efficiency of our method.

PMID:39365719 | DOI:10.1109/TMI.2024.3473970

IEEE Trans Biomed Eng. 2024 Oct 4;PP. doi: 10.1109/TBME.2024.3474049. Online ahead of print.

ABSTRACT

OBJECTIVE: Motor imagery-based brain-computer interfaces (MI-BCIs) have been playing an increasingly vital role in neural rehabilitation. However, the long-term task-based calibration required for enhanced model performance leads to an unfriendly user experience, while the inadequacy of EEG data hinders the performance of deep learning models. To address these challenges, a task-free transfer learning strategy (TFTL) for EEG-based cross-subject & cross-dataset MI-BCI is proposed for calibration time reduction and multi-center data co-modeling.

METHODS: TFTL strategy consists of data alignment, shared feature extractor, and specific classifiers, in which the label predictor for MI tasks classification, as well as domain and dataset discriminator for inter-subject variability reduction are concurrently optimized for knowledge transfer from subjects across different datasets to the target subject. Moreover, only resting data of the target subject is used for subject-specific model construction to achieve task-free.

RESULTS: We employed three deep learning methods (ShallowConvNet, EEGNet, and TCNet-Fusion) as baseline approaches to evaluate the effectiveness of the proposed strategy on five datasets (BCIC IV Dataset 2a, Dataset 1, Physionet MI, Dreyer 2023, and OpenBMI). The results demonstrate a significant improvement with the inclusion of the TFTL strategy compared to the baseline methods, reaching a maximum enhancement of 15.67% with a statistical significance (p=2.4e-5<0.05). Moreover, task-free resulted in MI trials needed for calibration being 0 for all datasets, which significantly alleviated the calibration burden for patients before usage.

CONCLUSION/SIGNIFICANCE: The proposed TFTL strategy effectively addresses challenges posed by prolonged calibration periods and insufficient EEG data, thus promoting MI-BCI from laboratory to clinical application.

PMID:39365711 | DOI:10.1109/TBME.2024.3474049

Environ Sci Pollut Res Int. 2024 Oct 4. doi: 10.1007/s11356-024-35182-w. Online ahead of print.

ABSTRACT

Evapotranspiration is one of the crucial elements in water balance equations and plays a pivotal role in the water and energy cycle of an area. An accurate and precise estimation and prediction of reference evapotranspiration (ETo) is necessary for regional management of water resources and irrigation scheduling. The challenge of predicting daily evapotranspiration with limited meteorological data in Bangladesh. This study aims to predict daily evapotranspiration using limited meteorological data of Bangladesh by three deep learning (CNN, GRU, LSTM) and one hybrid (CNN-GRU) model. The novel method of hybrid CNN-GRU models, which have not been commonly used for this purpose. The performance of models was evaluated by five accuracy matrices R2, RMSE, MAE, MAPE, and CE and comparison is visualized by radar graphs. The study's novelty lies in the use of hybrid CNN-GRU models to estimate reference evapotranspiration, as this algorithm has not been commonly used for this purpose. In the case of the Rangpur station, the hybrid CNN-GRU algorithm outperformed other models, achieving the best values across various statistical metrics during both the training and testing phases. The highest correlation coefficient values of approximately 0.994 and 0.995. Moreover, during training and testing stages, the hybrid model had the lowest MAE (0.076, 0.068) and RMSE (0.138, 0.106) at the Rangpur station. Additionally, in the Sreemangal station, it can be notable that the statistical parameter RSME found superior results in the hybrid model around 0.225 and 0.174, respectively. In addition, the highest R2 and CE values were noted as 0.986, 0.987 and 0.985, 0.986 during the training and testing phases, respectively. The comparison suggests that the hybrid model will be best suited for prediction with the limited meteorological data. The outcome of the present research signifies the ability of deep learning methods in the prediction of evapotranspiration and the dominant variables affecting the changes the in context of Bangladesh.

PMID:39365537 | DOI:10.1007/s11356-024-35182-w

ACS Nano. 2024 Oct 4. doi: 10.1021/acsnano.4c05153. Online ahead of print.

ABSTRACT

Successful integration of point-of-care testing (POCT) into clinical settings requires improved assay sensitivity and precision to match laboratory standards. Here, we show how innovations in amplified biosensing, imaging, and data processing, coupled with deep learning, can help improve POCT. To demonstrate the performance of our approach, we present a rapid and cost-effective paper-based high-sensitivity vertical flow assay (hs-VFA) for quantitative measurement of cardiac troponin I (cTnI), a biomarker widely used for measuring acute cardiac damage and assessing cardiovascular risk. The hs-VFA includes a colorimetric paper-based sensor, a portable reader with time-lapse imaging, and computational algorithms for digital assay validation and outlier detection. Operating at the level of a rapid at-home test, the hs-VFA enabled the accurate quantification of cTnI using 50 μL of serum within 15 min per test and achieved a detection limit of 0.2 pg/mL, enabled by gold ion amplification chemistry and time-lapse imaging. It also achieved high precision with a coefficient of variation of <7% and a very large dynamic range, covering cTnI concentrations over 6 orders of magnitude, up to 100 ng/mL, satisfying clinical requirements. In blinded testing, this computational hs-VFA platform accurately quantified cTnI levels in patient samples and showed a strong correlation with the ground truth values obtained by a benchtop clinical analyzer. This nanoparticle amplification-based computational hs-VFA platform can democratize access to high-sensitivity point-of-care diagnostics and provide a cost-effective alternative to laboratory-based biomarker testing.

