Waste Manag Res. 2025 Mar 20:734242X241313286. doi: 10.1177/0734242X241313286. Online ahead of print.

ABSTRACT

As the Internet of things (IoT) continues to transform modern technologies, innovative applications in waste management and air pollution monitoring are becoming critical for sustainable development. In this manuscript, a novel smart waste management (SWM) and air pollution forecasting (APF) system is proposed by leveraging IoT sensors and the fully Elman neural network (FENN) model, termed as SWM-APF-IoT-FENN. The system integrates real-time data from waste and air quality sensors including weight, trash level, odour and carbon monoxide (CO) that are collected from smart bins connected to a Google Cloud Server. Here, the MaxAbsScaler is employed for data normalization, ensuring consistent feature representation. Subsequently, the atmospheric contaminants surrounding the waste receptacles were observed using a FENN model. This model is utilized to predict the atmospheric concentration of CO and categorize the bin status as filled, half-filled and unfilled. Moreover, the weight parameter of the FENN model is tuned using the secretary bird optimization algorithm for better prediction results. The implementation of the proposed methodology is done in Python tool, and the performance metrics are analysed. Experimental results demonstrate significant improvements in performance, achieving 15.65%, 18.45% and 21.09% higher accuracy, 18.14%, 20.14% and 24.01% higher F-Measure, 23.64%, 24.29% and 29.34% higher False Acceptance Rate (FAR), 25.00%, 27.09% and 31.74% higher precision, 20.64%, 22.45% and 28.64% higher sensitivity, 26.04%, 28.65% and 32.74% higher specificity, 9.45%, 7.38% and 4.05% reduced computational time than the conventional approaches such as Elman neural network, recurrent artificial neural network and long short-term memory with gated recurrent unit, respectively. Thus, the proposed method offers a streamlined, efficient framework for real-time waste management and pollution forecasting, addressing critical environmental challenges.

PMID:40111379 | DOI:10.1177/0734242X241313286

Med Phys. 2025 Mar 20. doi: 10.1002/mp.17763. Online ahead of print.

ABSTRACT

BACKGROUND: Accurate segmentation of diffuse large B-cell lymphoma (DLBCL) lesions is challenging due to their complex patterns in medical imaging. Traditional methods often struggle to delineate these lesions accurately.

OBJECTIVE: This study aims to develop a precise segmentation method for DLBCL using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) and computed tomography (CT) images.

METHODS: We propose a 3D segmentation method based on an encoder-decoder architecture. The encoder incorporates a dual-branch design based on the shifted window transformer to extract features from both PET and CT modalities. To enhance feature integration, we introduce a multi-scale information fusion (MSIF) module that performs multi-scale feature fusion using cross-attention mechanisms with a shifted window framework. A gated neural network within the MSIF module dynamically adjusts feature weights to balance the contributions from each modality. The model is optimized using the dice similarity coefficient (DSC) loss function, minimizing discrepancies between the model prediction and ground truth. Additionally, we computed the total metabolic tumor volume (TMTV) and performed statistical analyses on the results.

RESULTS: The model was trained and validated on a private dataset of 165 DLBCL patients and a publicly available dataset (autoPET) containing 145 PET/CT scans of lymphoma patients. Both datasets were analyzed using five-fold cross-validation. On the private dataset, our model achieved a DSC of 0.7512, sensitivity of 0.7548, precision of 0.7611, an average surface distance (ASD) of 3.61 mm, and a Hausdorff distance at the 95th percentile (HD95) of 15.25 mm. On the autoPET dataset, the model achieved a DSC of 0.7441, sensitivity of 0.7573, precision of 0.7427, ASD of 5.83 mm, and HD95 of 21.27 mm, outperforming state-of-the-art methods (p < 0.05, t-test). For TMTV quantification, Pearson correlation coefficients of 0.91 (private dataset) and 0.86 (autoPET) were observed, with R2 values of 0.89 and 0.75, respectively. Extensive ablation studies demonstrated the MSIF module's contribution to enhanced segmentation accuracy.

CONCLUSION: This study presents an effective automatic segmentation method for DLBCL that leverages the complementary strengths of PET and CT imaging. The method demonstrates robust performance on both private and publicly available datasets, ensuring its reliability and generalizability. Our method provides clinicians with more precise tumor delineation, which can improve the accuracy of diagnostic interpretations and assist in treatment planning for DLBCL patients. The code for the proposed method is available at https://github.com/chenzhao2023/lymphoma_seg.

