JMIR Formative Research最新文献

Background: Cardiovascular diseases remain the leading global cause of mortality, yet traditional electrocardiogram (ECG) interpretation shows subjective variability and limited sensitivity to complex pathologies.

Objective: This study aims to address these challenges by proposing the Cardiovascular Multimodal Prediction Network (CaMPNet), a transformer-based multimodal architecture that integrates raw 12-lead ECG waveforms, 9-structured machine-measured ECG features, and demographic data (age and sex) through cross-attention fusion.

Methods: The model was trained on 384,877 records from the Medical Information Mart for Intensive Care IV - Electrocardiogram Matched Subset database and evaluated across 12 cardiovascular disease labels. To further assess temporal robustness, a temporal external validation was performed using the most recent 10% of the data, withheld chronologically from model development.

Results: On the internal test set, the model achieved a mean area under the curve (AUC) of 0.845 (SD 0.04) and area under the precision-recall curve of 0.489, outperforming the residual networks-ECG baseline (AUC=0.848 but F1-score=0.152) and all single-modality variants. Subgroup analyses demonstrated consistent performance across demographics (male AUC= 0.846 vs female=0.843; youngest quartile 0.884 vs oldest 0.811). CaMPNet retained moderate discriminative ability in temporal external validation with a mean AUC of 0.715 (SD 0.03) and area under the precision-recall curve of 0.298, although performance declined due to temporal distribution shifts. Despite this, major disease categories, such as atrial fibrillation, heart failure, and normal rhythm, maintained high AUCs (>0.84). Attention-based visualization revealed clinically interpretable patterns (eg, ST-segment elevations in ST-segment elevation myocardial infarction), and ablation experiments verified the model's tolerance to missing structured inputs.

Conclusions: CaMPNet demonstrates robust and interpretable multimodal ECG-based diagnosis, offering a scalable framework for comorbidity screening and continual learning under real-world temporal dynamics.

Background: Enhancing care coordination and sharing information in cancer care improves patient experiences by promoting clarity and satisfaction.

Objective: This study aims to assess the impact of cross-sectoral video consultation on patient perceptions of care coordination and satisfaction with received information compared to usual care.

Methods: This study presents secondary outcomes on patient perceptions of care coordination and satisfaction with received information from a 7-month follow-up of the Partnership Project. In this randomized controlled trial, patients with cancer were allocated to either an intervention group receiving cross-sectoral video consultation (oncologist, general practitioner, and patient) or a control group receiving usual care. Patients' perceptions of care coordination and information quality were assessed using the Australian Cancer Care Coordination Questionnaire (CCCQ) and the European Organisation for Research and Treatment of Cancer Quality of Life Information Questionnaire 25 at baseline and 7 months. Changes over time between groups were analyzed using generalized estimating equations.

Results: Of the 278 participants randomized (1:1), only 80 (28.8%) patients received the intervention due to technical and administrative issues. A total of 210 (75.5%) patients completed the baseline questionnaire, while 118 (42.4%) responded at 7 months. No significant differences were observed in the changes over time between the intervention and control groups in any outcome. The estimated differences in the change in score from baseline to 7 months were as follows: for the total CCCQ score, 1.11 (95% CI -2.32 to 4.53; P=.53); for the overall European Organisation for Research and Treatment of Cancer Quality of Life Information Questionnaire 25 score, 1.49 (95% CI -2.98 to 5.96; P=.51); for the CCCQ communication subscale, -1.49 (95% CI -1.33 to 4.31; P=.30); and for the navigation subscale, -0.03 (95% CI -1.52 to 1.46; P=.97).

Conclusions: Our findings indicate no statistically significant improvement in patients' reported care coordination or satisfaction with received information over 7 months. Technical issues with the video setup reduced fidelity rates and follow-up participation. Further research is needed to optimize the structure and content of cross-sectoral video consultations to better support patients' perceived outcomes.

Trial registration: ClinicalTrials.gov NCT02716168; https://clinicaltrials.gov/study/NCT02716168.

