Search Results (92)

High-quality, openly accessible clinical datasets remain a significant bottleneck in advancing both research and clinical applications within medical artificial intelligence. Case reports, often rich in multimodal clinical data, represent an underutilized resource for developing medical AI applications. We present an enhanced version of MultiCaRe, a dataset derived from open-access case reports on PubMed Central. This new version addresses the limitations identified in the previous release and incorporates newly added clinical cases and images (totaling 93,816 and 130,791, respectively), along with a refined hierarchical taxonomy featuring over 140 categories. Image labels have been meticulously curated using a combination of manual and machine learning-based label generation and validation, ensuring a higher quality for image classification tasks and the fine-tuning of multimodal models. To facilitate its use, we also provide a Python package for dataset manipulation, pretrained models for medical image classification, and two dedicated websites. The updated MultiCaRe dataset expands the resources available for multimodal AI research in medicine. Its scale, quality, and accessibility make it a valuable tool for developing medical AI systems, as well as for educational purposes in clinical and computational fields. Full article

Task-oriented medical dialogue systems face two fundamental challenges: the explosion of state-action space caused by numerous diseases and symptoms and the sparsity of informative signals during interactive diagnosis. These issues significantly hinder the accuracy and efficiency of automated clinical reasoning. To address these problems, we propose MA-HRL, a multi-agent hierarchical reinforcement learning framework that decomposes the diagnostic task into specialized agents. A high-level controller coordinates symptom inquiry via multiple worker agents, each targeting a specific disease group, while a two-tier disease classifier refines diagnostic decisions through hierarchical probability reasoning. To combat sparse rewards, we design an information entropy-based reward function that encourages agents to acquire maximally informative symptoms. Additionally, medical knowledge graphs are integrated to guide decision-making and improve dialogue coherence. Experiments on the SymCat-derived SD dataset demonstrate that MA-HRL achieves substantial improvements over state-of-the-art baselines, including +7.2% diagnosis accuracy, +0.91% symptom hit rate, and +15.94% symptom recognition rate. Ablation studies further verify the effectiveness of each module. This work highlights the potential of hierarchical, knowledge-aware multi-agent systems for interpretable and scalable medical diagnosis. Full article

Breast cancer is a condition characterized by the uncontrolled growth of breast cancer cells. The treatment for the disease, such as surgery, chemotherapy, radiotherapy, and systemic therapy, can significantly impact patients’ body image and overall quality of life. This study aimed to evaluate body image perceptions and cancer-related quality of life in women who underwent surgical treatment for breast cancer at a reference hospital in southern Brazil. One hundred six women with breast cancer, aged 21 to 93 years (M = 55.3; SD = 12.9), participated in this cross-sectional study. They responded to the Body Image and Relationships Scale (BIRS), Functional Assessment of Cancer Therapy for Breast Cancer scale (FACT-B), and a questionnaire on clinical and sociodemographic variables. Multiple linear regression analyses revealed that general perceived body image, as measured by BIRS, was significantly predicted by younger age and chemotherapy (F(2, 99) = 7.376, p = 0.003). These predictors accounted for 11.2% of the variance in BIRS (adjusted R² = 0.112). Hierarchical multiple regression analysis indicated that cancer-related quality of life was significantly predicted by younger age, use of psychiatric medication, and body image domains, including strength and health, social barriers, and appearance and sexuality. The complete model, encompassing all predictors, was significant (F(5, 96) = 15.970, p < 0.001) and explained 42.6% of the variance in FACT-B (adjusted R² = 0.426). Clinicians should be aware that younger patients who have undergone chemotherapy for breast cancer may experience changes in body image perception following surgery. Contributing factors such as younger age, use of psychiatric medications, and negative postoperative body image may be associated with a diminished quality of life related to cancer. Full article

