Search Results (726)

Background/Objectives: Radiodermitis is an inflammatory or dystrophic skin process caused by the direct action of ionizing radiation. The primary objective was to study two clinical cases. The secondary objective was to propose the foundations of an intelligent system for decision support in complex cases of radiodermitis diagnosis that can operate even in the case of a low amount of available clinical data that can be used for training. Methods: The first case is a female patient, aged 74 years, with squamous cell carcinoma on a chronic radiodermitis site, which appeared after 20 years of local radiotherapy treatment for mammary adenocarcinoma. Dermatologic examination revealed five round-oval nodules between 2 and 8 cm in diameter. They were pink colored with lilac edges, hard and infiltrated on palpation, adherent to the subcutaneous tissue, painless, and located above and lateral on the right chest and the upper region of the right hypochondrium. The second case concerns a 60-year-old patient with verrucous squamous cell carcinoma appearing on a chronic radiodermatitis 40 years after local radio-therapeutic treatment with Chaoul rays for a deep right temporal region mycosis. There are presented artificial intelligence (AI) challenges regarding the application of advanced hybrid models in decision support for diagnosis of difficult radiodermitis cases, in that intelligent computing must be made in the context of very little available data, and collaboration between physicians is necessary. Results: Both cases were confirmed by histology as squamos cell carcinomas. In the AI research, the adaptation of the IntMediSys intelligent system was proposed for solving complex cases of radiodermitis. The proposal integrates different AI technologies, which include agents, intelligent computing, and blackboard systems. Conclusions: The presented first cases confirm the presence of a squamous cell carcinoma that appeared on chronic radiodermitis after a long latency. The foundations of a highly complex collaboration and decision support system that can assist physicians in the radiodermitis diagnostics establishment that opens the path for further development are presented. Full article

This article presents a methodological framework for elective surgery scheduling based on the integration of patient-specific Digital Twins (DTs) and reinforcement learning (RL). The proposed approach aims to support the future development of an intelligent e-health platform for dynamic, data-driven prioritization of surgical patients. We generate prioritization scores by modeling clinical, economic, behavioral, and social variables in real time and optimize access through a reinforcement learning engine designed to maximize long-term system performance. The methodology is designed as a modular, transparent, and interoperable digital decision-support architecture aligned with the goals of organizational transformation and equitable healthcare delivery. To validate its potential, we simulate realistic surgical scheduling scenarios using synthetic patient data. Results demonstrate substantial improvements compared withto traditional strategies, including a 55.1% reduction in average wait time, a 41.9% decrease in clinical risk at surgery, a 16.1% increase in OR utilization, and a significant increase in the prioritization of socially vulnerable patients. These findings highlight the value of the proposed framework as a foundation for future smart healthcare platforms that support transparent, adaptive, and ethically aligned decision-making in surgical scheduling. Full article

Background/Objectives: Breast reconstruction (BR) following mastectomy plays a critical role in post-cancer care by offering both physical and psychological benefits. Despite advancements in techniques and shared decision-making (SDM), BR uptake remains inconsistent. This systematic review aims to synthesize evidence on objective (medical and socioeconomic) and subjective (psychological and personal) factors influencing BR decision-making among women undergoing mastectomy for breast cancer. Methods: A systematic search was conducted across PubMed, ScienceDirect, OVID, and Google Scholar, identifying peer-reviewed studies published between January 2013 and 25 July 2024. Eligible studies examined determinants of BR decisions in women undergoing therapeutic mastectomy, excluding perspectives of non-patient stakeholders and post-decision outcomes. The risk of bias and study quality were assessed using the Quality Appraisal for Diverse Studies (QuADS) tool. This review was registered in PROSPERO (CRD42023456198) and followed PRISMA guidelines. Results: Twenty-seven studies comprising 994,528 participants across 16 countries met the inclusion criteria. The objective factors included age, comorbidities, insurance coverage, physician recommendations, and healthcare access. The subjective factors encompassed body image concerns, self-esteem, fear of recurrence, and emotional readiness. Younger age, private insurance, and active physician counseling were associated with increased BR uptake, while older age, lack of information, and financial or logistical barriers reduced uptake. Regional disparities were noted across healthcare systems. Conclusions: BR decisions are influenced by complex, interrelated clinical, psychological, and systemic factors. Integrating SDM tools, enhancing patient education, and addressing healthcare inequities are essential for supporting informed and equitable BR decision-making. Future research should prioritize longitudinal studies and policy interventions to improve access to and patient satisfaction with BR outcomes. Full article

