Commun Biol. 2025 Feb 5;8(1):181. doi: 10.1038/s42003-025-07570-6.

ABSTRACT

Oligodendrocytes are the myelinating cells within the central nervous system, but the mechanisms by which transcription factors (TFs) cooperate for gene regulation in oligodendrocytes remain unclear. We introduce coTF-reg, an analytical framework that integrates scRNA-seq and scATAC-seq data to identify cooperative TFs co-regulating the target gene (TG). First, we identify co-binding TF pairs in the same oligodendrocyte-specific regulatory regions. Next, we train a deep learning model to predict each TG expression using the co-binding TFs' expressions. Shapley interaction scores reveal high interactions between co-binding TF pairs, such as SOX10-TCF12. Validation using oligodendrocyte eQTLs and their eGenes that are regulated by these cooperative TFs show potential regulatory roles for genetic variants. Experimental validation using ChIP-seq data confirms some cooperative TF pairs, such as SOX10-OLIG2. Prediction performance of our models is evaluated through holdout data and additional datasets, and an ablation study is also conducted. The results demonstrate stable and consistent performance.

PMID:39910206 | DOI:10.1038/s42003-025-07570-6

J Med Internet Res. 2025 Feb 5;27:e62647. doi: 10.2196/62647.

ABSTRACT

BACKGROUND: Alzheimer disease (AD) is a progressive condition characterized by cognitive decline and memory loss. Vision transformers (ViTs) are emerging as promising deep learning models in medical imaging, with potential applications in the detection and diagnosis of AD.

OBJECTIVE: This review systematically examines recent studies on the application of ViTs in detecting AD, evaluating the diagnostic accuracy and impact of network architecture on model performance.

METHODS: We conducted a systematic search across major medical databases, including China National Knowledge Infrastructure, CENTRAL (Cochrane Central Register of Controlled Trials), ScienceDirect, PubMed, Web of Science, and Scopus, covering publications from January 1, 2020, to March 1, 2024. A manual search was also performed to include relevant gray literature. The included papers used ViT models for AD detection versus healthy controls based on neuroimaging data, and the included studies used magnetic resonance imaging and positron emission tomography. Pooled diagnostic accuracy estimates, including sensitivity, specificity, likelihood ratios, and diagnostic odds ratios, were derived using random-effects models. Subgroup analyses comparing the diagnostic performance of different ViT network architectures were performed.

RESULTS: The meta-analysis, encompassing 11 studies with 95% CIs and P values, demonstrated pooled diagnostic accuracy: sensitivity 0.925 (95% CI 0.892-0.959; P<.01), specificity 0.957 (95% CI 0.932-0.981; P<.01), positive likelihood ratio 21.84 (95% CI 12.26-38.91; P<.01), and negative likelihood ratio 0.08 (95% CI 0.05-0.14; P<.01). The area under the curve was notably high at 0.924. The findings highlight the potential of ViTs as effective tools for early and accurate AD diagnosis, offering insights for future neuroimaging-based diagnostic approaches.

CONCLUSIONS: This systematic review provides valuable evidence for the utility of ViT models in distinguishing patients with AD from healthy controls, thereby contributing to advancements in neuroimaging-based diagnostic methodologies.

TRIAL REGISTRATION: PROSPERO CRD42024584347; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=584347.

PMID:39908541 | DOI:10.2196/62647

J Chem Inf Model. 2025 Feb 5. doi: 10.1021/acs.jcim.4c01876. Online ahead of print.

ABSTRACT

Researchers are developing increasingly robust molecular representations, motivating the need for thorough methods to stress-test and validate them. Here, we use a variational auto-encoder (VAE), an unsupervised deep learning model, to generate anomalous examples of SELF-referencIng Embedded Strings (SELFIES), a popular molecular string format. These anomalies defy the assertion that all SELFIES convert into valid SMILES strings. Interestingly, we find specific regions within the VAE's internal landscape (latent space), whose decoding frequently generates inconvertible SELFIES anomalies. The model's internal landscape self-organization helps with exploring factors affecting molecular representation reliability. We show how VAEs and similar anomaly generation methods can empirically stress-test molecular representation robustness. Additionally, we investigate reasons for the invalidity of some discovered SELFIES strings (version 2.1.1) and suggest changes to improve them, aiming to spark ongoing molecular representation improvement.