PMID:40111352 | DOI:10.1002/mp.17763

Med Phys. 2025 Mar 20. doi: 10.1002/mp.17752. Online ahead of print.

ABSTRACT

BACKGROUND: Deep learning (DL)-based systems have not yet been broadly implemented in clinical practice, in part due to unknown robustness across multiple imaging protocols.

PURPOSE: To this end, we aim to evaluate the performance of several previously developed DL-based models, which were trained to distinguish idiopathic pulmonary fibrosis (IPF) from non-IPF among interstitial lung disease (ILD) patients, under standardized reference CT imaging protocols. In this study, we utilized CT scans from non-IPF ILD subjects, acquired using various imaging protocols, to assess the model performance.

METHODS: Three DL-based models, including one 2D and two 3D models, have been previously developed to classify ILD patients into IPF or non-IPF based on chest CT scans. These models were trained on CT image data from 389 IPF and 700 non-IPF ILD patients, retrospectively, obtained from five multicenter studies. For some patients, multiple CT scans were acquired (e.g., one at inhalation and one at exhalation) and/or reconstructed (e.g., thin slice and/or thick slice). Thus, for each patient, one CT image dataset was selected to be used in the construction of the classification model, so the parameters of that data set serve as the reference conditions. In one non-IPF ILD study, due to its specific study protocol, many patients had multiple CT image data sets that were acquired under both prone and supine positions and/or reconstructed under different imaging parameters. Therefore, to assess the robustness of the previously developed models under different (e.g., non-reference) imaging protocols, we identified 343 subjects from this study who had CT data from both the reference condition (used in model construction) and non-reference conditions (e.g., evaluation conditions), which we used in this model evaluation analysis. We reported the specificities from three model under the non-reference conditions. Generalized linear mixed effects model (GLMM) was utilized to identify the significant CT technical and clinical parameters that were associated with getting inconsistent diagnostic results between reference and evaluation conditions. Selected parameters include effective tube current-time product (known as "effective mAs"), reconstruction kernels, slice thickness, patient orientation (prone or supine), CT scanner model, and clinical diagnosis. Limitations include the retrospective nature of this study.

RESULTS: For all three DL models, the overall specificity of the previously trained IPF diagnosis model decreased (p < 0.05 for two out of three models). GLMM further suggests that for at least one out of three models, mean effective mAs across the scan is the key factor that leads to the decrease in model predictive performance (p < 0.001); the difference of mean effective mAs between the reference and evaluation conditions (p = 0.03) and slice thickness (3 mm; p = 0.03) are flagged as significant factors for one out of three models; other factors are not statistically significant (p > 0.05).

CONCLUSION: Preliminary findings demonstrated the lack of robustness of IPF diagnosis model when the DL-based model is applied to CT series collected under different imaging protocols, which indicated that care should be taken as to the acquisition and reconstruction conditions used when developing and deploying DL models into clinical practice.

PMID:40111345 | DOI:10.1002/mp.17752

J Phys Chem Lett. 2025 Mar 20:3165-3176. doi: 10.1021/acs.jpclett.4c03650. Online ahead of print.

ABSTRACT

Interpretability is fundamental in the precise identification of single-molecule charge transport, and its absence in deep learning models is currently the major barrier to the usage of such powerful algorithms in the field. Here, we have pioneered a novel identification method employing fusion attention-based deep learning technologies. Central to our approach is the innovative neural network architecture, SingleFACNN, which integrates convolutional neural networks with a fusion of multihead self-attention and spatial attention mechanisms. Our findings demonstrate that SingleFACNN accurately classifies the three-type and four-type STM-BJ data sets, leveraging the convolutional layers' robust feature extraction and the attention layers' capacity to capture long-range interactions. Through comprehensive gradient-weighted class activation mapping and ablation studies, we identified and analyzed the critical features impacting classification outcomes with remarkable accuracy, thus enhancing the interpretability of our deep learning model. Furthermore, SingleFACNN's application was extended to mixed samples with varying proportions, achieving commendable prediction performance at low computational cost. Our study underscores the potential of SingleFACNN in advancing the interpretability and credibility of deep learning applications in single-molecule charge transport, opening new avenues for single-molecule detection in complex systems.

