Plant J. 2024 Aug 12. doi: 10.1111/tpj.16979. Online ahead of print.

ABSTRACT

Deep learning offers new approaches to investigate the mechanisms underlying complex biological phenomena, such as subgenome dominance. Subgenome dominance refers to the dominant expression and/or biased fractionation of genes in one subgenome of allopolyploids, which has shaped the evolution of a large group of plants. However, the underlying cause of subgenome dominance remains elusive. Here, we adopt deep learning to construct two convolutional neural network (CNN) models, binary expression model (BEM) and homoeolog contrast model (HCM), to investigate the mechanism underlying subgenome dominance using DNA sequence and methylation sites. We apply these CNN models to analyze three representative polyploidization systems, Brassica, Gossypium, and Cucurbitaceae, each with available ancient and neo/synthetic polyploidized genomes. The BEM shows that DNA sequence of the promoter region can accurately predict whether a gene is expressed or not. More importantly, the HCM shows that the DNA sequence of the promoter region predicts dominant expression status between homoeologous gene pairs retained from ancient polyploidizations, thus predicting subgenome dominance associated with these events. However, HCM fails to predict gene expression dominance between new homoeologous gene pairs arising from the neo/synthetic polyploidizations. These results are consistent across the three plant polyploidization systems, indicating broad applicability of our models. Furthermore, the two models based on methylation sites produce similar results. These results show that subgenome dominance is associated with long-term sequence differentiation between the promoters of homoeologs, suggesting that subgenome expression dominance precedes and is the driving force or even the determining factor for sequence divergence between subgenomes following polyploidization.

PMID:39133828 | DOI:10.1111/tpj.16979

PLoS One. 2024 Aug 12;19(8):e0305859. doi: 10.1371/journal.pone.0305859. eCollection 2024.

ABSTRACT

PURPOSE: This study aimed to develop an algorithm for the automatic detecting chest percutaneous catheter drainage (PCD) and evaluating catheter positions on chest radiographs using deep learning.

METHODS: This retrospective study included 1,217 chest radiographs (proper positioned: 937; malpositioned: 280) from a total of 960 patients underwent chest PCD from October 2017 to February 2023. The tip location of the chest PCD was annotated using bounding boxes and classified as proper positioned and malpositioned. The radiographs were randomly allocated into the training, validation sets (total: 1,094 radiographs; proper positioned: 853 radiographs; malpositioned: 241 radiographs), and test datasets (total: 123 radiographs; proper positioned: 84 radiographs; malpositioned: 39 radiographs). The selected AI model was used to detect the catheter tip of chest PCD and evaluate the catheter's position using the test dataset to distinguish between properly positioned and malpositioned cases. Its performance in detecting the catheter and assessing its position on chest radiographs was evaluated by per radiographs and per instances. The association between the position and function of the catheter during chest PCD was evaluated.

RESULTS: In per chest radiographs, the selected model's accuracy was 0.88. The sensitivity and specificity were 0.86 and 0.92, respectively. In per instance, the selected model's the mean Average Precision 50 (mAP50) was 0.86. The precision and recall were 0.90 and 0.79 respectively. Regarding the association between the position and function of the catheter during chest PCD, its sensitivity and specificity were 0.93 and 0.95, respectively.

CONCLUSION: The artificial intelligence model for the automatic detection and evaluation of catheter position during chest PCD on chest radiographs demonstrated acceptable diagnostic performance and could assist radiologists and clinicians in the early detection of catheter malposition and malfunction during chest percutaneous catheter drainage.

PMID:39133733 | DOI:10.1371/journal.pone.0305859

PLoS One. 2024 Aug 12;19(8):e0305708. doi: 10.1371/journal.pone.0305708. eCollection 2024.