PMID:39365271 | DOI:10.1021/acsnano.4c05153

Aesthet Surg J. 2024 Oct 4:sjae204. doi: 10.1093/asj/sjae204. Online ahead of print.

ABSTRACT

BACKGROUND: Botulinum Toxin Type A (BoNT-A) injections are widely used for facial rejuvenation, but their effects on facial expressions remain unclear.

OBJECTIVES: This study aims to objectively measure the impact of BoNT-A injections on facial expressions using deep learning techniques.

METHODS: 180 patients aged 25-60 years who underwent BoNT-A application to the upper face were included. Patients were photographed with neutral, happy, surprised, and angry expressions before and 14 days after the procedure. A Convolutional Neural Network (CNN)-based Facial Emotion Recognition (FER) system analyzed 1440 photographs using a hybrid dataset of clinical images and the Karolinska Directed Emotional Faces (KDEF) dataset.

RESULTS: The CNN model accurately predicted 90.15% of the test images. Significant decreases in the recognition of angry and surprised expressions were observed post-injection (p<0.05), with no significant changes in happy and neutral expressions (p>0.05). Angry expressions were often misclassified as neutral or happy (p<0.05), and surprised expressions were more likely to be perceived as neutral (p<0.05).

CONCLUSIONS: Deep learning can effectively assess the impact of BoNT-A injections on facial expressions, providing more standardized data than traditional surveys. BoNT-A may reduce the expression of anger and surprise, potentially leading to a more positive facial appearance and emotional state. Further studies are needed to understand the broader implications of these changes.

PMID:39365026 | DOI:10.1093/asj/sjae204

Pain Pract. 2024 Oct 4. doi: 10.1111/papr.13416. Online ahead of print.

ABSTRACT

OBJECTIVES: Letters of recommendation (LORs) are an important part of pain medicine fellowship applications that may be subject to implicit bias by the letter's author. This study evaluated letters of recommendation for applications to pain medicine fellowships in the United States to characterize biases and differences among applicants over four application cycles.

METHODS: This was a retrospective single-site cohort study. De-identified LORs were collected from 2020 to 2023 from one institution. The Valence Aware Dictionary and sEntiment Reasoner (VADER) natural language processing package scored positive LOR sentiment. In addition, the deep learning tool, Empath, scored LORs for 15 sentiments. Wilcoxon rank-sum and one-way ANOVA tests compared scores between applicant demographics: gender, race, medical school type, residency specialty, and chief resident status, as well as letter writers' academic position.

RESULTS: Nine hundred and sixty-four applications were studied over four application cycles. Program directors wrote fewer words (p = 0.020) and less positively (p < 0.001) compared to department chairs and letter writers with neither position. Department chairs wrote with less "negative emotion" compared to both program directors and writers with neither position (p < 0.001). Anesthesiologist applicants received more letters highlighting "achievement" (p < 0.001) while PM&R applicants submitted letters with less "negative emotion" (p < 0.001) compared to other specialties. Chief residents' letters scored higher in "leader" sentiment (p < 0.001) and lower in "negative emotion" (p < 0.001).

DISCUSSION: Linguistic content did not favor certain genders or races over others. However, disparities in LORs do exist depending on an applicant's specialty and chief resident status, as well as the academic status of the letter writer.

PMID:39364730 | DOI:10.1111/papr.13416

Phys Chem Chem Phys. 2024 Oct 4. doi: 10.1039/d4cp02781g. Online ahead of print.

ABSTRACT

Small-scale systems based on periodic boundary conditions often cannot accurately describe real-world situations, especially when conducting molecular dynamics simulations to study phase transitions, where it is very necessary to use large-scale systems. However, studying phase transitions in large-scale systems is an important and difficult task. Though ab initio molecular dynamics (AIMD), based on density functional theory (DFT), provides advantages in terms of accuracy, it is very difficult to study phase transitions in large-scale systems due to the considerable computational time required. In addition, although traditional empirical potentials are faster, their lower calculation accuracy makes it difficult to use them for phase transition studies. It is crucial to devise a method that has enabled a promising fusion of computational efficiency and precision to effectively investigate phase transitions in large-scale systems. In this work, the obtained machine learning potential function of carbon through deep neural networks not only demonstrates strong scalability but also effectively enables the study of the formation mechanisms of amorphous diamond and polycrystalline diamond using C60 crystals and graphene as precursors under high-pressure high-temperature conditions (HPHT). Furthermore, the structure search software (AIRSS) was used to generate numerous initial structures which were optimized using the machine learning potential, a process which led to finding new structural clusters of carbon. Interestingly, the predictive capabilities of the machine learning potential for symmetric and asymmetric carbon clusters aligned well with the Gaussian approximation potential (GAP), yet the former demonstrated higher computational efficiency, making it more suitable for carbon material research. The results of this work signify significant progress in the field of carbon transition study, opening up new possibilities for exploring and understanding carbon materials with improved computational efficacy.

