DIGITAL HEALTH最新文献

Objective: Social interactions and experiences are increasingly occurring online, including for young adults with psychosis. Healthy social interactions and experiences are widely recognized as a critical component of social recovery, yet research thus far has focused predominantly on offline interactions with limited understanding of these interactions online. We developed the Social Media and Internet sociaL Engagement (SMILE) questionnaire to assess the type, frequency, and nature of online social interactions and experiences among young adults with early psychosis to better assess online social activity and ultimately support personalized interventions.

Methods: Participants (N = 49) completed the SMILE questionnaire which asked about online platforms used, frequency of use, and if positive and negative experiences were more likely to happen online or offline. Participants completed additional self-report measures of victimization, positive psychotic symptoms, social functioning, and demographics. Exploratory factor analysis and correlations between identified factors and clinical measures of interest were completed.

Results: Exploratory factor analysis revealed three factors: positive engagement, victimization, and internalizing experiences. Most participants (6%-37%) experienced positive engagement offline. Victimization occurred equally online and offline (8%-27% and 4%-24%, respectively). Most participants (37%-51%) endorsed internalizing experiences as occurring equally offline and online, but approximately a third of participants reported internalizing experiences more frequently offline (20%-35%). Victimization was moderately (r = 0.34) correlated with overall online social experiences, suggesting more online time may increase the likelihood of victimization. Age was inversely related to the frequency of overall online social experiences.

Conclusion: Young adults with early psychosis experience positive and negative social experiences online and offline. New scales and measures to comprehensively assess the nature and function of online social interactions and experiences are needed.

Objective: Tuberculosis remains a major global health challenge, with delayed diagnosis contributing to increased transmission and disease burden. While microbiological tests are the gold standard for confirming active tuberculosis, many cases lack microbiological evidence, necessitating additional clinical and laboratory data for diagnosis. The complete blood count (CBC), an inexpensive and widely available test, could provide a valuable tool for tuberculosis diagnosis by analyzing disturbances in blood parameters. This study aimed to develop and evaluate a machine learning (ML)-based web application, TubIAgnosis, for diagnosing active tuberculosis using CBC data.

Methods: We conducted a retrospective case-control study using data from 449 tuberculosis patients and 1200 healthy controls in Oran, Algeria, from January 2016 to April 2023. Eight ML algorithms were trained on 18 CBC parameters and demographic data. Model performance was evaluated using balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC).

Results: The best-performing model, Extreme Gradient Boosting (XGB), achieved a balanced accuracy of 83.3%, AUC of 89.4%, sensitivity of 83.3%, and specificity of 83.3% on the testing dataset. Platelet-to-lymphocyte ratio was the most influential parameter in this ML predictive model. The best performing model (XGB) was made available online as a web application called TubIAgnosis, which is available free of charge at https://yh5f0z-ghermi-mohamed.shinyapps.io/TubIAgnosis/.

Conclusions: TubIAgnosis, a ML-based web application utilizing CBC data, demonstrated promising performance for diagnosing active tuberculosis. This accessible and cost-effective tool could complement existing diagnostic methods, particularly in resource-limited settings. Prospective studies are warranted to further validate and refine this approach.

Objective: The COVID-19 pandemic has spurred an increased interest in online healthcare and a surge in usage of online healthcare platforms, leading to a proliferation of user-generated online physician reviews. Yet, distinguishing between genuine and fake reviews poses a significant challenge. This study aims to address the challenges delineated above by developing a reliable and effective fake review detection model leveraging deep learning approaches based on a fake review dataset tailored to the context of Chinese online medical platforms.

Methods: Inspired by prior research, this paper adopts a crowdsourcing approach to assemble the fake review dataset for Chinese online medical platforms. To develop the fake review detection models, classical machine learning models, along with deep learning models such as Convolutional Neural Network and Bidirectional Encoder Representations from Transformers, were applied.

Results: Our experimental deep learning model exhibited superior performance in identifying fake reviews on online medical platforms, achieving a precision of 98.36% and an F2-Score of 97.97%. Compared to the traditional machine learning models (i.e., logistic regression, support vector machine, random forest, ridge regression), this represents an 8.16% enhancement in precision and a 7.7% increase in F2-Score.

Conclusion: Overall, this study provides a valuable contribution toward the development of an effective fake physician review detection model for online medical platforms.

Objective: Digital interventions can be effective in preventing and treating common mental health conditions among university students. Incorporating student experiences and perspectives in the design and implementation of these programmes may improve uptake and engagement. This qualitative study explored university students' perspectives of a low-intensity video-based mental health intervention, their recommendations for implementing the programme in university settings, and their views and recommendations to address barriers to engagement.

