Frontiers in digital health最新文献

Background: Digital Healthcare Solutions (DHS) are transforming healthcare by improving patients' experiences, safety and quality of care. However, despite all the proposed and observed advantages of DHS, a growing body of research suggests that these DHS are not equally accessible to all. This research aimed to assess whether equity frameworks for digital health solutions can be used to guide the development of digital health solutions to increase access to care for dementia patients in the UK and, thereafter, develop practical guidelines to guide the design of equitable DHS products to address this growing issue.

Methods: A scoping review across four databases and grey literature was done to identify equity frameworks and design principles for DHS. The equity frameworks and design principles were analyzed to make recommendations on increasing equity in the product.

Results: 34 publications and reports met the inclusion criteria. Four equity frameworks were analyzed and one was selected. Equitable product development guidelines were created based on patient-centered design principles.

Conclusion: Although DHS can increase inequity in healthcare, concrete methods and practical guidelines can minimize this if DHS developers design for maximum equity and closely collaborate with healthcare providers and end-users in product development. Future research could use these guidelines to test usability for developers and investigate other equitable approaches like institutional barriers to adoption.

Introduction: Ecosystem-centered healthcare innovations, such as digital health platforms, patient-centric records, and mobile health applications, depend on the semantic interoperability of health data. This ensures efficient, patient-focused healthcare delivery in a mobile world where citizens frequently travel for work and leisure. Beyond healthcare delivery, semantic interoperability is crucial for secondary health data use. This paper introduces a tool and techniques for achieving health data semantic interoperability, using reusable visual transformation components to create and validate transformation rules and maps, making them usable for domain experts with minimal technical skills.

Methods: The tool and techniques for health data semantic interoperability have been developed and validated using Design Science, a common methodology for developing software artifacts, including tools and techniques.

Results: Our tool and techniques are designed to facilitate the interoperability of Electronic Health Records (EHRs) by enabling the seamless unification of various health data formats in real time, without the need for extensive physical data migrations. These tools simplify complex health data transformations, allowing domain experts to specify and validate intricate data transformation rules and maps. The need for such a solution arises from the ongoing transition of the Estonian National Health Information System (ENHIS) from Clinical Document Architecture (CDA) to Fast Healthcare Interoperability Resources (FHIR), but it is general enough to be used for other data transformation needs, including the European Health Data Space (EHDS) ecosystem.

Conclusion: The proposed tool and techniques simplify health data transformation by allowing domain experts to specify and validate the necessary data transformation rules and maps. Evaluation by ENHIS domain experts demonstrated the usability, effectiveness, and business value of the tool and techniques.

Introduction: Identity verification plays a crucial role in modern society, with applications spanning from online services to security systems. As the need for robust automatic authentication systems increases, various methodologies-software, hardware, and biometric-have been developed. Among these, biometric modalities have gained significant attention due to their high accuracy and resistance to falsification. This paper focuses on utilizing electrocardiogram (ECG) signals for identity verification, capitalizing on their unique, individualized characteristics.

Methods: In this study, we propose a novel identity verification framework based on ECG signals. Notable datasets, such as the NSRDB and MITDB, are employed to evaluate the performance of the system. These datasets, however, contain inherent noise, which necessitates preprocessing. The proposed framework involves two main steps: (1) signal cleansing to remove noise and (2) transforming the signals into the frequency domain for feature extraction. This is achieved by applying the Wigner-Ville distribution, which converts ECG signals into image data. Each image captures unique cardiac signal information of the individual, ensuring distinction in a noise-free environment. For recognition, deep learning techniques, particularly convolutional neural networks (CNNs), are applied. The GoogleNet architecture is selected for its effectiveness in processing complex image data, and is used for both training and testing the system.

Results: The identity verification model achieved impressive results across two benchmark datasets. For the NSRDB dataset, the model achieved an accuracy of 99.3% and an Equal Error Rate (EER) of 0.8%. Similarly, for the MITDB dataset, the model demonstrated an accuracy of 99.004% and an EER of 0.8%. These results indicate that the proposed framework offers superior performance in comparison to alternative biometric authentication methods.

Discussion: The outcomes of this study highlight the effectiveness of using ECG signals for identity verification, particularly in terms of accuracy and robustness against noise. The proposed framework, leveraging the Wigner-Ville distribution and GoogleNet architecture, demonstrates the potential of deep learning techniques in biometric authentication. The results from the NSRDB and MITDB datasets reflect the high reliability of the model, with exceptionally low error rates. This approach could be extended to other biometric modalities or combined with additional layers of security to enhance its practical applications. Furthermore, future research could explore additional preprocessing techniques or alternative deep learning architectures to further improve the performance of ECG-based identity verification systems.

Objective: The COVID-19 pandemic has placed unprecedented strain on healthcare systems, mainly due to the highly variable and challenging to predict patient length of stay (LOS). This study aims to identify the primary factors impacting LOS for patients before and during the COVID-19 pandemic.

Methods: This study collected electronic medical record data from Zhongnan Hospital of Wuhan University. We employed six machine learning algorithms to predict the probability of LOS.