Women exhibit marked physiological transformations in pregnancy, mandating regular and holistic assessment. Maternal and fetal vitality is governed by a spectrum of clinical, demographic, and lifestyle factors throughout this critical period. The existing maternal health monitoring techniques lack precision in assessing pregnancy-related risks, often leading to late interventions and adverse outcomes. Accurate and timely risk prediction is crucial to avoid miscarriages. This research proposes a deep learning framework for personalized pregnancy risk prediction using the NFHS-5 dataset, and class imbalance is addressed through a hybrid NearMiss-SMOTE approach. Fifty-one primary features are selected via the LASSO to refine the dataset and enhance model interpretability and efficiency. The framework integrates a multimodal model (NFHS-5, fetal plane images, and EHG time series) along with two core architectures. ResRNN-Net further combines Bi-LSTM, CNNs, and attention mechanisms to capture sequential dependencies. MultiScaleFusion-Net leverages GRU and multiscale convolutions for effective feature extraction. Additionally, TabNet and MLP models are explored to compare interpretability and computational efficiency. SHAP and Grad-CAM are used to ensure transparency and explainability, offering both feature importance and visual explanations of predictions. The proposed models are trained using 5-fold stratified cross-validation and evaluated with metrics including accuracy, precision, recall, F1-score, and ROC–AUC. The results demonstrate that MultiScaleFusion-Net balances accuracy and computational efficiency, making it suitable for real-time clinical deployment, while ResRNN-Net achieves higher precision at a slight computational cost. Performance comparisons with baseline machine learning models confirm the superiority of deep learning approaches, achieving over 80% accuracy in pregnancy complication prediction. Full article

Artificial intelligence (AI) is transforming dentomaxillofacial radiology education by enabling adaptive, personalized, and data-driven learning experiences. This review critically examines the pedagogical potential of AI within dental curricula, focusing on its ability to enhance student engagement, improve diagnostic competencies, and streamline clinical decision-making processes. Key innovations include real-time feedback systems, AI-guided simulations, automated assessments, and clinical decision support tools. Through these resources, AI transforms static learning into dynamic, interactive, and competency-based education. Additionally, this review discusses the integration of AI into formative assessment frameworks, such as OSCEs and mini-CEX, and its impact on student confidence, performance tracking, and educational scalability. Although primarily narrative in structure, this review synthesizes the current literature on dentomaxillofacial radiology education, supported by selected insights from medical radiology, to provide a comprehensive and up-to-date perspective on the educational applications of AI. Challenges (including ethical implications and other practical considerations) are addressed, alongside future directions for research and curriculum development. Overall, AI has the potential to significantly enhance radiology education by fostering clinically competent, ethically grounded, and technologically literate dental professionals. Full article

Background: This study investigated hematological and biochemical parameters, including cell population data (CPD), to evaluate their association with severity in COVID-19 and non-COVID-19 patients. Identifying these parameters could aid in disease monitoring and clinical decision-making. Methods: A retrospective analysis of 8401 patients, including 603 COVID-19 cases and 7546 non-COVID-19 cases, were conducted. Complete blood count (CBC) and routine chemistry results obtained near the time of real-time polymerase chain reaction testing were analyzed to assess their associations with disease severity. A matched cohort analysis was performed to adjust for potential confounding factors, such as age and sex. Results: COVID-19 patients with elevated neutrophil side fluorescence light (NE-SFL), platelet-to-lymphocyte ratio (PLR), glucose, and aspartate aminotransferase (AST), along with decreased plateletcrit, were more likely to experience severe outcomes, such as hospitalization or death. In addition, decreased hemoglobin, lymphocyte side scatter (LY-SSC), and albumin, as well as increased leukocyte and monocyte side scatter (MO-SSC), were associated with a greater severity, regardless of COVID-19 status. Conclusions: We identified hematologic and chemical assay biomarkers that correlate with severe COVID-19. These findings may provide important information regarding the disease progression and clinical management. Incorporating these biomarkers into clinical decision support systems could facilitate personalized treatment strategies, optimize resource allocation, and enable real-time severity stratification. Full article

