Interactive Journal of Medical Research最新文献

Machine and Deep Learning for Detection of Moderate-to-Vigorous Physical Activity From Accelerometer Data: Systematic Scoping Review. 从加速度计数据中检测中高强度身体活动的机器和深度学习：系统范围审查。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2026-01-08 DOI: 10.2196/76601

Yahua Zi, Sjors Rb van de Ven, Eco Jc de Geus, Peijie Chen

Background: Accurate monitoring of moderate-to-vigorous physical activity (MVPA) is critical for advancing public health research and personalized interventions. Traditional accelerometry methods, reliant on regression-derived intensity cut points, exhibit significant misclassification errors and poor generalizability to the free-living environment. Recent advancements in machine learning (ML) and deep learning (DL) offer promising alternatives for automated MVPA detection.Objective: This scoping review synthesizes evidence on ML and DL techniques for MVPA estimation and prediction using accelerometer data, focusing on performance, algorithm bias, sensor configurations, and translational potential.Methods: Following PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines, we conducted a systematic search across PubMed, IEEE Xplore, and Web of Science (February 1995-April 2025), supplemented by snowball citation tracking. Two independent reviewers screened titles, abstracts, and full texts against predefined inclusion criteria. Data from included studies were charted by one reviewer and verified by the other, extracting details on study characteristics, sensor configuration, ML and DL techniques, validation methods, and performance metrics. A narrative synthesis approach was used, guided by 6 research questions, to collate and summarize the findings. The synthesis process was rigorously reviewed by multiple authors to ensure consistency.Results: Of 1938 screened studies, 40 met the inclusion criteria, with 4 studies added by follow-up manual searches. While traditional ML models (eg, random forest, support vector machine) achieved strong laboratory performance with F1-score of 87.4%-100% and accuracy of 87.9%-100%, their real-world performance declined by 8.0%-13.3% in F1-score and 6.6%-12.2% in accuracy, due to environment noise and device heterogeneity. DL architectures (eg, convolutional neural networks, transformers) achieved robust performance by leveraging raw signal dynamics with an F1-score of 71.9%-79.8% and an accuracy of 87.9%-100% in free-living settings. Hybrid models (eg, convolutional neural networks and long short-term memory) demonstrated state-of-the-art performance (F1-score 91.4%-98.4%, accuracy 97.7%-99.0%). Wrist-worn sensors dominated studies (30/40, 75%) and matched hip/thigh placements in lab settings (mean F1-scores: 86.5%-88.6%), but multisensor configurations (wrist + hip) yielded the highest accuracy (89.7%). Key challenges included algorithmic bias reducing applicability in older adult populations, and impaired reproducibility, with only 42.5% (17/40) of studies sharing code and data. Emerging opportunities are noted for edge computing and hybrid models integrating contextual data.Conclusions: <

背景：准确监测中高强度身体活动（MVPA）对于推进公共卫生研究和个性化干预至关重要。传统的加速度测量方法依赖于回归导出的强度切点，存在明显的误分类误差，并且对自由生活环境的泛化能力差。机器学习（ML）和深度学习（DL）的最新进展为自动MVPA检测提供了有前途的替代方案。目的：本综述综合了使用加速度计数据进行MVPA估计和预测的ML和DL技术的证据，重点关注性能、算法偏差、传感器配置和转化潜力。方法：根据PRISMA-ScR （Preferred Reporting Items for Systematic Reviews and meta - analysis Extension for Scoping Reviews）指南，我们对PubMed、IEEE Xplore和Web of Science（1995年2月- 2025年4月）进行了系统检索，并辅以滚雪球式引文跟踪。两名独立的审稿人根据预先确定的纳入标准筛选标题、摘要和全文。纳入研究的数据由一位审稿人绘制图表，并由另一位审稿人进行验证，提取有关研究特征、传感器配置、ML和DL技术、验证方法和性能指标的详细信息。在6个研究问题的指导下，采用叙事综合方法对研究结果进行整理和总结。合成过程由多个作者严格审查，以确保一致性。结果：在1938项筛选的研究中，40项符合纳入标准，其中4项研究通过随访人工检索增加。传统的机器学习模型（如随机森林、支持向量机）在实验室的f1得分为87.4%-100%，准确率为87.9%-100%，但由于环境噪声和设备异质性的影响，它们在现实世界的f1得分下降了8.0%-13.3%，准确率下降了6.6%-12.2%。深度学习架构（如卷积神经网络、变压器）通过利用原始信号动态实现了强大的性能，在自由生活环境中f1得分为71.9%-79.8%，准确率为87.9%-100%。混合模型（如卷积神经网络和长短期记忆）表现出了最先进的性能（f1得分91.4%-98.4%，准确率97.7%-99.0%）。腕带传感器在研究中占主导地位（30/ 40,75%），在实验室设置中匹配臀部/大腿位置（平均f1得分：86.5%-88.6%），但多传感器配置（手腕+臀部）产生了最高的准确性（89.7%）。主要的挑战包括算法偏差降低了在老年人群中的适用性，以及可重复性受损，只有42.5%（17/40）的研究共享代码和数据。边缘计算和集成上下文数据的混合模型是新兴的机会。结论：ML和DL通过自动特征提取和提高对自由生活变异性的适应性，显著增强了MVPA监测。然而，持续的可泛化性差距、不一致的验证协议和透明度缺陷阻碍了翻译。研究结果表明，未来的研究需要优先考虑包容性模型培训、标准化报告框架和开放科学实践，以实现人工智能驱动的体育活动评估的公平潜力。

{"title":"Machine and Deep Learning for Detection of Moderate-to-Vigorous Physical Activity From Accelerometer Data: Systematic Scoping Review.","authors":"Yahua Zi, Sjors Rb van de Ven, Eco Jc de Geus, Peijie Chen","doi":"10.2196/76601","DOIUrl":"https://doi.org/10.2196/76601","url":null,"abstract":"Background: Accurate monitoring of moderate-to-vigorous physical activity (MVPA) is critical for advancing public health research and personalized interventions. Traditional accelerometry methods, reliant on regression-derived intensity cut points, exhibit significant misclassification errors and poor generalizability to the free-living environment. Recent advancements in machine learning (ML) and deep learning (DL) offer promising alternatives for automated MVPA detection.Objective: This scoping review synthesizes evidence on ML and DL techniques for MVPA estimation and prediction using accelerometer data, focusing on performance, algorithm bias, sensor configurations, and translational potential.Methods: Following PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines, we conducted a systematic search across PubMed, IEEE Xplore, and Web of Science (February 1995-April 2025), supplemented by snowball citation tracking. Two independent reviewers screened titles, abstracts, and full texts against predefined inclusion criteria. Data from included studies were charted by one reviewer and verified by the other, extracting details on study characteristics, sensor configuration, ML and DL techniques, validation methods, and performance metrics. A narrative synthesis approach was used, guided by 6 research questions, to collate and summarize the findings. The synthesis process was rigorously reviewed by multiple authors to ensure consistency.Results: Of 1938 screened studies, 40 met the inclusion criteria, with 4 studies added by follow-up manual searches. While traditional ML models (eg, random forest, support vector machine) achieved strong laboratory performance with F1-score of 87.4%-100% and accuracy of 87.9%-100%, their real-world performance declined by 8.0%-13.3% in F1-score and 6.6%-12.2% in accuracy, due to environment noise and device heterogeneity. DL architectures (eg, convolutional neural networks, transformers) achieved robust performance by leveraging raw signal dynamics with an F1-score of 71.9%-79.8% and an accuracy of 87.9%-100% in free-living settings. Hybrid models (eg, convolutional neural networks and long short-term memory) demonstrated state-of-the-art performance (F1-score 91.4%-98.4%, accuracy 97.7%-99.0%). Wrist-worn sensors dominated studies (30/40, 75%) and matched hip/thigh placements in lab settings (mean F1-scores: 86.5%-88.6%), but multisensor configurations (wrist + hip) yielded the highest accuracy (89.7%). Key challenges included algorithmic bias reducing applicability in older adult populations, and impaired reproducibility, with only 42.5% (17/40) of studies sharing code and data. Emerging opportunities are noted for edge computing and hybrid models integrating contextual data.Conclusions: <","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":"15 ","pages":"e76601"},"PeriodicalIF":1.9,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145936121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sleep Disturbance and Its Association With Purchasing Behavior of COVID-19 Medicine Among the Public After the Adjustment of Zero-COVID Policy in China: Results From a Web-Based Survey Study. 零新冠政策调整后公众睡眠障碍及其与新冠药物购买行为的关系——基于网络的调查研究结果

