Technology and Health Care最新文献

BackgroundDigital healthcare's advance has underscored an urgent requirement for solid medical record quality control, critical for data integrity, surpassing manual methods' inadequacies.ObjectiveThe goal was to develop an AI system to manage medical record quality control comprehensively, using advanced AI like reinforcement learning and NLP to boost management's precision and efficiency.MethodsThis AI system uses a closed-loop framework for real-time record review using natural language processing techniques and reinforcement learning, synchronized with the hospital information system. It features a data layer for monitoring, a service layer for AI analysis, and a presentation layer for user engagement. Its impact was evaluated by comparing quality metrics pre- and post-deployment.ResultsWith the AI system, quality control became fully operational, with review times per record plummeting from 4200 s to 2 s. The share of Grade A records rose from 89.43% to 99.21%, and the system markedly minimized formal and substantive record errors, enhancing completeness and accuracy. The implementation of the artificial intelligence-based medical record quality control system optimizes the quality control process, dynamically regulates the diagnostic behavior of medical staff, and promotes the standardization and normalization of clinical medical record writing.ConclusionsThe AI-driven system significantly upgraded the management of medical records in terms of efficiency and accuracy. It provides a scalable approach for hospitals to refine quality control, propelling healthcare towards heightened intelligence and automation, and foreshadowing AI's pivotal role in future healthcare quality management.

Background: Peripherally Inserted Central Catheters (PICC) are widely used for long-term intravenous therapy in pediatric patients and are effective in preventing catheter displacement.

Objective: This study aimed to investigate the effect of magnetic navigation technology compared with ultrasound imaging and manual control of the catheter path.

Methods: The control group underwent PICC placement using the Seldinger technique under ultrasound guidance (n = 86), while the magnetic navigation group received magnet-assisted PICC placement (n = 80). Both groups used chest X-ray (CXR) after catheter placement to confirm the tip position. Insertion time, first-attempt success rate, complication rate, post-procedural pain, post-procedural anxiety, and family satisfaction were compared.

Results: Compared to the control group, magnetic navigation significantly reduced catheter insertion time (28.2 ± 3.67 min vs. 34.85 ± 2.94 min, P < 0.001), improved first-attempt success rate (91.25% vs. 41.86%, P < 0.001), and lowered the complication rate (21.25% vs. 66.28%, P < 0.001). In addition, magnetic navigation alleviated post-procedural pain and anxiety (P < 0.01), and improved family satisfaction (P < 0.01).

Conclusion: Compared to traditional ultrasound-guided methods, magnetic navigation offers superior efficiency in pediatric PICC placement, highlighting its promising potential for clinical application and broader implementation.

Introduction: Infective endocarditis (IE), despite advancements in diagnostic and therapeutic strategies, remains a life-threatening condition with high in-hospital mortality. The aim of this study was to assess an importance of a different echocardiographic techniques in the evaluation of patients with IE.

Methods: This prospective study included all consecutive patients hospitalized with a diagnosis of IE. Each patient underwent both 2D transesophageal echocardiography (2DTOE) and 3D transesophageal echocardiography (3DTOE) as part of the initial diagnostic evaluation. Laboratory results, isolated pathogens, and monitoring during hospitalization were also taken into account.

Results: The study included 59 patients (69.49% male, mean age 64.4 ± 16.0). Native valve endocarditis (NVE) was present in 32 (54.24%), prosthetic valve endocarditis (PVE) in 17 (28.81%), and cardiac device-related IE (CDIE) in 10 (16.95%). Blood cultures were positive in 72.4% of cases, with Enterococcus faecalis predominant in NVE, and Staphylococcus species in PVE (S. epidermidis) and CDIE (S. aureus) (p = 0.039). TOE provided detailed imaging, detecting more lesions, with 3D TOE excelling in identifying destructive lesions, particularly perforations (p < 0.001). Vegetations were most frequent in NVE and CDIE, while destructive lesions were more common in PVE (p < 0.05). 3D TOE identified longer vegetations and more destructive lesions, especially in PVE (p < 0.05).

Conclusion: 3D TOE, provide a detailed real time imaging, and could be considered as key adjunctive modality in practice when the cardiac anatomy is not precisely visualized by 2D TOE, particularly when advanced surgical planning is required.