PMID:40111072 | DOI:10.1021/acs.jpclett.4c03650

J Chem Inf Model. 2025 Mar 20. doi: 10.1021/acs.jcim.5c00130. Online ahead of print.

ABSTRACT

Accurately predicting the effect of mutations on protein-protein interactions (PPIs) is essential for understanding the protein structure and function, as well as providing insights into disease-causing mechanisms. Many recent popular approaches based on the three-dimensional structure of proteins have been proposed to predict the changes in binding affinity caused by mutations, i.e. ΔΔG. However, how to effectively use the structural information to comprehensively exploit complex interactions within proteins and integrate multisource features remains a significant challenge. In this study, we propose SFM-Net, a powerful deep learning model constructed with GNN-based multiway feature extractors and a new context-aware selective fusion module that jointly leverages the sequence, structural, and evolutionary information. Such design enables SFM-Net to effectively and selectively use features from different sources to facilitate binding affinity change prediction. Benchmarking experiments and targeted ablation studies illustrate the effectiveness and robustness of our method for improving the binding affinity change prediction.

PMID:40111004 | DOI:10.1021/acs.jcim.5c00130

Aust J Rural Health. 2025 Apr;33(2):e70031. doi: 10.1111/ajr.70031.

ABSTRACT

OBJECTIVE: Diabetic retinopathy (DR) screening rates are poor in remote Western Australia where communities rely on outdated primary care-based retinal cameras. Deep learning systems (DLS) may improve access to screening, however, require validation in real-world settings. This study describes and evaluates the implementation of a new, mobile DR screening model that incorporates artificial intelligence (AI) into routine care.

DESIGN: Prospective, population-based study.

SETTING: The model was co-designed with local Aboriginal communities and implemented in the remote, Pilbara region of Western Australia. A research officer without formal healthcare qualification performed retinal screening aboard a Mercedes Sprinter Van using an automated retinal camera with integrated AI diagnostics. Patients received their diagnosis on-the-spot and completed an evaluation survey. A remote clinician provided supervision and on-the-spot telehealth consultation for referable disease.

PARTICIPANTS: People with diabetes from the Pilbara region.

MAIN OUTCOME MEASURE(S): Number of people screened, acceptability of AI to patients.

RESULTS: From February to August 2024, DR screening was provided to 9 communities across the Pilbara region. 78 patients provided research consent, of which 56.4% were Aboriginal or Torres Strait Islanders. 10.3% of retinal photos had referable DR and 8.4% of photos were ungradable. 96% of patients were 'Happy with the use of AI'.

CONCLUSION: Our new model for AI-assisted DR screening was culturally safe, acceptable to patients and effective, demonstrating an 11-fold increase in screening rates compared to 2023 Pilbara data. In remote Australian settings, AI-assisted DR screening may overcome historical barriers to service provision and improve minimisation of preventable blindness.

PMID:40110918 | DOI:10.1111/ajr.70031

SAR QSAR Environ Res. 2025 Mar 20:1-26. doi: 10.1080/1062936X.2025.2475407. Online ahead of print.

ABSTRACT

P38α has been identified as a key target for drug design to treat a wide range of diseases. In this study, multiple independent Gaussian accelerated molecular dynamics (GaMD) simulations, deep learning (DL), and the molecular mechanics generalized Born surface area (MM-GBSA) method were used to investigate the binding mechanism of inhibitors (SB2, SK8, and BMU) to DFG-in and DFG-out P38α and clarify the effect of conformational differences in P38α on inhibitor binding. GaMD trajectory-based DL effectively identified important functional domains, such as the A-loop and N-sheet. Post-processing analysis on GaMD trajectories showed that binding of the three inhibitors profoundly affected the structural flexibility and dynamical behaviour of P38α situated at the DFG-in and DFG-out states. The MM-GBSA calculations not only revealed that differences in the binding ability of inhibitors are affected by DFG-in and DFG-out conformations of P38α, but also confirmed that van der Waals interactions are the primary force driving inhibitor-P38α binding. Residue-based free energy estimation identifies hot spots of inhibitor-P38α binding across DFG-in and DFG-out conformations, providing potential target sites for drug design towards P38α. This work is expected to offer valuable theoretical support for the development of selective inhibitors of P38α family members.