PMID:39908426 | DOI:10.1021/acs.jcim.4c01876

PLoS One. 2025 Feb 5;20(2):e0316569. doi: 10.1371/journal.pone.0316569. eCollection 2025.

ABSTRACT

Drum roller surface defect detection is of great research significance for control production quality. Aiming at solving the problems that the traditional light source visual imaging system, which does not clearly reflect defect features, the defect detection efficiency is low, and the accuracy is not enough, this paper designs an image acquisition system based on line fringe structured light and proposes an improved deep learning network model based on YOLOv8n to achieve efficient detection of defects on the rolling surface of a drum roller. In the aspect of image acquisition, this paper selected the line fringe structured light as the system light source, which made up for the problem that the traditional light source does not reflect the defect characteristics. In terms of algorithms, firstly, using deformable convolution instead of standard convolution to enhance the feature extraction ability of the backbone network. Then, a new feature fusion module was proposed to enable the fusion network to learn additional original information. Finally, Wise-IoU was applied to replace CIoU in the loss function, so that the network pays more attention to the high-quality samples. The experimental results show that the improved YOLOv8n algorithm has a certain improvement in detection accuracy. The main average accuracy (mAP) is 97.2%, and the detection time is 4.3ms. The system and algorithm designed in this paper can better ensure the production quality of drum rollers. While effective, the model's standard rectangular bounding boxes may limit precision for elongated defects. Future work could explore rotated bounding boxes and broader dataset diversity to enhance generalization in real-world applications.

PMID:39908278 | DOI:10.1371/journal.pone.0316569

Med Biol Eng Comput. 2025 Feb 5. doi: 10.1007/s11517-025-03291-4. Online ahead of print.

ABSTRACT

Breast cancer affects a significant number of patients worldwide, and early diagnosis is critical for improving cure rates and prognosis. Deep learning-based breast cancer classification algorithms have substantially alleviated the burden on medical personnel. However, existing breast cancer diagnosis models face notable limitations which are challenging to obtain in clinical settings, such as reliance on a large volume of labeled samples, an inability to comprehensively extract features from breast cancer images, and susceptibility to overfitting on account of imbalanced class distribution. Therefore, we propose the class-aware multi-level attention learning model focused on semi-supervised breast cancer diagnosis to effectively reduce the dependency on extensive data annotation. Additionally, we develop the multi-level fusion attention learning module, which integrates multiple mutual attention components across different layers, allowing the model to precisely identify critical regions for lesion categorization. Finally, we design the class-aware adaptive pseudo-labeling module which adaptively predicts category distribution in unlabeled data, and directs the model to focus on underrepresented categories, ensuring a balanced learning process. Experimental results on the BACH dataset demonstrate that our proposed model achieves an accuracy of 86.7% with only 40% labeled microscopic data, showcasing its outstanding contribution to semi-supervised breast cancer diagnosis.

PMID:39907850 | DOI:10.1007/s11517-025-03291-4

Eur J Nucl Med Mol Imaging. 2025 Feb 5. doi: 10.1007/s00259-025-07117-1. Online ahead of print.

ABSTRACT

INTRODUCTION: Providing tools for comprehensively evaluating scintigraphy images could enhance transthyretin amyloid cardiomyopathy (ATTR-CM) diagnosis. This study aims to automatically detect and score ATTR-CM in total body scintigraphy images using deep learning on multi-tracer, multi-scanner, and multi-center datasets.

METHODS: In the current study, we employed six datasets (from 12 cameras) for various tasks and purposes. Dataset #1 (93 patients, 99mTc-MDP) was used to develop the 2D-planar segmentation and localization models. Dataset #2 (216 patients, 99mTc-DPD) was used for the detection (grade 0 vs. grades 1, 2, and 3) and scoring (0 and 1 vs. grades 2 and 3) of ATTR-CM. Datasets #3 (41 patients, 99mTc-HDP), #4 (53 patients, 99mTc-PYP), and #5 (129 patients, 99mTc-DPD) were used as external centers. ATTR-CM detection and scouring were performed by two physicians in each center. Moreover, Dataset #6 consisting of 3215 patients without labels, was employed for retrospective model performance evaluation. Different regions of interest were cropped and fed into the classification model for the detection and scoring of ATTR-CM. Ensembling was performed on the outputs of different models to improve their performance. Model performance was measured by classification accuracy, sensitivity, specificity, and AUC. Grad-CAM and saliency maps were generated to explain the models' decision-making process.