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2026-01-06 DOI: 10.2196/79903

Yu Huang, Xiang Zhao, Lei Wang, Qiaohong Lv, Qingqing Wu, Shuiyang Xu, Xuehai Zhang, Shuxian Wu

Background: In December 2022, in light of the weakened pathogenicity of the new variants and other scientific considerations, China optimized its zero-COVID policy. As the situation evolved, the virus spread more widely across the country.Objective: This study aims to explore the public's sleep status and its association with purchasing behavior of COVID-19 medicine after the adjustment of zero-COVID policy in China.Methods: A cross-sectional, internet-based survey among residents aged 18-69 years was conducted in Zhejiang province, China, from December 16 to 30, 2022, to collect data on sociodemographic characteristics, COVID-19 drug purchasing behavior, sleep disturbance levels, etc. Chi-square tests, univariate analyses, and multivariate analyses were used to explore the associations among these factors.Results: Out of 38,480 participants, 20,803 (54.1%) reported sleep disruption after China's COVID-19 response policy adjustment. The degree of impact varied, with 10,964 (52.70%) reporting "slight," 3105 (14.93%) "moderate," 3493 (16.79%) "significant," and 3241 (15.58%) "very significant" impacts. Only 20.90% (782/3742) of those who deemed purchasing unnecessary had sleep disruptions, compared to 45.19% (6214/13,752) of those who acquired medications and 65.79% (13,807/20,986) of those who tried but failed to obtain them. Sleep disturbance levels were significantly associated with sociodemographic factors like age, education levels, occupation, marital status, and presence of family members diagnosed with COVID-19 (P<.05). By age, sleep disturbance proportions differed notably: 36.32% (409/1126) for those under 20 years, 54.81% (19,714/35,970) for the 20 to 60 age group, and 49.13% (680/1384) for individuals over 60 years. For education level, the proportions were 57.44% (517/900, primary school), 54.34% (3928 /7229, junior high school), 54.27% (3808/7017, senior high school), 53.99% (11,974/22,180, junior college/undergraduate), and 49.91% (576/1154, master's degree), showing a clear downward trend as education level increased. By occupation, farmers had the highest rate (855/1447, 59.09%), followed by business/service industry workers and stay-at-home/unemployed individuals (13,925/24,750, 56.26%) and government staff (4161/7712, 53.95%), while 1242 out of 3049 (40.73%) health workers and 620 out of 1522 (40.74%) students had lower rates. Married participants had a 55.21% (17,143/31,053) sleep disturbance rate, and those with COVID-positive family members had the highest rate (2023/2873, 70.41%). Multivariate logistic regression, adjusting for these sociodemographic factors, showed that compared to those who thought purchasing COVID-19 medications was unnecessary, those who acquired medications were 3.11 times (adjusted odds ratio 3.11, 95% CI 2.85-3.39) more likely, and those who tried but couldn't get medications were 7.11 times (adjusted odds ratio

背景：2022年12月，考虑到新冠病毒致病性减弱和其他科学考虑，中国优化了零冠政策。随着形势的发展，病毒在全国范围内更广泛地传播。目的：本研究旨在探讨零covid政策调整后中国公众睡眠状况及其与COVID-19药品购买行为的关系。方法：于2022年12月16日至30日对中国浙江省18-69岁居民进行横断面网络调查，收集社会人口学特征、新冠肺炎药物购买行为、睡眠障碍水平等数据。采用卡方检验、单因素分析和多因素分析来探讨这些因素之间的相关性。结果：在38,480名参与者中，20,803人（54.1%）报告了中国COVID-19应对政策调整后的睡眠中断。影响程度各不相同，其中10,964（52.70%）报告为“轻微”，3105（14.93%）报告为“中度”，3493（16.79%）报告为“显著”，3241（15.58%）报告为“非常显著”。只有20.90%（782/3742）的人认为购买不必要的药物有睡眠障碍，而获得药物的人中有45.19%（6214/ 13752）和65.79%（13807 / 20986）的人试图获得药物但未能获得。睡眠障碍水平与年龄、受教育程度、职业、婚姻状况、家庭中是否存在新冠肺炎患者等社会人口学因素显著相关(p结论：中国零冠政策的调整影响了公众的睡眠健康，而睡眠健康与药品购买状况密切相关，尤其是老年人、受教育程度较低的人群和家庭中是否存在新冠肺炎患者。它强调需要制定和部署旨在促进危机时期更好睡眠健康的干预措施。

{"title":"Sleep Disturbance and Its Association With Purchasing Behavior of COVID-19 Medicine Among the Public After the Adjustment of Zero-COVID Policy in China: Results From a Web-Based Survey Study.","authors":"Yu Huang, Xiang Zhao, Lei Wang, Qiaohong Lv, Qingqing Wu, Shuiyang Xu, Xuehai Zhang, Shuxian Wu","doi":"10.2196/79903","DOIUrl":"10.2196/79903","url":null,"abstract":"Background: In December 2022, in light of the weakened pathogenicity of the new variants and other scientific considerations, China optimized its zero-COVID policy. As the situation evolved, the virus spread more widely across the country.Objective: This study aims to explore the public's sleep status and its association with purchasing behavior of COVID-19 medicine after the adjustment of zero-COVID policy in China.Methods: A cross-sectional, internet-based survey among residents aged 18-69 years was conducted in Zhejiang province, China, from December 16 to 30, 2022, to collect data on sociodemographic characteristics, COVID-19 drug purchasing behavior, sleep disturbance levels, etc. Chi-square tests, univariate analyses, and multivariate analyses were used to explore the associations among these factors.Results: Out of 38,480 participants, 20,803 (54.1%) reported sleep disruption after China's COVID-19 response policy adjustment. The degree of impact varied, with 10,964 (52.70%) reporting \"slight,\" 3105 (14.93%) \"moderate,\" 3493 (16.79%) \"significant,\" and 3241 (15.58%) \"very significant\" impacts. Only 20.90% (782/3742) of those who deemed purchasing unnecessary had sleep disruptions, compared to 45.19% (6214/13,752) of those who acquired medications and 65.79% (13,807/20,986) of those who tried but failed to obtain them. Sleep disturbance levels were significantly associated with sociodemographic factors like age, education levels, occupation, marital status, and presence of family members diagnosed with COVID-19 (P<.05). By age, sleep disturbance proportions differed notably: 36.32% (409/1126) for those under 20 years, 54.81% (19,714/35,970) for the 20 to 60 age group, and 49.13% (680/1384) for individuals over 60 years. For education level, the proportions were 57.44% (517/900, primary school), 54.34% (3928 /7229, junior high school), 54.27% (3808/7017, senior high school), 53.99% (11,974/22,180, junior college/undergraduate), and 49.91% (576/1154, master's degree), showing a clear downward trend as education level increased. By occupation, farmers had the highest rate (855/1447, 59.09%), followed by business/service industry workers and stay-at-home/unemployed individuals (13,925/24,750, 56.26%) and government staff (4161/7712, 53.95%), while 1242 out of 3049 (40.73%) health workers and 620 out of 1522 (40.74%) students had lower rates. Married participants had a 55.21% (17,143/31,053) sleep disturbance rate, and those with COVID-positive family members had the highest rate (2023/2873, 70.41%). Multivariate logistic regression, adjusting for these sociodemographic factors, showed that compared to those who thought purchasing COVID-19 medications was unnecessary, those who acquired medications were 3.11 times (adjusted odds ratio 3.11, 95% CI 2.85-3.39) more likely, and those who tried but couldn't get medications were 7.11 times (adjusted odds ratio","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":"15 ","pages":"e79903"},"PeriodicalIF":1.9,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12774404/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145913803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Correction: Digital Health for Australia: Bridging the Rural, Regional, and Remote Health Gap. 更正：澳大利亚的数字卫生：弥合农村、地区和远程卫生差距。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-12-29 DOI: 10.2196/89755