PMID:40110797 | DOI:10.1080/1062936X.2025.2475407

Oncologist. 2025 Mar 10;30(3):oyaf013. doi: 10.1093/oncolo/oyaf013.

ABSTRACT

BACKGROUND: Accurate prediction of early recurrence (ER) is essential to improve the prognosis of patients with hepatocellular carcinoma (HCC) underwent thermal ablation (TA). Therefore, a deep learning model system using longitudinal magnetic resonance imaging (MRI) was developed to predict ER of patients with HCC.

METHODS: From 2014, April to 2017, May, a total of 289 eligible patients with HCC underwent TA were retrospectively enrolled from 3 hospitals and assigned into one training cohort (n = 254) and one external testing cohort (n = 35). Two deep learning models (Pre and PrePost) were developed using the pre-operative MRI and longitudinal MRI (pre- and post-operative) to predict ER for the patients with HCC after TA, respectively. Then, an integrated model (DL_Clinical) incorporating PrePost model signature and clinical variables was built for post-ablation ER risk stratification for the patients with HCC.

RESULTS: In the external testing cohort, the area under the receiver operating characteristic curve (AUC) of the DL_Clinical model was better than that of the Clinical (0.740 vs 0.571), Pre (0.740 vs 0.648), and PrePost model (0.740 vs 0.689). Additionally, there was a significant difference in RFS between the high- and low-risk groups which were divided by the DL_Clinical model (P = .04).

CONCLUSIONS: The PrePost model developed using longitudinal MRI showed outstanding performance for predicting post-ablation ER of HCC. The DL_Clinical model could stratify the patients into high- and low-risk groups, which may help physicians in treatment and surveillance strategy selection in clinical practice.

PMID:40110765 | DOI:10.1093/oncolo/oyaf013

ACS Appl Mater Interfaces. 2025 Mar 20. doi: 10.1021/acsami.4c19494. Online ahead of print.

ABSTRACT

The emergence of inverse design approaches leveraging generative models offers a promising avenue for thermoelectric material design. However, these models heavily depend on diverse training data, and current thermoelectric data sets are limited, primarily encompassing group IV-VI materials operating within moderate temperature ranges. This constraint poses a significant challenge in the pursuit of materials with high thermoelectric figure of merit (zT) through generative modeling. Our study introduces an inverse design model tailored for the constrained thermoelectric materials data set. By augmenting the data with 2000 entries from the experimental literature and incorporating a generative model featuring a diversity loss function and residual network (ResNet) architecture to enhance complexity, our approach has been trained to systematically generate high-zT thermoelectric materials across various temperature ranges. Under predefined high-zT criteria, our deep generative model successfully predicted 100 doped materials with zT values exceeding 1.0. Furthermore, this research analyzes density of states (DOS) plots for the generated materials, identifying 25 unreported previously potential thermoelectric candidates in the material database. Notably, we experimentally validated the synthesis of Mg3.1Sb0.5Bi1.497Te0.003, a representative thermoelectric material from the Mg3(Sb, Bi)2 family suitable for room temperature applications. This validation underscores the efficacy of our model in exploring and discovering novel thermoelectric materials.

PMID:40110715 | DOI:10.1021/acsami.4c19494

Technol Health Care. 2024 Dec 16:9287329241291334. doi: 10.1177/09287329241291334. Online ahead of print.

