Search Results (2,737)

This paper aims to leverage artificial intelligence (AI) to assist physicians in utilizing advanced deep learning techniques integrated into developed models within electronic health records (EHRs) in medical information systems (MISes), which have been in use for over 15 years in health centers across the Republic of Serbia. This paper presents a human-centered AI approach that emphasizes physician decision-making supported by AI models. This study presents two developed and implemented deep neural network (DNN) models in the EHR. Both models were based on data that were collected during the COVID-19 outbreak. The models were evaluated using five-fold cross-validation. The convolutional neural network (CNN), based on the pre-trained VGG19 architecture for classifying chest X-ray images, was trained on a publicly available smaller dataset containing 196 entries, and achieved an average classification accuracy of 91.83 ± 2.82%. The DNN model for optimizing patient appointment scheduling was trained on a large dataset (341,569 entries) and a rich feature design extracted from the MIS, which is daily used in Serbia, achieving an average classification accuracy of 77.51 ± 0.70%. Both models have consistent performance and good generalization. The architecture of a realized MIS, incorporating the positioning of developed AI tools that encompass both developed models, is also presented in this study. Full article

Background/Objective: The use of artificial intelligence to assist in medical applications is an emerging area of investigation and discussion. The researchers studied whether there was a difference between homeopathy guidance provided by artificial intelligence (AI) (automated) and live professional practitioners (live) for acute illnesses. Additionally, the study explored the practical challenges associated with validating AI tools used for homeopathy and sought to generate insights on the potential value and limitations of these tools in the management of acute health complaints. Method: Randomly selected cases at a homeopathy teaching clinic (n = 100) were entered into a commercially available homeopathic remedy finder to investigate the consistency between automated and live recommendations. Client symptoms, medical disclaimers, remedies, and posology were compared. The findings of this study show that the purpose-built homeopathic remedy finder is not a one-to-one replacement for a live practitioner. Result: In the 100 cases compared, the automated online remedy finder provided between 1 and 20 prioritized remedy recommendations for each complaint, leaving the user to make the final remedy decision based on how well their characteristic symptoms were covered by each potential remedy. The live practitioner-recommended remedy was included somewhere among the auto-mated results in 59% of the cases, appeared in the top three results in 37% of the cases, and was a top remedy match in 17% of the cases. There was no guidance for managing remedy responses found in live clinical settings. Conclusion: This study also highlights the challenge and importance of validating AI remedy recommendations against real cases. The automated remedy finder used covered 74 acute complaints. The live cases from the teaching clinic included 22 of the 74 complaints. Full article

If we do not urgently educate current and future medical professionals to critically evaluate and distinguish credible AI-assisted diagnostic tools from those whose performance is artificially inflated by data leakage or improper validation, we risk undermining clinician trust in all AI diagnostics and jeopardizing future advances in patient care. For instance, machine learning models have shown high accuracy in diagnosing Parkinson’s Disease when trained on clinical features that are themselves diagnostic, such as tremor and rigidity. This study systematically investigates the impact of data leakage and feature selection on the true clinical utility of machine learning models for early Parkinson’s Disease detection. We constructed two experimental pipelines: one excluding all overt motor symptoms to simulate a subclinical scenario and a control including these features. Nine machine learning algorithms were evaluated using a robust three-way data split and comprehensive metric analysis. Results reveal that, without overt features, all models exhibited superficially acceptable F1 scores but failed catastrophically in specificity, misclassifying most healthy controls as Parkinson’s Disease. The inclusion of overt features dramatically improved performance, confirming that high accuracy was due to data leakage rather than genuine predictive power. These findings underscore the necessity of rigorous experimental design, transparent reporting, and critical evaluation of machine learning models in clinically realistic settings. Our work highlights the risks of overestimating model utility due to data leakage and provides guidance for developing robust, clinically meaningful machine learning tools for early disease detection. Full article

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a worldwide challenge. There are an estimated 17–24 million patients worldwide, with an estimated 60 percent or more who have not been diagnosed. Without a known cure, no specific curative medication, disability lasting years to being life-long, and disagreement among healthcare providers as to how to most appropriately treat these patients, ME/CFS patients are in need of assistance. Appropriate healthcare provider education would increase the percentage of patients diagnosed and treated; however, in-school healthcare provider education is limited. To address the latter issue, the New Jersey Myalgic Encephalomyelitis/Chronic Fatigue Syndrome Association (NJME/CFSA) has developed an independent, incentive-driven, learning program for students of the health professions. NJME/CFSA offers a yearly scholarship program in which applicants write a scholarly paper on an ME/CFS-related topic. The efficacy of the program is demonstrated by the 2024–2025 first place scholarship winner’s essay, which addresses the biological basis of ME/CFS and how the healthcare provider can improve the quality of life of ME/CFS patients. For the reader, the essay provides an update on what is known regarding the biological underpinnings of ME/CFS, as well as a medical student’s perspective as to how the clinician can provide care and support for ME/CFS patients. The original essay has been slightly modified to demonstrate that ME/CFS is a worldwide problem and for publication. Full article

