DIGITAL HEALTH最新文献

Introduction: Sedentary lifestyle and consumption of an unhealthy diet are significantly associated with hypertension in Nigeria and Ghana. Increasing the uptake of physical activity and diet rich in fruits and vegetables has been a challenge in the region. This study aimed at assessing the effect of a mobile health intervention (mhealth) on physical activity, and fruits and vegetables intake in patients with hypertension in Nigeria and Ghana.

Methods: The study was a quasi-experimental study conducted in Mamprobi Hospital (MH) in Ghana, and State University Teaching Hospital (EKSUTH) in Nigeria. One hundred and sixteen consenting adult patients with hypertension were consecutively recruited and given regular reminders on physical activity and intake of fruits and vegetables via mobile app (mnotify^®) for six months. All participants were followed up for six months and data collected at Baseline, three months and six months. Analysis was done using Stata 14 software (StataCorp. College Station, TX) assuming an alpha level of 0.05. Ethical approval was obtained from both countries and ethical standards were followed.

Results: A total of 116 (53 from Ghana and 63 from Nigeria) patients with hypertension participated in the study. Respondents had a mean age of 61.0 ± 9.1 years, and were mostly females (64.7%). There was an increase in the level of physical activity which was significant by the third month (p < 0.0001) but became insignificant by the 6^th month (p = 0.311). Fruits and vegetables intake also improved at 3 months (p = 0.054) and significantly at 6 months (p = 0.002).

Conclusion: The study found the use of telehealth as an effective tool for the delivery of adjunct therapy for lifestyle modification in the management of hypertension in Nigeria and Ghana. It is therefore recommended that telehealth be incorporated into the management of hypertension and other chronic diseases for better health outcome.

Introduction: Healthcare amelioration is exponential to technological advancement. In the recent era of automation, the consolidation of artificial intelligence (AI) in dentistry has rendered transformation in oral healthcare from a hardware-centric approach to a software-centric approach, leading to enhanced efficiency and improved educational and clinical outcomes.

Objectives: The aim of this narrative overview is to extend the succinct of the major events and innovations that led to the creation of modern-day AI and dentistry and the applicability of the former in dentistry. This article also prompts oral healthcare workers to endeavor a liable and optimal approach for effective incorporation of AI technology into their practice to promote oral health by exploring the potentials, constraints, and ethical considerations of AI in dentistry.

Methods: A comprehensive approach for searching the white and grey literature was carried out to collect and assess the data on AI, its use in dentistry, and the associated challenges and ethical concerns.

Results: AI in dentistry is still in its evolving phase with paramount applicabilities relevant to risk prediction, diagnosis, decision-making, prognosis, tailored treatment plans, patient management, and academia as well as the associated challenges and ethical concerns in its implementation.

Conclusion: The upsurging advancements in AI have resulted in transformations and promising outcomes across all domains of dentistry. In futurity, AI may be capable of executing a multitude of tasks in the domain of oral healthcare, at the level of or surpassing the ability of mankind. However, AI could be of significant benefit to oral health only if it is utilized under responsibility, ethicality and universality.

Objective: The objective of this study was to assess the predictability of admissions to a MH inpatient ward using ML models, based on routine data collected during triage in EDs. This research sought to identify the most effective ML model for this purpose while considering the practical implications of model interpretability for clinical use.

Methods: The study utilised existing data from January 2016 to December 2021. After data pre-processing, an exploratory analysis revealed the non-linear nature of the dataset. Six different ML models were tested: Random Forest, XGBoost, CatBoost, k-Nearest Neighbours (kNN), Explainable Boosting Machine (EBM) using InterpretML, and Support Vector Machine using Support Vector Classification (SVC). The performance of these models was evaluated using various metrics including the Matthews Correlation Coefficient (MCC).

Results: Among the models evaluated, the CatBoost model achieved the highest MCC score of 0.1952, demonstrating superior balanced accuracy and predictive power, particularly in correctly identifying positive cases. The InterpretML model also performed well, with an MCC score of 0.1914. While CatBoost showed strong predictive capabilities, its complexity poses challenges for clinical interpretation. Conversely, the InterpretML model, though slightly less powerful, offers better transparency and is more practical for clinical use.

Conclusion: The findings suggest that the CatBoost model is a compelling choice for scenarios prioritising the detection of positive cases. However, the InterpretML model's ease of interpretation makes it more suitable for clinical application. Integrating explanation methods like SHAP with non-linear models could enhance model transparency and foster clinician trust. Further research is recommended to refine non-linear models within decision support systems, explore multi-source data integration, understand clinician attitudes towards ML, and develop real-time data collection systems. This study highlights the potential of ML in predicting MH admissions from ED data while stressing the importance of interpretability, ethical considerations, and ongoing validation for successful clinical implementation.