ABSTRACT

BackgroundThe complexity and diversity of brain activity patterns make it difficult to accurately diagnose neurological disorders such epilepsy, Parkinson's disease, schizophrenia, stroke, and Alzheimer's disease. Integrated and effective analysis of multiple data sources is often beyond the scope of traditional diagnostic procedures. With the use of multi-modal data, recent developments in neural network approaches present encouraging opportunities for raising diagnostic accuracy.ObjectivesA novel approach has been proposed toward the integration of different Nondestructive Evaluation data with EEG signals for improving the diagnosis of neurological disorders such as stroke, epilepsy, Parkinson's disease, and schizophrenia, by leveraging advanced neural network techniques in order to improve the identification and correlation of shared latent features across heterogeneous NDE datasets.MethodsWe determined the 2D scalogram images using a specific encoder-decoder neural network after transforming the EEG signals using wavelet signal processing. Several NDE data types can be easily integrated for thorough analysis due to this network's ability to extract and correlate important aspects from each form of data. Aiming to uncover common patterns indicating of neurological disorders, the technique was evaluated on datasets containing EEG signals and corresponding NDE data.ResultsOur method demonstrated a significant improvement in diagnostic accuracy and efficiency. The encoder-decoder network effectively identified shared latent features across the heterogeneous NDE datasets, leading to more precise and reliable diagnoses. The fusion of multi-modality NDE data with EEG signals provided a robust framework for the automatic identification of multiple neurological disorders.ConclusionsThis innovative approach represents a substantial advancement in the field of neurological disorder diagnosis. By integrating diverse NDE data with EEG signals through advanced neural network techniques, we have developed a method that enhances the accuracy and efficiency of diagnosing multiple neurological conditions. This fusion of multi-modality data has the potential to revolutionize current diagnostic practices in neurology, paving the way for more precise and automated identification of neurological disorders.

PMID:40110612 | DOI:10.1177/09287329241291334

Front Behav Neurosci. 2025 Mar 5;19:1549666. doi: 10.3389/fnbeh.2025.1549666. eCollection 2025.

ABSTRACT

Social hierarchy refers to the set of social ranks in a group of animals where individuals can gain priority access to resources through repeated social interactions. Key mechanisms involved in this process include conflict, social negotiation, prior experience, and physical advantages. The establishment and maintenance of social hierarchies not only promote group stability and well-being but also shape individual social behaviors by fostering cooperation and reducing conflict. Existing research indicates that social hierarchy is closely associated with immune responses, neural regulation, metabolic processes, and endocrine functions. These physiological systems collectively modulate an individual's sensitivity to stress and influence adaptive responses, thereby playing a critical role in the development of psychiatric disorders such as depression and anxiety. This review summarizes the primary behavioral methods used to assess social dominance in mice, evaluates their applicability and limitations, and discusses potential improvements. Additionally, it explores the underlying neural mechanisms associated with these methods to deepen our understanding of their biological basis. By critically assessing existing methodologies and proposing refinements, this study aims to provide a systematic reference framework and methodological guidance for future research, facilitating a more comprehensive exploration of the neural mechanisms underlying social behavior. The role of sex differences in social hierarchy formation remains underexplored. Most studies focus predominantly on males, while the distinct social strategies and physiological mechanisms of females are currently overlooked. Future studies should place greater emphasis on evaluating social hierarchy in female mice to achieve a more comprehensive understanding of sex-specific social behaviors and their impact on group structure and individual health. Advances in automated tracking technologies may help address this gap by improving behavioral assessments in female mice. Future research may also benefit from integrating physiological data (e.g., hormone levels) to gain deeper insights into the relationships between social status, stress regulation, and mental health. Additionally, developments in artificial intelligence and deep learning could enhance individual recognition and behavioral analysis, potentially reducing reliance on chemical markers or implanted devices.

PMID:40110389 | PMC:PMC11920152 | DOI:10.3389/fnbeh.2025.1549666

Front Plant Sci. 2025 Mar 5;16:1538051. doi: 10.3389/fpls.2025.1538051. eCollection 2025.

ABSTRACT

The removal of non-tobacco related materials (NTRMs) is crucial for improving tobacco product quality and consumer safety. Traditional NTRM detection methods are labor-intensive and inefficient. This study proposes a novel approach for real-time NTRM detection using hyperspectral imaging (HSI) and an enhanced YOLOv8 model, named Dual-branch-YOLO-Tobacco (DBY-Tobacco). We created a dataset of 1,000 images containing 4,203 NTRMs by using a hyperspectral camera, SpectraEye (SEL-24), with a spectral range of 400-900 nm. To improve processing efficiency of HSIs data, three characteristic wavelengths (580nm, 680nm, and 850nm) were extracted by analyzing the weighted coefficients of the principal components. Then the pseudo color image fusion and decorrelation contrast stretch methods were applied for image enhancement. The DBY-Tobacco model features a dual-branch backbone network and a BiFPN-Efficient-Lighting-Feature-Pyramid-Network (BELFPN) module for effective feature fusion. Experimental results demonstrate that the DBY-Tobacco model achieves high performance metrics, including an F1 score of 89.7%, mAP@50 of 92.8%, mAP@50-95 of 73.7%, and a processing speed of 151 FPS, making it suitable for real-time applications in dynamic production environments. The study highlights the potential of combining HSI with advanced deep learning techniques for improving tobacco product quality and safety. Future work will focus on addressing limitations such as stripe noise in HSI and expanding the detection to other types of NTRMs. The dataset and code are available at: https://github.com/Ikaros-sc/DBY-Tobacco.

