Sci Rep. 2025 Feb 14;15(1):5449. doi: 10.1038/s41598-025-88551-x.

ABSTRACT

Opportunistic computed tomography (CT) scans, which can assess relevant bones of interest, offer a potential solution for identifying osteoporotic individuals. However, it has been well documented that image protocol parameters, such as reconstruction kernel, impact the quantitative analysis of volumetric bone mineral density (vBMD) from CT scans. The purpose of this study was to investigate the impact that CT reconstruction kernels have on quantitative results for vBMD from clinical CT scans using phantom and internal calibration. 45 clinical CT scans were reconstructed using the standard kernel and seven alternative kernels: soft, chest, detail, edge, bone, bone plus and lung [GE HealthCare]. Two methods of image calibration, internal and phantom, were used to calibrate the scans. The total hip and fourth lumbar vertebra (L4) were extracted from the scans via deep learning segmentation. Integral vBMD was calculated based on both calibration techniques from CT scans reconstructed with the eight kernels. Linear regression and Bland-Altman analyses were used to determine the coefficient of determination [Formula: see text] and to quantify the agreement between the different kernels. Differences between the reconstruction kernels were determined using paired t tests, and mean differences from the standard were computed. Using internal calibration, the smoothest kernel (soft) yielded a mean difference of -0.95 mg/cc (-0.33%) compared to the reference standard at the L4 vertebra and 2.07 mg/cc (0.51%) at the left femur. The sharpest kernel (lung) yielded a mean difference of 25.36 mg/cc (9.63%) at the L4 vertebra and -25.10 mg/cc (-5.98%) at the left femur. Alternatively, using phantom calibration soft yielded higher mean differences than internal calibration at both locations, with mean differences of 1.21 mg/cc (0.42%) at the L4 vertebra and 2.53 mg/cc (0.65%) at the left femur. The most error-prone results stemmed from the use of the lung kernel, as this kernel displayed a mean difference of -21.90 mg/cc (-7.38%) and -17.24 mg/cc (-4.34%) at the L4 vertebra and femur, respectively. These results indicate when performing opportunistic CT analysis, errors due to interchanging smoothing kernels soft, chest and detail are negligible, but that interchanging between sharpening kernels (lung, bone, bone plus, edge) results in large errors that can significantly impact vBMD measures for osteoporosis screening and diagnosis.

PMID:39953113 | DOI:10.1038/s41598-025-88551-x

Opt Lett. 2025 Feb 15;50(4):1269-1272. doi: 10.1364/OL.547399.

ABSTRACT

Fourier-inspired single-pixel holography (FISH) is an effective digital holography (DH) approach that utilizes a single-pixel detector instead of a conventional camera to capture light field information. FISH combines the Fourier single-pixel imaging and off-axis holography technique, allowing one to acquire useful information directly, rather than recording the hologram in the spatial domain and filtering unwanted terms in the Fourier domain. Furthermore, we employ a deep learning technique to jointly optimize the sampling mask and the imaging enhancement model, to achieve high-quality results at a low sampling ratio. Both simulations and experimental results demonstrate the effectiveness of FISH in single-pixel phase imaging. FISH combines the strengths of single-pixel imaging (SPI) and DH, potentially expanding DH's applications to specialized spectral bands and low-light environments while equipping SPI with capabilities for phase detection and coherent gating.

PMID:39951780 | DOI:10.1364/OL.547399

Opt Lett. 2025 Feb 15;50(4):1261-1264. doi: 10.1364/OL.544342.

