Gigascience. 2024 Jan 2;13:giae080. doi: 10.1093/gigascience/giae080.

ABSTRACT

Identification of protein-protein and protein-nucleic acid binding sites provides insights into biological processes related to protein functions and technical guidance for disease diagnosis and drug design. However, accurate predictions by computational approaches remain highly challenging due to the limited knowledge of residue binding patterns. The binding pattern of a residue should be characterized by the spatial distribution of its neighboring residues combined with their physicochemical information interaction, which yet cannot be achieved by previous methods. Here, we design GraphRBF, a hierarchical geometric deep learning model to learn residue binding patterns from big data. To achieve it, GraphRBF describes physicochemical information interactions by designing an enhanced graph neural network and characterizes residue spatial distributions by introducing a prioritized radial basis function neural network. After training and testing, GraphRBF shows great improvements over existing state-of-the-art methods and strong interpretability of its learned representations. Applying GraphRBF to the SARS-CoV-2 omicron spike protein, it successfully identifies known epitopes of the protein. Moreover, it predicts multiple potential binding regions for new nanobodies or even new drugs with strong evidence. A user-friendly online server for GraphRBF is freely available at http://liulab.top/GraphRBF/server.

PMID:39484977 | DOI:10.1093/gigascience/giae080

J Chem Phys. 2024 Nov 7;161(17):174106. doi: 10.1063/5.0237101.

ABSTRACT

Machine-learning interatomic potential models based on graph neural network architectures have the potential to make atomistic materials modeling widely accessible due to their computational efficiency, scalability, and broad applicability. The training datasets for many such models are derived from density-functional theory calculations, typically using a semilocal exchange-correlation functional. As a result, long-range interactions such as London dispersion are often missing in these models. We investigate whether this missing component can be addressed by combining a graph deep learning potential with semiempirical dispersion models. We assess this combination by deriving the equations of state for layered pnictogen chalcohalides BiTeBr and BiTeI and performing crystal structure optimizations for a broader set of V-VI-VII compounds with various stoichiometries, many of which possess van der Waals gaps. We characterize the optimized crystal structures by calculating their x-ray diffraction patterns and radial distribution function histograms, which are also used to compute Earth mover's distances to quantify the dissimilarity between the optimized and corresponding experimental structures. We find that dispersion-corrected graph deep learning potentials generally (though not universally) provide a more realistic description of these compounds due to the inclusion of van der Waals attractions. In particular, their use results in systematic improvements in predicting not only the van der Waals gap but also the layer thickness in layered V-VI-VII compounds. Our results demonstrate that the combined potentials studied here, derived from a straightforward approach that neither requires fine-tuning the training nor refitting the potential parameters, can significantly improve the description of layered polar crystals.

PMID:39484895 | DOI:10.1063/5.0237101

J Chem Inf Model. 2024 Nov 1. doi: 10.1021/acs.jcim.4c01475. Online ahead of print.

ABSTRACT

In the realm of biomedical research, understanding the intricate structure of proteins is crucial, as these structures determine how proteins function within our bodies and interact with potential drugs. Traditionally, methods like X-ray crystallography and cryo-electron microscopy have been used to unravel these structures, but they are often challenging, time-consuming and costly. Recently, a breakthrough in computational biology has emerged with the development of deep learning algorithms capable of predicting protein structures based on their amino acid sequences (Jumper, J., et al. Nature 2021, 596, 583. Lane, T. J. Nature Methods 2023, 20, 170. Kryshtafovych, A., et al. Proteins: Structure, Function and Bioinformatics 2021, 89, 1607). This study focuses on predicting the dynamic changes that proteins undergo upon ligand binding, specifically when they bind to allosteric sites, i.e. a pocket different from the active site. Allosteric modulators are particularly important for drug discovery, as they open new avenues for designing drugs that can target proteins more effectively and with fewer side effects (Nussinov, R.; Tsai, C. J. Cell 2013, 153, 293). To study this, we curated a data set of 578 X-ray structures comprised of proteins displaying orthosteric and allosteric binding as well as a general framework to evaluate deep learning-based structure prediction methods. Our findings demonstrate the potential and current limitations of deep learning methods, such as AlphaFold2 (Jumper, J., et al. Nature 2021, 596, 583), NeuralPLexer (Qiao, Z., et al. Nat Mach Intell 2024, 6, 195), and RoseTTAFold All-Atom (Krishna, R., et al. Science 2024, 384, eadl2528) to predict not just static protein structures but also the dynamic conformational changes. Herein we show that predicting the allosteric induce-fit conformation still poses a challenge to deep learning methods as they more accurately predict the orthosteric bound conformation compared to the allosteric induce fit conformation. For AlphaFold2, we observed that conformational diversity, and sampling between the apo and holo state could be increased by modifying the MSA depth, but this did not enhance the ability to generate conformations close to the allosteric induced-fit conformation. To further support advancements in protein structure prediction field, the curated data set and evaluation framework are made publicly available.

