IEEE J Biomed Health Inform. 2025 May 12;PP. doi: 10.1109/JBHI.2025.3569726. Online ahead of print.

ABSTRACT

Breast cancer poses a serious threat to women's health, and its early detection is crucial for enhancing patient survival rates. While deep learning has significantly advanced mammographic image analysis, existing methods struggle to balance between view consistency with input adaptability. Furthermore, current models face challenges in accurately capturing multi-scale features, especially when subtle lesion variations across different scales are involved. To address this challenge, this paper proposes a Hybrid View Learning (HVL) paradigm that unifies traditional Single-View and Multi-View Learning approaches. The core component of this paradigm, our Attention-based Hybrid View Learning (AHVL) framework, incorporates two essential attention mechanisms: Contrastive Switch Attention (CSA) and Selective Pooling Attention (SPA). The CSA mechanism flexibly alternates between self-attention and cross-attention based on data integrity, integrating a pre-trained language model for contrastive learning to enhance model stability. Meanwhile, the SPA module employs multi-scale feature pooling and selection to capture critical features from mammographic images, overcoming the limitations of traditional models that struggle with fine-grained lesion detection. Experimental validation on the INbreast and CBIS-DDSM datasets shows that the AHVL framework outperforms both single-view and multi-view methods, especially under extreme view missing conditions. Even with an 80% missing rate on both datasets, AHVL maintains the highest accuracy and experiences the smallest performance decline in metrics like F1 score and AUC-PR, demonstrating its robustness and stability. This study redefines mammographic image analysis by leveraging attention-based hybrid view processing, setting a new standard for precise and efficient breast cancer diagnosis.

PMID:40354201 | DOI:10.1109/JBHI.2025.3569726

J Med Internet Res. 2025 May 12;27:e67156. doi: 10.2196/67156.

ABSTRACT

BACKGROUND: Accurate prediction of population-wide depression incidence is vital for effective public mental health management. However, this incidence is often influenced by socioeconomic factors, such as abrupt events or changes, including pandemics, economic crises, and social unrest, creating complex structural break scenarios in the time-series data. These structural breaks can affect the performance of forecasting methods in various ways. Therefore, understanding and comparing different models across these scenarios is essential.

OBJECTIVE: This study aimed to develop depression incidence forecasting models and compare the performance of autoregressive integrated moving average (ARIMA) and vector-ARIMA (VARIMA) and temporal fusion transformers (TFT) under different structural break scenarios.

METHODS: We developed population-wide depression incidence forecasting models and compared the performance of ARIMA and VARIMA-based methods to TFT-based methods. Using monthly depression incidence from 2002 to 2022 in Hong Kong, we applied sliding windows to segment the whole time series into 72 ten-year subsamples. The forecasting models were trained, validated, and tested on each subsample. Within each 10-year subset, the first 7 years were used for training, with the eighth year for setting hold-out validation, and the ninth and tenth years for testing. The accuracy of the testing set within each 10-year subsample was measured by symmetric mean absolute percentage error (SMAPE).

RESULTS: We found that in subsamples without significant slope or trend change (structural break), multivariate TFT significantly outperformed univariate TFT, vector-ARIMA (VARIMA), and ARIMA, with an average SMAPE of 11.6% compared to 13.2% (P=.01) for univariate TFT, 16.4% (P=.002) for VARIMA, and 14.8% (P=.003) for ARIMA. Adjusting for the unemployment rate improved TFT performance more effectively than VARIMA. When fluctuating outbreaks happened, TFT was more robust to sharp interruptions, whereas VARIMA and ARIMA performed better when incidence surged and remained high.

CONCLUSIONS: This study provides a comparative evaluation of TFT and ARIMA and VARIMA models for forecasting depression incidence under various structural break scenarios, offering insights into predicting disease burden during both stable and unstable periods. The findings support a decision-making framework for model selection based on the nature of disruptions and data characteristics. For public health policymaking, the results suggest that TFT may be a more suitable tool for disease burden forecasting during periods of stable burden level or when sudden temporary interruption, such as pandemics or socioeconomic variation, impacts disease occurrence.

PMID:40354111 | DOI:10.2196/67156

Eur Arch Paediatr Dent. 2025 May 12. doi: 10.1007/s40368-025-01046-1. Online ahead of print.