ABSTRACT

The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet technique was utilized for the investigation. The study adapts the fine-tune model to learn the pertinent patterns from mel spectrogram images specific to this bird species classification task. The fine-tuned EfficientNet model combined with a type of Recurrent Neural Networks (RNNs) namely Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). RNNs are employed to capture the temporal dependencies in audio signals, thereby enhancing bird species classification accuracy. The dataset utilized in this work contains nearly 17,000 bird sound recordings across a diverse range of species. The experiment was conducted with several combinations of EfficientNet and RNNs, and EfficientNet-B7 with GRU surpasses other experimental models with an accuracy of 84.03% and a macro-average precision score of 0.8342.

PMID:39133732 | DOI:10.1371/journal.pone.0305708

PLOS Digit Health. 2024 Aug 12;3(8):e0000569. doi: 10.1371/journal.pdig.0000569. eCollection 2024 Aug.

ABSTRACT

Prediction of sepsis using machine-learning approaches has recently gained traction. However, the lack of translation of these algorithms into clinical routine remains a major issue. Existing early sepsis detection methods are either based on the older definition of sepsis or do not accurately detect sepsis leading to the high frequency of false-positive alarms. This results in a well-known issue of clinicians' "alarm fatigue", leading to decreased responsiveness and identification, ultimately resulting in delayed clinical intervention. Hence, there is a fundamental, unmet need for a clinical decision system capable of accurate and timely sepsis diagnosis, running at the point of need. In this work, SepsisAI-a deep-learning algorithm based on long short-term memory (LSTM) networks was developed to predict the early onset of hospital-acquired sepsis in real-time for patients admitted to the ICU. The models are trained and validated with data from the PhysioNet Challenge, consisting of 40,336 patient data files from two healthcare systems: Beth Israel Deaconess Medical Center and Emory University Hospital. In the short term, the algorithm tracks frequently measured vital signs, sparsely available lab parameters, demographic features, and certain derived features for making predictions. A real-time alert system, which monitors the trajectory of the predictions, is developed on top of the deep-learning framework to minimize false alarms. On a balanced test dataset, the model achieves an AUROC, AUPRC, sensitivity, and specificity of 0.95, 0.96, 88.19%, and 96.75%, respectively at the patient level. In terms of lookahead time, the model issues a warning at a median of 6 hours (IQR 6 to 20 hours) and raises an alert at a median of 4 hours (IQR 2 to 5 hours) ahead of sepsis onset. Most importantly, the model achieves a false-alarm ratio of 3.18% for alerts, which is significantly less than other sepsis alarm systems. Additionally, on a disease prevalence-based test set, the algorithm reported similar outcomes with AUROC and AUPRC of 0.94 and 0.87, respectively, with sensitivity, and specificity of 97.05%, and 96.75%, respectively. The proposed algorithm might serve as a clinical decision support system to assist clinicians in the accurate and timely diagnosis of sepsis. With exceptionally high specificity and low false-alarm rate, this algorithm also helps mitigate the well-known issue of clinician alert fatigue arising from currently proposed sepsis alarm systems. Consequently, the algorithm partially addresses the challenges of successfully integrating machine-learning algorithms into routine clinical care.

PMID:39133661 | DOI:10.1371/journal.pdig.0000569

IEEE Trans Nanobioscience. 2024 Aug 12;PP. doi: 10.1109/TNB.2024.3441590. Online ahead of print.

ABSTRACT

Bioinformatics is a rapidly growing field involving the application of computational methods to the analysis and interpretation of biological data. An important task in bioinformatics is the identification of novel drug-target interactions (DTIs), which is also an important part of the drug discovery process. Most computational methods for predicting DTI consider it as a binary classification task to predict whether drug target pairs interact with each other. With the increasing amount of drug-target binding affinity data in recent years, this binary classification task can be transformed into a regression task of drug-target affinity (DTA), which reflects the degree of drug-target binding and can provide more detailed and specific information than DTI, making it an important tool in drug discovery through virtual screening. Effectively predicting how compounds interact with targets can help speed up the drug discovery process. In this study, we propose a deep learning model called TC-DTA for the prediction of the DTA, which makes use of the convolutional neural networks (CNN) and encoder module of the transformer architecture. First, the raw drug SMILES strings and protein amino acid sequences are extracted from the dataset. These are then represented using different encoding methods. We then use CNN and the Transformer's encoder module to extract feature information from drug SMILES strings and protein amino acid sequences, respectively. Finally, the feature information obtained is concatenated and fed into a multi-layer perceptron for prediction of the binding affinity score. We evaluated our model on two benchmark DTA datasets, Davis and KIBA, against methods including KronRLS, SimBoost and DeepDTA. On evaluation metrics such as Mean Squared Error, Concordance Index and r2m index, TC-DTA outperforms these baseline methods. These results demonstrate the effectiveness of the Transformer's encoder and CNN in the extraction of meaningful representations from sequences, thereby improving the accuracy of DTA prediction. The deep learning model for DTA prediction can accelerate drug discovery by identifying drug candidates with high binding affinity to specific targets. Compared to traditional methods, the use of machine learning technology allows for a more effective and efficient drug discovery process.