Three-dimensional printed polycaprolactone (PCL) tissue engineering scaffolds have drawn increasing interest from the medical industry due to their excellent biocompatibility and biodegradability, yet PCL’s poor mechanical performance has limited their applications. This study introduces a biocompatible and biodegradable polylactic acid (PLA) fiber reinforced PCL (PLA/PCL) composite as the filament for 3D printed scaffolds to significantly enhance their mechanical performance: Special-made PLA short fiber mat was infused with PCL matrix and rolled into PLA/PCL filaments through a “Vacuum Assisted Resin Infusion” (VARI) process. The investigation revealed that the PLA fibers are highly oriented along the printing direction when using this filament for 3D printing due to the unique microstructure formed during the VARI process. At the same PLA fiber content, the percentage increase in Young’s modulus of the 3D printed strands using the filaments produced by the VARI process is 127.6% higher than the 3D printed strands using the filaments produced by the conventional melt blending process. The 3D printed tissue engineering scaffolds using the PLA/PCL composite filament with 11 wt% PLA fiber content also achieved an exceptional 84.2% and 143.3% increase in peak load and stiffness compared to the neat PCL counterpart. Full article

Adverse drug events (ADEs) significantly impact patient safety and health outcomes. Manual ADE detection from clinical narratives is time-consuming, labor-intensive, and costly. Recent advancements in large language models (LLMs), including transformer-based architectures such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pretrained Transformer (GPT) series, offer promising methods for automating ADE extraction from clinical data. These models have been applied to various aspects of pharmacovigilance and clinical decision support, demonstrating potential in extracting ADE-related information from real-world clinical data. Additionally, chatbot-assisted systems have been explored as tools in clinical management, aiding in medication adherence, patient engagement, and symptom monitoring. This narrative review synthesizes the current state of LLMs in ADE detection from a clinical perspective, organizing studies into categories such as human-facing decision support tools, immune-related ADE detection, cancer-related and non-cancer-related ADE surveillance, and personalized decision support systems. In total, 39 articles were included in this review. Across domains, LLM-driven methods have demonstrated promising performances, often outperforming traditional approaches. However, critical limitations persist, such as domain-specific variability in model performance, interpretability challenges, data quality and privacy concerns, and infrastructure requirements. By addressing these challenges, LLM-based ADE detection could enhance pharmacovigilance practices, improve patient safety outcomes, and optimize clinical workflows. Full article

The aim of this work is to analyse the effectiveness of the medical use of the Cavitron Ultrasonic Surgical Aspirator (CUSA) in microsurgical treatment of Intramedullary Spinal Cord Tumors (IMSCTs), with a focus on the thermo-mechanical effects on neighbouring tissues to assess any potential damage. Indeed, CUSA emerges as an innovative solution, minimally invasive tumor excision technique, enabling controlled and focused operations. This study employs a Finite Element Analysis (FEA) to simulate the vibratory and thermal interactions occurring during CUSA application. A computational model of a vertebral column segment affected by an IMSCT was developed and analysed using ANSYS 2024 software. The simulations examined strain distribution, heat generation, and temperature propagation within the biological tissues. The FEA results demonstrate that the vibratory-induced strain remains highly localised to the application site, and thermal effects, though measurable, do not exceed the critical safety threshold of 46 °C established in the literature. These findings suggest that CUSA can be safely used within defined operational parameters, provided that energy settings and exposure times are carefully managed to mitigate excessive thermal accumulation. These conclusions contribute to the understanding of the thermo-mechanical interactions in ultrasonic tumour resection and aim to assist medical professionals in optimising surgical protocols. Full article