Shakeel Mahmood, M Mamun Huda, Kedir Yimam Ahmed, Thapa Subash, Feleke Hailemichael Astawesegn, Anayochukwu Edward Anyasodor, Mohammad Ali Moni, Muhammad J A Shiddiky, Utpal K Mondal, Setognal Birara Aychiluhm, Santosh Giri, Allen G Ross

[This corrects the article DOI: 10.2196/67460.].

[更正文章DOI: 10.2196/67460]。

引用次数: 0

A Proposed Taxonomy to Holistically Classify Employee Mental Health Programs: Qualitative Taxonomy Development Study. 一种对员工心理健康项目进行整体分类的建议分类：定性分类发展研究。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-12-18 DOI: 10.2196/67752

Benedict Sevov, Robin Huettemann, Maximillian Zinner, Sven Meister, Leonard Fehring

Background: The number and diversity of employee mental health programs (EMHPs), solutions employers offer to their workforce to improve mental health, have expanded rapidly in recent years, driven by advancements in digital technology and increased global awareness of employee mental health. This dynamic has resulted in a diverse and nontransparent EMHP landscape. While existing taxonomies address specific aspects of mental health programs, a comprehensive taxonomy for classifying EMHPs in more detail remains absent. Establishing such a taxonomy would benefit researchers and practitioners by providing a common standard for categorizing EMHPs and thereby enhance transparency.Objective: This research aimed to develop and evaluate a comprehensive taxonomy to holistically classify EMHPs, providing a practical and standardized tool for various target groups to categorize, develop, and select EMHPs.Methods: A thorough taxonomy development process with 4 iterations was applied. The first 2 iterations used conceptual-to-empirical approaches and involved scoping reviews to identify relevant dimensions and characteristics of EMHPs. The latter 2 iterations used empirical-to-conceptual approaches and included semistructured qualitative interviews. The third iteration, involving employee interviews, aimed to identify further dimensions and characteristics of EMHPs to develop the initial taxonomy. During the fourth iteration, 17 international experts were interviewed to refine and validate the initial taxonomy. After the fourth iteration, the taxonomy was evaluated by applying it to 3 real-world EMHPs through a focus group with 5 experts to ensure that all ending conditions and the evaluation goals were met. The interrater reliability was analyzed using the proportion of observed agreement and Fleiss κ.Results: The resulting taxonomy comprises 2 metadimensions, 21 dimensions, and 69 characteristics, offering a standardized framework for EMHP classification and analysis. Experts successfully applied the taxonomy to classify 3 selected EMHPs, resulting in an overall proportion of observed agreement of 85% and a Fleiss κ of 66%. Across dimensions, the proportion of observed agreement ranged from 64% to 100%, with Fleiss κ ranging from 20% to 100% (P values ranging from P=.004 to P<.001).Conclusions: This taxonomy contributes to establishing a common standard for holistic EMHP classification. It benefits both mental health researchers and practitioners in fostering transparency and serves as a structured tool for EMHP analysis. The taxonomy enables researchers to conduct relevant future research, including the systematic identification of EMHP archetypes. In practice, the taxonomy can guide providers in market gap identification and EMHP development, inform employers in decision-making, and assist policymakers in setting up targeted support mechanis

背景：近年来，在数字技术进步和全球员工心理健康意识提高的推动下，雇主为员工提供的改善心理健康的解决方案——员工心理健康计划（EMHPs）的数量和多样性迅速扩大。这种动态导致了一个多样化和不透明的EMHP景观。虽然现有的分类法针对心理健康项目的特定方面，但对emhp进行更详细分类的综合分类法仍然缺乏。建立这样的分类法将为emhp的分类提供通用标准，从而提高透明度，从而使研究人员和从业人员受益。目的：建立并评价一套全面的emhp分类体系，为不同目标群体对emhp进行分类、开发和选择提供实用、规范的工具。方法：采用4次迭代的完整分类法开发过程。前两次迭代使用从概念到经验的方法，并涉及范围审查，以确定emhp的相关维度和特征。后两次迭代使用了从经验到概念的方法，并包括半结构化的定性访谈。第三次迭代涉及员工访谈，旨在确定emhp的进一步维度和特征，以开发初始分类。在第四次迭代中，采访了17位国际专家，以完善和验证初始分类法。在第四次迭代之后，通过5名专家组成的焦点小组，将该分类法应用于3个实际emhp进行评估，以确保满足所有结束条件和评估目标。用观察到的一致性比例和Fleiss κ来分析互译者的信度。结果：该分类包含2个元维度、21个维度和69个特征，为EMHP分类和分析提供了一个标准化的框架。专家们成功地应用该分类法对3个选定的emhp进行了分类，结果观察到的一致性总体比例为85%，Fleiss κ为66%。在各个维度上，观察到的一致性比例从64%到100%不等，Fleiss κ的范围从20%到100%不等（P值从P= 0.004到P）。结论：该分类有助于建立整体EMHP分类的通用标准。它有利于心理健康研究人员和从业者促进透明度，并作为EMHP分析的结构化工具。该分类使研究人员能够进行相关的未来研究，包括系统地识别EMHP原型。在实践中，该分类可以指导供应商识别市场缺口和制定EMHP，为雇主提供决策信息，并帮助决策者建立有针对性的EMHP实施支持机制。

{"title":"A Proposed Taxonomy to Holistically Classify Employee Mental Health Programs: Qualitative Taxonomy Development Study.","authors":"Benedict Sevov, Robin Huettemann, Maximillian Zinner, Sven Meister, Leonard Fehring","doi":"10.2196/67752","DOIUrl":"10.2196/67752","url":null,"abstract":"Background: The number and diversity of employee mental health programs (EMHPs), solutions employers offer to their workforce to improve mental health, have expanded rapidly in recent years, driven by advancements in digital technology and increased global awareness of employee mental health. This dynamic has resulted in a diverse and nontransparent EMHP landscape. While existing taxonomies address specific aspects of mental health programs, a comprehensive taxonomy for classifying EMHPs in more detail remains absent. Establishing such a taxonomy would benefit researchers and practitioners by providing a common standard for categorizing EMHPs and thereby enhance transparency.Objective: This research aimed to develop and evaluate a comprehensive taxonomy to holistically classify EMHPs, providing a practical and standardized tool for various target groups to categorize, develop, and select EMHPs.Methods: A thorough taxonomy development process with 4 iterations was applied. The first 2 iterations used conceptual-to-empirical approaches and involved scoping reviews to identify relevant dimensions and characteristics of EMHPs. The latter 2 iterations used empirical-to-conceptual approaches and included semistructured qualitative interviews. The third iteration, involving employee interviews, aimed to identify further dimensions and characteristics of EMHPs to develop the initial taxonomy. During the fourth iteration, 17 international experts were interviewed to refine and validate the initial taxonomy. After the fourth iteration, the taxonomy was evaluated by applying it to 3 real-world EMHPs through a focus group with 5 experts to ensure that all ending conditions and the evaluation goals were met. The interrater reliability was analyzed using the proportion of observed agreement and Fleiss κ.Results: The resulting taxonomy comprises 2 metadimensions, 21 dimensions, and 69 characteristics, offering a standardized framework for EMHP classification and analysis. Experts successfully applied the taxonomy to classify 3 selected EMHPs, resulting in an overall proportion of observed agreement of 85% and a Fleiss κ of 66%. Across dimensions, the proportion of observed agreement ranged from 64% to 100%, with Fleiss κ ranging from 20% to 100% (P values ranging from P=.004 to P<.001).Conclusions: This taxonomy contributes to establishing a common standard for holistic EMHP classification. It benefits both mental health researchers and practitioners in fostering transparency and serves as a structured tool for EMHP analysis. The taxonomy enables researchers to conduct relevant future research, including the systematic identification of EMHP archetypes. In practice, the taxonomy can guide providers in market gap identification and EMHP development, inform employers in decision-making, and assist policymakers in setting up targeted support mechanis","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":"14 ","pages":"e67752"},"PeriodicalIF":1.9,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12746229/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145851465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effectiveness, facilitators and barriers of digital mental health services for First Nations Peoples in Australia: A systematic scoping review. 澳大利亚第一民族数字心理健康服务的有效性、促进因素和障碍：系统范围审查。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-12-17 DOI: 10.2196/80386