Background: Health care professionals must stay updated with the latest guidelines for basic life support (BLS) and advanced cardiac life support (ACLS) to effectively assist patients during cardiac emergencies. Since its launch in 2018, the Ghana Heart Initiative has significantly enhanced the skills and knowledge of health care professionals in managing cardiovascular diseases, including cardiac emergencies.

Objective: This study aims to assess the knowledge and skills of BLS and ACLS among health care professionals immediately after training in Ghana.

Methods: This cross-sectional, training-based study involved 541 and 302 health care professionals trained in BLS and ACLS, respectively. Among them, 229 BLS and 124 ACLS-trained participants completed the questionnaires immediately after the training, and their data were included in the final analysis. Knowledge was assessed using a standardized questionnaire and an instructor-led skills evaluation based on the updated 2018 and 2020 American Heart Association guidelines for cardiopulmonary resuscitation and emergency cardiovascular care.

Results: This study shows that 74.6% (171/229) of the health care professionals had adequate knowledge and skills in BLS. Those working in tertiary health care facilities were 80% less likely (adjusted odds ratio [AOR] 0.20, 95% CI 0.07-0.59; P=.003) to have adequate BLS knowledge and skills than those in primary health care facilities. Health care professionals from regions such as Volta and Oti were 4.94 times more likely to have adequate BLS knowledge and skills compared to those from Bono East (AOR 4.94, 95% CI 1.17-20.80; P=.03). Over 73.3% (91/124) of health care professionals had adequate knowledge and skills in ACLS. Males were 7.05 times more likely (AOR 7.05, 95% CI 2.69-18.46; P<.001) than females to possess adequate ACLS knowledge and skills.

Conclusions: Given an opportunity to learn and practice, health care professionals in Ghana attain adequate knowledge and skills in BLS and ACLS.

Background: There is a gap in mental health care among Latino/x and Spanish-speaking communities, and the care that is available is often difficult to access, lacks cultural nuance, and results in low engagement and satisfaction.

Objective: The study aimed to evaluate the reach, adoption, and acceptability of digital Spanish-language psychosocial and emotional wellness services among Latino/x adults offered by the digital health company Sanarai.

Methods: Data included in this study were collected between August 2020 and September 2024 by Sanarai as part of its ongoing services. Quantitative data sources included individual customers' appointment data, individual session payment data, and customer satisfaction data. Qualitative data were obtained from transcribed notes of telephone or video-based user interviews conducted by Sanarai staff between August 2020 and May 2024.

Results: Between August 2020 and September 2024, Sanarai served 6163 users (n=3662, 59.42% women participants) across all 50 US states, with the highest concentration of participants in Texas and California. Results showed 94% (n=5793) of users scheduled a first appointment within 1 week, with 43% (n=2650) doing so within 1 day. Over 62.60% (n=3858) of participants engaged in two or more sessions, attending an average of 8.94 (SD 13) sessions over 110 days (SD 169). The platform delivered a total of 36,858 appointments, including individual and couples sessions. Only 22.47% (n=1385) of users responded to a customer satisfaction survey for a total of 2287 distinct responses; among this subgroup, session satisfaction was high with an average satisfaction rating of 4.88 out of 5.0 (SD 0.49) and a Net Promoter Score of +85. Nearly all responses (n=2174, 95.06%) expressed intent to schedule another session, but these results should be interpreted with caution, given the low response rate. Qualitative interviews with 30 users (n=21, 70% women) revealed a diverse user base. Many users reported prior mental health service experiences, while one-third were new to care. Participants cited cost, cultural fit, language access, and convenience as key reasons for choosing Sanarai over local services. Users highlighted the platform's affordability, scheduling flexibility, and provider professionalism as central to their positive experiences.

Conclusions: These findings underscore the value of culturally responsive, accessible online mental health care for Spanish-speaking communities.

Background: As a highly lethal circulatory failure syndrome, the pathophysiological mechanisms of shock can lead to multiple organ dysfunction syndrome (MODS), which significantly increases the demand for intensive care and the length of hospitalization. There is therefore an urgent need for the public to be informed about health-related issues. In recent years, videos have become a significant medium for health education, and this study aimed to evaluate shock-related videos on video sharing platforms.