BackgroundChatbots are increasingly integrated into healthcare, offering personalized and accessible health advice. However, the impact of factors such as chatbot authority, health information type, and interaction style on users' decision-making remains unclear.ObjectiveThis study aims to investigate how these elements influence users' willingness to adopt health advice provided by chatbots.MethodsA 2 × 2 × 2 factorial experiment was conducted with 480 university students to examine the effects of chatbot authority (authoritative vs. non-authoritative), health information type (preventive vs. treatment-related), and interaction style (formal vs. informal). Participants' willingness to adopt the health advice was measured before and after interacting with the chatbot.ResultsThe study found that a authoritative chatbot delivering treatment-related advice in a formal style significantly increased willingness to adopt the advice. Conversely, preventive information was more effective when presented informally by a non-authoritative chatbot. These results support the media evocation paradigm, which suggests that chatbots framed as authoritative figures evoke greater user engagement and trust in health contexts.ConclusionThe findings extend the media evocation paradigm by demonstrating that chatbot authority, information type, and interaction style should be aligned with the nature of health advice to maximize effectiveness. This study provides insights for designing chatbots that improve health decision-making by tailoring their communication strategies.

BackgroundLiver cancer is still one of the most common causes of death from cancer globally. The accurate segmentation of liver tumors from CT images is critical for diagnosis, treatment planning, and tracking. Conventional segmentation techniques frequently struggle to handle the intricacy of medical images, requiring the usage of sophisticated artificial intelligence (AI) methods to enhance accuracy and effectiveness.ObjectiveThe main objective of this study is to create and test an improved U-Net model (AM-UNet) that incorporates an attention mechanism to enhance the segmentation and classification accuracy of liver tumors in CT images. This method seeks to surpass previous techniques in terms of accuracy, precision, recall, and F1 score.MethodsThe dataset used includes 194 liver tumor CT scans obtained from 131 individuals for training and 70 for testing. The open-source 3DIRCAD-B dataset, which is incorporated into LiTS, contains images of both normal and pathological conditions. Preprocessing methods such as Median Filtering (MF) and Histogram Equalization (HE) were used to reduce noise and improve contrast. The AM-UNet model was then used to segment the tumors before classifying them as malignant or benign. The efficiency was assessed utilizing metrics like accuracy, precision, recall, F1-score, and ROC (Receiver Operating Characteristic).ResultsThe suggested AM-UNet model produced excellent outcomes, with a recall of 95%, accuracy of 92%, precision of 94%, and an F1-score of 93%. These metrics show that the model outperforms conventional techniques in correctly segmenting and classifying liver tumors in CT images.ConclusionThe AM-UNet model improves the segmentation and classification of liver tumors, providing substantial performance metrics over traditional methods. Its utilization can transform liver cancer diagnosis by assisting physicians in accurate tumor identification and treatment planning, resulting in improved patient results.

Background: Functional myocardial ischemia (FMI) in stable coronary artery disease (SCAD) remains a critical challenge in cardiovascular care. While fractional flow reserve (FFR) is a gold-standard diagnostic technology, its clinical adoption is limited by cost and complexity. Integrating technological biomarkers and advanced analytics could enhance risk stratification and guide precision interventions.

Objective: This study leverages data-driven methodologies to identify and validate technological biomarkers associated with FMI in SCAD, aiming to optimize clinical decision-making through predictive modeling.

Methods: A systematic search across PubMed, Embase, and Web of Science (inception-October 2023) identified studies evaluating SCAD and FMI.

Inclusion criteria: cohort/case-control studies (n ≥ 100) using FFR or angiographic technologies. Meta-analyses were conducted via RevMan 5.4 and Stata 16.0, employing fixed/random-effects models. Heterogeneity was assessed using I² statistics.

Results: Analysis of 15 studies (n = 4854) revealed that anatomical biomarkers-stenosis severity (DS%: SMD = 0.95, p < 0.0001), minimal lumen diameter (SMD = -1.33, p < 0.0001), and lesion length (SMD = 0.72, p < 0.0001)-were strongly linked to FMI. Diabetes (OR = 1.31, p = 0.003) and smoking (OR = 1.47, p < 0.0001) emerged as significant modifiable risks, while hypertension showed no association (p = 0.14). Age and gender disparities highlighted the need for personalized risk algorithms.

Conclusion: Technological biomarkers and data-driven modeling provide actionable insights into FMI risk in SCAD, bridging gaps between anatomical assessments and functional outcomes. Future integration of machine learning and predictive analytics could refine risk stratification, enabling tailored therapeutic strategies.

BackgroundIn recent years, the large-scale epidemics and the increasing demand for rehabilitation generated a demand for remote rehabilitation, while digital twin provided technical support for home-based rehabilitation.ObjectiveIn order to monitor the operation status of rehabilitation robot and make dynamic adjustments, a virtual-real interaction system for an ankle rehabilitation robot (VRIS-ARR) is designed based on the digital twin theory, and its virtual-real interaction characteristics is researched.MethodsThe VRIS-ARR is consisted of physical layer, communication layer, virtual layer and application layer, and is designed by the application of software tools such as 3ds Max, Unity 3D, C#, Python. The database technology and multi-threaded development method are applied to realize the virtual-real interaction function of the system.ResultsThe performance and function experiments of the VRIS-ARR are carried out, and the system has the characteristics of strong virtual-real interaction, which can work smoothly with high control accuracy and without obvious delay.ConclusionThe experimental results indicate that the developed VRIS-ARR is very reliable between the ankle rehabilitation robot and the host computer.

