Informatics for health & social care最新文献

Introduction: The increasing advancement in Information and Communication Technology (ICT) has led to the adoption of Health Information Systems (HIS) in healthcare settings to enhance service delivery. This study evaluated the effect of HIS implementation on the timeliness of medical claims submission within the National Catholic Health Service (NCHS) in Ghana.

Methods: Using longitudinal data from 2010 to 2019, the study compared monthly claims submission times across facilities using both paper-based and electronic HIS. The number of days taken to submit claims each month was analyzed using a segmented Interrupted Time-Series approach, employing the Prais-Winsten method. This allowed comparison of claim submission times before and after HIS adoption. A meta-analysis was conducted to determine the overall impact across facilities.

Results: Facilities using HIS submitted claims significantly faster than those using paper-based systems, with average submission times of 35.11 days versus 56.51 days, respectively (p < 0.0001). HIS implementation led to an immediate 5.84-day reduction in average submission time. Findings showed that over 75% of the facilities achieved timely submission of claims.

Conclusion: In conclusion, HIS significantly improves the timeliness of medical claims submission. Scaling up HIS use for claims processing can enhance efficiency and promote prompt reimbursements from health insurers.

Objective: Investigating whether there is a difference in health literacy and healthy lifestyle behaviors between individuals who have and have not had infection after the COVID-19 outbreak, and also to examine the relationship between health literacy and healthy lifestyle behaviors.

Methods: Participants were assessed with the European Health Literacy Survey (HLS-EU-Q) and the Healthy Lifestyle Profile-II (HPLP-II) scales online via Google Forms using various social media platforms. Also, the individuals' habits of obtaining health-related knowledge and general health conditions, health-related recourse sources, and the frequency of exercise were also recorded and compared.

Results: Three hundred and sixty-seven individuals (64.4% female) participated in the study and analysis of the HLS-EU-Q and HPLP-II Scale results of all participants revealed a positive correlation between two scales (p = .009, r = 0.137). However, no significant difference was found between participants with (Group I, n = 183) and without (Group II, n = 184) COVID-19 infection in terms of HLS-EU-Q and HPLP-II scales (p > .05).

Conclusion: It was concluded that the health literacy levels and healthy lifestyle behaviors of individuals who had and did not have COVID-19 infection were similar. However, there was a weak but significant correlation between the level of health literacy and the adoption of healthy lifestyle behaviors.

Telemedicine holds significant potential to transform healthcare delivery in rural Nigerian communities; however, its adoption remains constrained by various barriers. This study explores patient-level barriers, including technological access, health literacy, and cultural attitudes, as well as provider-level challenges such as training, infrastructure, and organizational support. Additionally, it investigates the role of socio-economic factors and community dynamics in shaping perceptions of telemedicine. Using qualitative interviews with 39 participants (24 patients and 15 providers), the study identifies key obstacles, including the high cost of devices and internet data, unreliable connectivity, low health literacy, and cultural stigma surrounding remote healthcare consultations. The findings align with Rogers' Diffusion of Innovation theory, revealing that barriers related to relative advantage, complexity, and compatibility significantly affect the adoption process. Strategies to mitigate these barriers include subsidizing technology costs, implementing digital literacy programs, providing culturally tailored telemedicine models, and ensuring better infrastructure and technical support for healthcare providers. Recommendations also emphasize the importance of community-centered engagement to enhance acceptance and usage. This study highlights the need for systemic interventions and participatory approaches to design context-specific solutions that address both patient and provider challenges. Future research should focus on participatory action research to develop and implement effective interventions for telemedicine adoption in rural areas.

Lung nodules (LNs) detection using computer tomography (CT) images is essential to reduce the mortality of lung cancer (LC). The complex three-dimensional structure of lung CT data and the variation in the forms and appearances of LNs make the accurate identification of pulmonary nodules still extremely challenging. Although deep learning (DL) methods outperform handcrafted approaches, several challenges remain to be solved. Detecting malignant regions alone is insufficient for clinical decision-making; segmentation by severity and grading analysis are necessary to reduce false positives. Training DL models also requires many datasets, which is difficult in the medical domain due to ethical concerns, limited expert annotations, and the scarcity of disease-specific images. Moreover, insufficient data and class imbalance often lead to overfitting and a reduction in performance. To address these limitations, this study proposes a hybrid pre-trained architecture for more accurate automated pulmonary nodule segmentation and classification. The research comprises 3 phases: preprocessing, segmentation, and classification. Initially, the CT lung images are gathered from the openly available LUNA16 dataset. Then, preprocessing is performed on the collected data by noise filtering using a guided filter and data augmentation to balance the dataset. Doing so improves the data quality for learning and classification processes and prevents the model from biased outcomes. Afterward, the Spatial Pyramid Pooling centered U-shaped network (SPPUNet) is employed to segment the lung regions, enabling the classifier to easily identify and analyze nodules, lesions, and other abnormalities. Finally, the classification is performed using the Global Context Attention integrated InceptionV3 (GCAINCPV3) network, which enables medical professionals to determine the nature of the nodule and provide the most appropriate treatment plan for patients. The outcomes demonstrated that the proposed system outperforms existing systems, achieving an accuracy of 99.23%.