RESULTS: In the internal test set, all models for detection and scoring achieved an AUC of more than 0.95 and an F1 score of more than 0.90. For detection in the external dataset, AUCs of 0.93, 0.95, and 1 were achieved for datasets 3, 4, and 5, respectively. For the scoring task, AUCs of 0.95, 0.83, and 0.96 were achieved for these datasets, respectively. In dataset #6, we found ten cases flagged as ATTR-CM by the network. Out of these, four cases were confirmed by a nuclear medicine specialist as possibly having ATTR-CM. GradCam and saliency maps showed that the deep-learning models focused on clinically relevant cardiac areas.

CONCLUSION: In the current study, we developed and evaluated a fully automated pipeline to detect and score ATTR-CM using large multi-tracer, multi-scanner, and multi-center datasets, achieving high performance on total body images. This fully automated pipeline could lead to more timely and accurate diagnoses, ultimately improving patient outcomes.

PMID:39907796 | DOI:10.1007/s00259-025-07117-1

Eur Radiol. 2025 Feb 5. doi: 10.1007/s00330-025-11406-6. Online ahead of print.

ABSTRACT

OBJECTIVES: The aim of this work is to evaluate the performance of deep learning (DL) models for breast cancer diagnosis with MRI.

MATERIALS AND METHODS: A literature search was conducted on Web of Science, PubMed, and IEEE Xplore for relevant studies published from January 2015 to February 2024. The study was registered with the PROSPERO International Prospective Register of Systematic Reviews (protocol no. CRD42024485371). The quality assessment of diagnostic accuracy studies-2 (QUADAS2) tool and the Must AI Criteria-10 (MAIC-10) checklist were used to assess quality and risk of bias. The meta-analysis included studies reporting DL for breast cancer diagnosis and their performance, from which pooled summary estimates for the area under the curve (AUC), sensitivity, and specificity were calculated.

RESULTS: A total of 40 studies were included, of which only 21 were eligible for quantitative analysis. Convolutional neural networks (CNNs) were used in 62.5% (25/40) of the implemented models, with the remaining 37.5% (15/40) hybrid composite models (HCMs). The pooled estimates of AUC, sensitivity, and specificity were 0.90 (95% CI: 0.87, 0.93), 88% (95% CI: 86, 91%), and 90% (95% CI: 87, 93%), respectively.

CONCLUSIONS: DL models used for breast cancer diagnosis on MRI achieve high performance. However, there is considerable inherent variability in this analysis. Therefore, continuous evaluation and refinement of DL models is essential to ensure their practicality in the clinical setting.

KEY POINTS: Question Can DL models improve diagnostic accuracy in breast MRI, addressing challenges like overfitting and heterogeneity in study designs and imaging sequences? Findings DL achieved high diagnostic accuracy (AUC 0.90, sensitivity 88%, specificity 90%) in breast MRI, with training size significantly impacting performance metrics (p < 0.001). Clinical relevance DL models demonstrate high accuracy in breast cancer diagnosis using MRI, showing the potential to enhance diagnostic confidence and reduce radiologist workload, especially with larger datasets minimizing overfitting and improving clinical reliability.

PMID:39907762 | DOI:10.1007/s00330-025-11406-6

Radiol Artif Intell. 2025 Feb 5:e240039. doi: 10.1148/ryai.240039. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate cancer detection and marker placement accuracy of two artificial intelligence (AI) models developed for interpretation of screening mammograms. Materials and Methods This retrospective study included data from 129 434 screening examinations (all female, mean age 59.2, SD = 5.8) performed between January 2008 and December 2018 in BreastScreen Norway. Model A was commercially available and B was an in-house model. Area under the receiver operating characteristic curve (AUC) with 95% confidence interval (CIs) were calculated. The study defined 3.2% and 11.1% of the examinations with the highest AI scores as positive, threshold 1 and 2, respectively. A radiologic review assessed location of AI markings and classified interval cancers as true or false negative. Results The AUC was 0.93 (95% CI: 0.92-0.94) for model A and B when including screen-detected and interval cancers. Model A identified 82.5% (611/741) of the screen-detected cancers at threshold 1 and 92.4% (685/741) at threshold 2. For model B, the numbers were 81.8% (606/741) and 93.7% (694/741), respectively. The AI markings were correctly localized for all screen-detected cancers identified by both models and 82% (56/68) of the interval cancers for model A and 79% (54/68) for B. At the review, 21.6% (45/208) of the interval cancers were identified at the preceding screening by either or both models, correctly localized and classified as false negative (n = 17) or with minimal signs of malignancy (n = 28). Conclusion Both AI models showed promising performance for cancer detection on screening mammograms. The AI markings corresponded well to the true cancer locations. ©RSNA, 2025.