ABSTRACT

Self-interference digital holography extends the application of digital holography to non-coherent imaging fields such as fluorescence and scattered light, providing a new solution, to the best of our knowledge, for wide field 3D imaging of low coherence or partially coherent signals. However, cross talk information has always been an important factor limiting the resolution of this imaging method. The suppression of cross talk information is a complex nonlinear problem, and deep learning can easily obtain its corresponding nonlinear model through data-driven methods. However, in real experiments, it is difficult to obtain such paired datasets to complete training. Here, we propose an unsupervised cross talk suppression method based on a cycle-consistent generative adversarial network (CycleGAN) for self-interference digital holography. Through the introduction of a saliency constraint, the unsupervised model, named crosstalk suppressing with unsupervised neural network (CS-UNN), can learn the mapping between two image domains without requiring paired training data while avoiding distortions of the image content. Experimental analysis has shown that this method can suppress cross talk information in reconstructed images without the need for training strategies on a large number of paired datasets, providing an effective solution for the application of the self-interference digital holography technology.

PMID:39951778 | DOI:10.1364/OL.544342

Anal Chem. 2025 Feb 14. doi: 10.1021/acs.analchem.4c02796. Online ahead of print.

ABSTRACT

Surface-enhanced Raman spectroscopy (SERS) has emerged as a crucial analytical tool in the field of oncology, particularly presenting significant challenges for the diagnosis and treatment of head and neck cancer. This Review provides an overview of the current status and prospects of SERS applications, highlighting their profound impact on molecular biology-level diagnosis, tissue-level identification, HNC therapeutic monitoring, and integration with emerging technologies. The application of SERS for single-molecule assays such as epidermal growth factor receptors and PD-1/PD-L1, gene expression analysis, and tumor microenvironment characterization is also explored. This Review showcases the innovative applications of SERS in liquid biopsies such as high-throughput lateral flow analysis for ctDNA quantification and salivary diagnostics, which can offer rapid and highly sensitive assays suitable for immediate detection. At the tissue level, SERS enables cancer cell visualization and intraoperative tumor margin identification, enhancing surgical precision and decision-making. The role of SERS in radiotherapy, chemotherapy, and targeted therapy is examined along with its use in real-time pharmacokinetic studies to monitor treatment response. Furthermore, this Review delves into the synergistic relationship between SERS and artificial intelligence, encompassing machine learning and deep learning algorithms, marking the dawn of a new era in precision oncology. The integration of SERS with genomics, metabolomics, transcriptomics, proteomics, and single-cell omics at the multiomics level will revolutionize our comprehension and management of HNC. This Review offers an overview of the transformative impacts of SERS and examines future directions as well as challenges in this dynamic research field.

PMID:39951652 | DOI:10.1021/acs.analchem.4c02796

PLoS One. 2025 Feb 14;20(2):e0315143. doi: 10.1371/journal.pone.0315143. eCollection 2025.

ABSTRACT

The smart grid is on the basis of physical grid, introducing all kinds of advanced communications technology and form a new type of power grid. It can not only meet the demand of users and realize the optimal allocation of resources, but also improve the safety, economy and reliability of power supply, it has become a major trend in the future development of electric power industry. But on the other hand, the complex network architecture of smart grid and the application of various high-tech technologies have also greatly increased the probability of equipment failure and the difficulty of fault diagnosis, and timely discovery and diagnosis of problems in the operation of smart grid equipment has become a key measure to ensure the safety of power grid operation. From the current point of view, the existing smart grid equipment fault diagnosis technology has problems that the application program is more complex, and the fault diagnosis rate is generally not high, which greatly affects the efficiency of smart grid maintenance. Therefore, Based on this, this paper adopts the multimodal semantic model of deep learning and knowledge graph, and on the basis of the original target detection network YOLOv4 architecture, introduces knowledge graph to unify the characterization and storage of the input multimodal information, and innovatively combines the YOLOv4 target detection algorithm with the knowledge graph to establish a smart grid equipment fault diagnosis model. Experiments show that compared with the existing fault detection algorithms, the YOLOv4 algorithm constructed in this paper is more accurate, faster and easier to operate.

PMID:39951439 | DOI:10.1371/journal.pone.0315143

PLoS One. 2025 Feb 14;20(2):e0318998. doi: 10.1371/journal.pone.0318998. eCollection 2025.