This study introduces the PROCDEC dataset, a novel collection of 1140 cases with 30 cardiovascular risk factors gathered over a 10-year period from school children in Santa Clara, Cuba. The dataset was curated with input from medical experts in pediatric cardiology, endocrinology, general medicine, and clinical laboratory, ensuring its clinical relevance. We conducted a rigorous performance evaluation of 10 machine learning (ML) algorithms to classify cardiovascular risk into two categories: at risk and not at risk. The models were assessed using a stratified k-fold cross-validation approach to enhance the reliability of the findings. Among the evaluated models—Bayes Net, Naive Bayes, SMO, K-Nearest Neighbors (KNN), Logistic Regression, AdaBoost, Multilayer Perceptron (MLP), J48, Logistic Model Tree (LMT), and Random Forest (RF)—the best-performing classifiers (MLP, LMT, J48 and Logistic Regression) achieved F1-score values exceeding 0.83, indicating strong predictive capability. To improve interpretability, we employed feature selection techniques to rank the most influential risk factors. Key contributors to classification performance included hypertension, hyperreactivity, body mass index (BMI), uric acid, cholesterol, parental hypertension, and sibling dyslipidemia. These findings align with established clinical knowledge and reinforce the potential of ML models for pediatric cardiovascular risk assessment. Unlike previous studies, our research not only evaluates multiple ML techniques but also emphasizes their clinical applicability and interpretability, which are critical for real-world implementation. Future work will focus on validating these models with external datasets and integrating them into decision-support systems for early risk detection. Full article

Background/Objectives: Artificial intelligence (AI)-based systems are increasingly being used to assist radiologists in detecting breast cancer on mammograms. However, applying fixed AI score thresholds across diverse lesion types may compromise diagnostic performance, especially in women with dense breasts. This study aimed to determine optimal category-specific AI thresholds and to analyze discrepancies between AI predictions and radiologist assessments, particularly for BI-RADS 4A versus 4B/4C lesions. Methods: We retrospectively analyzed 194 mammograms (76 BI-RADS 4A and 118 BI-RADS 4B/4C) using FDA-approved AI software. Lesion characteristics, breast density, AI scores, and pathology results were collected. A receiver operating characteristic (ROC) analysis was conducted to determine the optimal thresholds via Youden’s index. Discrepancy analysis focused on BI-RADS 4A lesions with AI scores of ≥35 and BI-RADS 4B/4C lesions with AI scores of <35. Results: AI scores were significantly higher in malignant versus benign cases (72.1 vs. 20.9; p < 0.001). The optimal AI threshold was 19 for BI-RADS 4A (AUC = 0.685) and 63 for BI-RADS 4B/4C (AUC = 0.908). In discordant cases, BI-RADS 4A lesions with scores of ≥35 had a malignancy rate of 43.8%, while BI-RADS 4B/4C lesions with scores of <35 had a malignancy rate of 19.5%. Conclusions: Using category-specific AI thresholds improves diagnostic accuracy and supports radiologist decision-making. However, limitations persist in BI-RADS 4A cases with overlapping scores, reinforcing the need for radiologist oversight and tailored AI integration strategies in clinical practice. Full article

Background/Objectives: Immediate implant-based breast reconstruction is an established option for selected patients undergoing mastectomy. However, patients with large and ptotic breasts present specific reconstructive challenges, often requiring tailored approaches to minimize complications and optimize aesthetics. This pilot study aimed to evaluate the clinical feasibility and effectiveness of a mobile application developed to support intraoperative decision-making based on an institutional algorithm for breast reconstruction. It is also important to underline that this pilot study was exploratory in nature and primarily aimed at assessing feasibility and adherence to an app-based decision pathway, rather than comparative efficacy. Methods: We conducted a prospective observational study from October 2023 to December 2024 at the University Hospital of Sassari. Female patients with large and ptotic breasts undergoing immediate implant-based reconstruction were included. A mobile app, developed using MIT App Inventor 2, implemented our institution’s algorithm and guided surgeons through both preoperative and intraoperative decision-making. Surgical options included subpectoral, prepectoral with autologous fascial flaps, or prepectoral with acellular dermal matrix (ADM) reconstruction, depending on flap thickness and fascia integrity. Results: Sixteen patients (21 reconstructed breasts) were included. Surgical planning and execution followed app-generated recommendations in all cases, with no intraoperative deviations. Subpectoral reconstruction was performed in six patients, prepectoral with ADM in eight, and prepectoral with fascial flaps in two. The app was rated positively by all surgeons and facilitated consistent decision-making. Conclusions: The proposed mobile application, described in this pilot study, proved to be a feasible and effective decision-support tool for implant-based breast reconstruction in patients with challenging anatomy. It standardized surgical choices, supported training, and has the potential to enhance reproducibility and safety in complex reconstructive procedures. Full article