PMID:39484820 | DOI:10.1021/acs.jcim.4c01475

Biomed Tech (Berl). 2024 Nov 4. doi: 10.1515/bmt-2024-0334. Online ahead of print.

ABSTRACT

OBJECTIVES: This study aims to develop a multimodal deep learning-based algorithm for detecting specific fetal heart rate (FHR) events, to enhance automatic monitoring and intelligent assessment of fetal well-being.

METHODS: We analyzed FHR and uterine contraction signals by combining various feature extraction techniques, including morphological features, heart rate variability features, and nonlinear domain features, with deep learning algorithms. This approach enabled us to classify four specific FHR events (bradycardia, tachycardia, acceleration, and deceleration) as well as four distinct deceleration patterns (early, late, variable, and prolonged deceleration). We proposed a multi-model deep neural network and a pre-fusion deep learning model to accurately classify the multimodal parameters derived from Cardiotocography signals.

RESULTS: These accuracy metrics were calculated based on expert-labeled data. The algorithm achieved a classification accuracy of 96.2 % for acceleration, 94.4 % for deceleration, 90.9 % for tachycardia, and 85.8 % for bradycardia. Additionally, it achieved 67.0 % accuracy in classifying the four distinct deceleration patterns, with 80.9 % accuracy for late deceleration and 98.9 % for prolonged deceleration.

CONCLUSIONS: The proposed multimodal deep learning algorithm serves as a reliable decision support tool for clinicians, significantly improving the detection and assessment of specific FHR events, which are crucial for fetal health monitoring.

PMID:39484683 | DOI:10.1515/bmt-2024-0334

Digit Health. 2024 Oct 7;10:20552076241288430. doi: 10.1177/20552076241288430. eCollection 2024 Jan-Dec.

ABSTRACT

BACKGROUND: Coronary artery disease (CAD) is a global health concern. Conventional single photon emission computed tomography myocardial perfusion imaging (SPECT MPI) is a noninvasive method for assessing the severity of CAD. However, it relies on manual classification by clinicians, which can lead to visual fatigue and potential errors. Deep learning techniques have displayed promising results in CAD diagnosis and prediction, providing efficient and accurate analysis of medical images.

METHODS: In this study, we explore the application of deep learning methods for assessing the severity of CAD and identifying cases of multivessel disease (MVD). We utilized the EfficientNet-V2 model in combination with DeepSMOTE to evaluate CAD severity using SPECT MPI images.

RESULTS: Utilizing a dataset consisting of 254 patients (176 with MVD and 78 with single-vessel disease [SVD]), our model achieved an accuracy rate of 84.31% and area under the receiver operating characteristic curve (AUC) value of 0.8714 in predicting cases of MVD. These results underline the promising potential of our approach in MVD prediction, offering valuable diagnostic insights and the prospect of reducing medical costs.