ABSTRACT

PURPOSE: An effective Deep learning (DL) based Early Childhood Caries (ECC) prediction model is crucial for early detection of ECC. This study aims to develop and evaluate a deep learning (DL) based hybrid statistical model for ECC prediction.

METHODS: The study employed a computational cross-sectional design, conducted over a three-year period from March 2021 to March 2024. Data analysis was carried out using a hybrid statistical approach that integrated bootstrap methods, Logistic Regression Modelling (LRM), and Multilayer Feed-Forward Neural Networks (MLFFNN). The sample comprised 157 parent-child pairs, providing a robust dataset for examining the research questions.

RESULTS: In the current study, the predictors named, "mother's education" (β1: 0.423; p < 0.25), "parent's knowledge of bottle-feeding habit during sleep can cause tooth decay" (β2: -1.264; p < 0.25), "attitude towards the importance of oral health as general health" (β4: -1.052; p < 0.25) and "parent's self-reported oral pain among their children" (β5: -2.107; p < 0.25) showed significant association with ECC. For this model, the Mean Absolute Deviation (MAD) was 0.02211, Predictive Mean Squared Error (PMSE) was 0.07909, and the accuracy level was 99.98%. No significant difference was observed from the t-test between the actual values and the predicted values of the model (p > 0.05).

CONCLUSION: It has been shown that this unique deep learning-based ECC prediction model appears an effective tool with high accuracy and interpretability for ECC prediction. After implementing the oral health intervention program, focusing on the potential predictors of ECC obtained from this innovative model, policymakers could be able to evaluate their prediction models comparing their results with the findings of the current study. This comparison will guide them in understanding, designing, and implementing a more effective intervention program for ECC prevention.

PMID:40354021 | DOI:10.1007/s40368-025-01046-1

Dentomaxillofac Radiol. 2025 May 12:twaf044. doi: 10.1093/dmfr/twaf044. Online ahead of print.

ABSTRACT

OBJECTIVES: To evaluate deep learning (DL)-based models for detecting periapical bone rarefaction (PBRs) in panoramic radiographs (PRs), analyzing their feasibility and performance in dental practice.

METHODS: A search was conducted across seven databases and partial grey literature up to November 15, 2024, using Medical Subject Headings and entry terms related to DL, PBRs, and PRs. Studies assessing DL-based models for detecting and classifying PBRs in conventional PRs were included, while those using non-PR imaging or focusing solely on non-PBR lesions were excluded. Two independent reviewers performed screening, data extraction, and quality assessment using the Quality Assessment of Diagnostic Accuracy Studies-2 tool, with conflicts resolved by a third reviewer.

RESULTS: Twelve studies met the inclusion criteria, mostly from Asia (58.3%). The risk of bias was moderate in 10 studies (83.3%) and high in 2 (16.7%). DL models showed moderate to high performance in PBR detection (sensitivity: 26-100%; specificity: 51-100%), with U-NET and YOLO being the most used algorithms. Only one study (8.3%) distinguished Periapical Granuloma from Periapical Cysts, revealing a classification gap. Key challenges included limited generalization due to small datasets, anatomical superimpositions in PRs, and variability in reported metrics, compromising models comparison.

CONCLUSION: This review underscores that DL-based has the potential to become a valuable tool in dental image diagnostics, but it cannot yet be considered a definitive practice. Multicenter collaboration is needed to diversify data and democratize those tools. Standardized performance reporting is critical for fair comparability between different models.

PMID:40353850 | DOI:10.1093/dmfr/twaf044

Magn Reson Med. 2025 May 12. doi: 10.1002/mrm.30486. Online ahead of print.

ABSTRACT

PURPOSE: The purpose of this study is to perform image registration and averaging of multiple free-breathing single-shot cardiac images, where the individual images may have a low signal-to-noise ratio (SNR).

METHODS: To address low SNR encountered in single-shot imaging, especially at low field strengths, we propose a fast deep learning (DL)-based image registration method, called Averaging Morph with Edge Detection (AiM-ED). AiM-ED jointly registers multiple noisy source images to a noisy target image and utilizes a noise-robust pre-trained edge detector to define the training loss. We validate AiM-ED using synthetic late gadolinium enhanced (LGE) images from the MR extended cardiac-torso (MRXCAT) phantom and free-breathing single-shot LGE images from healthy subjects (24 slices) and patients (5 slices) under various levels of added noise. Additionally, we demonstrate the clinical feasibility of AiM-ED by applying it to data from patients (6 slices) scanned on a 0.55T scanner.

