DIGITAL HEALTH最新文献

Background: Although adolescent birth rates have declined globally, the sexual and reproductive health of adolescent mothers remains an area of specific concern, and these were impacted by the COVID-19 pandemic. This study investigates characteristics, utilization of reproductive health services (RHS) and artificial intelligence (AI) prediction during the pandemic.

Methods: We conducted an exploratory study using data for 2020-2022 from the Taipei City Government Health Bureau. Adolescent mothers under the age of 20 received post-birth telephone-based RHS, covering contraception, abortion, postpartum care, and social welfare support. The data analysis included descriptive statistics, and various machine learning techniques were employed, including random forest, SVM, KNN, logistic regression, and Bayesian network analysis.

Results: Of 112 participants, most were aged 17 to 19 (80.4%) and married (58.0%). The majority had full-term deliveries (86.6%) with healthy infants. A high percentage had not used contraception before conception (60.7%), and some had had earlier abortion or termination experiences (13.4%). In the examination of eight influential factors, the machine learning models, specifically the random forest and Bayesian network analyses, exhibited the highest accuracy, achieving 90.91% and 89%, respectively, in predicting service acceptance. The key determinants identified were abortion experience and marital status, directly influencing the acceptance of services.

Conclusion: The COVID-19 pandemic reduced hospital visits for adolescent mothers, but the RHS provided timely guidance. Telemedicine consultations and internet-based psychological consultations may play a crucial role in facilitating such services in the future.

Background: Colorectal surgeries are complex procedures associated with high rates of complications and hospital readmission.

Objective: This study aimed to develop an electronic post-discharge follow-up plan to remotely monitor patients' symptoms in the postoperative period of colorectal surgeries and evaluate the outcomes of emergency department visits and the rate of severe complications within 15 days after hospital discharge.

Design: We developed a digital tool capable of remotely assessing symptoms that could indicate complications related to colorectal surgical procedures and directing early management. This project was divided into two stages. The first was platform development with an algorithm for identifying symptoms and directing conduct, and the second was clinical validation of the program and evaluation of patient's experience. Patients who underwent elective oncological colorectal surgery were invited to participate in this study. We used commercial software (CleverCare) that was adjusted according to the clinical algorithm developed in this study, predicting complications and directing conduct with minimal human intervention using a Chatbot with Natural Language Processing (NPL) and artificial intelligence.

Results: We planned three Interim Analyses to evaluate the outcomes of complications, referrals to the Emergency Department (ED), ED visits, adherence, and patient satisfaction. After each analysis, specialists validated the changes before implementation. A total of 92 eligible participants agreed to participate in the study. The ability to detect complications increased with each adjustment phase, and after the third and last phase, the digital solution identified 3(4.8%) real complications, with a sensitivity of 75%, specificity of 83%, accuracy of 82%, positive predictive value of 27%, and negative predictive value of 97%. Complete adherence to the monitoring program was 83.7% with an NPS score of 94 in the last evaluation phase.

Conclusion: The digital platform is safe with high adherence rates and good patient acceptance.

Telemedicine (TM) is a new medical service model in which computer, communication, and medical technologies and equipment are used to provide "face-to-face" communication between medical personnel and patients through the integrated transmission of data, voice, images, and video. This model has been increasingly applied to the management of patients with sleep disorders, including those with obstructive sleep apnea syndrome (OSAS). TM technology plays an important role in condition monitoring, treatment compliance, and management of OSAS cases. Herein, we review the concept of TM, its application to OSAS, and the related effects and present relevant application suggestions and strategies, which may provide concepts and references for OSAS-related TM development and application.

Objective: While exposure therapy (ET) has the potential to help people tolerate intense situation-specific emotions and change avoidance behaviours, no smartphone solution exists to guide the process of in-vivo ET. A geolocation-based smartphone software component was designed and developed to instrumentalize patient guidance in in-vivo ET and its psychological validity was assessed by a group of independent psychology experts.

Methods: A team of computer scientists and psychologists developed the ET Component for in-vivo ET using geolocation-based technology, following the process-centred design methodology. The ET Component was integrated into the SyMptOMS-ET Android application, which was developed following the co-design methodology. Next, nine independent psychology experts tested and evaluated the ET Component and the SyMptOMS-ET app in the field, following the think-aloud methodology. Participants also completed the Mobile Application Rating Scale (MARS) instrument to quantitatively evaluate the solutions.