ABSTRACT

Alzheimer's disease (AD) is a leading cause of disability worldwide. Early detection is critical for preventing progression and formulating effective treatment plans. This study aims to develop a novel deep learning (DL) model, Hybrid-RViT, to enhance the detection of AD. The proposed Hybrid-RViT model integrates the pre-trained convolutional neural network (ResNet-50) with the Vision Transformer (ViT) to classify brain MRI images across different stages of AD. The ResNet-50 adopted for transfer learning, facilitates inductive bias and feature extraction. Concurrently, ViT processes sequences of image patches to capture long-distance relationships via a self-attention mechanism, thereby functioning as a joint local-global feature extractor. The Hybrid-RViT model achieved a training accuracy of 97% and a testing accuracy of 95%, outperforming previous models. This demonstrates its potential efficacy in accurately identifying and classifying AD stages from brain MRI data. The Hybrid-RViT model, combining ResNet-50 and ViT, shows superior performance in AD detection, highlighting its potential as a valuable tool for medical professionals in interpreting and analyzing brain MRI images. This model could significantly improve early diagnosis and intervention strategies for AD.

PMID:39951414 | DOI:10.1371/journal.pone.0318998

Ann Nucl Med. 2025 Feb 14. doi: 10.1007/s12149-025-02020-z. Online ahead of print.

ABSTRACT

OBJECTIVE: Bone scintigraphy is widely employed for detecting bone metastases, with the bone scan index (BSI) gaining traction as a quantitative tool in this domain. VSBONE BSI, an automated image analysis software, identifies abnormal hyperaccumulation areas in bone scintigraphy and computes BSI scores. The software, originally developed using data from conventional gamma cameras (C-Camera), has undergone two upgrades. This study hypothesized that the upgrades enhance the diagnostic accuracy for bone metastases and assessed the software's applicability to images obtained using a cadmium-zinc-telluride detector gamma camera (CZT-Camera). The aim was to compare the diagnostic accuracy of VSBONE BSI across software versions using both conventional and CZT detectors and to evaluate its utility.

METHODS: A total of 287 patients with breast or prostate carcinoma who underwent whole-body bone scintigraphy were included. VSBONE BSI automatically analyzed and calculated the BSI. The analysis results were compared with the presence or absence of metastases for each software version by using detector type of camera. The diagnostic agreement was evaluated.

RESULTS: Receiver operating characteristic analysis showed an area under the curve (AUC) exceeding 0.7 across all groups, indicating good diagnostic performance. AUC values significantly increased with version upgrades for all patients and for breast carcinoma patients. In metastasis-negative cases, BSI values decreased with each software version upgrade, with the reduction being more pronounced in breast carcinoma patients scanned with the CZT-Camera.

CONCLUSIONS: Using the VSBONE BSI, version 2 or 3 had a higher rate of diagnostic concordance with the clinical prognosis than version 1. In metastasis-negative patients, newer software versions yielded lower BSI values, especially for breast carcinoma patients scanned using the CZT-Camera, highlighting the improved diagnostic accuracy of the updated software.

PMID:39951220 | DOI:10.1007/s12149-025-02020-z

Aging Ment Health. 2025 Feb 14:1-9. doi: 10.1080/13607863.2025.2464704. Online ahead of print.

ABSTRACT

OBJECTIVES: Dementia can change oculomotor behavior, which is detectable through eye-tracking. This study aims to systematically review and conduct a meta-analysis of current literature on the intersection between eye-tracking and artificial intelligence (AI) in detecting dementia.

METHOD: PubMed, Embase, Scopus, Web of Science, Cochrane, and IEEE databases were searched up to July 2023. All types of studies that utilized eye-tracking and AI to detect dementia and reported the performance metrics, were included. Data on the dementia type, performance, artificial intelligence, and eye-tracking paradigms were extracted. The registered protocol is available online on PROSPERO (ID: CRD42023451996).

RESULTS: Nine studies were finally included with a sample size ranging from 57 to 583 participants. Alzheimer's disease (AD) was the most common dementia type. Six studies used a machine learning model while three used a deep learning model. Meta-analysis revealed the accuracy, sensitivity, and specificity of using eye-tracking and artificial intelligence in detecting dementia, 88% [95% CI (83%-92%)], 85% [95% CI (75%-93%)], and 86% [95% CI (79%-93%)], respectively.