RESULTS: Compared with a traditional energy-minimization-based image registration method and DL-based VoxelMorph, images registered using AiM-ED exhibit higher values of recovery SNR and three perceptual image quality metrics. An ablation study shows the benefit of both jointly processing multiple source images and using an edge map in AiM-ED.

CONCLUSION: For single-shot LGE imaging, AiM-ED outperforms existing image registration methods in terms of image quality. With fast inference, minimal training data requirements, and robust performance at various noise levels, AiM-ED has the potential to benefit single-shot CMR applications.

PMID:40353517 | DOI:10.1002/mrm.30486

Curr Pharm Des. 2025 May 9. doi: 10.2174/0113816128381171250415171256. Online ahead of print.

ABSTRACT

Artificial intelligence (AI) can completely transform drug development methods by delivering faster, more accurate, efficient results. However, the effective use of AI requires the accessibility of data of excellent quality, the resolution of ethical dilemmas, and an awareness of the drawbacks of AI-based techniques. Moreover, the application of AI in drug discovery is gaining popularity as an alternative to both the complex and time-consuming process of discovering as well as developing novel medications. Importantly, machine learning (ML) as well as natural language processing, for example, may boost both productivity as well as accuracy by analyzing vast volumes of data. This review article discusses in detail the promise of AI in drug discovery as well as offers insights into various topics such as societal issues related to the application of AI in medicine (e.g., legislation, interpretability and explainability, privacy and anonymity, and ethics and fairness), the importance of AI in the development of drug delivery systems, causability and explainability of AI in medicine, and opportunities and challenges for AI in clinical adoption, threat or opportunity of AI in medical imaging, the missing pieces of AI in medicine, approval of AI and ML-based medical devices.

PMID:40353469 | DOI:10.2174/0113816128381171250415171256

Med Sci Educ. 2025 Jan 8;35(2):939-948. doi: 10.1007/s40670-024-02256-w. eCollection 2025 Apr.

ABSTRACT

INTRODUCTION: Reflection is a critical cognitive process that involves thinking deeply about experiences, actions, or concepts to gain insights and enhance learning. Online collaborative environments, such as forums, facilitate peer learning and reflection on educational experiences. This study aimed to analyze medical students' opinions on electronic Peer-Assisted Reflection (ePAR) in an educational forum focused on psychology-related courses.

METHODS: This qualitative study utilized content analysis methods. The sample consisted of opinions gathered across 16 forums encompassing a total of 389 students specializing in medicine, laboratory science, and public health at Jahrom University of Medical Sciences (JUMS), IRAN. The instructor delivered the courses to the class and posed questions based on the discussion forum within the Learning Management System. Following each course, students' experiences regarding discussions and question-and-answer sessions were assessed in a forum setting. The data were analyzed using inductive content analysis.

RESULTS: A content analysis of the data obtained from students' opinions yielded 51 codes (items), which were classified into two main categories: effectiveness and setting. The most significant factors were effectiveness (Including: Thinking, Peer-Assisted Learning, Active Learning, and Self-Critique) and setting (Environment, Teachers, and Students). The open codes (items) most frequently mentioned by students included the potential to correct inaccurate interpretations of others' learning experiences and misconceptions (94 mentions), improving students' ability to compare and analyze (93 mentions), promoting and strengthening criticism and analysis (93 mentions), and fostering active and deep learning (92 mentions).

CONCLUSION: The forum environment can enhance participation, active learning, and critical thinking among students while providing a rich educational context for medical education. Therefore, utilizing this method in education without time or place constraints can be a practical approach to improving medical science education.

PMID:40352990 | PMC:PMC12058557 | DOI:10.1007/s40670-024-02256-w

Front Artif Intell. 2025 Apr 25;8:1444891. doi: 10.3389/frai.2025.1444891. eCollection 2025.