Objective: The objective of this study is to identify the top 100 videos related to impact on TikTok, Bilibili, and Xiaohongshu. These videos will then be assessed in terms of their effectiveness and credibility. Following this evaluation, relevant recommendations will be provided.

Methods: The study included a search for videos related to shock on the three video-sharing platforms: TikTok, Bilibili, and Xiaohongshu. The Global Quality Score (GQS) and mDISCERN tools were used to evaluate the credibility and quality of the videos, in addition to employing the Patient Education Materials Evaluation Tool for Audiovisual Content (PEMAT-A/V). Finally, the video was evaluated by examining disease definitions, clinical manifestations, risk factors, assessment, management, and outcomes.

Results: A total of 244 videos (TikTok:87, Bilibili:80, Xiaohongshu:77）were retrieved from the three platforms. The overall video quality was found to be moderately low. The majority of videos were uploaded by health advocates (n=102, 41.8%) and health professionals (n=98, 40.1%). The individual video sources of the GQS were of lower quality (1-3), the mDISCERN scores were moderate (2-4), and the quality of individual users is higher than that of organizational users. The PEMAT A/V scores were as follows: in the overall comprehensibility evaluation, 91% (220) videos of the scores were above 70%; in the actionability evaluation, 65% (157) videos of the scores were below 70%. It should be noted that the actionability scores for different video sources were generally low. In 172 videos (70.4%), the definition of shock and its clinical manifestations were explained in detail, while in 137 videos (56.1%), the definition of shock and its clinical manifestations were also clearly explained. The majority of videos provided a relatively comprehensive explanation of the definition of shock and its clinical signs and symptoms.

Conclusions: Our study have demonstrated that the content and information quality of shock videos is unsatisfactory, as a general rule. This underscores the necessity for pertinent regulatory bodies to oversee the caliber of health-related videos, and for content creators to enhance the quality of their content.

Background: HIV self-testing is an important strategy in the US Ending the HIV Epidemic initiative. To facilitate uptake of self-testing, we developed the mLab app, which complements existing self-test options to support the potential for higher uptake of the HIV self-test. Syphilis, a sexually transmitted infection with currently rising prevalence and overlap in risk profiles with HIV, could similarly benefit from the advantages of companion diagnostic mobile apps such as mLab. Due to the success of the mLab app in promoting HIV self-testing during a randomized controlled trial and the scientific evidence of need for at-home syphilis testing, our team developed the mLab+ app, which supports both HIV and syphilis testing through an image processing algorithm that incorporates a duplex HIV and syphilis point-of-care test.

Objective: We conducted a pilot study to assess the feasibility and usability of the mLab+ app for HIV and syphilis testing.

Methods: We recruited participants who were assigned male sex at birth and reported sex with another man. Participants came to the Nurse Practitioner Group clinic for baseline and follow-up visits. Participants rated the usability of the app using the Health Information Technology Usability Evaluation Scale and the Post-Study System Usability Questionnaire at their 3-month follow-up visit. The primary outcome was the number of participants who were able to self-administer the DPP HIV-Syphilis test with the assistance of the mLab+ app. Feasibility was measured through recruitment pace, retention over 3 months, app usability, and paradata.

Results: Of the 20 participants, 19 identified as male and 1 identified as nonbinary. Most participants (n=16) were able to complete the DPP HIV-Syphilis test with facilitation support from the mLab+ app. The average duration of an app session, from after authentication until log-out or abandonment, was 30 minutes and 33 seconds (SD 21 minutes and 40 seconds). Apart from the 27% (13/48) of sessions that were 5 minutes or less, the distribution of session durations was approximately normal. Users spent the longest time viewing testing screens (ie, timer screens, initial testing screen, test guided walkthroughs, test results, and picture and result upload). The overall mean scores on the Post-Study System Usability Questionnaire (2.65, SD 1.06) and Health Information Technology Usability Evaluation Scale (3.62, SD 1.07) indicated medium to high usability. The retention rate for the 3-month trial was 80% (16/20).

Conclusions: The findings support the use of the mLab+ app as a tool for assisting consumers in self-testing for HIV and syphilis. The limitations of the study design warrant further examination outside of clinic settings to better understand the utility of these tools for improving consumer health outcomes.