CONCLUSION: This study emphasizes the feasibility of employing deep learning techniques for predicting MVD based on SPECT MPI images. The integration of Efficient-Net-V2 and DeepSMOTE methods effectively evaluates CAD severity and distinguishes MVD from SVD. Our research presents a practical approach to the early prediction and diagnosis of MVD, ultimately leading to enhanced patient outcomes and reduced healthcare costs.

PMID:39484655 | PMC:PMC11526402 | DOI:10.1177/20552076241288430

bioRxiv [Preprint]. 2024 Oct 24:2024.10.21.619560. doi: 10.1101/2024.10.21.619560.

ABSTRACT

Computational enhancement is an important strategy for inferring high-resolution features from genome-wide chromosome conformation capture (Hi-C) data, which typically have limited resolution. Deep learning has been highly successful in this task but we show that it creates prevalent artificial structures in the enhanced data due to the need to divide the large contact matrix into small patches. In addition, previous deep learning methods largely focus on local patterns, which cannot fully capture the complexity of Hi-C data. Here we propose Smooth, High-resolution, and Accurate Reconstruction of Patterns (SHARP) for enhancing Hi-C data. It uses the novel approach of decomposing the data into three types of signals, due to one-dimensional proximity, contiguous domains, and other fine structures, and applies deep learning only to the third type of signals, such that enhancement of the first two is unaffected by the patches. For the deep learning part, SHARP uses both local and global attention mechanisms to capture multi-scale contextual information. We compare SHARP with state-of-the-art methods extensively, including application to data from new samples and another species, and show that SHARP has superior performance in terms of resolution enhancement accuracy, avoiding creation of artificial structures, identifying significant interactions, and enrichment in chromatin states.

PMID:39484541 | PMC:PMC11526948 | DOI:10.1101/2024.10.21.619560

bioRxiv [Preprint]. 2024 Oct 25:2024.10.23.619915. doi: 10.1101/2024.10.23.619915.

ABSTRACT

Quantitatively mapping enzyme sequence-catalysis landscapes remains a critical challenge in understanding enzyme function, evolution, and design. Here, we expand an emerging microfluidic platform to measure catalytic constants- k cat and K M -for hundreds of diverse naturally occurring sequences and mutants of the model enzyme Adenylate Kinase (ADK). This enables us to dissect the sequence-catalysis landscape's topology, navigability, and mechanistic underpinnings, revealing distinct catalytic peaks organized by structural motifs. These results challenge long-standing hypotheses in enzyme adaptation, demonstrating that thermophilic enzymes are not slower than their mesophilic counterparts. Combining the rich representations of protein sequences provided by deep-learning models with our custom high-throughput kinetic data yields semi-supervised models that significantly outperform existing models at predicting catalytic parameters of naturally occurring ADK sequences. Our work demonstrates a promising strategy for dissecting sequence-catalysis landscapes across enzymatic evolution and building family-specific models capable of accurately predicting catalytic constants, opening new avenues for enzyme engineering and functional prediction.

PMID:39484523 | PMC:PMC11526920 | DOI:10.1101/2024.10.23.619915

bioRxiv [Preprint]. 2024 Oct 25:2024.10.23.619844. doi: 10.1101/2024.10.23.619844.

ABSTRACT

Biomedical research and clinical practice are in the midst of a transition toward significantly increased use of artificial intelligence (AI) and machine learning (ML) methods. These advances promise to enable qualitatively deeper insight into complex challenges formerly beyond the reach of analytic methods and human intuition while placing increased demands on ethical and explainable artificial intelligence (XAI), given the opaque nature of many deep learning methods. The U.S. National Institutes of Health (NIH) has initiated a significant research and development program, Bridge2AI, aimed at producing new "flagship" datasets designed to support AI/ML analysis of complex biomedical challenges, elucidate best practices, develop tools and standards in AI/ML data science, and disseminate these datasets, tools, and methods broadly to the biomedical community. An essential set of concepts to be developed and disseminated in this program along with the data and tools produced are criteria for AI-readiness of data, including critical considerations for XAI and ethical, legal, and social implications (ELSI) of AI technologies. NIH Bridge to Artificial Intelligence (Bridge2AI) Standards Working Group members prepared this article to present methods for assessing the AI-readiness of biomedical data and the data standards perspectives and criteria we have developed throughout this program. While the field is rapidly evolving, these criteria are foundational for scientific rigor and the ethical design and application of biomedical AI methods.