PMID:39907587 | DOI:10.1148/ryai.240039

Radiol Artif Intell. 2025 Feb 5:e240167. doi: 10.1148/ryai.240167. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate the performance of Physics-Informed Autoencoder (PIA), a self-supervised deep learning model, in measuring tissue-based biomarkers for prostate cancer (PCa) using hybrid multidimensional MRI. Materials and Methods This retrospective study introduces PIA, a novel self-supervised deep learning model that integrates a three-compartment diffusion-relaxation model with hybrid multidimensional MRI. PIA was trained to encode the biophysical model into a deep neural network to predict measurements of tissue-specific biomarkers for PCa without extensive training data requirements. Comprehensive in-silico and in-vivo experiments, using histopathology measurements as the reference standard, were conducted to validate the model's efficacy in comparison to the traditional Non-Linear Least Squares (NLLS) algorithm. PIA's robustness to noise was tested in in-silico experiments with varying signal-to-noise ratio (SNR) conditions, and in-vivo performance for estimating volume fractions was evaluated in 21 patients (mean age 60 (SD:6.6) years; all male) with PCa (n = 71 regions of interest). Evaluation metrics included the intraclass correlation coefficient (ICC) and Pearson correlation coefficient. Results PIA predicted the reference standard tissue parameters with high accuracy, outperforming conventional NLLS methods, especially under noisy conditions (rs = 0.80 versus 0.65, P < .001 for epithelium volume at SNR = 20:1). In in-vivo validation, PIA's noninvasive volume fraction estimates matched quantitative histology (ICC = 0.94, 0.85 and 0.92 for epithelium, stroma, and lumen compartments, respectively, P < .001 for all). PIA's measurements strongly correlated with PCa aggressiveness (r = 0.75, P < .001). Furthermore, PIA ran 10,000 faster than NLLS (0.18 seconds versus 40 minutes per image). Conclusion PIA provided accurate prostate tissue biomarker measurements from MRI data with better robustness to noise and computational efficiency compared with the NLLS algorithm. The results demonstrate the potential of PIA as an accurate, noninvasive, and explainable AI method for PCa detection. ©RSNA, 2025.

PMID:39907585 | DOI:10.1148/ryai.240167

Int J Neural Syst. 2025 Feb 4:2550014. doi: 10.1142/S0129065725500145. Online ahead of print.

ABSTRACT

Cross-user variability is a well-known challenge that leads to severe performance degradation and impacts the robustness of practical myoelectric control systems. To address this issue, a novel method for myoelectric recognition of finger movement patterns is proposed by incorporating a neural decoding approach with unsupervised domain adaption (UDA) learning. In our method, the neural decoding approach is implemented by extracting microscopic features characterizing individual motor unit (MU) activities obtained from a two-stage online surface electromyogram (SEMG) decomposition. A specific deep learning model is designed and initially trained using labeled data from a set of existing users. The model can update adaptively when recognizing the movement patterns of a new user. The final movement pattern was determined by a fuzzy weighted decision strategy. SEMG signals were collected from the finger extensor muscles of 15 subjects to detect seven dexterous finger-movement patterns. The proposed method achieved a movement pattern recognition accuracy of ([Formula: see text])% over seven movements under cross-user testing scenarios, much higher than that of the conventional methods using global SEMG features. Our study presents a novel robust myoelectric pattern recognition approach at a fine-grained MU level, with wide applications in neural interface and prosthesis control.

PMID:39907499 | DOI:10.1142/S0129065725500145

Laryngoscope. 2025 Feb 5. doi: 10.1002/lary.32036. Online ahead of print.