PMID:39133595 | DOI:10.1109/TNB.2024.3441590

IEEE J Biomed Health Inform. 2024 Aug 12;PP. doi: 10.1109/JBHI.2024.3441600. Online ahead of print.

ABSTRACT

Walking-assistive devices require adaptive control methods to ensure smooth transitions between various modes of locomotion. For this purpose, detecting human locomotion modes (e.g., level walking or stair ascent) in advance is crucial for improving the intelligence and transparency of such robotic systems. This study proposes Deep-STF, a unified end-to-end deep learning model designed for integrated feature extraction in spatial, temporal, and frequency dimensions from surface electromyography (sEMG) signals. Our model enables accurate and robust continuous prediction of nine locomotion modes and 15 transitions at varying prediction time intervals, ranging from 100 to 500 ms. Experimental results showcased Deep-STP's cutting-edge prediction performance across diverse locomotion modes and transitions, relying solely on sEMG data. When forecasting 100 ms ahead, Deep-STF achieved an improved average prediction accuracy of 96.60%, outperforming seven benchmark models. Even with an extended 500ms prediction horizon, the accuracy only marginally decreased to 93.22%. The averaged stable prediction times for detecting next upcoming transitions spanned from 31.47 to 371.58 ms across the 100-500 ms time advances. Although the prediction accuracy of the trained Deep-STF initially dropped to 71.12% when tested on four new terrains, it achieved a satisfactory accuracy of 92.51% after fine-tuning with just 5 trials and further improved to 96.27% with 15 calibration trials. These results demonstrate the remarkable prediction ability and adaptability of Deep-STF, showing great potential for integration with walking-assistive devices and leading to smoother, more intuitive user interactions.

PMID:39133593 | DOI:10.1109/JBHI.2024.3441600

J Imaging Inform Med. 2024 Aug 12. doi: 10.1007/s10278-024-01215-6. Online ahead of print.

ABSTRACT

Time-of-flight magnetic resonance angiography (TOF-MRA) is a non-contrast technique used to visualize neurovascular. However, manual reconstruction of the volume render (VR) by radiologists is time-consuming and labor-intensive. Deep learning-based (DL-based) vessel segmentation technology may provide intelligent automation workflow. To evaluate the image quality of DL vessel segmentation for automatically acquiring intracranial arteries in TOF-MRA. A total of 394 TOF-MRA scans were selected, which included cerebral vascular health, aneurysms, or stenoses. Both our proposed method and two state-of-the-art DL methods are evaluated on external datasets for generalization ability. For qualitative assessment, two experienced clinical radiologists evaluated the image quality of cerebrovascular diagnostic and visualization (scoring 0-5 as unacceptable to excellent) obtained by manual VR reconstruction or automatic convolutional neural network (CNN) segmentation. The proposed CNN outperforms the other two DL-based methods in clinical scoring on external datasets, and its visualization was evaluated by readers as having the appearance of the radiologists' manual reconstructions. Scoring of proposed CNN and VR of intracranial arteries demonstrated good to excellent agreement with no significant differences (median, 5.0 and 5.0, P ≥ 12) at healthy-type scans. All proposed CNN image quality were considered to have adequate diagnostic quality (median scores > 2). Quantitative analysis demonstrated a superior dice similarity coefficient of cerebrovascular overlap (training sets and validation sets; 0.947 and 0.927). Automatic cerebrovascular segmentation using DL is feasible and the image quality in terms of vessel integrity, collateral circulation and lesion morphology is comparable to expert manual VR without significant differences.