Siyu Zhai, Andrew Goodman, Anthony C Smith, Sandra Diminic, Xiaoyun Zhou

Background: First Nations peoples in Australia experience inequitable mental health outcomes and service access. Digital mental health (DMH) services, which refer to offering mental health services through digital platforms, are considered potential solutions to address such mental health service inequities and improve First Nations Australians' mental health outcomes. However, evidence on the effectiveness of DMH for First Nations Peoples in Australia is yet to be synthesised.

Objective: This systematic scoping review aimed to fill this gap, and to identify the facilitators and barriers that influence the implementation of DMH services in this context.

Methods: A systematic search was conducted across six academic databases to search for studies related to DMH services for First Nations Peoples in Australia. Search terms relating to First Nations Peoples, geographic terminologies of Australia, mental health, and digital mental health services were used. Studies were included if they assessed the effectiveness, or determinants of facilitators and barriers of implementing digital mental health interventions among First Nations people in Australia. Data were extracted based on study design, targeted services, and research findings, then synthesised using a thematic analysis framework.

Results: In total, 22 studies met the inclusion criteria. DMH services were used to provide support, treatment, and psychological assessments for First Nations Australians. Evidence of effectiveness was stronger for non-severe mental health conditions. Determinants of facilitators and barriers of the implementation of DMH services included: (i) organisational and administrative factors; (ii) cultural appropriateness; (iii) accessibility; (iv) integration of DMH services to the existing health system; (v) engagement between clients and service providers; (vi) coverage of different conditions and clients; (vii) acceptability to DMH services; (viii) digital literacy, and (ix) efficiency.

Conclusions: Evidence on the use of digital mental health (DMH) services for First Nations Australians remains heterogeneous in study design and outcome measurement. DMH services appear most effective for managing non-severe mental health conditions. Successful implementation requires multi-level structural support, including policy and organisational commitment, enhanced digital infrastructure, workforce training and engagement, and the design of culturally responsive DMH models to improve uptake and equitable access to mental health care among First Nations Australians.

Clinicaltrial:

背景：澳大利亚原住民的心理健康结果和获得服务的机会不公平。数字心理健康（DMH）服务指的是通过数字平台提供心理健康服务，被认为是解决这种心理健康服务不平等问题和改善土著澳大利亚人心理健康结果的潜在解决方案。然而，关于DMH对澳大利亚第一民族的有效性的证据还有待综合。目的：本系统的范围审查旨在填补这一空白，并确定在此背景下影响DMH服务实施的促进因素和障碍。方法：在六个学术数据库中进行系统搜索，以搜索与澳大利亚第一民族DMH服务相关的研究。使用了与第一民族、澳大利亚地理术语、心理健康和数字心理健康服务相关的搜索词。如果研究评估了在澳大利亚原住民中实施数字心理健康干预措施的有效性或促成因素的决定因素和障碍，则将其纳入研究。根据研究设计、目标服务和研究结果提取数据，然后使用主题分析框架进行综合。结果：共有22项研究符合纳入标准。DMH服务被用来为澳大利亚原住民提供支持、治疗和心理评估。对于非严重的精神健康状况，有效性的证据更强。DMH服务实施的促进因素和障碍的决定因素包括：(i)组织和行政因素；（ii）文化适宜性；(3)易访问性;（iv）将DMH服务纳入现有卫生系统；(v)客户与服务提供商之间的合作；（vi）不同条件和客户的覆盖范围；（vii） DMH服务的可接受性；（viii）数字素养，以及（ix）效率。结论：关于第一民族澳大利亚人使用数字心理健康（DMH）服务的证据在研究设计和结果测量方面仍然存在差异。DMH服务似乎对管理非严重精神健康状况最有效。成功的实施需要多层次的结构支持，包括政策和组织承诺、加强数字基础设施、劳动力培训和参与，以及设计符合文化的精神卫生保健模式，以改善土著澳大利亚人接受和公平获得精神卫生保健的机会。临床试验:

{"title":"Effectiveness, facilitators and barriers of digital mental health services for First Nations Peoples in Australia: A systematic scoping review.","authors":"Siyu Zhai, Andrew Goodman, Anthony C Smith, Sandra Diminic, Xiaoyun Zhou","doi":"10.2196/80386","DOIUrl":"https://doi.org/10.2196/80386","url":null,"abstract":"Background: First Nations peoples in Australia experience inequitable mental health outcomes and service access. Digital mental health (DMH) services, which refer to offering mental health services through digital platforms, are considered potential solutions to address such mental health service inequities and improve First Nations Australians' mental health outcomes. However, evidence on the effectiveness of DMH for First Nations Peoples in Australia is yet to be synthesised.Objective: This systematic scoping review aimed to fill this gap, and to identify the facilitators and barriers that influence the implementation of DMH services in this context.Methods: A systematic search was conducted across six academic databases to search for studies related to DMH services for First Nations Peoples in Australia. Search terms relating to First Nations Peoples, geographic terminologies of Australia, mental health, and digital mental health services were used. Studies were included if they assessed the effectiveness, or determinants of facilitators and barriers of implementing digital mental health interventions among First Nations people in Australia. Data were extracted based on study design, targeted services, and research findings, then synthesised using a thematic analysis framework.Results: In total, 22 studies met the inclusion criteria. DMH services were used to provide support, treatment, and psychological assessments for First Nations Australians. Evidence of effectiveness was stronger for non-severe mental health conditions. Determinants of facilitators and barriers of the implementation of DMH services included: (i) organisational and administrative factors; (ii) cultural appropriateness; (iii) accessibility; (iv) integration of DMH services to the existing health system; (v) engagement between clients and service providers; (vi) coverage of different conditions and clients; (vii) acceptability to DMH services; (viii) digital literacy, and (ix) efficiency.Conclusions: Evidence on the use of digital mental health (DMH) services for First Nations Australians remains heterogeneous in study design and outcome measurement. DMH services appear most effective for managing non-severe mental health conditions. Successful implementation requires multi-level structural support, including policy and organisational commitment, enhanced digital infrastructure, workforce training and engagement, and the design of culturally responsive DMH models to improve uptake and equitable access to mental health care among First Nations Australians.Clinicaltrial: ","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145847083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Obesity Prevention and Reduction in China Using the Social Media Platform WeChat: Scoping Review. 中国使用社交媒体平台b微信预防和减少肥胖：范围审查。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-12-11 DOI: 10.2196/65538