Objective: The use of social media during the COVID-19 pandemic has been researched extensively since the outbreak. Sina Weibo, as one of most commonly used social media platforms in China, played an important role in public expression for the duration of COVID-19. We investigated the themes that emerged from the posts and examined the sentiments associated with each theme.

Methods: For this study, we collected 72,084 Weibo posts related to the 2022 Shanghai public health event to present a thematic and sentiment analysis of posts by the public.

Results: The findings showed that the public was more inclined to express concerns about the impact of the outbreak and of outbreak containment measures on their personal lives on social media and exhibited negative attitudes and opinions rather than discussing the impact of COVID-19 on human life and health, suggesting that the impact of the outbreak on people's daily lives was greater than was the impact on their livelihoods and health risks.

Conclusions: This research highlights the importance of understanding the role of social media in times of crisis and the potential insights that can be gained from analyzing online public discourse. Our empirical findings provide insights for future public health communication strategies and crisis management plans in China in the information age.

Objectives: To provide a comprehensive review of the use of electronic patient-reported outcomes measures (ePROs) as digital health tools to assess health-related quality of life (HRQoL) in women with breast, ovarian, cervical, and endometrial cancers.

Methods: A systematic review was conducted to identify studies that used ePROs to evaluate HRQoL in women diagnosed with breast and gynecological cancers. The review followed the 2020 update of the PRISMA guidelines and a pre-registered protocol in PROSPERO (CRD42024516737). Inclusion criteria encompassed studies focusing on ePROs for HRQoL assessment in the specified cancers, without language restrictions, and published between January 2000 and December 2023. Studies were retrieved from PubMed, Web of Science, and Scopus. Two reviewers independently screened titles, abstracts, and full texts to identify eligible studies.

Results: The search yielded 4978 articles. After removing duplicates, 900 articles were assessed for eligibility by screening the titles and abstracts. After screening the full text of 168 articles, a total of 16 studies were included in this systematic review. These studies were mainly conducted in Europe and the Americas and included different study designs such as randomized controlled trials (four articles), prospective studies (seven articles), and feasibility and validation studies (five articles). The majority of the studies focused on breast cancer (87.5%), with fewer studies addressing ovarian and cervical cancers. A variety of ePRO tools were used, including the FACT and EORTC QLQ. Findings show that ePROs enhance therapeutic management, treatment adherence, and HRQoL through improved symptom monitoring and communication between patients and providers.

Conclusion: The integration of ePROs in oncology care facilitates a patient-centered approach, enhances communication between patients and healthcare providers, and supports personalized treatment strategies. These findings underscore the importance of incorporating ePROs into routine cancer care to improve overall patient outcomes and HRQoL.

Objective: This study aims to address the challenge of privacy-preserving Alzheimer's disease classification using federated learning across various data distributions, focusing on real-world applicability. The goal is to improve the efficiency of classification by minimizing communication rounds between clients and the central server.

Methods: The proposed approach leverages two key strategies: increasing parallelism by utilizing more clients in each communication round and increasing computation per client during the intervals between rounds. To reflect real-world scenarios, data is divided into three distributions: identical and independently distributed, non-identical and independently distributed equal, and non-identical and independently distributed unequal. The impact of extreme quantity distribution skew is also examined. A convolutional neural network is used to evaluate the performance across these setups.

Results: The empirical study demonstrates that the proposed federated learning approach achieves a maximum accuracy of 84.75%, a precision of 86%, a recall of 85%, and an F1-score of 84%. Increasing the number of local epochs improves classification performance and reduces communication needs. The experiments show that federated learning is effective in handling heterogeneous datasets when all clients participate in each round of training. However, the results also indicate that extreme quantity distribution skew negatively impacts classification performance.

Conclusions: The study confirms that federated learning is a viable solution for Alzheimer's disease classification while preserving data privacy. Increasing local computation and client participation enhances classification performance, though extreme distribution imbalances present a challenge. Further investigation is needed to address these limitations in real-world scenarios.

Objectives: Cervical cancer, a leading cause of cancer-related deaths among women globally, has a significantly higher survival rate when diagnosed early. Traditional diagnostic methods like Pap smears and cervical biopsies rely heavily on the skills of cytologists, making the process prone to errors. This study aims to develop CerviXpert, a multi-structural convolutional neural network designed to classify cervix types and detect cervical cell abnormalities efficiently.

Methods: We introduced CerviXpert, a computationally efficient convolutional neural network model that classifies cervical cancer using images from the publicly available SiPaKMeD dataset. Our approach emphasizes simplicity, using a limited number of convolutional layers followed by max-pooling and dense layers, trained from scratch. We compared CerviXpert's performance against other state-of-the-art convolutional neural network models, including ResNet50, VGG16, MobileNetV2, and InceptionV3, evaluating them on accuracy, computational efficiency, and robustness using five-fold cross-validation.