PMID:39484409 | PMC:PMC11526931 | DOI:10.1101/2024.10.23.619844

medRxiv [Preprint]. 2024 Oct 18:2024.10.17.24315675. doi: 10.1101/2024.10.17.24315675.

ABSTRACT

Atherosclerotic cardiovascular disease, the leading cause of global mortality, is driven by lipid accumulation and plaque formation within arterial walls. Carotid plaques, detectable via ultrasound, are a well-established marker of subclinical atherosclerosis. In this study, we trained a deep learning model to detect plaques in 177,757 carotid ultrasound images from 19,499 UK Biobank (UKB) participants (aged 47-83 years) to assess the prevalence, risk factors, prognostic significance, and genetic architecture of carotid atherosclerosis in a large population-based cohort. The model demonstrated high performance metrics with accuracy, sensitivity, specificity, and positive predictive value of 89.3%, 89.5%, 89.2%, and 82.9%, respectively, identifying carotid plaques in 45% of the population. Plaque presence and count were significantly associated with future cardiovascular events over a median follow-up period of up to 7 years, leading to improved risk reclassification beyond established clinical prediction models. A genome-wide association study (GWAS) meta-analysis of carotid plaques (29,790 cases, 36,847 controls) uncovered two novel genomic loci (p < 5×10 -8 ) with downstream analyses implicating lipoprotein(a) and interleukin-6 signaling, both targets of investigational drugs in advanced clinical development. Observational and Mendelian randomization analyses showed associations between smoking, low-density-lipoprotein (LDL) cholesterol, and high blood pressure and the odds of carotid plaque presence. Our study underscores the potential of carotid plaque assessment for improving cardiovascular risk prediction, provides novel insights into the genetic basis of subclinical atherosclerosis, and offers a valuable resource for advancing atherosclerosis research at the population scale.

PMID:39484270 | PMC:PMC11527046 | DOI:10.1101/2024.10.17.24315675

medRxiv [Preprint]. 2024 Oct 15:2024.10.14.24314447. doi: 10.1101/2024.10.14.24314447.

ABSTRACT

Automatic analysis of pathologic vertebrae from computed tomography (CT) scans could significantly improve the diagnostic management of patients with metastatic spine disease. We provide the first publicly available annotated imaging dataset of cancerous CT spines to help develop artificial intelligence frameworks for automatic vertebrae segmentation and classification. This collection contains a dataset of 55 CT scans collected on patients with various types of primary cancers at two different institutions. In addition to raw images, data include manual segmentations and contours, vertebral level labeling, vertebral lesion-type classifications, and patient demographic details. Our automated segmentation model uses nnU-Net, a freely available open-source framework for deep learning in healthcare imaging, and is made publicly available. This data will facilitate the development and validation of models for predicting the mechanical response to loading and the resulting risk of fractures and spinal deformity.

PMID:39484265 | PMC:PMC11527073 | DOI:10.1101/2024.10.14.24314447

medRxiv [Preprint]. 2024 Oct 16:2024.10.14.24315465. doi: 10.1101/2024.10.14.24315465.

ABSTRACT

Pressure injury (PI) detection is challenging, especially in dark skin tones, due to the unreliability of visual inspection. Thermography may serve as a viable alternative as temperature differences in the skin can indicate impending tissue damage. Although deep learning models hold considerable promise toward reliably detecting PI, existing work fails to evaluate performance on diverse skin tones and varying data collection protocols. We collected a new dataset of 35 participants focused on darker skin tones where temperature differences are induced through cooling and cupping protocols. The dataset includes different cameras, lighting, patient pose, and camera distance. We compare the performance of three convolutional neural network (CNN) models trained on either the thermal or the optical images on all skin tones. Our results suggest thermography-based CNN is robust to data collection protocols. Moreover, the visual explanation often captures the region of interest without requiring explicit bounding box labels.