Yinuo Wang, Xuxiu Zhuang, Samantha Sundermeir, Joel Gittelsohn

Background: Digital interventions for obesity have demonstrated efficacy in obesity prevention and management. The emergence of smartphones and ubiquitous apps such as WeChat represents potential modality to enhance the reach, sustainability, and cost-effectiveness of such interventions. By the end of the first quarter of 2024, WeChat had approximately 1.36 billion monthly active users, accounting for 96.5% of China's population. The use of this platform for obesity interventions has been validated in multiple Chinese trials, most published in Chinese language journals.Objective: We aim to synthesize the existing evidence on obesity interventions delivered through WeChat to generate implications for future intervention design and development, thereby reaching an international audience.Methods: We conducted a scoping review of PubMed and China National Knowledge Infrastructure using search terms including "WeChat," "obesity," "weight," "BMI," "waist circumference," "hip circumference," "waist-to-hip ratio," "body fat," "skin fold thickness," and these Chinese equivalents "weixin," "feipang," "tizhong," "tizhongzhishu," "yaowei," "tunwei," "yaotunbi," "tizhi," and "pizhehoudu." We included only original research studies, theses, or dissertations with measurable outcomes that used WeChat functions as intervention strategies. Study quality was assessed using the National Institutes of Health Quality Assessment Tool, with specific tools selected based on study design. Descriptive statistics were applied, with categorical variables summarized as frequencies and percentages (n, %) to report study distribution.Results: Our scoping review based on PubMed and China National Knowledge Infrastructure identified 665 initial records, among which 43 studies met eligibility criteria and were included for data extraction to characterize intervention details. Results indicated effectiveness in 86.0% (37/43) of studies, with WeChat-assisted obesity interventions achieving significant short- and long-term weight loss measured by objective outcomes (body weight, BMI, waist circumference, hip circumference, waist-to-hip ratio, and body fat percentage). However, formative research informing intervention design was insufficient. Common methodological limitations included lack of randomization and blinding (42/43, 97.7%) and unreported intervention compliance metrics (39/43, 92.0%). Functionally, interventions primarily used "WeChat group" and "Official Account"-public accounts that provide health education, diet or physical activity logging, and other features.Conclusions: Overall, WeChat represents a promising platform for obesity interventions; however, current apps fail to leverage its full features (eg, online payment and live streaming). Key limitations include methodological heterogeneity and cultural specificity, which were addressed through narrati

背景：数字干预在肥胖预防和管理方面已经证明了有效性。智能手机和微信等无处不在的应用程序的出现，代表了增强此类干预措施覆盖面、可持续性和成本效益的潜在模式。截至2024年第一季度末，b微信的月活跃用户约为13.6亿，占中国人口的96.5%。该平台对肥胖干预的使用已在多个中国试验中得到验证，其中大多数发表在中文期刊上。目的：我们旨在综合通过微信提供的肥胖干预措施的现有证据，为未来干预措施的设计和开发提供启示，从而达到国际受众。方法：我们对PubMed和中国国家知识基础设施进行了范围审查，使用搜索词包括“微信”，“肥胖”，“体重”，“BMI”，“腰围”，“臀围”，“腰臀比”，“体脂”，“皮肤折叠厚度”，以及这些中文对等词“微胖”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“肥瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”，“瘦瘦”和“瘦瘦”。我们只纳入了具有可测量结果的原始研究、论文或论文，这些研究使用微信函数作为干预策略。使用美国国立卫生研究院质量评估工具评估研究质量，并根据研究设计选择特定工具。采用描述性统计，分类变量总结为频率和百分比（n, %）来报告研究分布。结果：我们基于PubMed和中国国家知识基础设施的范围审查确定了665项初始记录，其中43项研究符合资格标准，并纳入数据提取以表征干预细节。结果显示86.0%（37/43）的研究有效，通过客观结果（体重、BMI、腰围、臀围、腰臀比和体脂率）衡量，微信辅助肥胖干预实现了显著的短期和长期体重减轻。然而，为干预设计提供信息的形成性研究还不够。常见的方法学局限性包括缺乏随机化和盲法（42/43,97.7%）和未报告的干预依从性指标（39/43,92.0%）。在功能上，干预措施主要使用“微信组”和“官方账户”——提供健康教育、饮食或体育活动记录和其他功能的公共账户。结论：总体而言，微信代表了一个很有前景的肥胖干预平台；然而，目前的应用程序未能充分利用其全部功能（例如，在线支付和直播）。主要的限制包括方法的异质性和文化特殊性，这是通过按研究类型分层的叙事综合来解决的。未来的研究应纳入形成阶段，并使用更严格的方法，如随机对照试验，通过这种方式优化干预设计和交付。

{"title":"Obesity Prevention and Reduction in China Using the Social Media Platform WeChat: Scoping Review.","authors":"Yinuo Wang, Xuxiu Zhuang, Samantha Sundermeir, Joel Gittelsohn","doi":"10.2196/65538","DOIUrl":"10.2196/65538","url":null,"abstract":"Background: Digital interventions for obesity have demonstrated efficacy in obesity prevention and management. The emergence of smartphones and ubiquitous apps such as WeChat represents potential modality to enhance the reach, sustainability, and cost-effectiveness of such interventions. By the end of the first quarter of 2024, WeChat had approximately 1.36 billion monthly active users, accounting for 96.5% of China's population. The use of this platform for obesity interventions has been validated in multiple Chinese trials, most published in Chinese language journals.Objective: We aim to synthesize the existing evidence on obesity interventions delivered through WeChat to generate implications for future intervention design and development, thereby reaching an international audience.Methods: We conducted a scoping review of PubMed and China National Knowledge Infrastructure using search terms including \"WeChat,\" \"obesity,\" \"weight,\" \"BMI,\" \"waist circumference,\" \"hip circumference,\" \"waist-to-hip ratio,\" \"body fat,\" \"skin fold thickness,\" and these Chinese equivalents \"weixin,\" \"feipang,\" \"tizhong,\" \"tizhongzhishu,\" \"yaowei,\" \"tunwei,\" \"yaotunbi,\" \"tizhi,\" and \"pizhehoudu.\" We included only original research studies, theses, or dissertations with measurable outcomes that used WeChat functions as intervention strategies. Study quality was assessed using the National Institutes of Health Quality Assessment Tool, with specific tools selected based on study design. Descriptive statistics were applied, with categorical variables summarized as frequencies and percentages (n, %) to report study distribution.Results: Our scoping review based on PubMed and China National Knowledge Infrastructure identified 665 initial records, among which 43 studies met eligibility criteria and were included for data extraction to characterize intervention details. Results indicated effectiveness in 86.0% (37/43) of studies, with WeChat-assisted obesity interventions achieving significant short- and long-term weight loss measured by objective outcomes (body weight, BMI, waist circumference, hip circumference, waist-to-hip ratio, and body fat percentage). However, formative research informing intervention design was insufficient. Common methodological limitations included lack of randomization and blinding (42/43, 97.7%) and unreported intervention compliance metrics (39/43, 92.0%). Functionally, interventions primarily used \"WeChat group\" and \"Official Account\"-public accounts that provide health education, diet or physical activity logging, and other features.Conclusions: Overall, WeChat represents a promising platform for obesity interventions; however, current apps fail to leverage its full features (eg, online payment and live streaming). Key limitations include methodological heterogeneity and cultural specificity, which were addressed through narrati","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":"14 ","pages":"e65538"},"PeriodicalIF":1.9,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12698035/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145745827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting Age-Related Hearing Loss in Community-Dwelling Older Adults: Multicenter Retrospective Cohort Study. 预测社区老年人年龄相关性听力损失：多中心回顾性队列研究。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-12-10 DOI: 10.2196/81135

Jing Li, Shuai Jin, Liu Sun, Jun-E Liu, Qiang Shen, Miao Shang, Hanting Wang, Yuanyuan Zhao

Background: Age-related hearing loss (ARHL) is associated with severe negative outcomes, including social isolation, depression, and cognitive decline. Despite this, routine ARHL screening is often neglected in primary care due to low awareness, resource limitations, and inefficiencies. A practical risk assessment tool could effectively address this gap.