Results: We present the SyMptOMS-ET app's main features and the ET Component exposure workflow. Next, we discuss the feedback obtained and the results of the MARS instrument. Participants who tested the app were satisfied with the ET Component during exposure scenarios (score of $\mu$ 4.32 out of 5 [ $\sigma$ 0.28] on MARS quality aspects), agreed on the soundness of the theoretical foundations of the solutions developed (score of $\mu$ 4.57 [ $\sigma$ 0.48] on MARS treatment support aspects), and provided minor think-a-loud comments to improve them.

Conclusions: The results of the expert evaluation demonstrate the psychological validity of the ET Component and the SyMptOMS-ET app. However, further studies are needed to discern the acceptability and efficacy of the mHealth tool in the target population.

Background: Understanding human behaviors has been the subject of several studies. Their main goal was to inform behavior change interventions aimed at promoting positive behaviors and improving negative ones. However, as a non-expert in behavioral science, it is extremely difficult for researchers from other disciplines to design and develop evidence-based behavior change interventions. Moreover, all existing frameworks stop at the conceptual stage and do not provide instructions for developing digital-based behavior change interventions.

Objective: We present an end-to-end framework for the design and development of mHealth-based behavior change interventions by drawing on the synergy of theory, practices, and evidence from previous research.

Methods: We reconcile the frameworks most used in the literature for the design of behavior change interventions. Therefore, the authors examined the steps of each framework, and the mapping between these steps was carried out through several iterations to obtain five common steps.

Results: The proposed framework includes five steps: (1) Definition of the scope of the intervention. (2) Understanding and explanation of behavior. (3) Definition of the intervention content and strategies. (4) Implementation of the intervention. (5) Evaluation of the intervention. Each step is explained in detail, while providing researchers with examples and the necessary materials that will boost the success of their interventions.

Conclusion: This work provides a framework that will guide researchers in the design and implementation of mHealth-based behavior change interventions. It differs from its predecessors in that it goes beyond the conceptual level of intervention design by providing details about the technical implementation of mHealth solutions. Also, explanations and examples for different steps are provided to help researchers and practitioners and design, implement, and evaluate their mHealth-based behavior change interventions.

Background: Healthcare institutions focus on improving the quality of life for end-users, with key performance indicators like access to essential medicines reflecting the effectiveness of management. Effective healthcare management involves planning, organizing, and controlling institutions built on human resources, data systems, service delivery, access to medicines, finance, and leadership. According to the World Health Organization, these elements must be balanced for an optimal healthcare system. Big data generated from healthcare institutions, including health records and genomic data, is crucial for smart staffing, decision-making, risk management, and patient engagement. Properly organizing and analysing this data is essential, and machine learning, a sub-field of artificial intelligence, can optimize these processes, leading to better overall healthcare management.

Objectives: This review examines the major applications of machine learning in healthcare management, the algorithms frequently used in data analysis, their limitations, and the evidence-based benefits of machine learning in healthcare.

Methods: Following PRISMA guidelines, databases such as IEEE Xplore, ScienceDirect, ACM Digital Library, and SCOPUS were searched for eligible articles published between 2011 and 2021. Articles had to be in English, peer-reviewed, and include relevant keywords like healthcare, management, and machine learning.

Results: Out of 51 relevant articles, 6 met the inclusion criteria. Identified algorithms include topic modelling, dynamic clustering, neural networks, decision trees, and ensemble classifiers, applied in areas such as electronic health records, chatbots, and multi-disease prediction.

Conclusion: Machine learning supports healthcare management by aiding decision-making, processing big data, and providing insights for system improvements.

Objective: Asthma is often inadequately controlled, which can result in exacerbations that lead to unplanned healthcare visits. Mobile application (app) use could help manage asthma exacerbations. We implemented the Amaze™ asthma disease management platform in clinical practice and assessed user satisfaction, usage, and usability.

Methods: Adults with asthma and healthcare professionals (HCPs) were enrolled from a community allergy practice (ClinicalTrials.gov Identifier: NCT04901260) and a large academic hospital (ClinicalTrials.gov Identifier: NCT04868500). Primary and exploratory outcomes included assessment of platform design, patient app usage, patient-reported daily asthma status, emergency room/urgent care visits, and ease of implementation by HCPs. The system usability scale and a post-clinic visit survey were also administered. HCPs/staff monitored the Amaze dashboard to assess patient needs and completed a post-study survey.

Results: Overall, 159 patients and five HCPs participated in the study. Patients' mean (SD) age was 38.7 (16.4) years; most were female (78%) and White (78%). Mean patient app usage began at 3.6 days/week but declined to 1.0 day/week by the end of the study. Throughout the study, most daily entries (>69%) reported patient asthma status as "good." Most patients were satisfied/very satisfied with the app (66%) and reported it helped them during discussions with their HCP (44%). Most patients rated the usability of Amaze as "excellent" (49%) or "good" (30%). Most HCPs (71%) reported that Amaze was "very easy" to implement.