This study investigates the evolutionary game dynamics of medical knowledge sharing (KS) among Chinese hospitals under government regulation, focusing on the strategic interactions between general hospitals, community health service centers, and governmental bodies. Leveraging evolutionary game theory, we construct a tripartite evolutionary game model incorporating replicator dynamics to characterize the strategic evolution of the involved parties. Our analysis examines the regulatory decisions of the government and the strategic choices of Chinese hospitals, considering critical factors such as KS costs, synergistic benefits, government incentives and penalties, and patient evaluations. The model is analyzed using replicator dynamic equations to derive evolutionary stable strategies (ESSs), complemented by numerical simulations for sensitivity analysis. Key findings reveal that the system’s equilibrium depends on the balance between KS benefits and costs, with government regulation and patient evaluations significantly influencing Chinese hospital behaviors. The results highlight that increasing government incentives and penalties, alongside enhancing patient feedback mechanisms, can effectively promote KS. However, excessive incentives may reduce willingness to regulate, suggesting the need for balanced policy design. This research provides novel theoretical insights and practical recommendations by (1) pioneering the application of a tripartite evolutionary game framework to model KS dynamics in China’s hierarchical healthcare system under government oversight, (2) explicitly integrating the dual influences of government regulation and patient evaluations on hospital strategies, and (3) revealing the non-linear effects of policy instruments. These contributions are crucial for optimizing Chinese medical resource allocation and fostering sustainable collaborative healthcare ecosystems. Full article

Clinical text classification presents significant challenges in healthcare informatics due to inherent asymmetries in domain-specific terminology, knowledge distribution across specialties, and imbalanced data availability. We introduce MTTL-ClinicalBERT, a symmetrical multi-task transfer learning framework that harmonizes knowledge sharing across diverse medical specialties while maintaining balanced performance. Our approach addresses the fundamental problem of symmetry in knowledge transfer through three innovative components: (1) an adaptive knowledge distillation mechanism that creates symmetrical information flow between related medical domains while preventing negative transfer; (2) a bidirectional hierarchical attention architecture that establishes symmetry between local terminology analysis and global contextual understanding; and (3) a dynamic task-weighting strategy that maintains equilibrium in the learning process across asymmetrically distributed medical specialties. Extensive experiments on the MTSamples dataset demonstrate that our symmetrical approach consistently outperforms asymmetric baselines, achieving average improvements of 7.2% in accuracy and 6.8% in F1-score across five major specialties. The framework’s knowledge transfer patterns reveal a symmetric similarity matrix between specialties, with strongest bidirectional connections between cardiovascular/pulmonary and surgical domains (similarity score 0.83). Our model demonstrates remarkable stability and balance in low-resource scenarios, maintaining over 85% classification accuracy with only 30% of training data. The proposed framework not only advances clinical text classification through its symmetrical design but also provides valuable insights into balanced information sharing between different medical domains, with broader implications for symmetrical knowledge transfer in multi-domain machine learning systems. Full article

Background/Objectives: Open-source AI models are increasingly applied in medical imaging, yet their effectiveness in detecting and classifying spinal stabilization systems remains underexplored. This study compares ChatGPT-4o (a large language model) and BiomedCLIP (a multimodal model) in their analysis of posturographic X-ray images (AP projection) to assess their accuracy in identifying the presence, type (growing vs. non-growing), and specific system (MCGR vs. PSF). Methods: A dataset of 270 X-ray images (93 without stabilization, 80 with MCGR, and 97 with PSF) was analyzed manually by neurosurgeons and evaluated using a three-stage AI-based questioning approach. Performance was assessed via classification accuracy, Gwet’s Agreement Coefficient (AC1) for inter-rater reliability, and a two-tailed z-test for statistical significance (p < 0.05). Results: The results indicate that GPT-4o demonstrates high accuracy in detecting spinal stabilization systems, achieving near-perfect recognition (97–100%) for the presence or absence of stabilization. However, its consistency is reduced when distinguishing complex growing-rod (MCGR) configurations, with agreement scores dropping significantly (AC1 = 0.32–0.50). In contrast, BiomedCLIP displays greater response consistency (AC1 = 1.00) but struggles with detailed classification, particularly in recognizing PSF (11% accuracy) and MCGR (4.16% accuracy). Sensitivity analysis revealed GPT-4o’s superior stability in hierarchical classification tasks, while BiomedCLIP excelled in binary detection but showed performance deterioration as the classification complexity increased. Conclusions: These findings highlight GPT-4o’s robustness in clinical AI-assisted diagnostics, particularly for detailed differentiation of spinal stabilization systems, whereas BiomedCLIP’s precision may require further optimization to enhance its applicability in complex radiographic evaluations. Full article