Results: After implementing variable selection, we identified 35 variables affecting the LOS for COVID-19 patients to establish the model. The top three predictive factors were out-of-pocket amount, medical insurance, and admission deplanement. The experiments conducted showed that XGBoost (XGB) achieved the best performance. The MAE, RMSE, and MAPE errors before and during the COVID-19 pandemic are lower than 3% on average for household registration in Wuhan and non-household registration in Wuhan.

Conclusions: Research finds machine learning is reasonable in predicting LOS before and during the COVID-19 pandemic. This study offers valuable guidance to hospital administrators for planning resource allocation strategies that can effectively meet the demand. Consequently, these insights contribute to improved quality of care and wiser utilization of scarce resources.

Introduction: Anxiety and depression are major causes of disability in Arab countries, yet resources for mental health services are insufficient. Mobile devices may improve mental health care delivery (mental m-Health), but the Arab region's mental m-Health app landscape remains under-documented. This study aims to systematically assess the features, quality, and digital safety of mental m-Health apps available in the Arab marketplace. We also contrast a set of recommended Australian apps to benchmark current strategies and evidence-based practices and suggest areas for improvement in Arabic apps.

Methods: Fifteen Arab country-specific iOS Apple Stores and an Android Google Play Store were searched. Apps that met the inclusion criteria were downloaded and evaluated using the Mobile App Rating Scale (MARS) and the Mobile App Development and Assessment Guide (MAG).

Results: Twenty-two apps met the inclusion criteria. The majority of apps showed no evidence of mental health experts being involved in the app design processes. Most apps offered real-time communication with specialists through video, text, or audio calls rather than evidence-based self-help techniques. Standardized quality assessment showed low scores for design features related to engagement, information, safety, security, privacy, usability, transparency, and technical support. In comparison to apps available in Australia, Arabic apps did not include evidence-based interventions like CBT, self-help tools and crisis-specific resources, including a suicide support hotline and emergency numbers.

Discussion: In conclusion, dedicated frameworks and strategies are required to facilitate the effective development, validation, and uptake of Arabic mental mHealth apps. Involving end users and healthcare professionals in the design process may help improve app quality, dependability, and efficacy.

Background: Musculoskeletal disorders are among the most common occupational injuries and disabilities in developing and industrialized countries. This study aims to determine the effectiveness of e-mail training to improve the physical posture of female computer users at Birjand University of Medical Sciences in Iran.

Methods: The present interventional research explores the effect of email-based training to correct the body posture of female computer users in Birjand, Iran. In this quasi-experiment, 120 women who worked in Birjand University of Medical Sciences using computers were selected through a census. 60 computer users were selected from the deputy of education and 60 from the deputy of development for the intervention group (IG) and control group (CG), respectively. A training program was developed on the ergonomics of office work (12 emails at an interval of 6 weeks). The data was collected using demographic, occupational information, and a knowledge assessment questionnaire. Nordic Musculoskeletal Questionnaire (NMQ) and Rapid Office Strain Assessment (ROSA) were used in both groups before the intervention and 6 months later.

Results: After the educational intervention, a significant increase was observed in the ergonomics knowledge of the IG compared to the control. The ROSA score was lowered from a high-risk to a low-and medium-risk level (p < 0.05). In the IG, 44 subjects (73.30%) who needed ergonomic intervention (a score above 5) were reduced to 10 subjects (16.70%) with a need for ergonomic intervention. According to NMQ, the highest frequency of pain in the IG and CG was related to the back (56.70% and 55%, respectively). The neck, shoulders, wrists, back and elbows were next.

Conclusions: This quasi-intervention study was conducted to determine the effect of email-based training on correcting female computer users' body posture in 2022. Training ergonomics through email is a practical and acceptable way to improve ergonomic behaviors among computer users. It enables them to adapt to the workplace by applying the correct ergonomics, changing their work behavior to prevent occupational musculoskeletal disorders, and reduce risks and complications.

Background: In recent years, text-based e-consultations have been widely implemented in general practice and are appreciated by patients for their convenience and efficiency. Policymakers aim to enhance patient access to clinical services with the general practitioner (GP) through text-based e-consultations. However, concerns are raised about their efficiency and security. We aimed to investigate users' perceptions of potential improvements in the text-based e-consultation service provided by the national health portal in Norway.

Method: We conducted an online survey among users of text-based e-consultations with the GP on the national health portal Helsenorge. The survey was available from January-February 2023 and consisted of 20 questions. This study focused on the free-text answers to the question "Do you have any suggestions to improve the service?" The framework method was used for a thematic analysis of the answers.

Results: The analysis of 2,954 free-text answers from users of the national e-consultation service resulted in six areas where suggestions for improvement were expressed. According to users, the service would benefit from: (1) a better set-up to facilitate the formulation of the patient's problem, (2) better value for money (in regards to both price and quality), (3) faster response time, (4) improved information and predictability about the status of the e-consultation (e.g., if it is received and when to expect an answer), (5) improvement in technical issues, and (6) improvement of access to dialogue-based services to replace or complement e-consultations.