PMID:39484234 | PMC:PMC11527050 | DOI:10.1101/2024.10.14.24315465

PeerJ. 2024 Oct 28;12:e18098. doi: 10.7717/peerj.18098. eCollection 2024.

ABSTRACT

BACKGROUND: Determining the status of breast cancer susceptibility genes (BRCA) is crucial for guiding breast cancer treatment. Nevertheless, the need for BRCA genetic testing among breast cancer patients remains unmet due to high costs and limited resources. This study aimed to develop a Bi-directional Self-Attention Multiple Instance Learning (BiAMIL) algorithm to detect BRCA status from hematoxylin and eosin (H&E) pathological images.

METHODS: A total of 319 histopathological slides from 254 breast cancer patients were included, comprising two dependent cohorts. Following image pre-processing, 633,484 tumor tiles from the training dataset were employed to train the self-developed deep-learning model. The performance of the network was evaluated in the internal and external test sets.

RESULTS: BiAMIL achieved AUC values of 0.819 (95% CI [0.673-0.965]) in the internal test set, and 0.817 (95% CI [0.712-0.923]) in the external test set. To explore the relationship between BRCA status and interpretable morphological features in pathological images, we utilized Class Activation Mapping (CAM) technique and cluster analysis to investigate the connections between BRCA gene mutation status and tissue and cell features. Significantly, we observed that tumor-infiltrating lymphocytes and the morphological characteristics of tumor cells appeared to be potential features associated with BRCA status.

CONCLUSIONS: An interpretable deep neural network model based on the attention mechanism was developed to predict the BRCA status in breast cancer. Keywords: Breast cancer, BRCA, deep learning, self-attention, interpretability.

PMID:39484212 | PMC:PMC11526788 | DOI:10.7717/peerj.18098

Adv Ophthalmol Pract Res. 2024 Jun 25;4(4):202-208. doi: 10.1016/j.aopr.2024.06.004. eCollection 2024 Nov-Dec.

ABSTRACT

PURPOSE: This study aimed to propose a novel deep learning-based approach to assess the extent of abduction in patients with abducens nerve palsy before and after strabismus surgery.

METHODS: This study included 13 patients who were diagnosed with abducens nerve palsy and underwent strabismus surgery in a tertiary hospital. Photographs of primary, dextroversion and levoversion position were collected before and after strabismus surgery. The eye location and eye segmentation network were trained via recurrent residual convolutional neural networks with attention gate connection based on U-Net (R2AU-Net). Facial images of abducens nerve palsy patients were used as the test set and parameters were measured automatically based on the masked images. Absolute abduction also was measured manually, and relative abduction was calculated. Agreements between manual and automatic measurements, as well as repeated automatic measurements were analyzed. Preoperative and postoperative results were compared.

RESULTS: The intraclass correlation coefficients (ICCs) between manual and automatic measurements of absolute abduction ranged from 0.985 to 0.992 (P＜0.001), and the bias ranged from -0.25 ​mm to -0.05 ​mm. The ICCs between two repeated automatic measurements ranged from 0.994 to 0.997 (P＜0.001), and the bias ranged from -0.11 ​mm to 0.05 ​mm. After strabismus surgery, absolute abduction of affected eye increased from 2.18 ​± ​1.40 ​mm to 3.36 ​± ​1.93 ​mm (P＜0.05). The relative abduction was improved in 76.9% patients (10/13) after surgery (P＜0.01).

CONCLUSIONS: This image analysis technique demonstrated excellent accuracy and repeatability for automatic measurements of ocular abduction, which has promising application prospects in objectively assessing surgical outcomes in patients with abducens nerve palsy.