PMID:39133457 | DOI:10.1007/s10278-024-01215-6

Int J Comput Assist Radiol Surg. 2024 Aug 12. doi: 10.1007/s11548-024-03246-4. Online ahead of print.

ABSTRACT

PURPOSE: The integration of a surgical robotic instrument tracking module within optical microscopes holds the potential to advance microsurgery practices, as it facilitates automated camera movements, thereby augmenting the surgeon's capability in executing surgical procedures.

METHODS: In the present work, an innovative detection backbone based on spatial attention module is implemented to enhance the detection accuracy of small objects within the image. Additionally, we have introduced a robust data association technique, capable to re-track surgical instrument, mainly based on the knowledge of the dual-instrument robotics system, Intersection over Union metric and Kalman filter.

RESULTS: The effectiveness of this pipeline was evaluated through testing on a dataset comprising ten manually annotated videos of anastomosis procedures involving either animal or phantom vessels, exploiting the Symani®Surgical System-a dedicated robotic platform designed for microsurgery. The multiple object tracking precision (MOTP) and the multiple object tracking accuracy (MOTA) are used to evaluate the performance of the proposed approach, and a new metric is computed to demonstrate the efficacy in stabilizing the tracking result along the video frames. An average MOTP of 74±0.06% and a MOTA of 99±0.03% over the test videos were found.

CONCLUSION: These results confirm the potential of the proposed approach in enhancing precision and reliability in microsurgical instrument tracking. Thus, the integration of attention mechanisms and a tailored data association module could be a solid base for automatizing the motion of optical microscopes.

PMID:39133431 | DOI:10.1007/s11548-024-03246-4

Abdom Radiol (NY). 2024 Aug 12. doi: 10.1007/s00261-024-04512-4. Online ahead of print.

ABSTRACT

Early identification of pancreatitis remains a significant clinical diagnostic challenge that impacts patient outcomes. The evolution of quantitative imaging followed by deep learning models has shown great promise in the non-invasive diagnosis of pancreatitis and its complications. We provide an overview of advancements in diagnostic imaging and quantitative imaging methods along with the evolution of artificial intelligence (AI). In this article, we review the current and future states of methodology and limitations of AI in improving clinical support in the context of early detection and management of pancreatitis.

PMID:39133362 | DOI:10.1007/s00261-024-04512-4

J Med Syst. 2024 Aug 12;48(1):74. doi: 10.1007/s10916-024-02098-4.

ABSTRACT

This review aims to assess the effectiveness of AI-driven CDSSs on patient outcomes and clinical practices. A comprehensive search was conducted across PubMed, MEDLINE, and Scopus. Studies published from January 2018 to November 2023 were eligible for inclusion. Following title and abstract screening, full-text articles were assessed for methodological quality and adherence to inclusion criteria. Data extraction focused on study design, AI technologies employed, reported outcomes, and evidence of AI-CDSS impact on patient and clinical outcomes. Thematic analysis was conducted to synthesise findings and identify key themes regarding the effectiveness of AI-CDSS. The screening of the articles resulted in the selection of 26 articles that satisfied the inclusion criteria. The content analysis revealed four themes: early detection and disease diagnosis, enhanced decision-making, medication errors, and clinicians' perspectives. AI-based CDSSs were found to improve clinical decision-making by providing patient-specific information and evidence-based recommendations. Using AI in CDSSs can potentially improve patient outcomes by enhancing diagnostic accuracy, optimising treatment selection, and reducing medical errors.

PMID:39133332 | DOI:10.1007/s10916-024-02098-4

Surg Endosc. 2024 Aug 12. doi: 10.1007/s00464-024-11160-8. Online ahead of print.

NO ABSTRACT

PMID:39133331 | DOI:10.1007/s00464-024-11160-8

Adv Biol (Weinh). 2024 Aug 12:e2400034. doi: 10.1002/adbi.202400034. Online ahead of print.