PMID:40110354 | PMC:PMC11921890 | DOI:10.3389/fpls.2025.1538051

Eur Heart J Digit Health. 2025 Jan 28;6(2):270-284. doi: 10.1093/ehjdh/ztaf005. eCollection 2025 Mar.

ABSTRACT

Intracoronary optical coherence tomography (OCT) is a valuable tool for, among others, periprocedural guidance of percutaneous coronary revascularization and the assessment of stent failure. However, manual OCT image interpretation is challenging and time-consuming, which limits widespread clinical adoption. Automated analysis of OCT frames using artificial intelligence (AI) offers a potential solution. For example, AI can be employed for automated OCT image interpretation, plaque quantification, and clinical event prediction. Many AI models for these purposes have been proposed in recent years. However, these models have not been systematically evaluated in terms of model characteristics, performances, and bias. We performed a systematic review of AI models developed for OCT analysis to evaluate the trends and performances, including a systematic evaluation of potential sources of bias in model development and evaluation.

PMID:40110224 | PMC:PMC11914731 | DOI:10.1093/ehjdh/ztaf005

Eur Heart J Digit Health. 2025 Feb 25;6(2):170-179. doi: 10.1093/ehjdh/ztae088. eCollection 2025 Mar.

ABSTRACT

AIMS: Sudden cardiac arrest (SCA) is a commonly fatal event that often occurs without prior indications. To improve outcomes and enable preventative strategies, the electrocardiogram (ECG) in conjunction with deep learning was explored as a potential screening tool.

METHODS AND RESULTS: A publicly available data set containing 10 s of 12-lead ECGs from individuals who did and did not have an SCA, information about time from ECG to arrest, and age and sex was utilized for analysis to individually predict SCA or not using deep convolution neural network models. The base model that included age and sex, ECGs within 1 day prior to arrest, and data sampled from windows of 720 ms around the R-waves from 221 individuals with SCA and 1046 controls had an area under the receiver operating characteristic curve of 0.77. With sensitivity set at 95%, base model specificity was 31%, which is not clinically applicable. Gradient-weighted class activation mapping showed that the model mostly relied on the QRS complex to make predictions. However, models with ECGs recorded between 1 day to 1 month and 1 month to 1 year prior to arrest demonstrated predictive capabilities.

CONCLUSION: Deep learning models processing ECG data are a promising means of screening for SCA, and this method explains differences in SCAs due to age and sex. Model performance improved when ECGs were nearer in time to SCAs, although ECG data up to a year prior had predictive value. Sudden cardiac arrest prediction was more dependent upon QRS complex data compared to other ECG segments.

PMID:40110219 | PMC:PMC11914729 | DOI:10.1093/ehjdh/ztae088

Eur Heart J Digit Health. 2025 Jan 16;6(2):209-217. doi: 10.1093/ehjdh/ztae097. eCollection 2025 Mar.

ABSTRACT

AIMS: Delayed diagnosis of pulmonary hypertension (PH) is a known cause of poor patient prognosis. We aimed to develop an artificial intelligence (AI) model, using ensemble learning method to detect PH using electrocardiography (ECG), chest X-ray (CXR), and brain natriuretic peptide (BNP), facilitating accurate detection and prompting further examinations.

METHODS AND RESULTS: We developed a convolutional neural network model using ECG data to predict PH, labelled by ECG from seven institutions. Logistic regression was used for the BNP prediction model. We referenced a CXR deep learning model using ResNet18. Outputs from each of the three models were integrated into a three-layer fully connected multimodal model. Ten cardiologists participated in an interpretation test, detecting PH from patients' ECG, CXR, and BNP data both with and without the ensemble learning model. The area under the receiver operating characteristic curves of the ECG, CXR, BNP, and ensemble learning model were 0.818 [95% confidence interval (CI), 0.808-0.828], 0.823 (95% CI, 0.780-0.866), 0.724 (95% CI, 0.668-0.780), and 0.872 (95% CI, 0.829-0.915). Cardiologists' average accuracy rates were 65.0 ± 4.7% for test without AI model and 74.0 ± 2.7% for test with AI model, a statistically significant improvement (P < 0.01).