ABSTRACT

Previous work has demonstrated that initialization is very important for both fitting a neural network by gradient descent methods, as well as for Variational inference of Bayesian neural networks. In this work we investigate how Layer wise Scaled Gaussian Priors perform with Markov Chain Monte Carlo trained Bayesian neural networks. From our experiments on 8 classifications datasets of various complexity, the results indicate that using Layer wise Scaled Gaussian Priors makes the sampling process more efficient as compared to using an Isotropic Gaussian Prior, an Isotropic Cauchy Prior, or an Isotropic Laplace Prior. We also show that the cold posterior effect does not arise when using a either an Isotropic Gaussian or a layer wise Scaled Prior for small feed forward Bayesian neural networks. Since Bayesian neural networks are becoming popular due to their advantages such as uncertainty estimation, and prevention of over-fitting, this work seeks to provide improvements in the efficiency of Bayesian neural networks learned using Markov Chain Monte Carlo methods.

PMID:40352974 | PMC:PMC12061901 | DOI:10.3389/frai.2025.1444891

Biol Methods Protoc. 2025 Apr 11;10(1):bpaf030. doi: 10.1093/biomethods/bpaf030. eCollection 2025.

ABSTRACT

Three-dimensional (3D) spheroid models have advanced cancer research by better mimicking the tumour microenvironment compared to traditional two-dimensional cell cultures. However, challenges persist in high-throughput analysis of morphological characteristics and cell viability, as traditional methods like manual fluorescence analysis are labour-intensive and inconsistent. Existing AI-based approaches often address segmentation or classification in isolation, lacking an integrated workflow. We propose a scalable, two-stage deep learning pipeline to address these gaps: (i) a U-Net model for precise detection and segmentation of 3D spheroids from microscopic images, achieving 95% prediction accuracy, and (ii) a CNN Regression Hybrid method for estimating live/dead cell percentages and classifying spheroids, with an R 2 value of 98%. This end-to-end pipeline automates cell viability quantification and generates key morphological parameters for spheroid growth kinetics. By integrating segmentation and analysis, our method addresses environmental variability and morphological characterization challenges, offering a robust tool for drug discovery, toxicity screening, and clinical research. This approach significantly improves efficiency and scalability of 3D spheroid evaluations, paving the way for advancements in cancer therapeutics.

PMID:40352793 | PMC:PMC12064216 | DOI:10.1093/biomethods/bpaf030

Narra J. 2025 Apr;5(1):e1361. doi: 10.52225/narra.v5i1.1361. Epub 2025 Mar 5.

ABSTRACT

Ground-glass opacities (GGOs) are hazy opacities on chest computed tomography (CT) scans that can indicate various lung diseases, including early COVID-19, pneumonia, and lung cancer. Artificial intelligence (AI) is a promising tool for analyzing medical images, such as chest CT scans. The aim of this study was to evaluate AI models' performance in detecting GGO nodules using metrics like accuracy, sensitivity, specificity, F1 score, area under the curve (AUC) and precision. We designed a search strategy to include reports focusing on deep learning algorithms applied to high-resolution CT scans. The search was performed on PubMed, Google Scholar, Scopus, and ScienceDirect to identify studies published between 2016 and 2024. Quality appraisal of included studies was conducted using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool, assessing the risk of bias and applicability concerns across four domains. Two reviewers independently screened studies reporting the diagnostic ability of AI-assisted CT scans in early GGO detection, where the review results were synthesized qualitatively. Out of 5,247 initially identified records, we found 18 studies matching the inclusion criteria of this study. Among evaluated models, DenseNet achieved the highest accuracy of 99.48%, though its sensitivity and specificity were not reported. WOANet showed an accuracy of 98.78%, with a sensitivity of 98.37% and high specificity of 99.19%, excelling particularly in specificity without compromising sensitivity. In conclusion, AI models can potentially detect GGO on chest CT scans. Future research should focus on developing hybrid models that integrate various AI approaches to improve clinical applicability.

PMID:40352244 | PMC:PMC12059966 | DOI:10.52225/narra.v5i1.1361

Virus Evol. 2025 Apr 29;11(1):veaf026. doi: 10.1093/ve/veaf026. eCollection 2025.