Background/Objectives: Panoramic radiography (PANO) is widely utilized for routine dental examinations, as a single PANO image captures most anatomical structures and clinical findings, enabling an initial assessment of overall dental health. Dentists rely on PANO images to enhance clinical diagnosis and inform treatment planning. With the advancement of artificial intelligence (AI), the integration of clinical data and AI-driven analysis presents significant potential for supporting medical applications. Methods: The proposed method focuses on the segmentation and localization of impacted third molars in PANO images, incorporating Sobel edge detection and enhancement methods to improve feature extraction. A convolutional neural network (CNN) was subsequently trained to develop an automated impacted tooth detection system. Results: Experimental results demonstrated that the trained CNN achieved an accuracy of 84.48% without image preprocessing and enhancement. Following the application of the proposed preprocessing and enhancement methods, the detection accuracy improved significantly to 98.66%. This substantial increase confirmed the effectiveness of the image preprocessing and enhancement strategies proposed in this study. Compared to existing methods, which achieve approximately 90% accuracy, the proposed approach represents a notable improvement. Furthermore, the entire process, from inputting a raw PANO image to completing the detection, takes only 4.4 s. Conclusions: This system serves as a clinical decision support system for dentists and medical professionals, allowing them to focus more effectively on patient care and treatment planning. Full article

Background: Polypharmacy, commonly defined as the use of five or more medications, is a growing concern in hospitals due to its association with adverse drug reactions, functional decline, and increased healthcare costs. Proactive deprescribing, which involves the planned discontinuation of unnecessary or potentially harmful medications, can optimise medication use. However, multiple barriers hinder its implementation. Saudi Arabia offers a unique context for deprescribing due to strong family roles in care, prevalent prescribing norms, and ongoing shifts toward value-based healthcare. This study explores the barriers and facilitators to proactive deprescribing among physicians in Saudi hospitals using the Theoretical Domains Framework (TDF). The TDF was used as it effectively identifies behavioural factors influencing clinical decision making in practice. Methods: Semi-structured interviews were conducted with 27 purposively sampled physicians experienced in managing polypharmacy. The interviews were transcribed and analysed thematically, with behavioural determinants identified and categorised according to the 14 domains of the Theory of Planned Behaviour (TDF). Results: Enablers included the availability of deprescribing guidelines, decision–support tools, interprofessional collaboration, and institutional backing. Physicians with specialised training expressed greater confidence in conducting deprescribing. Identified barriers included limited time, heavy workload, absence of standardised protocols, medico-legal concerns, resistance from patients and caregivers, and lack of formal training. These factors were categorised under seven key TDF domains, with Environmental Context and Resources, Social Influences, and Beliefs About Capabilities identified as the most influential in shaping physicians’ deprescribing practices. Interactions between factors were observed, where supportive environments and collaborative teams helped offset key barriers such as time constraints, legal concerns, and patient resistance. Conclusions: This study identified key behavioural and contextual factors influencing proactive deprescribing in Saudi hospital settings. Addressing barriers such as heavy workload, medico-legal concerns, and lack of standardised protocols through targeted interventions, including clinician training, institutional support, and multidisciplinary collaboration, may facilitate the integration of deprescribing into routine practice. The findings offer context-specific insights to inform future efforts aimed at improving medication safety and optimising prescribing in the Saudi healthcare system. Full article

Background: Bloodstream infections continue to pose a serious global health threat due to their high morbidity and mortality, further worsened by rising antimicrobial resistance and delays in starting targeted therapy. This study assesses the accuracy and timeliness of therapeutic recommendations produced by an artificial intelligence (AI)-driven and machine-learning (ML) clinical decision support system (CDSS), comparing results based on molecular diagnostics alone with those that combine molecular and phenotypic data (standard cultures). Methods: In a prospective cross-sectional study conducted in Lima, Peru, 117 blood cultures were analyzed using FilmArray/GeneXpert for molecular identification and MALDI-TOF/VITEK 2.0 for phenotypic profiling. The AI/ML-based CDSS provided treatment recommendations in two formats, which were assessed for concordance and turnaround time. Results: Therapeutic recommendations showed 80.3% consistency between data types, with 86.3% concordance in pathogen and resistance detection. Notably, molecular-only recommendations were delivered 29 h earlier than those incorporating phenotypic data. Escherichia coli was the most frequently isolated pathogen, with a 95% concordance in suggested therapy. A substantial agreement was observed in treatment consistency (Kappa = 0.80). Conclusions: These findings highlight the potential of using AI-powered CDSS in conjunction with molecular diagnostics to accelerate clinical decision-making in bacteremia, supporting more timely interventions and improved antimicrobial stewardship. Further research is warranted to assess scalability and impact across diverse clinical settings. Full article

