Background: Most survivors of cancer have multiple cardiovascular risk factors, increasing their risk of poor cardiovascular and cancer outcomes. The Automated Heart-Health Assessment (AH-HA) tool is a novel electronic health record clinical decision support tool based on the American Heart Association’s Life’s Simple 7 cardiovascular health metrics to promote cardiovascular health assessment and discussion in outpatient oncology. Before proceeding to future implementation trials, it is critical to establish the acceptability of the tool among providers and survivors. Objective: This study aims to assess provider and survivor acceptability of the AH-HA tool and provider training at practices randomized to the AH-HA tool arm within WF-1804CD. Methods: Providers (physicians, nurse practitioners, and physician assistants) completed a survey to assess the acceptability of the AH-HA training, immediately following training. Providers also completed surveys to assess AH-HA tool acceptability and potential sustainability. Tool acceptability was assessed after 30 patients were enrolled at the practice with both a survey developed for the study as well as with domains from the Unified Theory of Acceptance and Use of Technology survey (performance expectancy, effort expectancy, attitude toward using technology, and facilitating conditions). Semistructured interviews at the end of the study captured additional provider perceptions of the AH-HA tool. Posttreatment survivors (breast, prostate, colorectal, endometrial, and lymphomas) completed a survey to assess the acceptability of the AH-HA tool immediately after the designated study appointment. Results: Providers (n=15) reported high overall acceptability of the AH-HA training (mean 5.8, SD 1.0) and tool (mean 5.5, SD 1.4); provider acceptability was also supported by the Unified Theory of Acceptance and Use of Technology scores (eg, effort expectancy: mean 5.6, SD 1.5). Qualitative data also supported provider acceptability of different aspects of the AH-HA tool (eg, “It helps focus the conversation and give the patient a visual of continuum of progress”). Providers were more favorable about using the AH-HA tool for posttreatment survivorship care. Enrolled survivors (n=245) were an average of 4.4 (SD 3.7) years posttreatment. Most survivors reported that they strongly agreed or agreed that they liked the AH-HA tool (n=231, 94.3%). A larger proportion of survivors with high health literacy strongly agreed or agreed that it was helpful to see their heart health score (n=161, 98.2%) compared to survivors with lower health literacy scores (n=68, 89.5%; P=.005). Conclusions: Quantitative surveys and qualitative interview data both demonstrate high acceptability of the AH-HA tool among both providers and survivors. Although most survivors found it helpful to see their heart health score, there may be room for improving communication with survivors who have lower health literacy. Trial Registration: ClinicalTrials.gov NCT03935282; http://clinicaltrials.gov/ct2/show/NCT03935282

Background: Although the implementation process of digital health technologies (DHTs) has been extensively documented in high-income countries, the factors that facilitate and prevent their implementation in lower- and middle-income countries (LMICs) may differ for various reasons. Objective: To address this gap in research, this scoping review aims to determine the facilitators and barriers to implementing DHTs in LMIC hospital settings following the onset of the COVID-19 pandemic. Additionally, the review outlined the types of DHTs that have been implemented in LMICs’ hospitals during this pandemic and finally developed a classification framework to categorize the landscape of DHTs. Methods: Systematic searches were conducted on PubMed, Scopus, Web of Science, and Google Scholar for studies published from March 2020 to December 2023. We extracted data on authors, publication years, study objectives, study countries, disease conditions, types of DHTs, fields of clinical medicine where the DHTs are applied, study designs, sample sizes, characteristics of the study population, study location, and data collection methods of the included studies. Both quantitative and qualitative data were utilized to conduct a thematic analysis, using a deductive method based on the Practical, Robust Implementation and Sustainability Model (PRISM), to identify facilitators and barriers to DHT implementation. Finally, all accessible DHTs were identified and organized to create a novel classification framework. Results: Twelve studies were included from 292 retrieved articles. Telemedicine (n=5) was the most commonly used DHT in LMICs’ hospitals, followed by hospital information systems (n=4), electronic medical records (n=2), and mobile health (n=1). These 4 DHTs, among the other existing DHTs, allowed us to develop a novel classification framework for DHTs. The included studies used qualitative methods (n=4), which included interviews and focus groups, quantitative methods (n=5), or a combination of both (n=2). Among the 64 facilitators of DHT implementation, the availability of continuous on-the-job training (n=3), the ability of DHTs to prevent cross-infection (n=2), and positive previous experiences using DHTs (n=2) were the top 3 reported facilitators. However, of the 44 barriers to DHT implementation, patients with poor digital literacy and skills in DHTs (n=3), inadequate awareness regarding DHTs among health care professionals and stakeholders (n=2), and concerns regarding the accuracy of disease diagnosis and treatment through DHTs (n=2) were commonly reported. Conclusions: In the postpandemic era, telemedicine, along with other DHTs, has seen increased implementation in hospitals within LMICs. All facilitators and barriers can be categorized into 6 themes, namely, (1) Aspects of the Health Care System; (2) Perspectives of Patients; (3) External Environment; (4) Implementation of Sustainable Infrastructure; (5) Characteristics of Health Care Organization; and (6) Characteristics of Patients.