Methods: Participants (N = 115) were students (mean = 20.63 years, SD = 2.10) with elevated distress from 31 Australian universities drawn from a randomised controlled trial of the Uni Virtual Clinic-Lite (UVC-Lite). Data from students randomised to the intervention condition were collected via semi-structured interviews (n = 12) and open-ended questions during post-intervention surveys (n = 103). Data were analysed using content analysis.

Results: Participants generally reported positive views of the intervention, and most felt it should be offered to students as a universal intervention. Multiple methods of disseminating the intervention were suggested, including through university counselling, official platforms (e.g. student support services) and informal channels (e.g. word-of-mouth promotion). Difficulty integrating the programme into everyday life, pre-existing beliefs about mental health and technology-related factors were highlighted as barriers to engagement.

Conclusion: A low-intensity video-based mental health intervention was generally considered to be acceptable and appropriate for students with mild to moderate distress. Participants provided several suggestions to encourage uptake of the intervention and possible pathways to disseminate the intervention to students. The effectiveness of these should be examined in future trials.

Objective: It is not clear whether self-rated health is associated with internet use among community-dwelling patients living with diabetes. This study investigated what kind and level of use of the internet is desirable for the subjective sense of health among patients living with diabetes in the community.

Research design and methods: This was a cross-sectional study of patients living with diabetes aged 18 years or older who visited our clinic between April 2022 and June 2022. The final analysis included 654 subjects (mean age: 56-90 years). The objective variable was self-rated health, and the explanatory variable was purpose of internet use. We used logistic regression analysis to identify odds ratios (ORs) and 95% confidence intervals (CIs) for the association between internet use and self-rated health by purpose of internet use.

Results: Of the 654 patients living with diabetes using our clinic, 488 (64.7%) were internet users. Communication with friends/family (66.6%) was the most common use of the internet, followed by social media (54.3%) and shopping (36.7%). Logistic regression models showed that social media (OR: 1.81; 95% CI [1.02, 3.21], p = 0.04), shopping for food and other items (OR: 1.95; 95% CI [1.00, 3.77], p = 0.04), online securities and banking (OR: 2.75; 95% CI [1.02, 7.39], p = 0.04) were associated with self-rated health.

Conclusions: Using the internet for social media, shopping, and banking were found to be associated with self-rated health. Use for these purposes could help support diabetic care.

Objective: Adolescents face various health challenges due to academic pressures and sedentary lifestyles. Establishing healthy habits during this critical period is essential for long-term well-being. With the widespread use of fitness apps, understanding their impact on adolescent health behaviors and the underlying mechanisms is crucial. Guided by social support theory and social comparison theory, this study examined the influence of WeRun, a fitness app within WeChat, on adolescents' adoption of healthy lifestyles. It investigated the correlation between WeRun usage and healthy behaviors, as well as the underlying mechanisms driving this relationship.

Methods: A cross-sectional survey was conducted across 31 provinces and metropolitans in China, utilizing a random cluster sampling approach targeting high school and freshman students aged 15-24 (N = 1312). A parallel mediation model was employed to test the hypotheses.

Results: The analysis showed that WeRun use positively predicted both social support and social comparison. Meanwhile, both social support and social comparison were positively associated with healthy lifestyles. Additionally, WeRun use could not directly predict healthy lifestyles. However, WeRun use indirectly predicted healthy lifestyles via social support and social comparison.

Conclusions: The study's findings revealed the pivotal roles of social support and social comparison as mediating variables in the relationship between adolescents' WeRun usage and adoption of healthy lifestyles. The results contributed to the current comprehension of the mechanisms linking app utilization to health-promoting behaviors. Furthermore, it provided valuable insights for promoting adolescent health and informed improved design strategies for fitness apps.

Introduction: An estimated one billion people globally are currently suffering from hypertension. Prevention and management of hypertension are suboptimal especially in low- and middle-income countries leading to increased complications and deaths. With increased mobile phone coverage globally, this study aims to review mobile health technologies used for the prevention and management of hypertension.

Methods: We conducted a literature search on electronic databases using identified keywords involving "hypertension", "mobile health technology" and their synonyms. Snowballing technique was also used. Papers were screened at two levels by independent reviewers. The targets were studies published in peer-reviewed journals reporting mobile health interventions for hypertension prevention and management. Only primary research studies published in English from January 2017 to April 2024 were included. Google Forms were used to extract the data along with other characteristics, and selected articles were categorised into: mobile application, web-based solutions, and Short Message Service (SMS) and other offline solutions.