This review aims to explore the role of immunotherapeutic strategies—primarily intravenous immunoglobulin (IVIG), plasma exchange (PLEX), and selected immunomodulatory agents—in the treatment of neurological and psychiatric disorders with suspected or confirmed autoimmune mechanisms. A central focus is placed on understanding the immunopathology of these conditions through the identification and characterization of disease-associated autoantibodies. Disorders such as autoimmune encephalitis, myasthenia gravis, limbic epilepsy, neuropsychiatric systemic lupus erythematosus (NPSLE), and certain forms of schizophrenia have shown clinical responses to immunotherapy, suggesting an underlying autoimmune basis in a subset of patients. The review also highlights the diagnostic relevance of detecting autoantibodies targeting neuronal receptors, such as NMDA and AMPA receptors, or neuromuscular junction components, as biomarkers that guide therapeutic decisions. Furthermore, we synthesize findings from published randomized controlled trials (RCTs) that have validated the efficacy of IVIG and PLEX in specific diseases, such as Guillain–Barré syndrome, and myasthenia gravis. Emerging clinical evidence supports expanding these treatments to other conditions where autoimmunity is implicated. By integrating immunological insights with clinical trial data, this review offers a comprehensive perspective on how immunotherapies may be tailored to target autoimmune contributors to neuropsychiatric disease. Full article

As the adoption of focal therapy (FT) for prostate cancer (PCa) grows, the demand for accurate post-treatment imaging to monitor outcomes and detect residual or recurrent cancer increases. Traditional diagnostic systems like the Prostate Imaging Reporting and Data System (PI-RADS) are ill-suited for post-FT evaluations due to treatment-induced tissue changes. MRI-based scoring systems specific for evaluation after FT have been developed to address these challenges and improve post-FT imaging accuracy by distinguishing benign alterations from recurrence. The currently developed scoring systems are Transatlantic Recommendations for Prostate Gland Evaluation with MRI after Focal Therapy (TARGET) and Prostate Imaging after Focal Ablation (PI-FAB). In this review, we describe and compare these two systems. These scoring systems standardize imaging assessments, enhance follow-up care, and support clinical decision-making. While promising, TARGET and PI-FAB require further large-scale validation to confirm their utility. Nevertheless, they represent critical advances in optimizing PCa management, particularly for patients undergoing FT, by improving diagnostic accuracy and guiding treatment decisions. Full article

Despite encouraging evidence for the efficacy of comprehensive and intensive behavioral intervention (CIBI) programs, the majority of studies have focused on relatively narrow, deficit-focused outcomes. More specifically, although adaptive social communication and interaction (SCI) are essential for facilitative functioning, the majority of studies have utilized instruments that capture only the severity of SCI symptoms. Thus, given the importance of the comprehensive and appropriate characterization of distinct SCI adaptive skills in CIBI, in this review, based on PubMed search strategies to identify relevant published articles, we provide a critical appraisal of two of the most commonly used adaptive functioning measures—the Vineland Adaptive Behavior Scales-Third Edition (Vineland-3) and the Adaptive Behavior Assessment System-Third Edition (ABAS-3), for characterizing SCI in the behavioral intervention context. The review focused on periodic outcome and treatment planning assessment in people with autism spectrum disorder receiving CIBI programs. Instrument technical manuals were reviewed and a PubMed search was used to identify published manuscripts, with relevance to Vineland-3 and ABAS-3 development, psychometric properties, or measure interpretation. Instrument analysis begins by introducing the roles of periodic outcome assessment for CIBI programs. Next, the Vineland-3 and ABAS-3 are evaluated in terms of their development processes, psychometric characteristics, and the practical aspects of their implementation. Examination of psychometric evidence for each measure demonstrated that the evidence for several key psychometric characteristics is either unavailable or suggests less-than-desirable properties. Evaluation of practical considerations for implementation revealed weaknesses in ongoing intervention monitoring and clinical decision support. The Vineland-3 and ABAS-3 have significant strengths for cross-sectional outpatient mental health assessment, particularly as related to the identification of intellectual disability, but also substantial weaknesses relevant to their application in CIBI outcome assessment. Alternative approaches are offered, including adopting measures specifically developed for the CIBI context. Full article