ABSTRACT

The fast evolution of SARS-CoV-2 and other infectious viruses poses a grand challenge to the rapid response in terms of viral tracking, diagnostics, and design and manufacture of monoclonal antibodies (mAbs) and vaccines, which are both time-consuming and costly. This underscores the need for efficient computational approaches. Recent advancements, like topological deep learning (TDL), have introduced powerful tools for forecasting emerging dominant variants, yet they require deep mutational scanning (DMS) of viral surface proteins and associated three-dimensional (3D) protein-protein interaction (PPI) complex structures. We propose an AlphaFold 3 (AF3)-assisted multi-task topological Laplacian (MT-TopLap) strategy to address this need. MT-TopLap combines deep learning with TDA models, such as persistent Laplacians (PL) to extract detailed topological and geometric characteristics of PPIs, thereby enhancing the prediction of DMS and binding free energy (BFE) changes upon virus mutations. Validation with four experimental DMS datasets of SARS-CoV-2 spike receptor-binding domain (RBD) and the human angiotensin-converting enzyme-2 (ACE2) complexes indicates that our AF3-assisted MT-TopLap strategy maintains robust performance, with only an average 1.1% decrease in Pearson correlation coefficients (PCC) and an average 9.3% increase in root mean square errors (RMSE), compared with the use of experimental structures. Additionally, AF3-assisted MT-TopLap achieved a PCC of 0.81 when tested with a SARS-CoV-2 HK.3 variant DMS dataset, confirming its capability to accurately predict BFE changes and adapt to new experimental data, thereby showcasing its potential for rapid and effective response to fast viral evolution.

PMID:40352163 | PMC:PMC12063592 | DOI:10.1093/ve/veaf026

Digit Health. 2025 May 8;11:20552076251341163. doi: 10.1177/20552076251341163. eCollection 2025 Jan-Dec.

ABSTRACT

OBJECTIVE: Telemedicine platforms played a crucial role during the COVID-19 pandemic, alleviating issues related to the shortage and unequal distribution of healthcare resources. The purpose of this study is to identify key factors affecting the service quality of telemedicine platforms in China, with the dual objectives of advancing patient wellbeing and informing evidence-based service innovations for industry stakeholders.

METHODS: To quantitatively assess the impact of these key factors on health and wellbeing from the perspective of healthcare consumers, a total of 25,499 valid online reviews were collected from telemedicine platforms. To establish a service quality evaluation framework, this study proposes a novel approach that combines the Servqual quality assessment model with a CNN-BiLSTM deep learning model enhanced by an attention mechanism.

RESULTS: Analysis of the full sample shows that healthcare consumers are most concerned about the quality of services provided by telemedicine platforms, with the most important being the professional competence of doctors, a critical factor for promoting consumer health and wellbeing. The proposed hybrid deep learning approach demonstrates superior performance in sentiment classification accuracy, outperforming conventional methods by 11.11 percentage points. This methodological innovation enables more precise identification of consumer sentiment patterns across service dimensions.

CONCLUSION: The novel quality assessment framework introduced here provides actionable insights for advancing telemedicine platforms, driving progress toward precision healthcare and consumer-centric wellbeing. Furthermore, it enables healthcare consumers to select telemedicine services aligned with their personalized needs.

PMID:40351848 | PMC:PMC12065986 | DOI:10.1177/20552076251341163

J Med Signals Sens. 2025 Apr 19;15:10. doi: 10.4103/jmss.jmss_37_24. eCollection 2025.

ABSTRACT

BACKGROUND: Clinical decisions for stroke treatments, such as thrombolytic drugs for ischemic strokes or anticoagulants for hemorrhagic strokes, rely on accurate diagnosis and severity assessment. Our study uses diffusion-weighted magnetic resonance imaging and Convolutional Neural Networks (CNNs) to differentiate healthy and stroke samples, classify stroke types, and predict severity, aiding in decision-making for stroke management.

METHODS: We evaluated 143 patients: 85 with ischemic stroke and 58 with hemorrhagic stroke. For stroke diagnosis, we compared multimodal (apparent diffusion coefficient and diffusion-weighted imaging [DWI]) and single-modal (using separate images) preprocessing techniques. Our study introduced two models, Added CNN Layer-ResNet-50 (ACL-ResNet-50) and Added CNN Layer-MobileNetV1 (ACL-MobileNetV1), based on transfer learning (MobileNetV1 and ResNet-50), enhancing performance through reinforced layers. We compared our proposed models with a scenario in which only the final layer was replaced in ResNet-50 and MobileNetV1. Furthermore, we predicted National Institutes of Health Stroke Scale (NIHSS) scores in three ranges based on DWI images to gauge stroke severity. Evaluation criteria for the models included accuracy, sensitivity, specificity, and area under the curve (AUC).