ABSTRACT

OBJECTIVE: To develop and validate a deep-learning classifier trained on voice data extracted from videolaryngostroboscopy recordings, differentiating between three different vocal fold (VF) states: healthy (HVF), unilateral paralysis (UVFP), and VF lesions, including benign and malignant pathologies.

METHODS: Patients with UVFP (n = 105), VF lesions (n = 63), and HVF (n = 41) were retrospectively identified. Voice samples were extracted from stroboscopic videos (Pentax Laryngeal Strobe Model 9400), including sustained /i/ phonation, pitch glide, and /i/ sniff task. Extracted audio files were converted into Mel-spectrograms. Voice samples were independently divided into training (80%), validation (10%), and test (10%) by patient. Pretrained ResNet18 models were trained to classify (1) HVF and pathological VF (lesions and UVFP), and (2) HVF, UVFP, and VF lesions. Both classifiers were further validated on an external dataset consisting of 12 UVFP, 13 VF lesions, and 15 HVF patients. Model performances were evaluated by accuracy and F1-score.

RESULTS: When evaluated on a hold-out test set, the binary classifier demonstrated stronger performance compared to the multi-class classifier (accuracy 83% vs. 40%; F1-score 0.90 vs. 0.36). When evaluated on an external dataset, the binary classifier achieved an accuracy of 63% and F1-score of 0.48, compared to 35% and 0.25 for the multi-class classifier.

CONCLUSIONS: Deep-learning classifiers differentiating HVF, UVFP, and VF lesions were developed using voice data from stroboscopic videos. Although healthy and pathological voice were differentiated with moderate accuracy, multi-class classification lowered model performance. The model performed poorly on an external dataset. Voice captured in stroboscopic videos may have limited diagnostic value, though further studies are needed.

LEVEL OF EVIDENCE: 4 Laryngoscope, 2025.

PMID:39907244 | DOI:10.1002/lary.32036

NMR Biomed. 2025 Mar;38(3):e70002. doi: 10.1002/nbm.70002.

ABSTRACT

The purpose of this study was to accelerate MR cholangiopancreatography (MRCP) acquisitions using deep learning-based (DL) reconstruction at 3 and 0.55 T. A total of 35 healthy volunteers underwent conventional twofold accelerated MRCP scans at field strengths of 3 and 0.55 T. We trained DL reconstructions using two different training strategies, supervised (SV) and self-supervised (SSV), with retrospectively sixfold undersampled data obtained at 3 T. We then evaluated the DL reconstructions against standard techniques, parallel imaging (PI) and compressed sensing (CS), focusing on peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) as metrics. We also tested DL reconstructions with prospectively accelerated acquisitions and evaluated their robustness when changing fields strengths from 3 to 0.55 T. DL reconstructions demonstrated a reduction in average acquisition time from 599/542 to 255/180 s for MRCP at 3 T/0.55 T. In both retrospective and prospective undersampling, PSNR and SSIM of DL reconstructions were higher than those of PI and CS. At the same time, DL reconstructions preserved the image quality of undersampled data, including sharpness and the visibility of hepatobiliary ducts. In addition, both DL approaches produced high-quality reconstructions at 0.55 T. In summary, DL reconstructions trained for highly accelerated MRCP enabled a reduction in acquisition time by a factor of 2.4/3.0 at 3 T/0.55 T while maintaining the image quality of conventional acquisitions.

PMID:39907193 | DOI:10.1002/nbm.70002

Anal Chem. 2025 Feb 5. doi: 10.1021/acs.analchem.4c05046. Online ahead of print.

ABSTRACT

Artificial intelligence (AI), especially through the development of deep learning techniques like convolutional neural networks (CNNs), has revolutionized numerous fields. CNNs, introduced by Yann LeCun in the 1990s (Hubbard, W.; Jackel, L. D. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput. 1989, 1 (4), 541- 551. https://doi.org/10.1162/neco.1989.1.4.541), have found applications in healthcare for medical diagnostics, autonomous vehicles in transportation, stock market prediction in finance, and image recognition in computer vision to name just a few. Similarly, in analytical chemistry, deep learning has enhanced data analysis from techniques like MS spectrometry, NMR, fluorescence spectroscopy, and chromatography. Another AI branch, Natural Language Processing (NLP), has surged recently with the advent of Large Language Models (LLMs), such as OpenAI's ChatGPT. This paper demonstrates the application of an LLM via a smartphone to conduct multivariate data analyses, in an interactive conversational manner, of a hyper-spectral imaging data set from laser-induced breakdown spectroscopy (LIBS). We demonstrate the potential of LLMs to process and analyze data sets, which automatically generate and execute code in response to user queries, and anticipate their growing role in the future of analytical chemistry.