ABSTRACT

3D co-cultures are key tools for in vitro biomedical research as they recapitulate more closely the in vivo environment while allowing a tighter control on the culture's composition and experimental conditions. The limited technologies available for the analysis of these models, however, hamper their widespread application. The separation of the contribution of the different cell types, in particular, is a fundamental challenge. In this work, ORACLE (OvaRiAn Cancer ceLl rEcognition) is presented, a deep neural network trained to distinguish between ovarian cancer and healthy cells based on the shape of their nucleus. The extensive validation that are conducted includes multiple cell lines and patient-derived cultures to characterize the effect of all the major potential confounding factors. High accuracy and reliability are maintained throughout the analysis (F1score> 0.9 and Area under the ROC curve -ROC-AUC- score = 0.99) demonstrating ORACLE's effectiveness with this detection and classification task. ORACLE is freely available (https://github.com/MarilisaCortesi/ORACLE/tree/main) and can be used to recognize both ovarian cancer cell lines and primary patient-derived cells. This feature is unique to ORACLE and thus enables for the first time the analysis of in vitro co-cultures comprised solely of patient-derived cells.

PMID:39133225 | DOI:10.1002/adbi.202400034

Bioinformatics. 2024 Aug 12:btae504. doi: 10.1093/bioinformatics/btae504. Online ahead of print.

ABSTRACT

MOTIVATION: The asymmetrical distribution of expressed mRNAs tightly controls the precise synthesis of proteins within human cells. This non-uniform distribution, a cornerstone of developmental biology, plays a pivotal role in numerous cellular processes. To advance our comprehension of gene regulatory networks, it is essential to develop computational tools for accurately identifying the subcellular localizations of mRNAs. However, considering multi-localization phenomena remains limited in existing approaches, with none considering the influence of RNA's secondary structure.

RESULTS: In this study, we propose Allocator, a multi-view parallel deep learning framework that seamlessly integrates the RNA sequence-level and structure-level information, enhancing the prediction of mRNA multi-localization. The Allocator models equip four efficient feature extractors, each designed to handle different inputs. Two are tailored for sequence-based inputs, incorporating multilayer perceptron and multi-head self-attention mechanisms. The other two are specialized in processing structure-based inputs, employing graph neural networks. Benchmarking results underscore Allocator's superiority over state-of-the-art methods, showcasing its strength in revealing intricate localization associations.

AVAILABILITY AND IMPLEMENTATION: The webserver of Allocator is available at http://Allocator.unimelb-biotools.cloud.edu.au; the source code and datasets are available on GitHub (https://github.com/lifuyi774/Allocator) and Zenodo (https://doi.org/10.5281/zenodo.13235798).

SUPPLEMENTARY INFORMATION: Available at Bioinformatics online.

PMID:39133151 | DOI:10.1093/bioinformatics/btae504

Brief Bioinform. 2024 Jul 25;25(5):bbae394. doi: 10.1093/bib/bbae394.

ABSTRACT

The molecular property prediction (MPP) plays a crucial role in the drug discovery process, providing valuable insights for molecule evaluation and screening. Although deep learning has achieved numerous advances in this area, its success often depends on the availability of substantial labeled data. The few-shot MPP is a more challenging scenario, which aims to identify unseen property with only few available molecules. In this paper, we propose an attribute-guided prototype network (APN) to address the challenge. APN first introduces an molecular attribute extractor, which can not only extract three different types of fingerprint attributes (single fingerprint attributes, dual fingerprint attributes, triplet fingerprint attributes) by considering seven circular-based, five path-based, and two substructure-based fingerprints, but also automatically extract deep attributes from self-supervised learning methods. Furthermore, APN designs the Attribute-Guided Dual-channel Attention module to learn the relationship between the molecular graphs and attributes and refine the local and global representation of the molecules. Compared with existing works, APN leverages high-level human-defined attributes and helps the model to explicitly generalize knowledge in molecular graphs. Experiments on benchmark datasets show that APN can achieve state-of-the-art performance in most cases and demonstrate that the attributes are effective for improving few-shot MPP performance. In addition, the strong generalization ability of APN is verified by conducting experiments on data from different domains.