PMID:39484054 | PMC:PMC11526073 | DOI:10.1016/j.aopr.2024.06.004

Acad Radiol. 2024 Oct 30:S1076-6332(24)00774-8. doi: 10.1016/j.acra.2024.10.014. Online ahead of print.

ABSTRACT

RATIONALE AND OBJECTIVES: To develop and evaluate an AI algorithm that detects breast cancer in MRI scans up to one year before radiologists typically identify it, potentially enhancing early detection in high-risk women.

MATERIALS AND METHODS: A convolutional neural network (CNN) AI model, pre-trained on breast MRI data, was fine-tuned using a retrospective dataset of 3029 MRI scans from 910 patients. These contained 115 cancers that were diagnosed within one year of a negative MRI. The model aimed to identify these cancers, with the goal of predicting cancer development up to one year in advance. The network was fine-tuned and tested with 10-fold cross-validation. Mean age of patients was 52 years (range, 18-88 years), with average follow-up of 4.3 years (range 1-12 years).

RESULTS: The AI detected cancers one year earlier with an area under the ROC curve of 0.72 (0.67-0.76). Retrospective analysis by a radiologist of the top 10% highest risk MRIs as ranked by the AI could have increased early detection by up to 30%. (35/115, CI:22.2-39.7%, 30% sensitivity). A radiologist identified a visual correlate to biopsy-proven cancers in 83 of prior-year MRIs (83/115, CI: 62.1-79.4%). The AI algorithm identified the anatomic region where cancer would be detected in 66 cases (66/115, CI:47.8-66.5%); with both agreeing in 54 cases (54/115, CI:%37.5-56.4%).

CONCLUSION: This novel AI-aided re-evaluation of "benign" breasts shows promise for improving early breast cancer detection with MRI. As datasets grow and image quality improves, this approach is expected to become even more impactful.

PMID:39482209 | DOI:10.1016/j.acra.2024.10.014

Eur J Surg Oncol. 2024 Oct 15:108735. doi: 10.1016/j.ejso.2024.108735. Online ahead of print.

ABSTRACT

BACKGROUND: Surgeons can experience elevated cognitive workload (CWL) during surgery due to various factors including operative technicalities and the environmental demands of the operating theatre. This can result in poorer outcomes and have a detrimental effect on surgeon well-being. The objective measurement of CWL provides a potential solution to facilitate classification of workload levels, however results are variable when physiological measures are used in isolation. The aim of this study is to develop and propose a multimodal machine learning (ML) approach to classify CWL levels using a bespoke sensor platform and to develop a ML approach to impute missing pupil diameter measures due to the effect of blinking or noise.

MATERIALS AND METHODS: Ten surgical trainees performed a simulated laparoscopic cholecystectomy under cognitive conditions of increasing difficulty, namely a modified auditory N-back task with increasing difficulty and a verbal clinical scenario. Physiological measures were recorded using a novel platform (MAESTRO). Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) were used as direct measures of CWL. Indirect measures included electromyography (EMG), electrocardiography (ECG) and pupil diameter (PD). A reference point for validation was provided by subjective assessment of perceived CWL using the SURG-TLX. A multimodal machine learning approach that systematically implements a CNN-BiLSTM, a binary version of the metaheuristic Manta Ray Foraging Optimisation (BMRFO) and a version of Fuzzy C-Means (FCM) called Optimal Completion Strategy (OCS) was used to classify the associated perceived CWL state.

RESULTS: Compared to other state of the art classification techniques, cross-validation results for the classification of CWL levels suggest that the CNN-BLSTM and BMRFO approach provides an average accuracy of 97 % based on the confusion matrix. Additionally, OCS demonstrated a superior average performance of 9.15 % in terms of Root-Mean-Square-Error (RMSE) when compared to other PD imputation methods.

CONCLUSION: Perceived CWL levels were correctly classified using a multimodal ML approach. This approach provides a potential route to accurately classify CWL levels, which may have application in future surgical training and assessment programs as well as the development of cognitive support systems in the operating room.