Medical Visual Question Answering (Med-VQA) is designed to accurately answer medical questions by analyzing medical images when given both a medical image and its corresponding clinical question. Designing the MedVQA system holds profound importance in assisting clinical diagnosis and enhancing diagnostic accuracy. Building upon this foundation, Hierarchical Medical VQA extends Medical VQA by organizing medical questions into a hierarchical structure and making level-specific predictions to handle fine-grained distinctions. Recently, many studies have proposed hierarchical Med-VQA tasks and established datasets. However, several issues still remain: (1) imperfect hierarchical modeling leads to poor differentiation between question levels, resulting in semantic fragmentation across hierarchies. (2) Excessive reliance on implicit learning in Transformer-based cross-modal self-attention fusion methods, which can obscure crucial local semantic correlations in medical scenarios. To address these issues, this study proposes a Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion (HiCA-VQA) method. Specifically, the hierarchical modeling includes two modules: Hierarchical Prompting for fine-grained medical questions and Hierarchical Answer Decoders. The hierarchical prompting module pre-aligns hierarchical text prompts with image features to guide the model in focusing on specific image regions according to question types, while the hierarchical decoder performs separate predictions for questions at different levels to improve accuracy across granularities. The framework also incorporates a cross-attention fusion module where images serve as queries and text as key-value pairs. This approach effectively avoids the irrelevant signals introduced by global interactions while achieving lower computational complexity compared to global self-attention fusion modules. Experiments on the Rad-Restruct benchmark demonstrate that the HiCA-VQA framework outperforms existing state-of-the-art methods in answering hierarchical fine-grained questions, especially achieving an 18 percent improvement in the F1 score. This study provides an effective pathway for hierarchical visual question answering systems, advancing medical image understanding. Full article

Background/Objective: In nursing practice, differences have been noted between the shared habitus acquired during academic training and professional practices within healthcare systems. In this context, nurses tend to experience an impact on their autonomy due to the ways in which their professional habitus has been established, which, in some way, alters the cultural capital acquired during their academic training. The objective of this study was to identify factors that facilitate and/or limit autonomy in nursing practice based on professional habitus. Method: This research was conducted using a hermeneutic qualitative study framed within a critical approach that incorporated Bourdieu’s theory of fields (habitus, field, and capital). This study included 11 registered nurses working in hospital settings, 17 nursing students, and six university professors. Data collection included 34 sociodemographic forms, 34 individual semi-structured interviews, and five focus group discussions conducted with an interview guide. The collected data were analyzed using an interpretative hermeneutic approach, integrating grounded theory and Bourdieu’s theory of fields, focusing on the concepts of habitus, field, and capital. Results: This study identified a central theme—clarification of the nurse’s role (professional habitus)—alongside three subthemes: (1) strengthening the nursing identity (identity habitus), (2) optimizing nursing education (optimization habitus), and (3) reinforcing professional credibility (validation habitus). Autonomy was found to be influenced by hierarchical structures, power relations, and institutional constraints within the healthcare social field, which led to limitations in the accumulation of nurses’ symbolic capital. Conclusions: The professional habitus of nurses is shaped by various elements within the healthcare social field. This field is constrained by hierarchical structures and factors such as subordination to the hegemonic biomedical discourse and the medical profession, limited recognition of humanized care, institutional restrictions on acknowledging the nursing process, and a lack of solidarity and leadership. These constraints ultimately hinder the accumulation of symbolic and social capital in nursing, leading to a loss of autonomy and hindering professional development. Full article

Treatment efficacy for age-related macular degeneration relies on early diagnosis and precise determination of the disease stage. This involves analyzing biomarkers in retinal images, which can be challenging when handling a large flow of patients and can compromise the quality of healthcare services. Clinical decision support systems offer a solution to this issue by employing intelligent algorithms to recognize biomarkers and specify the age-related macular degeneration stage through the analysis of retinal images. However, different stages of age-related macular degeneration may exhibit similar biomarkers, complicating the application of intelligent algorithms. This article presents a hybrid and hierarchical classification method for solving these problems. By leveraging the hybrid structure of the classifier, we can effectively manage issues commonly encountered with medical datasets, such as class imbalance and strong correlations between variables. The modifications to the intelligent algorithm proposed in this work for staging age-related macular degeneration resulted in an increase in average accuracy, sensitivity, and specificity of 20% compared to initial values. The Cohen’s Kappa coefficient, used for consistency estimation between the regression model and expert assessments of the intermediate class severity, was 0.708, indicating a high level of agreement. Full article