PMID:39133096 | DOI:10.1093/bib/bbae394

J Mass Spectrom. 2024 Sep;59(9):e5078. doi: 10.1002/jms.5078.

ABSTRACT

Understanding fungal lipid biology and metabolism is critical for antifungal target discovery as lipids play central roles in cellular processes. Nuances in lipid structural differences can significantly impact their functions, making it necessary to characterize lipids in detail to understand their roles in these complex systems. In particular, lipid double bond (DB) locations are an important component of lipid structure that can only be determined using a few specialized analytical techniques. Ozone-induced dissociation mass spectrometry (OzID-MS) is one such technique that uses ozone to break lipid DBs, producing pairs of characteristic fragments that allow the determination of DB positions. In this work, we apply OzID-MS and LipidOz software to analyze the complex lipids of Saccharomyces cerevisiae yeast strains transformed with different fatty acid desaturases from Histoplasma capsulatum to determine the specific unsaturated lipids produced. The automated data analysis in LipidOz made the determination of DB positions from this large dataset more practical, but manual verification for all targets was still time-consuming. The DL model reduces manual involvement in data analysis, but since it was trained using mammalian lipid extracts, the prediction accuracy on yeast-derived data was reduced. We addressed both shortcomings by retraining the DL model to act as a pre-filter to prioritize targets for automated analysis, providing confident manually verified results but requiring less computational time and manual effort. Our workflow resulted in the determination of detailed DB positions and enzymatic specificity.

PMID:39132905 | DOI:10.1002/jms.5078

Mach Learn. 2024;113(9):6871-6910. doi: 10.1007/s10994-024-06574-3. Epub 2024 Jul 16.

ABSTRACT

The field of 'explainable' artificial intelligence (XAI) has produced highly acclaimed methods that seek to make the decisions of complex machine learning (ML) methods 'understandable' to humans, for example by attributing 'importance' scores to input features. Yet, a lack of formal underpinning leaves it unclear as to what conclusions can safely be drawn from the results of a given XAI method and has also so far hindered the theoretical verification and empirical validation of XAI methods. This means that challenging non-linear problems, typically solved by deep neural networks, presently lack appropriate remedies. Here, we craft benchmark datasets for one linear and three different non-linear classification scenarios, in which the important class-conditional features are known by design, serving as ground truth explanations. Using novel quantitative metrics, we benchmark the explanation performance of a wide set of XAI methods across three deep learning model architectures. We show that popular XAI methods are often unable to significantly outperform random performance baselines and edge detection methods, attributing false-positive importance to features with no statistical relationship to the prediction target rather than truly important features. Moreover, we demonstrate that explanations derived from different model architectures can be vastly different; thus, prone to misinterpretation even under controlled conditions.

PMID:39132312 | PMC:PMC11306297 | DOI:10.1007/s10994-024-06574-3

Brief Bioinform. 2024 Jul 25;25(5):bbae375. doi: 10.1093/bib/bbae375.

ABSTRACT

Effective clustering of T-cell receptor (TCR) sequences could be used to predict their antigen-specificities. TCRs with highly dissimilar sequences can bind to the same antigen, thus making their clustering into a common antigen group a central challenge. Here, we develop TouCAN, a method that relies on contrastive learning and pretrained protein language models to perform TCR sequence clustering and antigen-specificity predictions. Following training, TouCAN demonstrates the ability to cluster highly dissimilar TCRs into common antigen groups. Additionally, TouCAN demonstrates TCR clustering performance and antigen-specificity predictions comparable to other leading methods in the field.

PMID:39129361 | DOI:10.1093/bib/bbae375

Heliyon. 2024 Jul 16;10(14):e34583. doi: 10.1016/j.heliyon.2024.e34583. eCollection 2024 Jul 30.