Digital maturity assessments can inform strategic decision-making. However, national approaches to assessing the digital maturity of health systems are in their infancy, and there is limited insight into the context and processes associated with such assessments. This viewpoint article describes and compares national approaches to assessing the digital maturity of hospitals. We reviewed 5 national approaches to assessing the digital maturity of hospitals in Queensland (Australia), Germany, the Netherlands, Norway, and Scotland, exploring context, drivers, and approaches to measure digital maturity in each country. We observed a common focus on interoperability, and assessment findings were used to shape national digital health strategies. Indicators were broadly aligned, but 4 of 5 countries developed their own tailored indicator sets. Key topic areas across countries included interoperability, capabilities, leadership, governance, and infrastructure. Analysis of indicators was centralized, but data were shared with participating organizations. Only 1 setting conducted an academic evaluation. Major challenges of digital maturity assessment included the high cost and time required for data collection, questions about measurement accuracy, difficulties in consistent long-term tracking of indicators, and potential biases due to self-reporting. We also observed tensions between the practical feasibility of the process with the depth and breadth required by the complexity of the topic and tensions between national and local data needs. There are several key challenges in assessing digital maturity in hospitals nationally that influence the validity and reliability of output. These need to be explicitly acknowledged when making decisions informed by assessments and monitored over time.

Background: Data on the social determinants of health could be used to improve care, support quality improvement initiatives, and track progress toward health equity. However, this data collection is not widespread. Artificial intelligence (AI), specifically natural language processing and machine learning, could be used to derive social determinants of health data from electronic medical records. This could reduce the time and resources required to obtain social determinants of health data. Objective: This study aimed to understand perspectives of a diverse sample of Canadians on the use of AI to derive social determinants of health information from electronic medical record data, including benefits and concerns. Methods: Using a qualitative description approach, in-depth interviews were conducted with 195 participants purposefully recruited from Ontario, Newfoundland and Labrador, Manitoba, and Saskatchewan. Transcripts were analyzed using an inductive and deductive content analysis. Results: A total of 4 themes were identified. First, AI was described as the inevitable future, facilitating more efficient, accessible social determinants of health information and use in primary care. Second, participants expressed concerns about potential health care harms and a distrust in AI and public systems. Third, some participants indicated that AI could lead to a loss of the human touch in health care, emphasizing a preference for strong relationships with providers and individualized care. Fourth, participants described the critical importance of consent and the need for strong safeguards to protect patient data and trust. Conclusions: These findings provide important considerations for the use of AI in health care, and particularly when health care administrators and decision makers seek to derive social determinants of health data.

Background: A meta-analysis is a quantitative, formal study design in epidemiology and clinical medicine that systematically integrates and quantitatively synthesizes findings from multiple independent studies. This approach not only enhances statistical power but also enables the exploration of effects across diverse populations and helps resolve controversies arising from conflicting studies. Objective: This study aims to develop and implement a user-friendly tool for conducting meta-analyses, addressing the need for an accessible platform that simplifies the complex statistical procedures required for evidence synthesis while maintaining methodological rigor. Methods: The platform available at MetaAnalysisOnline.com enables comprehensive meta-analyses through an intuitive web interface, requiring no programming expertise or command-line operations. The system accommodates diverse data types including binary (total and event numbers), continuous (mean and SD), and time-to-event data (hazard rates with CIs), while implementing both fixed-effect and random-effect models using established statistical approaches such as DerSimonian-Laird, Mantel-Haenszel, and inverse variance methods for effect size estimation and heterogeneity assessment. Results: In addition to statistical tests, graphical representations including the forest plot, the funnel plot, and the z score plot can be drawn. A forest plot is highly effective in illustrating heterogeneity and pooled results. The risk of publication bias can be revealed by a funnel plot. A z score plot provides a visual assessment of whether more research is needed to establish a reliable conclusion. All the discussed models and visualization options are integrated into the registration-free web-based portal. Leveraging MetaAnalysisOnline.com's capabilities, we examined treatment-related adverse events in patients with cancer receiving perioperative anti–PD-1 immunotherapy through a systematic review encompassing 10 studies with 8099 total participants. Meta-analysis revealed that anti–PD-1 therapy doubled the risk of adverse events (risk ratio 2.15, 95% CI 1.39-3.32), with significant between-study heterogeneity (I²=95%) and publication bias detected through the Egger test (P=.02). While these findings suggest increased toxicity associated with anti–PD-1 treatment, the z score analysis indicated that additional studies are needed for definitive conclusions. Conclusions: In summary, the web-based tool aims to bridge the void for clinical and life science researchers by offering a user-friendly alternative for the swift and reproducible meta-analysis of clinical and epidemiological trials. Trial Registration:

Background: Gastrointestinal bleeding is a serious adverse event of coronary artery bypass grafting and lacks tailored risk assessment tools for personalized prevention. Objective: This study aims to develop and validate predictive models to assess the risk of gastrointestinal bleeding after coronary artery bypass grafting (GIBCG) and to guide personalized prevention. Methods: Participants were recruited from 4 medical centers, including a prospective cohort and the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. From an initial cohort of 18,938 patients, 16,440 were included in the final analysis after applying the exclusion criteria. Thirty combinations of machine learning algorithms were compared, and the optimal model was selected based on integrated performance metrics, including the area under the receiver operating characteristic curve (AUROC) and the Brier score. This model was then developed into a web-based risk prediction calculator. The Shapley Additive Explanations method was used to provide both global and local explanations for the predictions. Results: The model was developed using data from 3 centers and a prospective cohort (n=13,399) and validated on the Drum Tower cohort (n=2745) and the MIMIC cohort (n=296). The optimal model, based on 15 easily accessible admission features, demonstrated an AUROC of 0.8482 (95% CI 0.8328-0.8618) in the derivation cohort. In external validation, the AUROC was 0.8513 (95% CI 0.8221-0.8782) for the Drum Tower cohort and 0.7811 (95% CI 0.7275-0.8343) for the MIMIC cohort. The analysis indicated that high-risk patients identified by the model had a significantly increased mortality risk (odds ratio 2.98, 95% CI 1.784-4.978; P<.001). For these high-risk populations, preoperative use of proton pump inhibitors was an independent protective factor against the occurrence of GIBCG. By contrast, dual antiplatelet therapy and oral anticoagulants were identified as independent risk factors. However, in low-risk populations, the use of proton pump inhibitors (χ²₁=0.13, P=.72), dual antiplatelet therapy (χ²₁=0.38, P=.54), and oral anticoagulants (χ²₁=0.15, P=.69) were not significantly associated with the occurrence of GIBCG. Conclusions: Our machine learning model accurately identified patients at high risk of GIBCG, who had a poor prognosis. This approach can aid in early risk stratification and personalized prevention. Trial Registration: Chinese Clinical Registry Center ChiCTR2400086050; http://www.chictr.org.cn/showproj.html?proj=226129

Health communication and promotion on the internet have evolved over time, driven by the development of new technologies, including generative artificial intelligence (GenAI). These technological tools offer new opportunities for both the public and professionals. However, these advancements also pose risks of exacerbating health disparities. Limited research has focused on combining these health communication mediums, particularly those enabled by new technologies like GenAI, and their applications for health promotion and health disparities. Therefore, this viewpoint, adopting a conceptual approach, provides an updated overview of health communication mediums and their role in understanding health promotion and disparities in the GenAI era. Additionally, health promotion and health disparities associated with GenAI are briefly discussed through the lens of the Technology Acceptance Model 2, the uses and gratifications theory, and the knowledge gap hypothesis. This viewpoint discusses the limitations and barriers of previous internet-based communication mediums regarding real-time responses, personalized advice, and follow-up inquiries, highlighting the potential of new technology for public health promotion. It also discusses the health disparities caused by the limitations of GenAI, such as individuals’ inability to evaluate information, restricted access to services, and the lack of skill development. Overall, this study lays the groundwork for future research on how GenAI could be leveraged for public health promotion and how its challenges and barriers may exacerbate health inequities. It underscores the need for more empirical studies, as well as the importance of enhancing digital literacy and increasing access to technology for socially disadvantaged populations.

This article aims to introduce emerging measurement domains made feasible through the electronic health record (EHR) use metadata, to inform the changing landscape of health care delivery. We reviewed emerging domains in which EHR metadata may be used to measure health care delivery, outlining a framework for evaluating measures based on desirability, feasibility, and viability. We argue that EHR use metadata may be leveraged to develop and operationalize novel measures in the domains of team structure and dynamics, workflows, and cognitive environment to provide a clearer understanding of modern health care delivery. Examples of measures feasible using metadata include quantification of teamwork and collaboration, patient continuity measures, workflow conformity measures, and attention switching. By enabling measures that can be used to inform the next generation of health care delivery, EHR metadata may be used to improve the quality of patient care and support clinician well-being. Careful attention is needed to ensure that these measures are desirable, feasible, and viable.