The Internet of Things (IoT) and cloud computing (CC) concepts are commonly incorporated in healthcare applications. In the healthcare industry, a huge quantity of patient data is generated by IoT devices. The integral storage of mobile devices and processing power is used to analyze the stored data in the cloud. The Internet of Medical Things (IoMT) combines health monitoring mechanisms with medical equipment and sensors to monitor patient records and offer extra smart and experienced healthcare services. This paper proposes an effective and walrus-optimized deep learning (DL) technique for chronic kidney disease (CKD) prediction in IoT. To begin, the data are collected from the CKD dataset, and the preprocessing procedures, such as missing value imputation, numerical conversion, and normalization, are performed to improve the quality of the dataset. Then, dataset balancing is done using the k-means (KM) clustering algorithm to prevent the model from making inaccurate predictions. After that, enhanced residual network 50 (EResNet50) is utilized to extract more discriminative features from the dataset. From that, the optimal features are selected via elite opposition and the Cauchy distribution-based walrus optimization algorithm (ECWOA). Finally, the classification uses the walrus-optimized bidirectional long short-term memory (WOBLSTM). The simulation outcomes demonstrated the effectiveness of our method over existing techniques, with a higher sensitivity of 99.89% for CKD prediction.

This study proposes a novel Dynamic Decision Support System (DDSS) framework aimed at enhancing countries' pandemic preparedness through robust forecasting and adaptive clustering analysis of Coronavirus Disease 2019 (COVID-19) data. The forecasting module integrates multiple Machine Learning (ML) models with a recursive error-adjustment mechanism that significantly improves long-term prediction accuracy of cumulative COVID-19 cases compared to conventional time series models such as Autoregressive Integrated Moving Average (ARIMA), Error Trend Seasonality (ETS), and Long Short-Term Memory (LSTM). The clustering component performs a dynamic, year-over-year classification of countries based on health, policy, and socio-economic indicators. By employing K-means clustering and Multi-Attribute Decision-Making (MADM) techniques, the study evaluates changes in countries' pandemic performance over time and identifies the stringency index as a critical determinant influencing cluster shifts. The proposed framework not only reveals performance trajectories and degradation risks for individual countries but also provides a structured data-driven basis for strategic policymaking. Notably, the analysis demonstrates how relaxing governmental measures, despite high vaccination rates, can adversely affect country classification, highlighting the indispensable role of strict interventions. This integrated approach, combining adaptive ML forecasting with temporal clustering and interpretability via Shapley Additive explanations (SHAP) analysis, provides a dynamic and practical decision-support framework for pandemic response.

This study aims to determine the relationship between health professionals' artificial intelligence (AI) literacy and their attitudes toward AI. This descriptive and correlational study was conducted between May and July 2024 in an educational research hospital located in eastern Turkey, encompassing 1378 health professionals. The sample size was calculated as 301 participants, with a 95% confidence interval and a 0.05 margin of error, and data collection was completed with 439 participants. 58.8% of the participants were male and 49.0% of them did not have information about the use of artificial intelligence in the field of health. Men, those in the 46-55 age group, postgraduates, those who received artificial intelligence education and those who support artificial intelligence in health showed higher AI literacy and positive attitudes. A strong positive correlation was found between AI literacy and attitudes (r = 0.782**; r = 0.710**), and some sociodemographic variables explained 62.1% and 48.9% of positive and negative attitudes, respectively. Participants exhibited moderate AI literacy, high positive and moderate negative attitudes; attitudes were significantly affected by sociodemographic factors.

Federated Learning (FL) is a revolutionary approach to machine learning that allows multiple institutions, such as healthcare organizations, to collaboratively train models without sharing sensitive data directly. The problem involves protecting Electronic Health Records (EHRs) in FL from adversarial attacks while maintaining privacy. This requires ensuring secure data aggregation, anonymization, and robust model training across diverse healthcare institutions without compromising sensitive patient information. The objectives are to enhance privacy and security in FL for EHRs by implementing anonymization, adversarial pattern detection, context-aware aggregation, and robust model training. This ensures protection from adversarial attacks while maintaining compliance with privacy standards like HIPAA. Adaptive Weighted Median Filtering (AWMF) improves FL robustness by reducing noise, outliers, and adversarial attacks, ensuring accurate, privacy-preserving model training. The Cuckoo-based Deep Convolutional Long-Term Memory (CDC-LSTM) combines convolutional layers and memory networks to enhance FL, improving robustness against adversarial attacks while ensuring secure EHR data processing. Federated Privacy-Preserving Mesh Networks (F-PPMN) enhance FL by creating secure, decentralized communication channels, protecting EHRs from adversarial attacks and preserving privacy. Findings show that anonymized EHR attributes (90%-290%) slightly reduce data richness compared to original attributes (100%-300%) while maintaining privacy. This demonstrates a balance between data utility and confidentiality in FL and is implemented in Python Software. Future advancements include integrating federated encryption, multi-party computation, and improved adversarial attack detection, enhancing privacy and security in FL for EHRs while ensuring robust, accurate model performance across diverse healthcare environments.

Information systems are increasingly playing a major role in the cost-effective delivery of healthcare services. Recently, the healthcare industry has shifted its focus toward patient-centered care, in which patients play a major role in managing their health. As a result, healthcare providers are employing patient portals - consumer-centric tools - to strengthen patients' ability to actively manage their health and healthcare. In this study, we extend the existing literature on patient portals by examining the functionalities and features of current portals from users' experiences with mobile patient portal apps, mapping the identified functionalities and features to established design principles of health behavioral change support systems, and identifying limitations of existing patient portals. Results show that current patient portal apps are limited with respect to integration with medical devices, social support, customization, persuasive messages, and peer-based technical support.