Objective: This study aims to develop and validate a user-friendly nomogram for identifying older adults at high risk of ARHL in community settings, thereby facilitating targeted screening and timely interventions.

Methods: This multicenter retrospective cohort study included 34,983 older adults from 3 primary health care centers in Beijing (January 2020 to October 2023). Data from center A (n=18,707) were used for model development, with external validation performed on cohorts from center B (n=11,008) and center C (n=5268). Least absolute shrinkage and selection operator and logistic regression identified the final predictors. Model performance was evaluated using discrimination, calibration, and decision curve analysis, leading to the development of an online nomogram.

Results: In the training cohort (center A), 1177 participants (6.3%) had hearing loss. Six key predictors were identified: age, education, exercise frequency, physical function, dietary habits, and hypertension. The multivariate logistic regression model demonstrated good discrimination in internal validation (area under the curve [AUC] 0.806, 95% CI 0.782-0.831; sensitivity 0.774; specificity 0.820). External validation confirmed its generalizability (AUC 0.720, 95% CI 0.670-0.771 and AUC 0.747, 95% CI 0.712-0.782). Decision curve analysis highlighted a substantial clinical net benefit. A user-friendly online prediction web page was also developed.

Conclusions: We successfully developed and validated a dynamic, online nomogram for predicting ARHL in older adults. Comprising 6 readily available predictors, this model shows potential as a practical, online tool for proactive risk identification in primary care. However, further validation in larger and more diverse populations is essential to confirm its generalizability and real-world clinical utility.

背景：年龄相关性听力损失（ARHL）与严重的负面结果相关，包括社会孤立、抑郁和认知能力下降。尽管如此，由于认识不足、资源限制和效率低下，常规ARHL筛查在初级保健中经常被忽视。一个实用的风险评估工具可以有效地解决这一差距。目的：本研究旨在开发和验证一种用户友好的nomogram方法，用于识别社区环境中ARHL高风险的老年人，从而促进有针对性的筛查和及时的干预。方法：本多中心回顾性队列研究纳入了北京3个初级卫生保健中心的34983名老年人（2020年1月至2023年10月）。来自A中心（n=18,707）的数据用于模型开发，并对来自B中心（n=11,008）和C中心（n=5268）的队列进行外部验证。最小绝对收缩和选择算子和逻辑回归确定了最终的预测因子。使用判别、校准和决策曲线分析来评估模型性能，从而形成在线nomogram。结果：在培训队列（A中心）中，1177名参与者（6.3%）有听力损失。确定了六个关键预测因素：年龄、教育程度、运动频率、身体功能、饮食习惯和高血压。多因素logistic回归模型在内部验证中具有良好的判别性（曲线下面积[AUC] 0.806, 95% CI 0.782-0.831；敏感性0.774；特异性0.820）。外部验证证实了其普遍性（AUC 0.720, 95% CI 0.670-0.771, AUC 0.747, 95% CI 0.712-0.782）。决策曲线分析强调了实质性的临床净收益。还开发了一个用户友好的在线预测网页。结论：我们成功开发并验证了预测老年人ARHL的动态在线nomogram。该模型包含6个现成的预测因子，显示出作为初级保健中主动风险识别的实用在线工具的潜力。然而，在更大和更多样化的人群中进一步验证是必不可少的，以确认其普遍性和现实世界的临床应用。

{"title":"Predicting Age-Related Hearing Loss in Community-Dwelling Older Adults: Multicenter Retrospective Cohort Study.","authors":"Jing Li, Shuai Jin, Liu Sun, Jun-E Liu, Qiang Shen, Miao Shang, Hanting Wang, Yuanyuan Zhao","doi":"10.2196/81135","DOIUrl":"10.2196/81135","url":null,"abstract":"Background: Age-related hearing loss (ARHL) is associated with severe negative outcomes, including social isolation, depression, and cognitive decline. Despite this, routine ARHL screening is often neglected in primary care due to low awareness, resource limitations, and inefficiencies. A practical risk assessment tool could effectively address this gap.Objective: This study aims to develop and validate a user-friendly nomogram for identifying older adults at high risk of ARHL in community settings, thereby facilitating targeted screening and timely interventions.Methods: This multicenter retrospective cohort study included 34,983 older adults from 3 primary health care centers in Beijing (January 2020 to October 2023). Data from center A (n=18,707) were used for model development, with external validation performed on cohorts from center B (n=11,008) and center C (n=5268). Least absolute shrinkage and selection operator and logistic regression identified the final predictors. Model performance was evaluated using discrimination, calibration, and decision curve analysis, leading to the development of an online nomogram.Results: In the training cohort (center A), 1177 participants (6.3%) had hearing loss. Six key predictors were identified: age, education, exercise frequency, physical function, dietary habits, and hypertension. The multivariate logistic regression model demonstrated good discrimination in internal validation (area under the curve [AUC] 0.806, 95% CI 0.782-0.831; sensitivity 0.774; specificity 0.820). External validation confirmed its generalizability (AUC 0.720, 95% CI 0.670-0.771 and AUC 0.747, 95% CI 0.712-0.782). Decision curve analysis highlighted a substantial clinical net benefit. A user-friendly online prediction web page was also developed.Conclusions: We successfully developed and validated a dynamic, online nomogram for predicting ARHL in older adults. Comprising 6 readily available predictors, this model shows potential as a practical, online tool for proactive risk identification in primary care. However, further validation in larger and more diverse populations is essential to confirm its generalizability and real-world clinical utility.","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":"14 ","pages":"e81135"},"PeriodicalIF":1.9,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12739456/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145726865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digital Health for Australia: Bridging the Rural, Regional, and Remote Health Gap. 澳大利亚的数字健康：弥合农村、地区和远程健康差距。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-12-02 DOI: 10.2196/67460

Shakeel Mahmood, M Mamun Huda, Kedir Yimam Ahmed, Thapa Subash, Feleke Hailemichael Astawesegn, Anayochukwu Edward Anyasodor, Mohammad Ali Moni, Muhammad J A Shiddiky, Utpal K Mondal, Setognal Birara Aychiluhm, Santosh Giri, Allen Ross

In rural Australia, recent trends reveal an exponential increase in the rates of physical inactivity, central obesity, metabolic syndrome, and cancer in the population. The limited rural health workforce, which is struggling to meet this growing burden, is boosted by digital technologies such as My Health Record, Cardihab, Healthdirect, and MindSpot, all of which offer opportunities for improved diagnostics, monitoring, and management of chronic diseases. However, implementing proven digital health technologies in rural communities has been challenging on numerous fronts. This perspective aims to (1) highlight the rural health gap and propose a way forward in implementing evidence-based digital health technologies in the rural, regional, and remote communities of Australia and (2) guide future rural health policy.