ABSTRACT

BACKGROUND: Three-dimensional cephalometric analysis is crucial in craniomaxillofacial assessment, with landmarks detection in craniomaxillofacial (CMF) CT scans being a key component. However, creating robust deep learning models for this task typically requires extensive CMF CT datasets annotated by experienced medical professionals, a process that is time-consuming and labor-intensive. Conversely, acquiring large volume of unlabeled CMF CT data is relatively straightforward. Thus, semi-supervised learning (SSL), leveraging limited labeled data supplemented by sufficient unlabeled dataset, could be a viable solution to this challenge.

METHOD: We developed an SSL model, named CephaloMatch, based on a strong-weak perturbation consistency framework. The proposed SSL model incorporates a head position rectification technique through coarse detection to enhance consistency between labeled and unlabeled datasets and a multilayers perturbation method which is employed to expand the perturbation space. The proposed SSL model was assessed using 362 CMF CT scans, divided into a training set (60 scans), a validation set (14 scans), and an unlabeled set (288 scans).

RESULT: The proposed SSL model attained a detection error of 1.60 ± 0.87 mm, significantly surpassing the performance of conventional fully supervised learning model (1.94 ± 1.12 mm). Notably, the proposed SSL model achieved equivalent detection accuracy (1.91 ± 1.00 mm) with only half the labeled dataset, compared to the fully supervised learning model.

CONCLUSIONS: The proposed SSL model demonstrated exceptional performance in landmarks detection using a limited labeled CMF CT dataset, significantly reducing the workload of medical professionals and enhances the accuracy of 3D cephalometric analysis.

PMID:39130473 | PMC:PMC11315087 | DOI:10.1016/j.heliyon.2024.e34583

Heliyon. 2024 Jul 15;10(14):e34593. doi: 10.1016/j.heliyon.2024.e34593. eCollection 2024 Jul 30.

ABSTRACT

This paper introduces a mobile cloud-based predictive model for assisting Parkinson's disease (PD) patients. PD, a chronic neurodegenerative disorder, impairs motor functions and daily tasks due to the degeneration of dopamine-producing neurons in the brain. The model utilizes smartphones to aid patients in collecting voice samples, which are then sent to a cloud service for storage and processing. A hybrid deep learning model, trained using the UCI Parkinson's Telemonitoring Voice dataset, analyzes this data to estimate the severity of PD symptoms. The model's performance is noteworthy, with accuracy, sensitivity, and specificity metrics of 96.2 %, 94.15 %, and 96.15 %, respectively. Additionally, it boasts a rapid response time of just 13 s. Results are delivered to users via smartphone alert notifications, coupled with a knowledge base feature that educates them about PD. This system provides reliable home-based assessment and monitoring of PD and enables prompt medical intervention, significantly enhancing the quality of life for patients with Parkinson's disease.

PMID:39130458 | PMC:PMC11315181 | DOI:10.1016/j.heliyon.2024.e34593

Heliyon. 2024 Jul 14;10(14):e34244. doi: 10.1016/j.heliyon.2024.e34244. eCollection 2024 Jul 30.

ABSTRACT

At the beginning of the "Disease X" outbreak, drug discovery and development are often challenged by insufficient and unbalanced data. To address this problem and maximize the information value of limited data, we propose a drug screening model, LGCNN, based on convolutional neural network (CNN), which enables rapid drug screening by integrating features of drug molecular structures and drug-target interactions at both local and global (LG) levels. Experimental results show that LGCNN exhibits better performance compared to other state-of-the-art classification methods under limited data. In addition, LGCNN was applied to anti-SARS-CoV-2 drug screening to realize therapeutic drug mining against COVID-19. LGCNN transcends the limitations of traditional models for predicting interactions between single drug targets and shows new advantages in predicting multi-target drug-target interactions. Notably, the cross-coronavirus generalizability of the model is also implied by the analysis of targets, drugs, and mechanisms in the prediction results. In conclusion, LGCNN provides new ideas and methods for rapid drug screening in emergency situations where data are scarce.

PMID:39130417 | PMC:PMC11315141 | DOI:10.1016/j.heliyon.2024.e34244