Conclusions: Most patients and HCPs were satisfied with Amaze. The Amaze platform may help patients and HCPs monitor asthma status, which could improve asthma control.

Objective: Individuals who work on health data systems and services are uniquely positioned to understand the risks of health data collection and use. We designed and conducted a survey assessing the perceptions of those who work with health data around health data consent, sharing, and privacy practices in healthcare and clinical research.

Methods: A 43-item online survey was distributed via a market research firm to individuals (18+) who work with health data in the United States from March to April 2023. Descriptive statistics were calculated for all variables. Associations with demographic variables were assessed using Pearson's X ² tests and ordinal logistic regression.

Results: Most of our respondents (61.7%) reported that they would trust people to use their health data across various sectors, but more respondents trusted those working in academic medical research (86.5%) and healthcare offices (89.9%) compared to those working in industry (68.2%). Despite this reported trust, a strong majority believed that individuals should have complete control over their health data (97.3%), specific consent should be obtained for each use of their health data (92.0%), and that there should be higher standards of consent and privacy for health records data than other types of data (93.7%).

Conclusions: Based on our findings, we might infer that people who work with health data generally trust institutions across sectors to protect their health data. However, many would prefer to have complete control over who has access to their health data and how it is used. These insights should be explored further through qualitative studies.

Objective: This study examines the emotional state and interpersonal relationships of social media influencers, focusing on the psychological effects of their popularity and engagement. Despite increased awareness of mental health issues, influencers remain underrepresented in research. Barriers such as low mental health literacy, stigma, access issues, and the pressure to maintain virtual personas highlight the need for this investigation. This research addresses these gaps by systematically examining the impact of social media on influencers' mental health.

Methods: An online survey was conducted using the positive and negative affect schedule (PANAS) and the Relationship Structures Questionnaire (ECR-RS). The target audience was social media influencers from various countries, with a specific focus on the United Arab Emirates (UAE). Participants were recruited from 2 November 2022, to 1 March 2023, through email, SMS, and direct messages on social media platforms. Statistical analyses included t-tests, ANOVA, and Pearson correlation coefficients.

Results: A total of 161 social media influencers completed the survey. A significant association was found between extended social media usage and heightened negative emotions among influencers spending more than 5 hours daily on these platforms (p < .05). Influencers earning less than $10,000 from social media reported the lowest negative feeling scores. However, higher income levels correlated with increased relationship avoidance and anxiety scores (e.g., p < .01 for avoidance and anxiety from parents and best friends). Additionally, an increase in the number of followers was associated with increased negative emotions (p = .001).

Conclusion: Our study provides compelling insights into the well-being, emotions, and relationship quality of social media influencers. It underscores the urgency of prioritizing their mental well-being on a global scale, helping them navigate the challenges of their digital careers while maintaining a positive impact on their audiences.

Objective: This study aims to explore a streamlined risk-adjusted cesarean section rate (RCSR) model and to compare its practical application effects with the traditional RCSR models.

Methods: Utilizing obstetric electronic health record (EHR) data from provincial multicenter hospitals, this study establishes a streamlined RCSR model alongside the traditional RCSR model and evaluates the efficacy of both models. Subsequently, the RCSRs of 56 hospitals within the province are calculated and ranked using both models. The consistency of these rankings is then quantified using Kendall's tau coefficient of concordance.

Result: Comparison of model effectiveness evaluation of the traditional RCSR model versus the streamlined RCSR model is as follows: AUC (0.840 vs 0.839), accuracy (0.875 vs 0.872), sensitivity (0.690 vs 0.685), specificity (0.898 vs 0.892), positive predictive value (0.908 vs 0.903), negative predictive value (0.664 vs 0.660), and Brier score (0.069 vs 0.067). In the test of the consistency of hospital rankings based on two models, Kendall's tau coefficients were observed to be 0.979 (year 2017), 0.978 (year 2018), and 0.978 (year 2019) over a span of 3 years, with an aggregate coefficient of 0.974.

Conclusion: In the realm of model performance evaluation as well as the pragmatic application within hospital settings, the streamlined model exhibits a substantial congruence with the traditional model. Therefore, the streamlined model can effectively serve as a viable surrogate for the traditional model, potentially establishing itself as a refined paradigm for the appraisal of quality in obstetric healthcare services.