ObjectiveEvaluate the usability and user satisfaction of an oral medicine application among public health professionals.MethodsA cross-sectional observational study was conducted with 101 dentists registered in the application, determined through sample size calculation. Data were collected using an online questionnaire. The System Usability Scale (SyUS) was used to assess usability, and an adapted questionnaire evaluated user satisfaction. Variables influencing satisfaction and usability were also analyzed.ResultsMost participants were female (73.3%), aged between 20 and 59 years (98%), with up to 10 years of professional experience (73%). The majority had a specialization (81%), including 24.8% in Collective and Family Health, and 80.2% worked in Primary Health Care. The mean SyUS usability score was 91.25 (scale: 0-100), exceeding the threshold of 70 for a viable product. Participants expressed high satisfaction with the app's theoretical and clinical support. Suggested improvements included a lesion database, chat functionality, interactive notifications, expanded attachment capacity, training initiatives, and broader specialty coverage.ConclusionThe application achieved high usability and satisfaction scores, proving essential, intuitive, and effective. It complements public health systems by supporting diagnosis and treatment, enhancing professional collaboration, and improving care quality while addressing continuity and problem-solving needs.

BackgroundCardiac Arrest (CA) is a major cause of mortality globally, often occurring suddenly without prior warning, making early detection and timely intervention crucial to saving lives. Traditional methods of predicting CA have proven inadequate due to the lack of clear warning signs. With the integration of Machine Learning (ML) techniques, the potential for more accurate early detection and intervention can improve survival rates.ObjectiveThis study proposes a machine learning-based approach for the early prediction of Cardiac Vascular Disease (CVD), which is a primary contributor to CA. The model incorporates various patient data, including lab results, vital signs, and Electrocardiogram (ECG) signal readings, to enhance prediction accuracy.MethodsThe study employs a range of advanced machine learning techniques, including Gradient-Boosting Algorithm (GBA), Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Networks (ANN). To process the data, Wavelet Transform (WT) is used to decompose the ECG signals, isolating important features while minimizing noise. Feature selection is performed through an innovative Modified Recursive Feature Elimination (MRFE) technique.ResultsThe machine learning models were validated using the MATLAB simulator, with evaluation metrics including accuracy, precision, recall, and F-score. Among the models, ANN demonstrated the highest performance, achieving 96.3% accuracy, 96.1% precision, 95% recall, and 94.65% F-score.ConclusionThis work demonstrates the effectiveness of machine learning in the early prediction of CA, enabling timely medical intervention and potentially saving lives. The results suggest that the proposed model could become a valuable tool for healthcare professionals in managing and preventing cardiac arrest.

Background: The main treatment plan for bladder cancer is surgery combined with postoperative chemotherapy. Patients often suffer from various adverse reactions after chemotherapy, which reduces the quality of life. Moreover, after chemotherapy, the resistance to chemotherapy drugs of tumor is often increased, and the tumor resistance to chemotherapy drugs is often accompanied by the deterioration of pathological classification, distant metastasis, and the decline of patients' survival period. Recent studies have found that cancer stem cells play a crucial role in tumor proliferation, invasion, metastasis and drug resistance.

Objective: This study would prove oncolytic adenovirus Ad5-E1A-UPII-PSCAE emerges as a potent agent against bladder cancer stem-like cells (CSCs), and triggers reactive oxygen species (ROS) accumulation, culminating in pyroptosis.

Methods: This study is based on transcriptome and proteomic analysis, supplemented by in vivo and in vitro experiments for validation.

Result: In vitro studies confirmed dose-dependent CSC killing (IC50: 3.6 × 10⁹ PFU), while transcriptomic and proteomic analyses highlighted mitochondrial dysfunction and ROS-driven pathways as central mechanisms. In vivo, OV-treated xenografts exhibited significant tumor regression and histopathological necrosis. By exploiting the NO/ROS-pyroptosis axis, Ad5-E1A-UPII-PSCAE overcomes CSC-mediated chemoresistance, offering a dual strategy to eradicate aggressive tumor subpopulations and suppress recurrence.

Conclusion: This study results demonstrated that OVs could kill cancer stem-like cells by promoting ROS levels, which induce cell pyroptosis.