Frontiers in digital health最新文献

{"title":"Supervised machine learning applied in nursing notes for identifying the need of childhood cancer patients for psychosocial support.","authors":"Akseli Reunamo, Hans Moen, Sanna Salanterä, Päivi M Lähteenmäki","doi":"10.3389/fdgth.2025.1585309","DOIUrl":"10.3389/fdgth.2025.1585309","url":null,"abstract":"<p><strong>Introduction: </strong>Childhood cancer survivors have a higher risk of mental health and adaptive problems compared with their siblings, for example. Assessing the need for psychosocial support is essential for prevention. This project aims to investigate the use of supervised machine learning in the form of text classification in identifying childhood cancer patients needing psychosocial support from nursing notes when at least 1 year had passed from their cancer diagnosis.</p><p><strong>Methods: </strong>We evaluated three well-known machine learning-based models to recognize patients who had outpatient clinic reservations in the mental health-related care units from free-text nursing notes of 1,672 patients. For model training, the patients were children diagnosed with diabetes mellitus or cancer, while evaluation of the model was done on the patients diagnosed with cancer. A stratified fivefold nested cross-validation was used. We designed this as a binary classification task, with the following labels: no support (0) or psychosocial support (1) was needed. Patients with the latter label were identified by having an outpatient appointment reservation in a mental health-related care unit at least 1 year after their primary diagnosis.</p><p><strong>Results: </strong>The random forest classification model trained on both cancer and diabetes patients performed best for the cancer patient population in three-times repeated nested cross-validation with 0.798 mean area under the receiver operating characteristics curve and was better with 99% probability (credibility interval -0.2840 to -0.0422) than the neural network-based model using only cancer patients in training when comparing all classifiers pairwise by using the Bayesian correlated t-test.</p><p><strong>Conclusions: </strong>Using machine learning to predict childhood cancer patients needing psychosocial support was possible using nursing notes with a good area under the receiver operating characteristics curve. The reported experiment indicates that machine learning may assist in identifying patients likely to need mental health-related support later in life.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1585309"},"PeriodicalIF":3.2,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12367647/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144980917","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}

{"title":"Digital twin for personalized medicine development.","authors":"Saniya Y Saratkar, Meher Langote, Praveen Kumar, Pradnyawant Gote, Induni Nayodhara Weerarathna, Gaurav V Mishra","doi":"10.3389/fdgth.2025.1583466","DOIUrl":"10.3389/fdgth.2025.1583466","url":null,"abstract":"<p><p>Digital Twin (DT) technology is revolutionizing healthcare by enabling real-time monitoring, predictive analytics, and highly personalized medical care. As a key innovation of Industry 4.0, DTs integrate advanced tools like artificial intelligence (AI), the Internet of Things (IoT), and machine learning (ML) to create dynamic, data-driven replicas of patients. These digital replicas allow simulations of disease progression, optimize diagnostics, and personalize treatment plans based on individual genetic and lifestyle profiles. This review explores the evolution, architecture, and enabling technologies of DTs, focusing on their transformative applications in personalized medicine (PM). While the integration of DTs offers immense potential to improve outcomes and efficiency in healthcare, challenges such as data privacy, system interoperability, and ethical concerns must be addressed. The paper concludes by highlighting future directions, where AI, cloud computing, and blockchain are expected to play a pivotal role in overcoming these limitations and advancing precision medicine.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1583466"},"PeriodicalIF":3.2,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12369496/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981134","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}

{"title":"Digital health technologies for improving the management of people with chronic obstructive pulmonary disease.","authors":"Hye Yun Park, Sunga Kong, Mangyeong Lee, Hyein Ryu, Yoko Hamakawa, Fabrizio Luppi, Janice M Leung","doi":"10.3389/fdgth.2025.1640585","DOIUrl":"10.3389/fdgth.2025.1640585","url":null,"abstract":"<p><p>Advances made in digital health in recent years have the potential to improve the care of patients living with chronic obstructive pulmonary disease (COPD) for whom substantial disability still exists. In particular, telehealth and telerehabilitation programs, wearable devices, and apps have been studied as novel methods of providing care to COPD patients who may have limited access to clinical centers or who may benefit from an increased level of monitoring. Many of these interventions gained traction during the COVID-19 pandemic when mandated social isolation required the rapid implementation of remote care models. While these digital health interventions have since demonstrated promise in delivering care to otherwise isolated communities, the ongoing need for more evidence proving their positive impact on important clinical outcomes remains a barrier to their full implementation. How to best integrate digital health solutions into existing care models requires greater consideration of the technological, financial, and labor demands such solutions may entail.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1640585"},"PeriodicalIF":3.2,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12365816/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981127","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}

{"title":"Applications of generative artificial intelligence in outcome prediction in intensive care medicine-a scoping review.","authors":"Tanja Stamm, Mohamed Bader-El-Den, James McNicholas, Jim Briggs, Peng Zhao","doi":"10.3389/fdgth.2025.1633458","DOIUrl":"10.3389/fdgth.2025.1633458","url":null,"abstract":"<p><p>When a patient survives the first 24 h in intensive care, outcome prediction is crucial for further treatment decisions. As recent advances have shown that Artificial Intelligence (AI) outperforms clinicians in prognostication, and especially generative AI has developed rapidly in the past ten years, this scoping review aimed to explore the use of generative AI models for outcome prediction in intensive care medicine. Of the 481 records found in the search, 119 studies were subjected to abstract screening and, when necessary, full-text review for eligibility assessment. Twenty-two studies and two review articles were finally included. The studies were categorized into three prototypical use cases for generative AI in outcome prediction in intensive care: (i) data augmentation, (ii) feature generation from unstructured data, and (iii) prediction by the generative model. In the first two use cases, the generative models worked together with downstream predictive models. In the third use case, the generative models made the predictions themselves. The studies within data augmentation either fell into the area of compensation for class imbalances by producing additional synthetic cases or imputation of missing values. Overall, Generative Adversarial Network (GAN) was the most frequently used technology (8/22 studies; 36%), followed by Generative Pretrained Transformer (GPT) (7/22 studies; 32%). All publications except one were from the last four years. This review shows that generative AI has immense potential in the future, and continuous monitoring of new technologies is necessary to ensure that patients receive the best possible care.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1633458"},"PeriodicalIF":3.2,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12361121/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981129","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}