PMID:39482204 | DOI:10.1016/j.ejso.2024.108735

Trends Cancer. 2024 Oct 30:S2405-8033(24)00222-X. doi: 10.1016/j.trecan.2024.10.003. Online ahead of print.

ABSTRACT

Gene expression regulation in hypoxic tumor microenvironments is mediated by O2 responsive transcription factors (O2R-TFs), fine-tuning cancer cell metabolic demand for O2 according to its availability. Here, we discuss key O2R-TFs and emerging artificial intelligence (AI)-based applications suitable for the interrogation of O2R-TF relationships specifying cancer cell metabolic adaptations to hypoxia.

PMID:39482194 | DOI:10.1016/j.trecan.2024.10.003

J Environ Sci (China). 2025 May;151:125-139. doi: 10.1016/j.jes.2024.03.037. Epub 2024 Mar 29.

ABSTRACT

PM2.5 constitutes a complex and diverse mixture that significantly impacts the environment, human health, and climate change. However, existing observation and numerical simulation techniques have limitations, such as a lack of data, high acquisition costs, and multiple uncertainties. These limitations hinder the acquisition of comprehensive information on PM2.5 chemical composition and effectively implement refined air pollution protection and control strategies. In this study, we developed an optimal deep learning model to acquire hourly mass concentrations of key PM2.5 chemical components without complex chemical analysis. The model was trained using a randomly partitioned multivariate dataset arranged in chronological order, including atmospheric state indicators, which previous studies did not consider. Our results showed that the correlation coefficients of key chemical components were no less than 0.96, and the root mean square errors ranged from 0.20 to 2.11 µg/m3 for the entire process (training and testing combined). The model accurately captured the temporal characteristics of key chemical components, outperforming typical machine-learning models, previous studies, and global reanalysis datasets (such as Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) and Copernicus Atmosphere Monitoring Service ReAnalysis (CAMSRA)). We also quantified the feature importance using the random forest model, which showed that PM2.5, PM1, visibility, and temperature were the most influential variables for key chemical components. In conclusion, this study presents a practical approach to accurately obtain chemical composition information that can contribute to filling missing data, improved air pollution monitoring and source identification. This approach has the potential to enhance air pollution control strategies and promote public health and environmental sustainability.

PMID:39481927 | DOI:10.1016/j.jes.2024.03.037

World Neurosurg. 2024 Oct 29:S1878-8750(24)01793-5. doi: 10.1016/j.wneu.2024.10.089. Online ahead of print.

ABSTRACT

BACKGROUND: The Ki-67 index is a histopathological marker that has been reported to be a crucial factor in the biological behavior and prognosis of meningiomas. Several studies have developed artificial intelligence (AI) models to predict the Ki-67 based on radiomics. In this study, we aimed to perform a systematic review and meta-analysis of AI models that predicted the Ki-67 index in meningioma.

METHODS: Literature records were retrieved on April 27th, 2024, using the relevant key terms without filters in PubMed, Embase, Scopus, and Web of Science. Records were screened according to the eligibility criteria, and the data from included studies were extracted. The quality assessment was performed using the QUADAS-2 tool. The meta-analysis, sensitivity analysis, and meta-regression were conducted using R software.

RESULTS: Our study included six studies. The mean Ki-67 ranged from 2.7 ± 2.97 to 4.8 ± 40.3. Of six studies, five utilized an ML method. The most used AI method was the least absolute shrinkage and selection operator (LASSO). The AUC and ACC ranged from 0.83 to 0.99 and 0.81 to 0.95, respectively. AI models demonstrated a pooled sensitivity of 87.5% (95% CI: 75.2%, 94.2%), a specificity of 86.9% (95% CI: 75.8%, 93.4%), and a diagnostic odds ratio (DOR) of 40.02 (95% CI: 13.5, 156.4). The summary receiver operating characteristic SROC curve indicated an AUC of 0.931 for the prediction of Ki-67 index status in intracranial meningiomas.