CONCLUSION: Our ensemble learning model improved doctors' accuracy in detecting PH from ECG, CXR, and BNP examinations. This suggests that earlier and more accurate PH diagnosis is possible, potentially improving patient prognosis.

PMID:40110214 | PMC:PMC11914732 | DOI:10.1093/ehjdh/ztae097

Front Physiol. 2025 Mar 4;16:1518732. doi: 10.3389/fphys.2025.1518732. eCollection 2025.

ABSTRACT

INTRODUCTION: Understanding the hemodynamics of blood circulation is crucial to reveal the processes contributing to stenosis and atherosclerosis development.

METHOD: Computational fluid dynamics (CFD) facilitates this understanding by simulating blood flow patterns in coronary arteries. Nevertheless, applying CFD in fast-response scenarios presents challenge due to the high computational costs. To overcome this challenge, we integrate a deep learning (DL) method to improve efficiency and responsiveness. This study presents a DL approach for predicting Time-Averaged Wall Shear Stress (TAWSS) values in coronary arteries' bifurcation.

RESULTS: To prepare the dataset, 1800 idealized models with varying morphological parameters are created. Afterward, we design a CNN-based U-net architecture to predict TAWSS by the point cloud of the geometries. Moreover, this architecture is implemented using TensorFlow 2.3.0. Our results indicate that the proposed algorithms can generate results in less than one second, showcasing their suitability for applications in terms of computational efficiency.

DISCUSSION: Furthermore, the DL-based predictions demonstrate strong agreement with results from CFD simulations, with a normalized mean absolute error of only 2.53% across various cases.

PMID:40110184 | PMC:PMC11920710 | DOI:10.3389/fphys.2025.1518732

Front Artif Intell. 2025 Mar 5;8:1546398. doi: 10.3389/frai.2025.1546398. eCollection 2025.

ABSTRACT

Predicting Gross Domestic Product (GDP) is one of the most crucial tasks in analyzing a nation's economy and growth. The primary goal of this study is to forecast GDP using factors such as government spending, inflation, official development aid, remittance inflows, and Foreign Direct Investment (FDI). Additionally, the paper aims to provide an alternative perspective to Generative Adversarial Networks method and demonstrate how such deep learning technique can enhance the accuracy of GDP predictions with small data and economy like The Gambia. We proposed the implementation of Generative Adversarial Networks to predict GDP using various economic factors over the period from 1970 to 2022. Performance metrics, including the coefficient of determination R2, mean absolute error (MAE), mean absolute percentage error (MAPE), and root- mean-square error (RMSE) were collected to evaluate the system's accuracy. Among the models tested-Random Forest Regression (RF), XGBoost (XGB), and Support Vector Regression (SVR)-the Generative Adversarial Networks (GAN) model demonstrated superior performance, achieving the highest accuracy, which is 99% prediction accuracies. The most dependable model for capturing intricate correlations between GDP and its affecting components, however, RF and XGBoost, also achieved an accuracy of 98% each. This makes GAN the most desirable model for GDP prediction for our study. Through data analysis, this project aims to provide actionable insights to support strategies that sustain economic boom. This approach enables the generation of accurate GDP forecasts, offering a valuable tool for policymakers and stakeholders.

PMID:40110175 | PMC:PMC11920123 | DOI:10.3389/frai.2025.1546398

Front Res Metr Anal. 2025 Mar 5;10:1509502. doi: 10.3389/frma.2025.1509502. eCollection 2025.