Conclusion: The analysis of users' suggestions for improvements to the e-consultation service emphasised the need to customise the service to address individual patient needs. Users found a one-size-fits-all approach with mandatory questions, fixed pricing, and inflexible response times less appreciated. Some also felt forced to rely on e-consultations due to the perceived poor availability of other GP services. This highlights the importance of perceiving e-consultations not as a replacement for dialogue-enabled services, but rather as a potentially efficient addition, ensuring a well-tailored setup for appropriate patient use.

Introduction: The integration of AI into healthcare is widely anticipated to revolutionize medical diagnostics, enabling earlier, more accurate disease detection and personalized care.

Methods: In this study, we developed and validated an AI-assisted diagnostic support tool using only routinely ordered and broadly available blood tests to predict the presence of major chronic and acute diseases as well as rare disorders.

Results: Our model was tested on both retrospective and prospective datasets comprising over one million patients. We evaluated the diagnostic performance by (1) implementing ensemble learning (mean ROC-AUC.9293 and mean DOR 63.96); (2) assessing the model's sensitivity via risk scores to simulate its screening effectiveness; (3) analyzing the potential for early disease detection (30-270 days before clinical diagnosis) through creating historical patient timelines and (4) conducting validation on real-world clinical data in collaboration with Synlab Hungary, to assess the tool's performance in clinical setting.

Discussion: Uniquely, our model not only considers stable blood values but also tracks changes from baseline across 15 years of patient history. Our AI-driven automated diagnostic tool can significantly enhance clinical practice by recognizing patterns in common and rare diseases, including malignancies. The models' ability to detect diseases 1-9 months earlier than traditional clinical diagnosis could contribute to reduced healthcare costs and improved patient outcomes. The automated evaluation also reduces evaluation time of healthcare providers, which accelerates diagnostic processes. By utilizing only routine blood tests and ensemble methods, the tool demonstrates high efficacy across independent laboratories and hospitals, making it an exceptionally valuable screening resource for primary care physicians.

Background: The rapid development of artificial intelligence (AI) has shown great potential in medical document generation. This study aims to evaluate the performance of Claude 3.5-Sonnet, an advanced AI model, in generating discharge summaries for patients with renal insufficiency, compared to human physicians.

Methods: A prospective, comparative study was conducted involving 100 patients (50 with acute kidney injury and 50 with chronic kidney disease) from the nephrology department of Ningbo Hangzhou Bay Hospital between January and June 2024. Discharge summaries were independently generated by Claude 3.5-Sonnet and human physicians. The main evaluation indicators included accuracy, generation time, and overall quality.

Results: Claude 3.5-Sonnet demonstrated comparable accuracy to human physicians in generating discharge summaries for both AKI (90 vs. 92 points, p > 0.05) and CKD patients (88 vs. 90 points, p > 0.05). The AI model significantly outperformed human physicians in terms of efficiency, requiring only about 30 s to generate a summary compared to over 15 min for physicians (p < 0.001). The overall quality scores showed no significant difference between AI-generated and physician-written summaries for both AKI (26 vs. 27 points, p > 0.05) and CKD patients (25 vs. 26 points, p > 0.05).

Conclusion: Claude 3.5-Sonnet demonstrates high efficiency and reliability in generating discharge summaries for patients with renal insufficiency, with accuracy and quality comparable to those of human physicians. These findings suggest that AI has significant potential to improve the efficiency of medical documentation, though further research is needed to optimize its integration into clinical practice and address ethical and privacy concerns.

Introduction: The 2024 Voice AI Symposium, hosted by the Bridge2AI-Voice Consortium in Tampa, FL, featured two keynote speeches that addressed the intersection of voice AI, healthcare, ethics, and law. Dr. Rupal Patel and Dr. Nicholson Price provided insights into the advancements, applications, and challenges of AI-driven voice tools in healthcare. The symposium aimed to advance cross-disciplinary collaboration and establish frameworks for the ethical use of AI technologies in healthcare.

Methods: The keynote speeches, delivered on May 1st and 2nd, were 30 minutes each, followed by 10-minutes Q&A sessions. The audio was recorded and transcribed using Whisper (v7.13.1). Content summaries were generated with the aid of ChatGPT (v4.0), and the authors reviewed and edited the final transcripts to ensure accuracy and clarity.

Results: Dr. Rupal Patel's keynote, "Reflections and New Frontiers in Voice AI", explored the potential of voice AI for early detection of health conditions, monitoring disease progression, and promoting non-invasive global health management. She highlighted innovative uses beyond traditional applications, such as examining menopause-related symptoms. Dr. Nicholson Price's keynote, "Governance for Clinical Voice AI", addressed the regulatory and ethical challenges posed by AI in healthcare. He stressed the need for context-aware systems and dynamic legal frameworks to address liability and accountability.

Conclusions: The 2024 Voice AI Symposium highlighted the transformative potential of voice AI for early detection, health monitoring, and reducing healthcare disparities. It also underscored the importance of dynamic governance to address the ethical and regulatory challenges of deploying AI in clinical settings.