RESULTS: In stroke classification (normal, ischemic, and hemorrhagic), ACL-MobileNetV1 outperformed other models, achieving 98% accuracy, 99% sensitivity, 98% specificity, and 99% AUC. For assessing ischemic stroke severity using NIHSS ranges, ACL-ResNet-50 showed the optimal performance with an accuracy of 0.92, sensitivity of 0.84, specificity of 0.92, and AUC of 0.95.

CONCLUSION: Our study's proposed method effectively classified stroke type and severity based on multimodal MR images, potentially as a practical decision support tool for stroke treatments.

PMID:40351777 | PMC:PMC12063969 | DOI:10.4103/jmss.jmss_37_24

JAMIA Open. 2025 May 9;8(3):ooaf033. doi: 10.1093/jamiaopen/ooaf033. eCollection 2025 Jun.

ABSTRACT

OBJECTIVES: This work evaluated algorithmic bias in biomarkers classification using electronic pathology reports from female breast cancer cases. Bias was assessed across 5 subgroups: cancer registry, race, Hispanic ethnicity, age at diagnosis, and socioeconomic status.

MATERIALS AND METHODS: We utilized 594 875 electronic pathology reports from 178 121 tumors diagnosed in Kentucky, Louisiana, New Jersey, New Mexico, Seattle, and Utah to train 2 deep-learning algorithms to classify breast cancer patients using their biomarkers test results. We used balanced error rate (BER), demographic parity (DP), equalized odds (EOD), and equal opportunity (EOP) to assess bias.

RESULTS: We found differences in predictive accuracy between registries, with the highest accuracy in the registry that contributed the most data (Seattle Registry, BER ratios for all registries >1.25). BER showed no significant algorithmic bias in extracting biomarkers (estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2) for race, Hispanic ethnicity, age at diagnosis, or socioeconomic subgroups (BER ratio <1.25). DP, EOD, and EOP all showed insignificant results.

DISCUSSION: We observed significant differences in BER by registry, but no significant bias using the DP, EOD, and EOP metrics for socio-demographic or racial categories. This highlights the importance of employing a diverse set of metrics for a comprehensive evaluation of model fairness.

CONCLUSION: A thorough evaluation of algorithmic biases that may affect equality in clinical care is a critical step before deploying algorithms in the real world. We found little evidence of algorithmic bias in our biomarker classification tool. Artificial intelligence tools to expedite information extraction from clinical records could accelerate clinical trial matching and improve care.

PMID:40351508 | PMC:PMC12063583 | DOI:10.1093/jamiaopen/ooaf033

Front Med (Lausanne). 2025 Apr 25;12:1475362. doi: 10.3389/fmed.2025.1475362. eCollection 2025.

ABSTRACT

Decalcification is crucial in enhancing the diagnostic accuracy and interpretability of cardiac CT images, particularly in cardiovascular imaging. Calcification in the coronary arteries and cardiac structures can significantly impact the quality of the images and hinder precise diagnostics. This study introduces a novel approach, Hybrid Models for Decalcify Cardiac CT (HMDC), aimed at enhancing the clarity of cardiac CT images through effective decalcification. Decalcification is critical in medical imaging, especially in cardiac CT scans, where calcification can hinder accurate diagnostics. The proposed HMDC leverages advanced deep-learning techniques and traditional image-processing methods for efficient and robust decalcification. The experimental results demonstrate the superior performance of HMDC, achieving an outstanding accuracy of 97.22%, surpassing existing decalcification methods. The hybrid nature of the model harnesses the strengths of both deep learning and traditional approaches, leading to more transparent and more diagnostically valuable cardiac CT images. The study underscores the potential impact of HMDC in improving the precision and reliability of cardiac CT diagnostics, contributing to advancements in cardiovascular healthcare. This research introduces a cutting-edge solution for decalcifying cardiac CT images and sets the stage for further exploration and refinement of hybrid models in medical imaging applications. The implications of HMDC extend beyond decalcification, opening avenues for innovation and improvement in cardiac imaging modalities, ultimately benefiting patient care and diagnostic accuracy.