Healthcare 4.0 addresses modernization and digital transformation challenges, such as home-based care and precision treatments, by leveraging advanced technologies to enhance accessibility and efficiency. Semantic technologies, particularly knowledge graphs (KGs), have proven instrumental in representing interconnected medical data and improving clinical decision-support systems. We previously introduced a semantic framework to assist medical experts during patient interactions. Operating iteratively, the framework prompts medical experts with relevant questions based on patient input, progressing toward accurate diagnoses in time-constrained settings. It comprises two components: (a) a KG representing symptoms, diseases, and their relationships, and (b) algorithms that generate questions and prioritize hypotheses—a ranked list of symptom–disease pairs. An earlier extension enriched the KG with a symptom ontology, incorporating hierarchical structures and inheritance relationships to improve accuracy and question-generation capabilities. This paper further extends the framework by introducing strategies tailored to specific medical domains. Strategies integrate domain-specific knowledge and algorithms, refining decision making while maintaining the iterative nature of expert–patient interactions. We demonstrate this approach using an emergency medicine case study, focusing on life-threatening conditions. The KG is enriched with attributes tailored to emergency contexts and supported by dedicated algorithms. Boolean rules attached to graph edges evaluate to TRUE or FALSE at runtime based on patient-specific data. These enhancements optimize decision making by embedding domain-specific goal-oriented knowledge and inference processes, providing a scalable and adaptable solution for diverse medical contexts. Full article

Background: Breast cancer screening through mammography interpretation is crucial for early detection and improved patient outcomes. However, the manual classification of mammograms using the BIRADS (Breast Imaging-Reporting and Data System) remains challenging due to subtle imaging features, inter-reader variability, and increasing radiologist workload. Traditional computer-aided detection systems often struggle with complex feature extraction and contextual understanding of mammographic abnormalities. To address these limitations, this study proposes MammoViT, a novel hybrid deep learning framework that leverages both ResNet50’s hierarchical feature extraction capabilities and Vision Transformer’s ability to capture long-range dependencies in images. Methods: We implemented a multi-stage approach utilizing a pre-trained ResNet50 model for initial feature extraction from mammogram images. To address the significant class imbalance in our four-class BIRADS dataset, we applied SMOTE (Synthetic Minority Over-sampling Technique) to generate synthetic samples for minority classes. The extracted feature arrays were transformed into non-overlapping patches with positional encodings for Vision Transformer processing. The Vision Transformer employs multi-head self-attention mechanisms to capture both local and global relationships between image patches, with each attention head learning different aspects of spatial dependencies. The model was optimized using Keras Tuner and trained using 5-fold cross-validation with early stopping to prevent overfitting. Results: MammoViT achieved 97.4% accuracy in classifying mammogram images across different BIRADS categories. The model’s effectiveness was validated through comprehensive evaluation metrics, including a classification report, confusion matrix, probability distribution, and comparison with existing studies. Conclusions: MammoViT effectively combines ResNet50 and Vision Transformer architectures while addressing the challenge of imbalanced medical imaging datasets. The high accuracy and robust performance demonstrate its potential as a reliable tool for supporting clinical decision-making in breast cancer screening. Full article