CONCLUSION: Eye-tracking coupled with AI revealed promising results in terms of dementia detection. Further studies must incorporate larger sample sizes, standardized guidelines, and include other dementia types.

PMID:39950960 | DOI:10.1080/13607863.2025.2464704

J Med Eng Technol. 2025 Feb 14:1-14. doi: 10.1080/03091902.2025.2463577. Online ahead of print.

ABSTRACT

Developing a robust and effective technique is crucial for interpreting a user's brainwave signals accurately in the realm of biomedical signal processing. The variability and uncertainty present in EEG patterns over time, compounded by noise, pose notable challenges, particularly in mental tasks like motor imagery. Introducing fuzzy components can enhance the system's ability to withstand noisy environments. The emergence of deep learning has significantly impacted artificial intelligence and data analysis, prompting extensive exploration into assessing and understanding brain signals. This work introduces a hybrid series architecture called FCLNET, which combines Compact-CNN to extract frequency and spatial features alongside the LSTM network for temporal feature extraction. The activation functions in the CNN architecture were implemented using type-2 fuzzy functions to tackle uncertainties. Hyperparameters of the FCLNET model are tuned by the Bayesian optimisation algorithm. The efficacy of this approach is assessed through the BCI Competition IV-2a database and the BCI Competition IV-1 database. By incorporating type-2 fuzzy activation functions and employing Bayesian optimisation for tuning, the proposed architecture indicates good classification accuracy compared to the literature. Outcomes showcase the exceptional achievements of the FCLNET model, suggesting that integrating fuzzy units into other classifiers could lead to advancements in motor imagery-based BCI systems.

PMID:39950750 | DOI:10.1080/03091902.2025.2463577

ACS Appl Mater Interfaces. 2025 Feb 14. doi: 10.1021/acsami.4c20821. Online ahead of print.

ABSTRACT

Prolonged use of digital devices and sedentary lifestyles have led to an increase in the prevalence of cervical spondylosis among young people, highlighting the urgent need for preventive measures. Recent advancements in triboelectric nanogenerators (TENGs) have shown their potential as self-powered sensors. In this study, we introduce a novel, flexible, and stretchable TENG for neck movement detection. The proposed TENG utilizes a glycerol/poly(vinyl alcohol) (GL/PVA) hydrogel and silicone rubber (GH-TENG). Through optimization of its concentration and thickness parameters and the use of environmentally friendly dopants, the sensitivity of the GH-TENG was improved to 4.50 V/kPa. Subsequently, we developed a smart neck ring with the proposed sensor for human neck movement monitoring. By leveraging the convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) algorithm, sensor data can be efficiently analyzed in both spatial and temporal dimensions, achieving a promising recognition accuracy of 97.14%. Additionally, we developed a neck motion monitoring system capable of accurately identifying and recording neck movements. The system can timely alert users if they maintain the same neck posture for more than 30 min and provide corresponding recommendations. By deployment on a Raspberry Pi 4B, the system offers a portable and efficient solution for cervical health protection.

PMID:39950449 | DOI:10.1021/acsami.4c20821

Plant Biotechnol J. 2025 Feb 14. doi: 10.1111/pbi.14577. Online ahead of print.

ABSTRACT

Genomic selection (GS) is a new breeding strategy. Generally, traditional methods are used for predicting traits based on the whole genome. However, the prediction accuracy of these models remains limited because they cannot fully reflect the intricate nonlinear interactions between genotypes and traits. Here, a novel single nucleotide polymorphism (SNP) feature extraction technique based on the Pearson-Collinearity Selection (PCS) is firstly presented and improves prediction accuracy across several known models. Furthermore, gene network prediction model (NetGP) is a novel deep learning approach designed for phenotypic prediction. It utilizes transcriptomic dataset (Trans), genomic dataset (SNP) and multi-omics dataset (Trans + SNP). The NetGP model demonstrated better performance compared to other models in genomic predictions, transcriptomic predictions and multi-omics predictions. NetGP multi-omics model performed better than independent genomic or transcriptomic prediction models. Prediction performance evaluations using several other plants' data showed good generalizability for NetGP. Taken together, our study not only offers a novel and effective tool for plant genomic selection but also points to new avenues for future plant breeding research.