CONCLUSION: AI models have demonstrated promising performance for predicting the Ki-67 index in meningiomas and can optimize the treatment strategy.

PMID:39481846 | DOI:10.1016/j.wneu.2024.10.089

Anal Biochem. 2024 Oct 29:115701. doi: 10.1016/j.ab.2024.115701. Online ahead of print.

ABSTRACT

The escalating global incidence of allergy patients illustrates the growing impact of allergic issues on global health. Allergens are small molecule antigens that trigger allergic reactions. A widely recognized strategy for allergy prevention involves identifying allergens and avoiding re-exposure. However, the laboratory methods to identify allergenic proteins are often time-consuming and resource-intensive. There is a crucial need to establish efficient and reliable computational approaches for the identification of allergenic proteins. In this study, we developed a novel allergenic proteins predictor named Alg-MFDL, which integrates pre-trained protein language models (PLMs) and traditional handcrafted features to achieve a more complete protein representation. First, we compared the performance of eight pre-trained PLMs from ProtTrans and ESM-2 and selected the best-performing one from each of the two groups. In addition, we evaluated the performance of three handcrafted features and different combinations of them to select the optimal feature or feature combination. Then, these three protein representations were fused and used as inputs to train the convolutional neural network (CNN). Finally, the independent validation was performed on benchmark datasets to evaluate the performance of Alg-MFDL. As a result, Alg-MFDL achieved an accuracy of 0.973, a precision of 0.996, a sensitivity of 0.951, and an F1 value of 0.973, outperforming the most of current state-of-the-art (SOTA) methods across all key metrics. We anticipated that the proposed model could be considered a useful tool for predicting allergen proteins. The datasets and code utilized in this study are freely available at https://github.com/Hupenpen/Alg-MFDL.

PMID:39481588 | DOI:10.1016/j.ab.2024.115701

Bone Joint J. 2024 Nov 1;106-B(11):1216-1222. doi: 10.1302/0301-620X.106B11.BJJ-2024-0453.R1.

ABSTRACT

AIMS: Machine learning (ML), a branch of artificial intelligence that uses algorithms to learn from data and make predictions, offers a pathway towards more personalized and tailored surgical treatments. This approach is particularly relevant to prevalent joint diseases such as osteoarthritis (OA). In contrast to end-stage disease, where joint arthroplasty provides excellent results, early stages of OA currently lack effective therapies to halt or reverse progression. Accurate prediction of OA progression is crucial if timely interventions are to be developed, to enhance patient care and optimize the design of clinical trials.

METHODS: A systematic review was conducted in accordance with PRISMA guidelines. We searched MEDLINE and Embase on 5 May 2024 for studies utilizing ML to predict OA progression. Titles and abstracts were independently screened, followed by full-text reviews for studies that met the eligibility criteria. Key information was extracted and synthesized for analysis, including types of data (such as clinical, radiological, or biochemical), definitions of OA progression, ML algorithms, validation methods, and outcome measures.

RESULTS: Out of 1,160 studies initially identified, 39 were included. Most studies (85%) were published between 2020 and 2024, with 82% using publicly available datasets, primarily the Osteoarthritis Initiative. ML methods were predominantly supervised, with significant variability in the definitions of OA progression: most studies focused on structural changes (59%), while fewer addressed pain progression or both. Deep learning was used in 44% of studies, while automated ML was used in 5%. There was a lack of standardization in evaluation metrics and limited external validation. Interpretability was explored in 54% of studies, primarily using SHapley Additive exPlanations.

CONCLUSION: Our systematic review demonstrates the feasibility of ML models in predicting OA progression, but also uncovers critical limitations that currently restrict their clinical applicability. Future priorities should include diversifying data sources, standardizing outcome measures, enforcing rigorous validation, and integrating more sophisticated algorithms. This paradigm shift from predictive modelling to actionable clinical tools has the potential to transform patient care and disease management in orthopaedic practice.

PMID:39481441 | DOI:10.1302/0301-620X.106B11.BJJ-2024-0453.R1