Background: Orofacial pain (OFP) encompasses a complex array of conditions affecting the face, mouth, and jaws, often leading to significant diagnostic challenges and high rates of misdiagnosis. Artificial intelligence, particularly large language models like GPT4 (OpenAI, San Francisco, CA, USA), offers potential as a diagnostic aid in healthcare settings. Objective: To evaluate the diagnostic accuracy of GPT4 in OFP cases as a clinical decision support system (CDSS) and compare its performance against treating clinicians, expert evaluators, medical students, and general practitioners. Methods: A total of 100 anonymized patient case descriptions involving diverse OFP conditions were collected. GPT4 was prompted to generate primary and differential diagnoses for each case using the International Classification of Orofacial Pain (ICOP) criteria. Diagnoses were compared to gold-standard diagnoses established by treating clinicians, and a scoring system was used to assess accuracy at three hierarchical ICOP levels. A subset of 24 cases was also evaluated by two clinical experts, two final-year medical students, and two general practitioners for comparative analysis. Diagnostic performance and interrater reliability were calculated. Results: GPT4 achieved the highest accuracy level (ICOP level 3) in 38% of cases, with an overall diagnostic performance score of 157 out of 300 points (52%). The model provided accurate differential diagnoses in 80% of cases (400 out of 500 points). In the subset of 24 cases, the model’s performance was comparable to non-expert human evaluators but was surpassed by clinical experts, who correctly diagnosed 54% of cases at level 3. GPT4 demonstrated high accuracy in specific categories, correctly diagnosing 81% of trigeminal neuralgia cases at level 3. Interrater reliability between GPT4 and human evaluators was low (κ = 0.219, p < 0.001), indicating variability in diagnostic agreement. Conclusions: GPT4 shows promise as a CDSS for OFP by improving diagnostic accuracy and offering structured differential diagnoses. While not yet outperforming expert clinicians, GPT4 can augment diagnostic workflows, particularly in primary care or educational settings. Effective integration into clinical practice requires adherence to rigorous guidelines, thorough validation, and ongoing professional oversight to ensure patient safety and diagnostic reliability. Full article

With technological advancements, remarkable progress has been made with the convergence of health sciences and Artificial Intelligence (AI). Modern health systems are proposed to ease patient diagnostics. However, the challenge is to provide AI-based precautions to patients and doctors for more accurate risk assessment. The proposed healthcare system aims to integrate patients, doctors, laboratories, pharmacies, and administrative personnel use cases and their primary functions onto a single platform. The proposed framework can also process microscopic images, CT scans, X-rays, and MRI to classify malignancy and give doctors a set of AI precautions for patient risk assessment. The proposed framework incorporates various DCNN models for identifying different forms of tumors and fractures in the human body i.e., brain, bones, lungs, kidneys, and skin, and generating precautions with the help of the Fined-Tuned Large Language Model (LLM) i.e., Generative Pretrained Transformer 4 (GPT-4). With enough training data, DCNN can learn highly representative, data-driven, hierarchical image features. The GPT-4 model is selected for generating precautions due to its explanation, reasoning, memory, and accuracy on prior medical assessments and research studies. Classification models are evaluated by classification report (i.e., Recall, Precision, F1 Score, Support, Accuracy, and Macro and Weighted Average) and confusion matrix and have shown robust performance compared to the conventional schemes. Full article

The rising prevalence of diseases linked to factors such as excessive alcohol and tobacco use, sedentary lifestyles, and poor nutrition has led to a greater focus on Personal Health Promotion (PHP) as a preventive measure. PHP emphasizes improving quality of life and well-being, driven by advances in medical technology, including virtual and augmented reality. However, as PHP systems grow in popularity, concerns over personal data security, such as account theft and information breaches, have become increasingly important. To address these concerns, this study proposes a game-based personalized health promotion system that integrates Key-Policy Attribute-Based Encryption (KP-ABE), key insulation, time-bound encryption. These methods ensure data security through hierarchical access control and dynamic time management, protecting personal health records and exercise prescriptions. The system also incorporates key insulation to enhance the security of private keys. This multi-layered security approach provides a robust solution for safeguarding sensitive data within PHP systems while accommodating dynamic subscription needs and legal access requirements. Full article

The path planning of flexible needles in robotic puncturing presents challenges such as limited model accuracy and poor real-time performance, which affect both efficiency and accuracy in complex medical scenarios. To address these issues, this paper proposes a deep reinforcement learning-based path planning method for flexible needles in robotic puncturing. Firstly, we introduce a unicycle model to describe needle motion and design a hierarchical model to simulate layered tissue interactions with the needle. The forces exerted by tissues at different positions on the flexible needle are considered, achieving a combination of kinematic and mechanical models. Secondly, a deep reinforcement learning framework is built, integrating obstacle avoidance and target attraction to optimize path planning. The design of state features, the action space, and the reward function is tailored to enhance the model’s decision-making capabilities. Moreover, we incorporate a retraction mechanism to bolster the system’s adaptability and robustness in the dynamic context of surgical procedures. Finally, laparotomy simulation results validate the proposed method’s effectiveness and generalizability, demonstrating its superiority over current state-of-the-art techniques in robotic puncturing. Full article