PMID:39907023 | DOI:10.1021/acs.analchem.4c05046

Health Data Sci. 2025 Feb 4;5:0221. doi: 10.34133/hds.0221. eCollection 2025.

ABSTRACT

Background: The electrocardiogram (ECG) is a valuable, noninvasive tool for monitoring heart-related conditions, providing critical insights. However, the interpretation of ECG data alongside patient information demands substantial medical expertise and resources. While deep learning methods help streamline this process, they often fall short in integrating patient data with ECG readings and do not provide the nuanced clinical suggestions and insights necessary for accurate diagnosis. Methods: Although recent advancements in multi-modal large language modeling have propelled their application scope beyond the natural language processing domain, their applicability to ECG processing remains largely unexplored, partly due to the lack of text-ECG data. To this end, we develop ECG-Language Model (ECG-LM), the first multi-modal large language model able to process natural language and understand ECG signals. The model employs a specialized ECG encoder that transforms raw ECG signals into a high-dimensional feature space, which is then aligned with the textual feature space derived from the large language model. To address the scarcity of text-ECG data, we generated text-ECG pairs by leveraging detailed ECG pattern descriptions from medical guidelines, creating a robust dataset for pre-training ECG-LM. Additionally, we fine-tune ECG-LM with public clinical conversation datasets and build an additional supervised fine-tuning dataset based on real clinical data from the hospital, aiming to provide a more comprehensive and customized user experience. Results: ECG-LM outperforms existing few-shot and zero-shot solutions in cardiovascular disease detection across all 3 tasks (diagnostic, rhythm, and form) while also demonstrating strong potential in ECG-related question answering. Conclusions: The results across various tasks demonstrate that ECG-LM effectively captures the intricate features of ECGs, showcasing its versatility in applications such as disease prediction and advanced question answering.

PMID:39906894 | PMC:PMC11791404 | DOI:10.34133/hds.0221

Heliyon. 2025 Jan 15;11(2):e41974. doi: 10.1016/j.heliyon.2025.e41974. eCollection 2025 Jan 30.

ABSTRACT

This systematic review examines the application of artificial intelligence (AI), including machine learning (ML) and deep learning (DL), for climate change adaptation and mitigation in Iran, Pakistan, and Turkey. These three nations-key Economic Cooperation Organization (ECO) members and a nexus between Europe and South Asia-are experiencing diverse environmental challenges due to varying climatic conditions. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we conducted a comprehensive search in the Scopus database, ultimately identifying 76 relevant articles out of an initial 492. Although some articles utilized multiple techniques, classical ML methods appeared in approximately 37.3 % of the studies, neural network paradigms in about 57.5 %, and optimization or meta-heuristic algorithms in around 5.0 %. Regarding thematic focus, about 33.3 % of the articles addressed water resource management, 22.2 % focused on climate prediction, 11.1 % on land and agriculture, 9 % on ecosystem modeling, and 24.2 % on natural disaster preparedness and response. The analysis reveals a growing but uneven body of research utilizing AI across the ECO countries. By highlighting successful applications, identifying key gaps-such as limited cross-border collaboration and inconsistent data availability-and proposing a framework for more integrated research, this review aims to guide future initiatives that leverage AI's potential to improve climate resilience and sustainability in the region.

PMID:39906868 | PMC:PMC11791260 | DOI:10.1016/j.heliyon.2025.e41974

Heliyon. 2025 Jan 16;11(2):e41973. doi: 10.1016/j.heliyon.2025.e41973. eCollection 2025 Jan 30.