PMID:40351458 | PMC:PMC12062122 | DOI:10.3389/fmed.2025.1475362

AI (Basel). 2024 Dec;5(4):2725-2738. doi: 10.3390/ai5040131. Epub 2024 Dec 3.

ABSTRACT

Substance use disorders affect 17.3% of Americans. Digital health solutions that use machine learning to detect substance use from wearable biosignal data can eventually pave the way for real-time digital interventions. However, difficulties in addressing severe between-subject data heterogeneity have hampered the adaptation of machine learning approaches for substance use detection, necessitating more robust technological solutions. We tested the utility of personalized machine learning using participant-specific convolutional neural networks (CNNs) enhanced with self-supervised learning (SSL) to detect drug use. In a pilot feasibility study, we collected data from 9 participants using Fitbit Charge 5 devices, supplemented by ecological momentary assessments to collect real-time labels of substance use. We implemented a baseline 1D-CNN model with traditional supervised learning and an experimental SSL-enhanced model to improve individualized feature extraction under limited label conditions. Results: Among the 9 participants, we achieved an average area under the receiver operating characteristic curve score across participants of 0.695 for the supervised CNNs and 0.729 for the SSL models. Strategic selection of an optimal threshold enabled us to optimize either sensitivity or specificity while maintaining reasonable performance for the other metric. Conclusion: These findings suggest that Fitbit data have the potential to enhance substance use monitoring systems. However, the small sample size in this study limits its generalizability to diverse populations, so we call for future research that explores SSL-powered personalization at a larger scale.

PMID:40351335 | PMC:PMC12065672 | DOI:10.3390/ai5040131

Small. 2025 May 12:e2503130. doi: 10.1002/smll.202503130. Online ahead of print.

ABSTRACT

In recent years, smart textile sensors have gained exponential growth in various sectors such as wearable technology and healthcare. However, addressing the demand for wearable textiles that offer both exceptional functionality (e.g., air-permeability, flexibility) and comfort remains a significant challenge. In this context, a rotary jet-spun textile piezoelectret is demonstrated, which is not reported so far. The piezoelectric output of the all-organic textile sensor is improved by 150% in voltage and 200% for current upon electrical poling. The finite element method revealed that the enhanced piezo-potential is attributed to the trapped polarized charges within the piezoelectret matrix. It exhibited outstanding piezoelectric properties with sensitivity of 400 mV kPa-1 (pressure range, 0.6-7 kPa), waterproofness (water contact angle ≈134°) and high breathability (10 kg m-2 per day), ensuring wearer comfort. Apart from monitoring different physiological signals such as pulse and respiratory rate, it also acted as a sensor array that displays the deep learning-aided pressure mapping with the accuracy of 98%. In addition, this textile accelerated faster proliferation and migration of L929 cell due to its piezoelectricity induced electrical stimulation, suggesting its potential application in wound dressings. Thus, this approach has huge potential to offer a scalable and versatile solution for biomedical technology.

PMID:40351106 | DOI:10.1002/smll.202503130

J Periodontal Implant Sci. 2025 Apr 2. doi: 10.5051/jpis.2500280014. Online ahead of print.

ABSTRACT

PURPOSE: The aim of this study was to evaluate the diagnostic and classification performance of a deep learning (DL) model for peri-implantitis-related bone defects using panoramic radiographs, focusing on defect morphology and severity.

METHODS: A dataset comprising 1,075 panoramic radiographs from 426 patients with peri-implantitis was analyzed. A total of 2,250 implant sites were annotated and categorized based on defect morphology (intraosseous [class I], supracrestal/horizontal [class II], or combined [class III]) and severity (slight, moderate, or severe). The ensemble-based YOLOv8 DL model was trained on 80% of the dataset, with the remaining 20% reserved for testing. Performance was assessed using classification metrics, including accuracy, precision, recall, and F1 score. The diagnostic accuracy of the DL model was also compared with that of 2 board-certified periodontal surgeons.