在澳大利亚农村，最近的趋势显示，人口中缺乏身体活动、中枢性肥胖、代谢综合征和癌症的发病率呈指数级增长。有限的农村卫生人力正在努力应对这一日益增长的负担，而My health Record、Cardihab、Healthdirect和MindSpot等数字技术则推动了这一进程，所有这些技术都为改进慢性病的诊断、监测和管理提供了机会。然而，在农村社区实施经过验证的数字卫生技术在许多方面都具有挑战性。这一视角旨在(1)突出农村卫生差距，并提出在澳大利亚农村、地区和偏远社区实施循证数字卫生技术的前进方向；(2)指导未来的农村卫生政策。

引用次数: 0

Impact of the COVID-19 Pandemic on Contraceptive Services at Selected Primary Health Care Facilities in India, Nigeria, and Tanzania: Cross-Sectional Study. COVID-19大流行对印度、尼日利亚和坦桑尼亚选定初级卫生保健机构避孕服务的影响：横断面研究

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-12-02 DOI: 10.2196/59874

Rita Kabra, Beena Joshi, Ester Elisaria, Tanimola Makanjuola Akande, Komal Preet Allagh, Adesola Olumide, Deepti Tandon, Ranjan Prusty, Mary Ramesh, Donat Shamba, Bhavya Mk, Shabana Khan, James Kiarie

Background: The COVID-19 pandemic disrupted sexual and reproductive health services, including family planning (FP) and contraceptive services. The World Health Organization conducted a multicountry study in India, Nigeria, and Tanzania to determine the impact of the pandemic on the health system's readiness to provide contraception services and trends in contraceptive uptake.

Objective: This study aimed to determine the status, availability, and health facility readiness to provide contraceptive services and to compare trends in contraceptive uptake before and during the pandemic.

Methods: This cross-sectional study was conducted by the Indian Council of Medical Research-National Institute of Research in Reproductive and Child Health (India), the University of Ilorin Teaching Hospital (Nigeria), and the Ifakara Health Institute (Tanzania). A total of 50 primary health facilities (11 in India, 6 in Nigeria, and 33 in Tanzania) were evaluated using a standardized facility assessment questionnaire, completed by the most knowledgeable senior health care provider or administrator at the facility. Monthly data on service utilization and contraceptive availability were collected to capture trends before and during the COVID-19 pandemic. Data were collected from May to August 2022. The study received ethical and scientific approval from the World Health Organization Ethics Review Committee and Research Project Review Panel and national regulatory bodies. Key outcomes included availability of FP guidelines and tools, service disruptions including contraceptive and abortion services, stock-outs, reasons for service disruptions, and mitigation measures to sustain service deliveries. Descriptive analysis was used to summarize the key trends and patterns.

Results: Health facilities in all three countries reported shortages of various contraceptives. Contraceptive services were partially disrupted in 91% facilities in India, 83% facilities in Nigeria, and 43% facilities in Tanzania. Abortion services were partially disrupted in all surveyed facilities offering these services in India and Nigeria and in 26.7% of facilities in Tanzania. Client visits declined in health facilities in 2020 compared to 2019 in India (30%) and Nigeria (11%), with a gradual recovery thereafter. In contrast, Tanzania experienced a 1% decline in client visits in 2020. Readiness measures such as telemedicine, task shifting, community outreach, triaging, and patient redirection were implemented to minimize service disruptions.

Conclusions: This study provides crucial insights into the challenges posed by the COVID-19 pandemic on contraceptive services and the measures taken to alleviate them. The findings can help countries to better prepare to prevent the disruption of FP and contraceptive services in future pandemics or emergencies.

背景：2019冠状病毒病大流行扰乱了性健康和生殖健康服务，包括计划生育和避孕服务。世界卫生组织在印度、尼日利亚和坦桑尼亚进行了一项多国研究，以确定大流行对卫生系统提供避孕服务的准备程度和避孕药具使用趋势的影响。目的：本研究旨在确定提供避孕服务的状况、可得性和卫生机构的准备情况，并比较大流行之前和期间避孕措施的使用趋势。方法：本横断面研究由印度医学研究委员会-国家生殖和儿童健康研究所（印度）、伊洛林大学教学医院（尼日利亚）和伊法卡拉卫生研究所（坦桑尼亚）进行。使用标准化设施评估问卷对总共50个初级卫生设施（印度11个、尼日利亚6个、坦桑尼亚33个）进行了评估，问卷由设施中知识最渊博的高级卫生保健提供者或管理人员完成。每月收集有关服务利用和避孕措施可得性的数据，以掌握COVID-19大流行之前和期间的趋势。数据收集于2022年5月至8月。该研究获得了世界卫生组织伦理审查委员会和研究项目审查小组以及国家监管机构的伦理和科学批准。主要成果包括计划生育准则和工具的提供、避孕和堕胎服务等服务中断、缺货、服务中断的原因以及维持服务提供的缓解措施。使用描述性分析来总结主要趋势和模式。结果：所有三个国家的保健设施都报告各种避孕药具短缺。印度91%的设施、尼日利亚83%的设施和坦桑尼亚43%的设施的避孕服务部分中断。在接受调查的印度和尼日利亚所有提供堕胎服务的机构以及坦桑尼亚26.7%的机构中，堕胎服务部分中断。与2019年相比，2020年印度（30%）和尼日利亚（11%）的医疗机构客户访问量有所下降，此后逐步恢复。相比之下，坦桑尼亚的客户访问量在2020年下降了1%。实施了远程医疗、任务转移、社区外展、分诊和病人重定向等准备措施，以尽量减少服务中断。结论：本研究对COVID-19大流行对避孕服务构成的挑战以及采取的缓解措施提供了重要见解。研究结果可以帮助各国更好地做好准备，防止计划生育和避孕服务在未来大流行或紧急情况下中断。

{"title":"Impact of the COVID-19 Pandemic on Contraceptive Services at Selected Primary Health Care Facilities in India, Nigeria, and Tanzania: Cross-Sectional Study.","authors":"Rita Kabra, Beena Joshi, Ester Elisaria, Tanimola Makanjuola Akande, Komal Preet Allagh, Adesola Olumide, Deepti Tandon, Ranjan Prusty, Mary Ramesh, Donat Shamba, Bhavya Mk, Shabana Khan, James Kiarie","doi":"10.2196/59874","DOIUrl":"10.2196/59874","url":null,"abstract":"Background: The COVID-19 pandemic disrupted sexual and reproductive health services, including family planning (FP) and contraceptive services. The World Health Organization conducted a multicountry study in India, Nigeria, and Tanzania to determine the impact of the pandemic on the health system's readiness to provide contraception services and trends in contraceptive uptake.Objective: This study aimed to determine the status, availability, and health facility readiness to provide contraceptive services and to compare trends in contraceptive uptake before and during the pandemic.Methods: This cross-sectional study was conducted by the Indian Council of Medical Research-National Institute of Research in Reproductive and Child Health (India), the University of Ilorin Teaching Hospital (Nigeria), and the Ifakara Health Institute (Tanzania). A total of 50 primary health facilities (11 in India, 6 in Nigeria, and 33 in Tanzania) were evaluated using a standardized facility assessment questionnaire, completed by the most knowledgeable senior health care provider or administrator at the facility. Monthly data on service utilization and contraceptive availability were collected to capture trends before and during the COVID-19 pandemic. Data were collected from May to August 2022. The study received ethical and scientific approval from the World Health Organization Ethics Review Committee and Research Project Review Panel and national regulatory bodies. Key outcomes included availability of FP guidelines and tools, service disruptions including contraceptive and abortion services, stock-outs, reasons for service disruptions, and mitigation measures to sustain service deliveries. Descriptive analysis was used to summarize the key trends and patterns.Results: Health facilities in all three countries reported shortages of various contraceptives. Contraceptive services were partially disrupted in 91% facilities in India, 83% facilities in Nigeria, and 43% facilities in Tanzania. Abortion services were partially disrupted in all surveyed facilities offering these services in India and Nigeria and in 26.7% of facilities in Tanzania. Client visits declined in health facilities in 2020 compared to 2019 in India (30%) and Nigeria (11%), with a gradual recovery thereafter. In contrast, Tanzania experienced a 1% decline in client visits in 2020. Readiness measures such as telemedicine, task shifting, community outreach, triaging, and patient redirection were implemented to minimize service disruptions.Conclusions: This study provides crucial insights into the challenges posed by the COVID-19 pandemic on contraceptive services and the measures taken to alleviate them. The findings can help countries to better prepare to prevent the disruption of FP and contraceptive services in future pandemics or emergencies.","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":"14 ","pages":"e59874"},"PeriodicalIF":1.9,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12683499/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145702429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Streamlining Ophthalmic Documentation With Anonymized, Fine-Tuned Language Models: Feasibility Study. 精简眼科文件与匿名，微调语言模型：可行性研究。