ABSTRACT

Coronary artery disease (CAD) is a leading cause of global mortality, often involving the development of atherosclerotic plaques in coronary arteries, particularly at bifurcation sites. Percutaneous coronary intervention (PCI) of bifurcation lesions presents challenges, necessitating accurate assessment of hemodynamic parameters such as wall shear stress (WSS) and oscillatory shear index (OSI) to predict acute coronary syndrome (ACS) risk. Computational fluid dynamics (CFD) provides valuable insights but is computationally intensive, prompting exploration of machine learning (ML) models for efficient hemodynamics prediction. This study aims to bridge the gap in understanding the influence of stenosis severity and location on hemodynamics in the left coronary artery (LCA) bifurcation by integrating ML algorithms with comprehensive CFD simulations, thereby enhancing non-invasive prediction of complex hemodynamics. An extensive dataset of 6858 synthetic LCA geometries with varying plaque severities and locations was generated for analysis. Hemodynamic parameters (TAWSS and OSI) were computed using CFD simulations and utilized for ML model training. Fourteen ML algorithms were employed for regression analysis, and their performance was evaluated using multiple metrics. The Decision Tree Regressor and K Nearest Neighbors models demonstrated the most effective prediction of TAWSS and OSI parameters, aligning well with CFD simulation results. The Decision Tree Regressor showed minimal prediction discrepancies (TAWSS: R2 = 0.998952, MAE = 0.000587, RMSE = 0.001626; OSI: R2 = 0.961977, MAE = 0.022264, RMSE = 0.041411) offering rapid and reliable assessments of hemodynamic conditions in the LCA bifurcation. Integration of ML algorithms with comprehensive CFD simulations provides a promising approach to enhance the non-invasive prediction of complex hemodynamics in the LCA bifurcation. The ability to efficiently predict hemodynamic parameters could significantly aid medical practitioners in time-sensitive clinical settings, offering valuable insights for coronary artery disease management. Further research is warranted to evaluate the effectiveness of deep learning models and address challenges in patient-specific applications.

PMID:39906857 | PMC:PMC11791239 | DOI:10.1016/j.heliyon.2025.e41973

Heliyon. 2025 Jan 13;11(2):e41835. doi: 10.1016/j.heliyon.2025.e41835. eCollection 2025 Jan 30.

ABSTRACT

BACKGROUND: Machine learning has tremendous potential in acute medical care, particularly in the field of precise medical diagnosis, prediction, and classification of brain tumors. Malignant gliomas, due to their aggressive growth and dismal prognosis, stand out among various brain tumor types. Recent advancements in understanding the genetic abnormalities that underlie these tumors have shed light on their histo-pathological and biological characteristics, which support in better classification and prognosis.

OBJECTIVES: This review aims to predict gene alterations and establish structured correlations among various tumor types, extending the prediction of genetic mutations and structures using the latest machine learning techniques. Specifically, it focuses on multi-modalities of Magnetic Resonance Imaging (MRI) and histopathology, utilizing Convolutional Neural Networks (CNN) for image processing and analysis.

METHODS: The review encompasses the most recent developments in MRI, and histology image processing methods across multiple tumor classes, including Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma. It identifies challenges in tumor classification, segmentation, datasets, and modalities, employing various neural network architectures. A competitive analysis assesses the performance of CNN. Furthermore it also implies K-MEANS clustering to predict Genetic structure, Genes Clusters prediction and Molecular Alteration of various types and grades of tumors e.g. Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma.

RESULTS: CNN and KNN structures, with their ability to extract highlights in image-based information, prove effective in tumor classification and segmentation, surmounting challenges in image analysis. Competitive analysis reveals that CNN and outperform others algorithms on publicly available datasets, suggesting their potential for precise tumor diagnosis and treatment planning.

CONCLUSION: Machine learning, especially through CNN and SVM algorithms, demonstrates significant potential in the accurate diagnosis and classification of brain tumors based on imaging and histo-pathological data. Further advancements in this area hold promise for improving the accuracy and efficiency of intra-operative tumor diagnosis and treatment.

PMID:39906822 | PMC:PMC11791217 | DOI:10.1016/j.heliyon.2025.e41835

Heliyon. 2025 Jan 17;11(2):e41779. doi: 10.1016/j.heliyon.2025.e41779. eCollection 2025 Jan 30.