Background: Continuous scientific and policy debate regarding the potential harm and/or benefit of media and social media on adolescent health has resulted, in part, from a deficiency in robust scientific evidence. Even with a lack of scientific consensus, public attitudes, and sweeping social media prohibitions have swiftly ensued. A focus on the diversity of adolescents around the world and their diverse use of language, culture, and social media is absent from these discussions. Objective: This study aims to guide communication policy and practice, including those addressing access to social media by adolescent populations. This study assesses physical and mental health information scanning and seeking behaviors across diverse language, cultural, and technological media and social media among Latinx adolescent residents in the United States. This study also explores how Latinx adolescents with mental health concerns use media and social media for support. Methods: In 2021, a cross-sectional survey was conducted among 701 US-based Latinx adolescents aged 13-20 years to assess their health-related media use. Assessments ascertained the frequency of media use and mental and physical health information scanning and seeking across various media technologies (eg, TV, podcasts, and social media) and language and cultural types (ie, Spanish, Latinx-tailored English, and general English). Linear regression models were used to estimate adjusted predicted means of mental and physical health information scanning and seeking across diverse language and cultural media types, net personal and family factors, in the full sample and by subsamples of mental health symptoms (moderate-high vs none-mild). Results: Among Latinx adolescents, media and social media use was similar across mental health symptoms. However, Latinx adolescents with moderate-high versus none-mild symptoms more often scanned general English media and social media for mental health information (P<.05), although not for physical health information. Also, Latinx adolescents with moderate-high versus none-mild symptoms more often sought mental health information on Latinx-tailored and general English media, and social media (P<.05); a similar pattern was found for physical health information seeking. In addition, Latinx adolescents with moderate-high versus none-mild symptoms often sought help from family and friends for mental and physical health problems and health care providers for mental health only (P<.05). Conclusions: While media and social media usage was similar across mental health, Latinx adolescents with moderate-high symptoms more often encountered mental health content in general English media and social media and turned to general English- and Latinx-tailored media and social media more often for their health concerns. Together these study findings suggest more prevalent and available mental health content in general English versus Spanish language and Latinx-tailored media and underscore the importance of providing accessible, quality health information across diverse language, cultural, and technological media and social networks as a viable opportunity to help improve adolescent health. Trial Registration:

Background: While the COVID-19 pandemic has induced massive discussion of available medications on social media, traditional studies focused only on limited aspects, such as public opinions, and endured reporting biases, inefficiency, and long collection times. Objective: Harnessing drug-related data posted on social media in real-time can offer insights into how the pandemic impacts drug use and monitor misinformation. This study aimed to develop a natural language processing (NLP) pipeline tailored for the analysis of social media discourse on COVID-19–related drugs. Methods: This study constructed a full pipeline for COVID-19–related drug tweet analysis, using pretrained language model–based NLP techniques as the backbone. This pipeline is architecturally composed of 4 core modules: named entity recognition and normalization to identify medical entities from relevant tweets and standardize them to uniform medication names for time trend analysis, target sentiment analysis to reveal sentiment polarities associated with the entities, topic modeling to understand underlying themes discussed by the population, and drug network analysis to dig potential adverse drug reactions (ADR) and drug-drug interactions (DDI). The pipeline was deployed to analyze tweets related to the COVID-19 pandemic and drug therapies between February 1, 2020, and April 30, 2022. Results: From a dataset comprising 169,659,956 COVID-19–related tweets from 103,682,686 users, our named entity recognition model identified 2,124,757 relevant tweets sourced from 1,800,372 unique users, and the top 5 most-discussed drugs: ivermectin, hydroxychloroquine, remdesivir, zinc, and vitamin D. Time trend analysis revealed that the public focused mostly on repurposed drugs (ie, hydroxychloroquine and ivermectin), and least on remdesivir, the only officially approved drug among the 5. Sentiment analysis of the top 5 most-discussed drugs revealed that public perception was predominantly shaped by celebrity endorsements, media hot spots, and governmental directives rather than empirical evidence of drug efficacy. Topic analysis obtained 15 general topics of overall drug-related tweets, with “clinical treatment effects of drugs” and “physical symptoms” emerging as the most frequently discussed topics. Co-occurrence matrices and complex network analysis further identified emerging patterns of DDI and ADR that could be critical for public health surveillance like better safeguarding public safety in medicines use. Conclusions: This study shows that an NLP-based pipeline can be a robust tool for large-scale public health monitoring and can offer valuable supplementary data for traditional epidemiological studies concerning DDI and ADR. The framework presented here aspires to serve as a cornerstone for future social media–based public health analytics.