PMID:39950326 | DOI:10.1111/pbi.14577

J Pathol. 2025 Feb 14. doi: 10.1002/path.6399. Online ahead of print.

ABSTRACT

Over 90% of gastrointestinal stromal tumors (GISTs) harbor mutations in KIT or PDGFRA that can predict response to tyrosine kinase inhibitor (TKI) therapies, as recommended by NCCN (National Comprehensive Cancer Network) guidelines. However, gene sequencing for mutation testing is expensive and time-consuming and is susceptible to a variety of preanalytical factors. To overcome the challenges associated with genetic screening by sequencing, in the current study we developed an artificial intelligence-based deep-learning （DL） model that uses convolutional neural networks (CNN) to analyze digitized hematoxylin and eosin staining in tumor histological sections to predict potential response to imatinib or avapritinib treatment in GIST patients. Assessment with an independent testing set showed that our DL model could predict imatinib sensitivity with an area under the curve (AUC) of 0.902 in case-wise analysis and 0.807 in slide-wise analysis. Case-level AUCs for predicting imatinib-dose-adjustment cases, avapritinib-sensitive cases, and wildtype GISTs were 0.920, 0.958, and 0.776, respectively, while slide-level AUCs for these respective groups were 0.714, 0.922, and 0.886, respectively. Our model showed comparable or better prediction of actual response to TKI than sequencing-based screening (accuracy 0.9286 versus 0.8929; DL model versus sequencing), while predictions of nonresponse to imatinib/avapritinib showed markedly higher accuracy than sequencing (0.7143 versus 0.4286). These results demonstrate the potential of a DL model to improve predictions of treatment response to TKI therapy from histology in GIST patients. © 2025 The Pathological Society of Great Britain and Ireland.

PMID:39950223 | DOI:10.1002/path.6399

Front Glob Womens Health. 2025 Jan 30;6:1447579. doi: 10.3389/fgwh.2025.1447579. eCollection 2025.

ABSTRACT

INTRODUCTION: Estimating a reliable gestational age (GA) is essential in providing appropriate care during pregnancy. With advancements in data science, there are several publications on the use of artificial intelligence (AI) models to estimate GA using ultrasound (US) images. The aim of this meta-analysis is to assess the accuracy of AI models in assessing GA against US as the gold standard.

METHODS: A literature search was performed in PubMed, CINAHL, Wiley Cochrane Library, Scopus, and Web of Science databases. Studies that reported use of AI models for GA estimation with US as the reference standard were included. Risk of bias assessment was performed using Quality Assessment for Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Mean error in GA was estimated using STATA version-17 and subgroup analysis on trimester of GA assessment, AI models, study design, and external validation was performed.

RESULTS: Out of the 1,039 studies screened, 17 were included in the review, and of these 10 studies were included in the meta-analysis. Five (29%) studies were from high-income countries (HICs), four (24%) from upper-middle-income countries (UMICs), one (6%) from low-and middle-income countries (LMIC), and the remaining seven studies (41%) used data across different income regions. The pooled mean error in GA estimation based on 2D images (n = 6) and blind sweep videos (n = 4) was 4.32 days (95% CI: 2.82, 5.83; l 2: 97.95%) and 2.55 days (95% CI: -0.13, 5.23; l 2: 100%), respectively. On subgroup analysis based on 2D images, the mean error in GA estimation in the first trimester was 7.00 days (95% CI: 6.08, 7.92), 2.35 days (95% CI: 1.03, 3.67) in the second, and 4.30 days (95% CI: 4.10, 4.50) in the third trimester. In studies using deep learning for 2D images, those employing CNN reported a mean error of 5.11 days (95% CI: 1.85, 8.37) in gestational age estimation, while one using DNN indicated a mean error of 5.39 days (95% CI: 5.10, 5.68). Most studies exhibited an unclear or low risk of bias in various domains, including patient selection, index test, reference standard, flow and timings and applicability domain.