ABSTRACT

Falling from height (FFH) is a major cause of injuries and fatalities on construction sites. Research has emphasized the role of technological advances in managing FFH safety risks. In this investigation, the objective is to forecast if a laborer is operating at an elevated position by utilizing an accelerometer, gyroscope, and pressure information through the application of deep-learning techniques. The study involved analyzing worker data to quickly implement safety measures for working at heights. A total of 45 analyses were conducted using DNN, CNN, and LSTM deep-learning models, with 5 different window sizes and 3 different overlap rates. The analysis revealed that the DNN model, utilizing a 1-s window size and a 75 % overlap rate, attained an accuracy of 94.6 % with a loss of 0.1445. Conversely, the CNN model, employing a 5-s window size and a 75 % overlap rate, demonstrated an accuracy of 94.9 % with a loss of 0.1696. The results of this study address information gaps by efficiently predicting workers' working conditions at heights without the need for complex calculations. By implementing this method at construction sites, it is expected to reduce the risk of FFH and align occupational health and safety practices with technological advancements.

PMID:39906815 | PMC:PMC11791131 | DOI:10.1016/j.heliyon.2025.e41779

Heliyon. 2025 Jan 20;11(2):e42119. doi: 10.1016/j.heliyon.2025.e42119. eCollection 2025 Jan 30.

ABSTRACT

Motion disorders affect a significant portion of the global population. While some symptoms can be managed with medications, these treatments often impact all muscles uniformly, not just the affected ones, leading to potential side effects including involuntary movements, confusion, and decreased short-term memory. Currently, there is no dedicated application for differentiating healthy muscles from abnormal ones. Existing analysis applications, designed for other purposes, often lack essential software engineering features such as a user-friendly interface, infrastructure independence, usability and learning ability, cloud computing capabilities, and AI-based assistance. This research proposes a computer-based methodology to analyze human motion and differentiate between healthy and unhealthy muscles. First, an IoT-based approach is proposed to digitize human motion using smartphones instead of hardly accessible wearable sensors and markers. The motion data is then simulated to analyze the neuromusculoskeletal system. An agent-driven modeling method ensures the naturalness, accuracy, and interpretability of the simulation, incorporating neuromuscular details such as Henneman's size principle, action potentials, motor units, and biomechanical principles. The results are then provided to medical and clinical experts to aid in differentiating between healthy and unhealthy muscles and for further investigation. Additionally, a deep learning-based ensemble framework is proposed to assist in the analysis of the simulation results, offering both accuracy and interpretability. A user-friendly graphical interface enhances the application's usability. Being fully cloud-based, the application is infrastructure-independent and can be accessed on smartphones, PCs, and other devices without installation. This strategy not only addresses the current challenges in treating motion disorders but also paves the way for other clinical simulations by considering both scientific and computational requirements.

PMID:39906796 | PMC:PMC11791118 | DOI:10.1016/j.heliyon.2025.e42119

Cureus. 2025 Feb 2;17(2):e78388. doi: 10.7759/cureus.78388. eCollection 2025 Feb.

ABSTRACT

This study evaluates the efficiency and dosimetric performance of RatoGuide, an artificial intelligence (AI)-assisted radiotherapy planning tool, by comparing AI-generated and manually created treatment plans for a 50-year-old male with right-sided oropharyngeal cancer (cT2N2bM0, cStage IVA) who underwent concurrent chemoradiotherapy. Treatment plans were created using volumetric-modulated arc therapy (VMAT) following the approach used by the Japanese Clinical Oncology Group (JCOG) protocol. RatoGuide generated two plans: one prioritizing the planning target volume (PTV) and the other focusing on organs at risk (OAR), while an experienced radiation oncologist manually developed a plan using a treatment planning system (TPS). Dosimetric comparisons focused on target coverage, OAR sparing, and dose homogeneity. Results showed that both AI-generated and TPS plans achieved comparable PTV coverage, with nearly identical values for Dmin, Dmean, and Dmax. The TPS plan exhibited slightly better dose homogeneity, whereas the AI-generated plan provided superior OAR sparing, particularly for the spinal cord and parotid glands, reducing the spinal cord's intermediate-dose volume (V30) by approximately 40%. However, the AI plan yielded slightly higher mean doses to both submandibular glands, though still within clinically acceptable thresholds. Additionally, the AI planning workflow was completed in just 30 minutes, significantly reducing the time required for manual planning. RatoGuide demonstrated efficiency in generating high-quality treatment plans, achieving comparable PTV coverage, and improving OAR sparing in certain areas. However, minor refinements are needed to optimize dose homogeneity and further minimize submandibular gland exposure. These findings suggest that AI-assisted planning has the potential to enhance radiotherapy efficiency and consistency.

PMID:39906643 | PMC:PMC11793990 | DOI:10.7759/cureus.78388