Results: CerviXpert achieved an accuracy of 98.04% in classifying cervical cell abnormalities into three classes (normal, abnormal, and benign) and 98.60% for five-class cervix type classification, outperforming MobileNetV2 and InceptionV3 in both accuracy and computational demands. It demonstrated comparable results to ResNet50 and VGG16, with significantly reduced computational complexity and resource usage.

Conclusion: CerviXpert offers a promising solution for efficient cervical cancer screening and diagnosis, striking a balance between accuracy and computational feasibility. Its streamlined architecture makes it suitable for deployment in resource-constrained environments, potentially improving early detection and management of cervical cancer.

Aims: To determine the acceptability and identify potential concerns and barriers of using a hypothetical smartphone application (app) for home monitoring (HM) of visual function among patients with diabetes.

Methods: Quantitative, cross-sectional study using a self-administered questionnaire. Patients diagnosed with diabetes aged between 20 and 70 years were included. The research was conducted across five regions in Saudi Arabia. The questions were adapted from a validated, published questionnaire and translated into Arabic. It focused on socio-demographic factors and barriers which associated with the acceptance of the hypothetical visual function HM app, using descriptive statistics.

Results: A total of 240 patients with diabetes participated in this study. About half of the participants (40.4%) ranged between 40 and 59 years; 42.5% were male, and most of the participants (93.8%) lived within 2 h of their healthcare facility. The rejection to the use of a hypothetical HM app was associated with increased age (p = 0.025), lower education level (p = 0.023), urbanicity (p = 0.011), residing closer to health centres (p = 0.021), and never experiencing telehealth services previously (p = 0.025). Logistic regression revealed that accepting a hybrid clinic approach was more likely to be acceptable by younger patients (20-39 years: OR, 5.01; 95% CI, 1.82-13.82; p < 0.001; and 40-59 years: OR, 2.28; 95% CI, 0.084-5.00; p = 0.48), as well as patients who attended primary healthcare or specialised governmental clinics (p = 0.038 and p = 0.019, respectively).

Conclusion: Factors that altered patients' acceptance of the hypothetical app included their age, educational level, urbanicity, traveling distance, and telehealth experience. Therefore, careful consideration of acceptability and barriers is essential before implementing such an intervention.

Objective: This study seeks to outline the features of digital competences among educators in health professions education and pinpoint areas in need of enhancement.

Methods: The transcribed interviews of nine educators in physiotherapy education were coded to align with The European Framework for the Digital Competence of Educators (DigCompEdu), adhering to a step-by-step procedure.

Results: In total, 320 significant units were coded to an individual competence. Three competence areas (Professional engagement, Teaching and learning, and Empowering learners accounted for (94.2%) of the codes, while the three remaining (Digital resources, Assessment, and Facilitating learners' digital competence) for 5.8% of cases. Several individual competences were not identified, across domains and the educators raised skepticism regarding the relevance of digital education for clinical practice.

Conclusion: The study reveals deficiencies in the digital competence of health professions educators, highlighting gaps in strategies to utilize technology in their work and the integration of technologies with clinical skills. Educators exhibit individual-driven rather than collaborative digital professional development, expressing skepticism about technology's efficacy in clinical skills training. The results emphasize the urgent need for comprehensive improvement. Without addressing these issues, health education students may graduate without essential digital skills, hindering their contribution to technology development.

Objective: The integration of medical large language models (MLLMs) into healthcare has garnered global interest, however, the determinants of their adoption by medical professionals remain underexplored. This study aims to elucidate the factors influencing doctors' intention to utilize MLLMs, encompassing both psychological determinants and demographic attributes.

Methods: An extended theoretical model was developed using constructs derived from the Technology Acceptance Model (TAM) and five constructs. A hybrid online and offline survey was conducted from March to December 2023, including 955 Chinese medical practitioners. Structural equation modeling was utilized to test the research hypotheses.

Results: The measurement model exhibited satisfactory reliability and validity, with fit indices meeting scholarly standards. Perceived ease of use emerged as a significant predictor of both perceived usefulness and satisfaction. Content quality was identified as a substantial influence on perceived satisfaction but did not significantly predict perceived usefulness. Technical support and social influence were found to significantly affect perceived usefulness without directly impacting satisfaction. Perceived usefulness positively influenced both satisfaction and usage behavior, while perceived risk had a negative effect. A significant relationship between perceived satisfaction and usage behavior was established, with gender, age, education, and professional title moderating this relationship.

Conclusions: The study provides empirical evidence for understanding the adoption of MLLMs by Chinese doctors, offering management implications for future technical research, development, and implementation in the medical field.