Result: The search yielded 184 articles, and 44 studies were included in the review. Most (n = 26) were randomised control trials. Twenty-two studies (22) focused only on mobile applications solutions, 12 on SMS and other offline mHealth, 5 web-based solutions, and 5 combined more than one type of mobile health technology. The United States of America had the majority of studies (n = 17), with 6 studies from other American countries, 11 from Asia and nine from Europe, while only one from Africa. A total of 36 studies reported that mobile health technology significantly improved hypertension care through reduced blood pressure, improved adherence to follow-up visits and medications, and lifestyle changes. SMS and offline mHealth strategies have also demonstrated effectiveness in promoting self-management and reducing racial disparities in hypertension care.

Conclusion: Mobile health technology has the potential to play a significant role in the prevention and management of hypertension. However, there is a need for mobile health solutions for hypertension prevention and management in African countries and other developing countries. Integrating mHealth into primary healthcare delivery would also go a long way in strengthening patient care and reducing the burden on healthcare systems.

Objective: Goal setting is a behavior change technique associated with improved change in outcomes. Digital (eHealth, mHealth) behavior change interventions often prescribe all goals with no opportunity for participants to create and track their own; thus, little is known about the types of goals participants create for themselves and their impacts on behavioral outcomes. This analysis describes the goals created by participants using an optional personal goal-setting component and evaluates the association between participant goal creation and weight loss in an eHealth adult weight loss intervention.

Methods: This represents a mixed methods QUANT-qual design to understand the types of goals users create for themselves and their impacts on behavior change outcomes. Qualitative codes were applied for the topic, behavior/outcome focus, adherence to SMART criteria, and repetition with count summaries. Quantitative analyses applied regression modeling to determine if the number of goals set was associated with the 6-month weight change, controlling for covariates.

Results: Participants (n = 363) set an average of 23.4 goals (SD = 22.7) over 6 months. Those who reached at least 5% weight loss set significantly more goals than those who lost between 1% and 4.99% or who lost <1% or gained weight (p's < 0.0001). Setting more personal goals was associated with significant weight loss reduction at 6 months, controlling for covariates (p's < 0.05).

Conclusions: Greater use of a personal goal-setting feature was associated with improved weight loss outcomes among active users. This can be a low-investment addition to digital behavior change interventions to contribute to improved outcomes.

Objective: To describe the experiences of healthcare professionals with integrating telemedicine in routine heart failure (HF) care.

Methods: Semi-structured interviews were conducted with healthcare professionals (n = 19) in the Netherlands who were involved in decision-making, implementation or routine use of telemedicine in HF management. Using purposive sampling, nurses, cardiologists and managers were selected to be interviewed. Interviews were performed in-person, recorded and transcribed verbatim. Interview data were analysed using a reflexive thematic analysis.

Results: This study identified four themes: (1) Responsibility - the lack of a clear delineation of roles and responsibilities among healthcare professionals, patients and suppliers in telemedicine. (2) Confidence and safety - telemedicine is seen by healthcare professionals as capable of enhancing safety, yet also introduces the risk of fostering a false sense of security among patients. (3) Collaboration - actively involving end-users in the development and implementation of telemedicine promotes the adoption. (4) Processes and mutual agreements - rather than replacing traditional care, telemedicine is perceived as an adjunct to it. Structured care pathways support telemedicine implementation, and personalised telemedicine can empower patients in self-care.

Conclusions: Telemedicine is a promising intervention in the management of HF. However, existing systems and care pathways have resulted in limited adoption. Improvements in the collaboration and establishing clear agreements on responsibilities between professional, patient and supplier can lead to more confidence in adopting telemedicine. Structured care pathways can be supportive. A personalised telemedicine approach can ensure that telemedicine remains manageable for patient and professional.

Objective: In the age of digital health, mankind has resources to write over the historical narrative of queer individuals' healthcare exclusions. The main purpose of this study was to explore the perspectives of both healthcare providers (HCPs) and queer individuals regarding the use of web-based tools and mobile health applications (mHealth apps) in the context of addressing queer individuals' sexual and reproductive health services and needs (SRHSN).

Methods: An overall study was conducted as an exploratory sequential mixed method. This article provides findings from the performed qualitative cycle. The selection method was led by purposeful sampling, which targeted 33 HCPs delivering SRHSN within the defined study settings. Additionally, respondent-driven sampling was employed to select 22 queer individuals. Throughout the study, semi-structured one-on-one face-to-face interviews were used to collect data.

Results: Four major themes and related sub-themes emerged from HCPs and queer individuals: (a) aid queer individuals with consultations and treatment improvements, (b) drawing parallels with technology in other sectors, (c) enhancing knowledge and education, and (d) positive perception of technological advancements.

Conclusions: In accordance with our findings, HCPs and queer individuals were all positive and sees mHealth apps as a tool to address SRHSN for homosexual people.