CONCLUSION: Preliminary experience with AI models shows good accuracy in estimating GA. This holds tremendous potential for pregnancy dating, especially in resource-poor settings where trained interpreters may be limited.

SYSTEMATIC REVIEW REGISTRATION: PROSPERO, identifier (CRD42022319966).

PMID:39950139 | PMC:PMC11821921 | DOI:10.3389/fgwh.2025.1447579

Digit Health. 2025 Feb 13;11:20552076251319667. doi: 10.1177/20552076251319667. eCollection 2025 Jan-Dec.

ABSTRACT

OBJECTIVE: Based on the current research status, this paper proposes a deep learning model named Covid-DenseNet for COVID-19 detection from CXR (computed tomography) images, aiming to build a model with smaller computational complexity, stronger generalization ability, and excellent performance on benchmark datasets and other datasets with different sample distribution features and sample sizes.

METHODS: The proposed model first extracts and obtains features of multiple scales from the input image through transfer learning, followed by assigning internal weights to the extracted features through the attention mechanism to enhance important features and suppress irrelevant features; finally, the model fuses these features of different scales through the multi-scale fusion architecture we designed to obtain richer semantic information and improve modeling efficiency.

RESULTS: We evaluated our model and compared it with advanced models on three publicly available chest radiology datasets of different types, one of which is the baseline dataset, on which we constructed the model Covid-DenseNet, and the recognition accuracy on this test set was 96.89%, respectively. With recognition accuracy of 98.02% and 96.21% on the other two publicly available datasets, our model performs better than other advanced models. In addition, the performance of the model was further evaluated on external test sets, trained on data sets with balanced sample distribution (experiment 1) and unbalanced sample distribution (experiment 2), identified on the same external test set, and compared with DenseNet121. The recognition accuracy of the model in experiment 1 and experiment 2 is 80% and 77.5% respectively, which is 3.33% and 4.17% higher than that of DenseNet121 on external test set. On this basis, we also changed the number of samples in experiment 1 and experiment 2, and compared the impact of the change in the number of training set samples on the recognition accuracy of the model on the external test set. The results showed that when the number of samples increased and the sample features became more abundant, the trained Covid-DenseNet performed better on the external test set and the model became more robust.

CONCLUSION: Compared with other advanced models, our model has achieved better results on multiple datasets, and the recognition effect on external test sets is also quite good, with good generalization performance and robustness, and with the enrichment of sample features, the robustness of the model is further improved, and it has better clinical practice ability.

PMID:39949849 | PMC:PMC11822832 | DOI:10.1177/20552076251319667

Data Min Knowl Discov. 2024 May;38(3):1493-1519. doi: 10.1007/s10618-024-01006-1. Epub 2024 Feb 9.