Background: Congenital diarrhea is persistent diarrhea that manifests during the neonatal period. Mutations in DGAT1, which is crucial for triglyceride synthesis and lipid absorption in the small intestine, are causal factors for congenital diarrhea. In this study, we aimed to determine the value of tissue RNA sequencing (RNA-seq) for assisting with the clinical diagnosis of some genetic variants of uncertain significance. Methods: We clinically evaluated a patient with watery diarrhea, vomiting, severe malnutrition, and total parenteral nutrition dependence. Possible pathogenic variants were detected using whole-exome sequencing (WES). RNA-seq was utilized to explore the transcriptional alterations in DGAT1 variants identified by WES with unknown clinical significance, according to the American College of Medical Genetics guidelines. Systemic examinations, including endoscopic and histopathological examinations of the intestinal mucosa, were conducted to rule out other potential diagnoses. Results: We successfully diagnosed a patient with congenital diarrhea and protein-losing enteropathy caused by a DGAT1 mutation and reviewed the literature of 19 cases of children with DGAT defects. The missense mutation c.620A>G, p.Lys207Arg located in exon 15, and the intronic mutation c.1249-6T>G in DGAT1 were identified by WES. RNA-seq revealed two aberrant splicing events in the DGAT1 gene of the patient’s small intestinal tissue. Both variants lead to loss-of-function consequences and are classified as pathogenic variants of congenital diarrhea. Conclusions: Rare DGAT1 variants were identified as pathogenic evidence of congenital diarrhea, and the detection of tissue-specific mRNA splicing and transcriptional effects can provide auxiliary evidence. Full article

Varicocele is a common, potentially correctable condition associated with impaired male fertility. Despite being frequently encountered in clinical andrology, its pathophysiological mechanisms, diagnostic criteria, and therapeutic approaches remain areas of active investigation and debate. The authors conducted a comprehensive literature search, using the PubMed database, covering clinical studies, systematic reviews, meta-analyses, and current international guidelines from the past ten years. Emphasis was placed on studies investigating novel diagnostic modalities, therapeutic innovations, and prognostic markers. Emerging evidence supports the multifactorial pathophysiology of varicocele, involving oxidative stress, hypoxia, inflammatory pathways, and potential genetic predisposition. Biomarkers, including microRNAs, antisperm antibodies, and sperm DNA fragmentation, offer diagnostic and prognostic utility, though their routine clinical implementation requires further validation. Advances in imaging, such as shear wave elastography, may improve diagnostic accuracy. While microsurgical subinguinal varicocelectomy remains the gold standard, technological refinements and non-surgical alternatives are being explored. Indications for treatment have expanded to include selected cases of non-obstructive azoospermia, hypogonadism, and optimization for assisted reproduction, though high-level evidence is limited. Full article

This article describes the design, methods, and baseline characteristics of the social needs assessment (SNA) of participants enrolled in an ongoing randomized clinical trial implementing a comprehensive approach to improving diabetes self-management and providing an intensive Diabetes Self-Management Education and Support (iDSMES) Program at St. Vincent’s House Clinic, a primary care practice serving resource-challenged diverse populations in Galveston, Texas. Standardized SNA was conducted to collect information on financial needs, psychosocial well-being, and other chronic health conditions. Based on their identified needs, participants were referred to non-medical existing community resources. A series of in-depth interviews were conducted with a subset of participants. A team member independently categorized these SNA narratives and aggregated them into two overarching groups: medical and social needs. Fifty-nine participants (with a mean age of 53 years and equal representation of men and women) completed an SNA. Most (71%) did not have health insurance. Among 12 potential social needs surveyed, the most frequently requested resources were occupational therapy (78%), utility assistance (73%), and food pantry services (71%). SNA provided data with the potential to address barriers that may hinder participation, retention, and outcomes in diabetes self-management. SNA findings may serve as tertiary prevention to mitigate diabetes-related complications and disparities. Full article

Pancreatic neuroendocrine neoplasms (PNENs) are a diverse group of rare tumor subtypes, representing less than 2% of all pancreatic tumors. Often detected late in the clinical course, they are associated with high rates of morbidity and mortality. Hereditary syndromes such as multiple endocrine neoplasia type-1 and von Hippel–Lindau are associated with the development of PNENs, although only a small portion of total tumors have a genetic basis. This review aims to explore the recent advances in laboratory diagnostics, imaging modalities, medical management, and surgical approaches to hormone-producing PNENs (including some common, less common, and some rare subtypes), with the goal of assisting physicians in the integration of evidence-based information into their practice. Full article

Recent advancements in deep learning have significantly enhanced brain tumor segmentation from MRI data, providing valuable support for clinical diagnosis and treatment planning. However, challenges persist in effectively integrating prior medical knowledge, capturing global multimodal features, and accurately delineating tumor boundaries. To address these challenges, the Hybrid Network for Multimodal Brain Tumor Segmentation (HN-MBTS) is proposed, which incorporates prior medical knowledge to refine feature extraction and boundary precision. Key innovations include the Two-Branch, Two-Model Attention (TB-TMA) module for efficient multimodal feature fusion, the Linear Attention Mamba (LAM) module for robust multi-scale feature modeling, and the Residual Attention (RA) module for enhanced boundary refinement. Experimental results demonstrate that this method significantly outperforms existing approaches. On the BraT2020 and BraT2023 datasets, the method achieved average Dice scores of 87.66% and 88.07%, respectively. These results confirm the superior segmentation accuracy and efficiency of the approach, highlighting its potential to provide valuable assistance in clinical settings. Full article