ABSTRACT

OBJECTIVE: Literature-based Discovery (LBD) identifies new knowledge by leveraging existing literature. It exploits interconnecting implicit relationships to build bridges between isolated sets of non-interacting literatures. It has been used to facilitate drug repurposing, new drug discovery, and study adverse event reactions. Within the last decade, LBD systems have transitioned from using statistical methods to exploring deep learning (DL) to analyze semantic spaces between non-interacting literatures. Recent works explore knowledge graphs (KG) to represent explicit relationships. These works envision LBD as a knowledge graph completion (KGC) task and use DL to generate implicit relationships. However, these systems require the researcher to have domain-expert knowledge when submitting relevant queries for novel hypothesis discovery.

METHODS: Our method explores a novel approach to identify all implicit hypotheses given the researcher's search query and expedites the knowledge discovery process. We revise the KGC task as the task of predicting interconnecting vertex embeddings within the graph. We train our model using a similarity learning objective and compare our model's predictions against all known vertices within the graph to determine the likelihood of an implicit relationship (i.e., connecting edge). We also explore three approaches to represent edge connections between vertices within the KG: average, concatenation, and Hadamard. Lastly, we explore an approach to induce inductive biases and expedite model convergence (i.e., input representation scaling).

RESULTS: We evaluate our method by replicating five known discoveries within the Hallmark of Cancer (HOC) datasets and compare our method to two existing works. Our results show no significant difference in reported ranks and model convergence rate when comparing scaling our input representations and not using this method. Comparing our method to previous works, we found our method achieves optimal performance on two of five datasets and achieves comparable performance on the remaining datasets. We further analyze our results using statistical significance testing to demonstrate the efficacy of our method.

CONCLUSION: We found our similarity-based learning objective predicts linking vertex embeddings for single relationship closed discovery replication. Our method also provides a ranked list of linking vertices between a set of inputs. This approach reduces researcher burden and allows further exploration of generated hypotheses.

PMID:40110121 | PMC:PMC11920161 | DOI:10.3389/frma.2025.1509502

ACS Med Chem Lett. 2025 Feb 10;16(3):410-419. doi: 10.1021/acsmedchemlett.4c00511. eCollection 2025 Mar 13.

ABSTRACT

AXL, part of the TAM receptor tyrosine kinase family, plays a significant role in the growth and survival of various tissues and tumors, making it a critical target for cancer therapy. This study introduces a novel high-throughput virtual screening (HTVS) methodology that merges an AI-enhanced graph neural network, PLANET, with a geometric deep learning algorithm, DeepDock. Using this approach, we identified potent AXL inhibitors from our database. Notably, compound 9, with an IC50 of 9.378 nM, showed excellent inhibitory activity, suggesting its potential as a candidate for further research. We also performed molecular dynamics simulations to explore the interactions between compound 9 and AXL, providing insights for future enhancements. This hybrid screening method proves effective in finding promising AXL inhibitors, and advancing the development of new cancer therapies.

PMID:40110119 | PMC:PMC11921171 | DOI:10.1021/acsmedchemlett.4c00511

J Dent. 2025 Mar 17:105690. doi: 10.1016/j.jdent.2025.105690. Online ahead of print.

ABSTRACT

OBJECTIVES: The graded diagnosis of periodontitis has always been a difficulty for dentists. This systematic review aimed to investigate the performance of artificial intelligence (AI) models for periodontitis classification.

DATA: This review includes original studies that explore the application of AI in periodontitis classification systems.

SOURCES: Two reviewers independently conducted a comprehensive search of literature published up to April 2024 in databases including PubMed, Web of Science, MEDLINE, Scopus, and Cochrane Library.

STUDY SELECTION: A total of 28 articles were eventually included in this study, from which 10 mapping parameters were extracted and evaluated separately for each article.

RESULTS: AI's diagnostic capabilities are comparable to those of a general dentist/periodontist, achieving an overall diagnostic accuracy rate of over 70% for periodontitis classification, with some reaching 80-90%. Variations in diagnosis accuracy rates were observed across different stages of periodontitis.

CONCLUSIONS: The AI model provides a novel and relatively reliable method for periodontitis classification. However, several key issues remain to be addressed, including access to and quality of data, interpretation of the decision-making process of the model, the ability of the model to generalize, and ethical and privacy considerations.

CLINICAL SIGNIFICANCE: The development of AI models for periodontitis classification is expected to assist dentists in improving diagnostic efficiency and enhancing diagnostic accuracy, and further development is expected to assist telemedicine and home self-testing.

PMID:40107599 | DOI:10.1016/j.jdent.2025.105690