ABSTRACT

The multivariate time series classification (MTSC) task aims to predict a class label for a given time series. Recently, modern deep learning-based approaches have achieved promising performance over traditional methods for MTSC tasks. The success of these approaches relies on access to the massive amount of labeled data (i.e., annotating or assigning tags to each sample that shows its corresponding category). However, obtaining a massive amount of labeled data is usually very time-consuming and expensive in many real-world applications such as medicine, because it requires domain experts' knowledge to annotate data. Insufficient labeled data prevents these models from learning discriminative features, resulting in poor margins that reduce generalization performance. To address this challenge, we propose a novel approach: supervised contrastive learning for time series classification (SupCon-TSC). This approach improves the classification performance by learning the discriminative low-dimensional representations of multivariate time series, and its end-to-end structure allows for interpretable outcomes. It is based on supervised contrastive (SupCon) loss to learn the inherent structure of multivariate time series. First, two separate augmentation families, including strong and weak augmentation methods, are utilized to generate augmented data for the source and target networks, respectively. Second, we propose the instance-level, and cluster-level SupCon learning approaches to capture contextual information to learn the discriminative and universal representation for multivariate time series datasets. In the instance-level SupCon learning approach, for each given anchor instance that comes from the source network, the low-variance output encodings from the target network are sampled as positive and negative instances based on their labels. However, the cluster-level approach is performed between each instance and cluster centers among batches, as opposed to the instance-level approach. The cluster-level SupCon loss attempts to maximize the similarities between each instance and cluster centers among batches. We tested this novel approach on two small cardiopulmonary exercise testing (CPET) datasets and the real-world UEA Multivariate time series archive. The results of the SupCon-TSC model on CPET datasets indicate its capability to learn more discriminative features than existing approaches in situations where the size of the dataset is small. Moreover, the results on the UEA archive show that training a classifier on top of the universal representation features learned by our proposed method outperforms the state-of-the-art approaches.

PMID:39949582 | PMC:PMC11825059 | DOI:10.1007/s10618-024-01006-1

Front Artif Intell. 2025 Jan 30;8:1518049. doi: 10.3389/frai.2025.1518049. eCollection 2025.

ABSTRACT

ChatGPT represents a transformative technology in healthcare, with demonstrated impacts across clinical practice, medical education, and research. Studies show significant efficiency gains, including 70% reduction in administrative time for discharge summaries and achievement of medical professional-level performance on standardized tests (60% accuracy on USMLE, 78.2% on PubMedQA). ChatGPT offers personalized learning platforms, automated scoring, and instant access to vast medical knowledge in medical education, addressing resource limitations and enhancing training efficiency. It streamlines clinical workflows by supporting triage processes, generating discharge summaries, and alleviating administrative burdens, allowing healthcare professionals to focus more on patient care. Additionally, ChatGPT facilitates remote monitoring and chronic disease management, providing personalized advice, medication reminders, and emotional support, thus bridging gaps between clinical visits. Its ability to process and synthesize vast amounts of data accelerates research workflows, aiding in literature reviews, hypothesis generation, and clinical trial designs. This paper aims to gather and analyze published studies involving ChatGPT, focusing on exploring its advantages and disadvantages within the healthcare context. To aid in understanding and progress, our analysis is organized into six key areas: (1) Information and Education, (2) Triage and Symptom Assessment, (3) Remote Monitoring and Support, (4) Mental Healthcare Assistance, (5) Research and Decision Support, and (6) Language Translation. Realizing ChatGPT's full potential in healthcare requires addressing key limitations, such as its lack of clinical experience, inability to process visual data, and absence of emotional intelligence. Ethical, privacy, and regulatory challenges further complicate its integration. Future improvements should focus on enhancing accuracy, developing multimodal AI models, improving empathy through sentiment analysis, and safeguarding against artificial hallucination. While not a replacement for healthcare professionals, ChatGPT can serve as a powerful assistant, augmenting their expertise to improve efficiency, accessibility, and quality of care. This collaboration ensures responsible adoption of AI in transforming healthcare delivery. While ChatGPT demonstrates significant potential in healthcare transformation, systematic evaluation of its implementation across different healthcare settings reveals varying levels of evidence quality-from robust randomized trials in medical education to preliminary observational studies in clinical practice. This heterogeneity in evidence quality necessitates a structured approach to future research and implementation.

PMID:39949509 | PMC:PMC11821943 | DOI:10.3389/frai.2025.1518049

Multivariate Behav Res. 2025 Feb 14:1-15. doi: 10.1080/00273171.2025.2455497. Online ahead of print.