PMID:39364607 | DOI:10.1039/d4cp02781g

Front Neurol. 2024 Sep 19;15:1477811. doi: 10.3389/fneur.2024.1477811. eCollection 2024.

ABSTRACT

PURPOSE: Rapid diagnosis of acute ischemic stroke (AIS) is critical to achieve positive outcomes and prognosis. This study aimed to construct a model to automatically identify the infarct core based on non-contrast-enhanced CT images, especially for small infarcts.

METHODS: The baseline CT scans of AIS patients, who had DWI scans obtained within less than 2 h apart, were included in this retrospective study. A modified Target-based deep learning model of YOLOv5 was developed to detect infarctions on CT. Randomly selected CT images were used for testing and evaluated by neuroradiologists and the model, using the DWI as a reference standard. Intraclass correlation coefficient (ICC) and weighted kappa were calculated to assess the agreement. The paired chi-square test was used to compare the diagnostic efficacy of physician groups and automated models in subregions. p < 0.05 was considered statistically significant.

RESULTS: Five hundred and eighty four AIS patients were enrolled in total, finally 275 cases were eligible. Modified YOLOv5 perform better with increased precision (0.82), recall (0.81) and mean average precision (0.79) than original YOLOv5. Model showed higher consistency to the DWI-ASPECTS scores (ICC = 0.669, κ = 0.447) than neuroradiologists (ICC = 0.452, κ = 0.247). The sensitivity (75.86% vs. 63.79%), specificity (98.87% vs. 95.02%), and accuracy (96.20% vs. 91.40%) were better than neuroradiologists. Automatic model had better diagnostic efficacy than physician diagnosis in the M6 region (p = 0.039).

CONCLUSION: The deep learning model was able to detect small infarct core on CT images more accurately. It provided the infarct portion and extent, which is valuable in assessing the severity of disease and guiding treatment procedures.

PMID:39364421 | PMC:PMC11447964 | DOI:10.3389/fneur.2024.1477811

Front Big Data. 2024 Sep 19;7:1393758. doi: 10.3389/fdata.2024.1393758. eCollection 2024.

ABSTRACT

Detecting lung diseases in medical images can be quite challenging for radiologists. In some cases, even experienced experts may struggle with accurately diagnosing chest diseases, leading to potential inaccuracies due to complex or unseen biomarkers. This review paper delves into various datasets and machine learning techniques employed in recent research for lung disease classification, focusing on pneumonia analysis using chest X-ray images. We explore conventional machine learning methods, pretrained deep learning models, customized convolutional neural networks (CNNs), and ensemble methods. A comprehensive comparison of different classification approaches is presented, encompassing data acquisition, preprocessing, feature extraction, and classification using machine vision, machine and deep learning, and explainable-AI (XAI). Our analysis highlights the superior performance of transfer learning-based methods using CNNs and ensemble models/features for lung disease classification. In addition, our comprehensive review offers insights for researchers in other medical domains too who utilize radiological images. By providing a thorough overview of various techniques, our work enables the establishment of effective strategies and identification of suitable methods for a wide range of challenges. Currently, beyond traditional evaluation metrics, researchers emphasize the importance of XAI techniques in machine and deep learning models and their applications in classification tasks. This incorporation helps in gaining a deeper understanding of their decision-making processes, leading to improved trust, transparency, and overall clinical decision-making. Our comprehensive review serves as a valuable resource for researchers and practitioners seeking not only to advance the field of lung disease detection using machine learning and XAI but also from other diverse domains.

PMID:39364222 | PMC:PMC11446784 | DOI:10.3389/fdata.2024.1393758

Front Microbiol. 2024 Sep 19;15:1450804. doi: 10.3389/fmicb.2024.1450804. eCollection 2024.

ABSTRACT

Although it is well known that the morphology of Gram-negative rods changes on exposure to antibiotics, the morphology of antibiotic-resistant bacteria in the absence of antibiotics has not been widely investigated. Here, we studied the morphologies of 10 antibiotic-resistant strains of Escherichia coli and used bioinformatics tools to classify the resistant cells under light microscopy in the absence of antibiotics. The antibiotic-resistant strains showed differences in morphology from the sensitive parental strain, and the differences were most prominent in the quinolone-and β-lactam-resistant bacteria. A cluster analysis revealed increased proportions of fatter or shorter cells in the antibiotic-resistant strains. A correlation analysis of morphological features and gene expression suggested that genes related to energy metabolism and antibiotic resistance were highly correlated with the morphological characteristics of the resistant strains. Our newly proposed deep learning method for single-cell classification achieved a high level of performance in classifying quinolone-and β-lactam-resistant strains.

PMID:39364166 | PMC:PMC11446759 | DOI:10.3389/fmicb.2024.1450804