IF 1.9 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Interactive Journal of Medical Research

Pub Date : 2025-11-26 DOI: 10.2196/72894

Sebastian Arens, Quang Vinh Ngo, Anna Richling, Lucas Stürzbecher, Daniel Böhringer, Thomas Reinhard, Felix Heilmeyer

Background: The growing administrative burden on clinicians, particularly in medical documentation, contributes to burnout and may compromise patient safety. Recent advancements in generative artificial intelligence (AI) offer a promising solution to improve documentation processes and address these challenges.Objective: This study aims to evaluate the feasibility of using a fine-tuned OpenAI Curie model to automate the generation of medical report summaries (epicrises) in ophthalmology. By assessing the model's performance through human and automated evaluations, this study seeks to determine its potential for reducing clinician workload while ensuring accuracy, usefulness, and compliance with regulatory requirements.Methods: A data set of around 60,000 anonymized medical letters was created using a custom algorithm to comply with General Data Protection Regulation guidelines. The Curie model was fine-tuned on this data set to generate epicrises from medical histories, diagnoses, and findings. The performance evaluation involved various human assessments and automated evaluations from 2 large language models (LLMs).Results: In the clinical context, 49.9% (384/769) of epicrises were evaluated as helpful or excellent, whereas only 25% (194/769) were considered disturbing. In a human (manual) evaluation, formal correctness was rated significantly higher than the neutral midpoint of 2.5 on the 4-point rating scale, as determined by a 1-sample Wilcoxon signed-rank test (mean 3.59, SD 0.85; W=1686; P<.001). Using paired t tests, we found a significant reduction in time, as correcting an AI epicrisis was faster than manually writing one (mean 109.52, SD 53.30 vs mean 54.25, SD 63.34 s; t68=3.39; P<.01). While medical accuracy and usefulness showed positive trends, these did not reach statistical significance when compared to the neutral midpoint (for medical accuracy, W= 7456; P=.08), for usefulness, W=7652.5; P=.18). Epicrises generated or corrected with AI were significantly shorter than manually written ones (mean 330.43, SD 115.42 vs mean 501.07, SD 243.50 characters; t68=-6.10; P<.001). Automated LLM assessments showed alignment with human ratings, with over 52% (356/679) and 66% (489/743) of responses in the top agreement categories, respectively. This supports overall consistency, though the comparison remains a proof of concept given methodological limitations.Conclusions: Our study demonstrates the technical and practical feasibility of introducing fine-tuned commercial LLMs into clinical practice. The AI-generated epicrises were formally and clinically correct in many cases and showed time-saving potential. While medical accuracy and usefulness varied across cases and should be focused on in further developments, a significant workload reduction is likely. Our anonymization process showed that regulatory ch

背景：临床医生日益增加的行政负担，特别是在医疗文件方面，导致职业倦怠，并可能危及患者安全。生成式人工智能（AI）的最新进展为改进文档流程和应对这些挑战提供了一个有希望的解决方案。目的：本研究旨在评估使用微调的OpenAI居里模型自动生成眼科医学报告摘要（epicrises）的可行性。通过人工和自动评估评估模型的性能，本研究试图确定其在确保准确性、实用性和符合法规要求的同时减少临床医生工作量的潜力。方法：使用自定义算法创建了大约60,000封匿名医疗信件的数据集，以遵守通用数据保护条例指南。居里模型在此数据集上进行了微调，以从病史、诊断和发现中生成epicepices。性能评估包括各种人工评估和来自2个大型语言模型（llm）的自动评估。结果：在临床环境中，49.9%（384/769）的外翻被评价为有益或优秀，而只有25%（194/769）的外翻被认为是令人不安的。在人类（手动）评估中，通过1样本Wilcoxon符号秩检验，形式正确性的评分明显高于4分制量表中2.5的中性中点（平均值3.59,SD 0.85； W=1686; P68=3.39; P68=-6.10; P68）。结论：我们的研究证明了将微调的商业llm引入临床实践的技术和实践可行性。人工智能生成的epicrise在许多情况下是正式和临床正确的，并显示出节省时间的潜力。虽然医疗准确性和有用性因病例而异，在进一步发展中应重点关注，但可能会大大减少工作量。我们的匿名化过程表明，可以有效地处理人工智能患者数据背景下的监管挑战。总之，本研究强调了基于变革的法学硕士在减少医疗保健管理任务方面的承诺。它概述了将法学硕士纳入欧盟临床实践的管道，强调需要仔细实施以确保效率和患者安全。

{"title":"Streamlining Ophthalmic Documentation With Anonymized, Fine-Tuned Language Models: Feasibility Study.","authors":"Sebastian Arens, Quang Vinh Ngo, Anna Richling, Lucas Stürzbecher, Daniel Böhringer, Thomas Reinhard, Felix Heilmeyer","doi":"10.2196/72894","DOIUrl":"10.2196/72894","url":null,"abstract":"Background: The growing administrative burden on clinicians, particularly in medical documentation, contributes to burnout and may compromise patient safety. Recent advancements in generative artificial intelligence (AI) offer a promising solution to improve documentation processes and address these challenges.Objective: This study aims to evaluate the feasibility of using a fine-tuned OpenAI Curie model to automate the generation of medical report summaries (epicrises) in ophthalmology. By assessing the model's performance through human and automated evaluations, this study seeks to determine its potential for reducing clinician workload while ensuring accuracy, usefulness, and compliance with regulatory requirements.Methods: A data set of around 60,000 anonymized medical letters was created using a custom algorithm to comply with General Data Protection Regulation guidelines. The Curie model was fine-tuned on this data set to generate epicrises from medical histories, diagnoses, and findings. The performance evaluation involved various human assessments and automated evaluations from 2 large language models (LLMs).Results: In the clinical context, 49.9% (384/769) of epicrises were evaluated as helpful or excellent, whereas only 25% (194/769) were considered disturbing. In a human (manual) evaluation, formal correctness was rated significantly higher than the neutral midpoint of 2.5 on the 4-point rating scale, as determined by a 1-sample Wilcoxon signed-rank test (mean 3.59, SD 0.85; W=1686; P<.001). Using paired t tests, we found a significant reduction in time, as correcting an AI epicrisis was faster than manually writing one (mean 109.52, SD 53.30 vs mean 54.25, SD 63.34 s; t68=3.39; P<.01). While medical accuracy and usefulness showed positive trends, these did not reach statistical significance when compared to the neutral midpoint (for medical accuracy, W= 7456; P=.08), for usefulness, W=7652.5; P=.18). Epicrises generated or corrected with AI were significantly shorter than manually written ones (mean 330.43, SD 115.42 vs mean 501.07, SD 243.50 characters; t68=-6.10; P<.001). Automated LLM assessments showed alignment with human ratings, with over 52% (356/679) and 66% (489/743) of responses in the top agreement categories, respectively. This supports overall consistency, though the comparison remains a proof of concept given methodological limitations.Conclusions: Our study demonstrates the technical and practical feasibility of introducing fine-tuned commercial LLMs into clinical practice. The AI-generated epicrises were formally and clinically correct in many cases and showed time-saving potential. While medical accuracy and usefulness varied across cases and should be focused on in further developments, a significant workload reduction is likely. Our anonymization process showed that regulatory ch","PeriodicalId":51757,"journal":{"name":"Interactive Journal of Medical Research","volume":"14 ","pages":"e72894"},"PeriodicalIF":1.9,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12696452/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145642601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0