RESULTS: The DL model achieved an overall accuracy of 85.33%, significantly outperforming the periodontal surgeons, who exhibited a mean accuracy of 75.6%. The DL model performed especially well for slight class II defects, with precision and recall values of 100% and 98%, respectively. In contrast, the periodontal surgeons demonstrated higher accuracy in severe cases, particularly for class II defects.

CONCLUSIONS: DL enables reliable and accurate detection of peri-implantitis bone defects. It outperformed periodontal surgeons in overall accuracy, demonstrating its potential as a valuable second-opinion tool to support clinical decision-making. Future research should focus on expanding datasets and incorporating multimodal imaging.

PMID:40350773 | DOI:10.5051/jpis.2500280014

J Xray Sci Technol. 2025 May 11:8953996251335115. doi: 10.1177/08953996251335115. Online ahead of print.

ABSTRACT

In recent years Covid-19 impact is causing unprecedented difficulties worldwide, affecting lifestyle choices. The post-pandemic era has made this even more critical.COVID-19 triggers widespread inflammation throughout the body, potentially causing damage to the heart and other vital organs. Mortality data from COVID-19 clearly show that the highest death rates occur in individuals with chronic conditions, such as diabetes, pneumonia, cardiovascular disease (CVD), and acute renal failure.CVD is a particular concern in the medical field. The early detection of CVD remains a significant challenge, as early identification can prompt lifestyle changes and ensure appropriate medical interventions when needed. Individuals with CVD are at an increased risk for heart attack and other serious complications. There is a limited amount of data available to study the effects of COVID-19 on CVD in COVID-19 patients. However, it is essential to monitor these patients to ensure full recovery without complications. The proposed system is specifically designed for individuals experiencing prolonged symptoms following a COVID-19 infection, commonly referred to as long COVID patients. This research introduces a novel Decision-Making System for CVD Prediction, utilizing an improved dual-attention residual bi-directional gated recurrent neural network unit (DA-ResBiGRU) algorithm with AI-Biruni Earth Radius Optimization (ABER). The proposed system employs state-of-the-art predictive algorithms and real-time monitoring to assess individual patient risk profiles accurately. This research addresses the critical need for personalized risk assessment in patients with long-term COVID, aiming to assist healthcare providers in timely and targeted interventions. By analyzing intricate patterns in patient data, the decision-making system enhances the precision of CVD prediction. Additionally, the system's adaptive nature allows it to continuously learn from new patient data, ensuring that its predictions remain up-to-date and reflective of the evolving understanding of long COVID-related cardiovascular risks. The simulation findings of this research highlight the potential of the proposed algorithm to be integrated into clinical decision-making, helping healthcare professionals identify high-risk patients more effectively. The proposed method outperformed existing algorithms, such as Deep Neural Network (DNN), Long short-term memory (LSTM), Inception-v3, Xception, and MobileNetV2, achieving the highest accuracy (97.88%), sensitivity (95.50%), specificity (94.29%), precision (96.68%), and F-measure (95.85%).

PMID:40350710 | DOI:10.1177/08953996251335115

J Xray Sci Technol. 2025 May 11:8953996251331790. doi: 10.1177/08953996251331790. Online ahead of print.

ABSTRACT

ObjectiveThe purpose of this study is to perform multiple (≥3) material decomposition with deep learning method for spectral cone-beam CT (CBCT) imaging based on ultra-slow kV switching.ApproachIn this work, a novel deep neural network called SkV-Net is developed to reconstruct multiple material density images from the ultra-sparse spectral CBCT projections acquired using the ultra-slow kV switching technique. In particular, the SkV-Net has a backbone structure of U-Net, and a multi-head axial attention module is adopted to enlarge the perceptual field. It takes the CT images reconstructed from each kV as input, and output the basis material images automatically based on their energy-dependent attenuation characteristics. Numerical simulations and experimental studies are carried out to evaluate the performance of this new approach.Main ResultsIt is demonstrated that the SkV-Net is able to generate four different material density images, i.e., fat, muscle, bone and iodine, from five spans of kV switched spectral projections. Physical experiments show that the decomposition errors of iodine and CaCl2 are less than 6%, indicating high precision of this novel approach in distinguishing materials.SignificanceSkV-Net provides a promising multi-material decomposition approach for spectral CBCT imaging systems implemented with the ultra-slow kV switching scheme.

PMID:40350700 | DOI:10.1177/08953996251331790