Background and Objectives: this pilot study aimed to evaluate the diagnostic accuracy of ChatGPT-4o in analyzing oral mucosal lesions from clinical images. Materials and Methods: a total of 110 clinical images, including 100 pathological lesions and 10 healthy mucosal images, were retrieved from Google Images and analyzed by ChatGPT-4o using a standardized prompt. An expert panel of five clinicians established a reference diagnosis, categorizing lesions as benign or malignant. The AI-generated diagnoses were classified as correct or incorrect and further categorized as plausible or not plausible. The accuracy, sensitivity, specificity, and agreement with the expert panel were analyzed. The Artificial Intelligence Performance Instrument (AIPI) was used to assess the quality of AI-generated recommendations. Results: ChatGPT-4o correctly diagnosed 85% of cases. Among the 15 incorrect diagnoses, 10 were deemed plausible by the expert panel. The AI misclassified three malignant lesions as benign but did not categorize any benign lesions as malignant. Sensitivity and specificity were 91.7% and 100%, respectively. The AIPI score averaged 17.6 ± 1.73, indicating strong diagnostic reasoning. The McNemar test showed no significant differences between AI and expert diagnoses (p = 0.084). Conclusions: In this proof-of-concept pilot study, ChatGPT-4o demonstrated high diagnostic accuracy and strong descriptive capabilities in oral mucosal lesion analysis. A residual 8.3% false-negative rate for malignant lesions underscores the need for specialist oversight; however, the model shows promise as an AI-powered triage aid in settings with limited access to specialized care. Full article

The increasing complexity and scale of electronic health records (EHRs) demand advanced tools for efficient data retrieval, summarization, and comparative analysis in clinical practice. MERA (Medical Electronic Records Assistant) is a Retrieval-Augmented Generation (RAG)-based AI system that addresses these needs by integrating domain-specific retrieval with large language models (LLMs) to deliver robust question answering, similarity search, and report summarization functionalities. MERA is designed to overcome key limitations of conventional LLMs in healthcare, such as hallucinations, outdated knowledge, and limited explainability. To ensure both privacy compliance and model robustness, we constructed a large synthetic dataset using state-of-the-art LLMs, including Mistral v0.3, Qwen 2.5, and Llama 3, and further validated MERA on de-identified real-world EHRs from the MIMIC-IV-Note dataset. Comprehensive evaluation demonstrates MERA’s high accuracy in medical question answering (correctness: 0.91; relevance: 0.98; groundedness: 0.89; retrieval relevance: 0.92), strong summarization performance (ROUGE-1 F1-score: 0.70; Jaccard similarity: 0.73), and effective similarity search (METEOR: 0.7–1.0 across diagnoses), with consistent results on real EHRs. The similarity search module empowers clinicians to efficiently identify and compare analogous patient cases, supporting differential diagnosis and personalized treatment planning. By generating concise, contextually relevant, and explainable insights, MERA reduces clinician workload and enhances decision-making. To our knowledge, this is the first system to integrate clinical question answering, summarization, and similarity search within a unified RAG-based framework. Full article

Precise medical image segmentation is crucial for advancing computer-aided diagnosis. Although deep learning-based medical image segmentation is now widely applied in this field, the complexity of human anatomy and the diversity of pathological manifestations often necessitate the use of image annotations to enhance segmentation accuracy. In this process, the scarcity of annotations and the lightweight design requirements of associated text encoders collectively present key challenges for improving segmentation model performance. To address these challenges, we propose MedLangViT, a novel language–vision multimodal model for medical image segmentation that incorporates medical descriptive information through lightweight text embedding rather than text encoders. MedLangViT innovatively leverages medical textual information to assist the segmentation process, thereby reducing reliance on extensive high-precision image annotations. Furthermore, we design an Enhanced Channel-Spatial Attention Module (ECSAM) to effectively fuse textual and visual features, strengthening textual guidance for segmentation decisions. Extensive experiments conducted on two publicly available text–image-paired medical datasets demonstrated that MedLangViT significantly outperforms existing state-of-the-art methods, validating the effectiveness of both the proposed model and the ECSAM. Full article