ABSTRACT

Automated detection of facial emotions has been an interesting topic for multiple decades in social and behavioral research but is only possible very recently. In this tutorial, we review three popular artificial intelligence based emotion detection programs that are accessible to R programmers: Google Cloud Vision, Amazon Rekognition, and Py-Feat. We present their advantages, disadvantages, and provide sample code so that researchers can immediately begin designing, collecting, and analyzing emotion data. Furthermore, we provide an introductory level explanation of the machine learning, deep learning, and computer vision algorithms that underlie most emotion detection programs in order to improve literacy of explainable artificial intelligence in the social and behavioral science literature.

PMID:39949325 | DOI:10.1080/00273171.2025.2455497

J Med Eng Technol. 2025 Feb 14:1-9. doi: 10.1080/03091902.2025.2463574. Online ahead of print.

ABSTRACT

The work proposes a methodology for five different classes of ECG signals. The methodology utilises moving average filter and discrete wavelet transformation for the remove of baseline wandering and powerline interference. The preprocessed signals are segmented by R peak detection process. Thereafter, the greyscale and scalograms images have been formed. The features of the images are extracted using the EfficientNet-B0 deep learning model. These features are normalised using z-score normalisation method and then optimal features are selected using the hybrid feature selection method. The hybrid feature selection is constructed utilising two filter methods and Self Adaptive Bald Eagle Search (SABES) optimisation algorithm. The proposed methodology has been applied to the ECG signals for the classification of the five types of beats. The methodology acquired 99.31% of accuracy.

PMID:39949269 | DOI:10.1080/03091902.2025.2463574

Math Biosci Eng. 2025 Jan 3;22(1):138-151. doi: 10.3934/mbe.2025007.

ABSTRACT

Bone age assessment (BAA) is a widely used clinical practice for the biological development of adolescents. The Tanner Whitehouse (TW) method is a traditionally mainstream method that manually extracts multiple regions of interest (ROIs) related to skeletal maturity to infer bone age. In this paper, we propose a deep learning-based method for fully automatic ROIs localization and BAA. The method consists of two parts: a U-net-based backbone, selected for its strong performance in semantic segmentation, which enables precise and efficient localization without the need for complex pre- or post-processing. This method achieves a localization precision of 99.1% on the public RSNA dataset. Second, an InceptionResNetV2 network is utilized for feature extraction from both the ROIs and the whole image, as it effectively captures both local and global features, making it well-suited for bone age prediction. The BAA neural network combines the advantages of both ROIs-based methods (TW3 method) and global feature-based methods (GP method), providing high interpretability and accuracy. Numerical experiments demonstrate that the method achieves a mean absolute error (MAE) of 0.38 years for males and 0.45 years for females on the public RSNA dataset, and 0.41 years for males and 0.44 years for females on an in-house dataset, validating the accuracy of both localization and prediction.

PMID:39949166 | DOI:10.3934/mbe.2025007

Math Biosci Eng. 2025 Jan;22(1):73-105. doi: 10.3934/mbe.2025004. Epub 2024 Dec 25.

ABSTRACT

Epileptic seizures, a prevalent neurological condition, necessitate precise and prompt identification for optimal care. Nevertheless, the intricate characteristics of electroencephalography (EEG) signals, noise, and the want for real-time analysis require enhancement in the creation of dependable detection approaches. Despite advances in machine learning and deep learning, capturing the intricate spatial and temporal patterns in EEG data remains challenging. This study introduced a novel deep learning framework combining a convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU), and convolutional block attention module (CBAM). The CNN extracts spatial features, the BiGRU captures long-term temporal dependencies, and the CBAM emphasizes critical spatial and temporal regions, creating a hybrid architecture optimized for EEG pattern recognition. Evaluation of a public EEG dataset revealed superior performance compared to existing methods. The model achieved 99.00% accuracy in binary classification, 96.20% in three-class tasks, 92.00% in four-class scenarios, and 89.00% in five-class classification. High sensitivity (89.00-99.00%) and specificity (89.63-99.00%) across all tasks highlighted the model's robust ability to identify diverse EEG patterns. This approach supports healthcare professionals in diagnosing epileptic seizures accurately and promptly, improving patient outcomes and quality of life.

PMID:39949163 | DOI:10.3934/mbe.2025004