{"title":"Correction: Online training program maintains motor functions and quality of life in patients with Parkinson's disease.","authors":"Hiroshi Nakanishi, Ryoma Morigaki, Joji Fujikawa, Hiroshi Ohmae, Keisuke Shinohara, Nobuaki Yamamoto, Yuishin Izumi, Yasushi Takagi","doi":"10.3389/fdgth.2025.1672261","DOIUrl":"10.3389/fdgth.2025.1672261","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fdgth.2024.1486662.].</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1672261"},"PeriodicalIF":3.2,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12362260/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981093","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}

{"title":"Editorial: Unleashing the power of large data: models to improve individual health outcomes.","authors":"Hyewon Jeong, Sanjat Kanjilal, Sherry H Yu, Akshay Kothakonda","doi":"10.3389/fdgth.2025.1668543","DOIUrl":"10.3389/fdgth.2025.1668543","url":null,"abstract":"","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1668543"},"PeriodicalIF":3.2,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12358951/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144884370","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}

{"title":"Determinants of chronic disease patients' intention to use Internet diagnosis and treatment services: based on the UTAUT2 model.","authors":"Jing Zhao, Bei Li, Jianwei Sun, Xu Zeng, Jing Zheng","doi":"10.3389/fdgth.2025.1543428","DOIUrl":"10.3389/fdgth.2025.1543428","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Chronic diseases are a significant public health concern. Internet diagnosis and treatment services can effectively monitor chronic diseases and are vital for alleviating the healthcare system burden caused by these conditions. Distinguishing itself from prior investigations, this study focuses on the critical cohort of chronic disease patients and, building upon the UTAUT2 framework, introduces additional constructs such as trust and medical habits. It systematically examines the pivotal determinants influencing the acceptance and utilization of Internet diagnosis and treatment services among chronic disease patients in Shenzhen, China.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study centers on the population of chronic disease patients in Shenzhen, China, by developing a theoretical model to elucidate their behavioral intentions toward utilizing Internet diagnosis and treatment services. Employing empirical methods, the research identifies the key determinants that influence patients' acceptance and adoption of these services. Furthermore, based on the interactive mechanisms among these factors, targeted policy recommendations are advanced to enhance service utilization rates and optimize the quality of Internet diagnosis and treatment services.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Guided by the theoretical framework, and informed by expert consultations and a preliminary survey, the questionnaire was meticulously designed and refined. Employing a five-point Likert scale, the survey investigated the usage patterns of Internet diagnosis and treatment services among chronic disease patients in Shenzhen, China, as well as the factors influencing their behavioral intention. Utilizing convenience sampling, a total of 823 valid responses were collected. Subsequent data analysis was conducted using SPSS 26.0 and AMOS 28.0 software, encompassing descriptive statistics and structural equation modeling. Furthermore, the Bootstrap method was employed to rigorously assess the mediating effects within the model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The empirical findings reveal that: (1) Model validation indicates that performance expectancy (&lt;i&gt;β&lt;/i&gt; = 0.151, &lt;i&gt;p&lt;/i&gt; = 0.002), effort expectancy (&lt;i&gt;β&lt;/i&gt; = 0.105, &lt;i&gt;p&lt;/i&gt; = 0.022), social influence (&lt;i&gt;β&lt;/i&gt; = 0.206, &lt;i&gt;p&lt;/i&gt; &lt; 0.001), price value (&lt;i&gt;β&lt;/i&gt; = 0.138, &lt;i&gt;p&lt;/i&gt; = 0.002), trust (&lt;i&gt;β&lt;/i&gt; = 0.124, &lt;i&gt;p&lt;/i&gt; = 0.003), and electronic health literacy (&lt;i&gt;β&lt;/i&gt; = 0.184, &lt;i&gt;p&lt;/i&gt; &lt; 0.001) exert significant positive effects on the behavioral intention to use Internet diagnosis and treatment services. Conversely, perceived risk negatively influences behavioral intention (&lt;i&gt;β&lt;/i&gt; = 0.094, &lt;i&gt;p&lt;/i&gt; = 0.008), whereas the effect of medical habits on behavioral intention is not statistically significant (&lt;i&gt;p&lt;/i&gt; &gt; 0.05). (2) Performance expectancy partially mediates the relationships between effort expectancy, trust, electronic health literacy, and behavioral intention, while effort ex","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1543428"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12354382/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877047","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}

{"title":"The status of machine learning in HIV testing in South Africa: a qualitative inquiry with stakeholders in Gauteng province.","authors":"Musa Jaiteh, Edith Phalane, Yegnanew A Shiferaw, Refilwe Nancy Phaswana-Mafuya","doi":"10.3389/fdgth.2025.1618781","DOIUrl":"10.3389/fdgth.2025.1618781","url":null,"abstract":"<p><strong>Background: </strong>The human immunodeficiency virus (HIV) remains one of the leading causes of death globally, with South Africa bearing a significant burden. As an effective way of reducing HIV transmission, HIV testing interventions are crucial and require the involvement of key stakeholders, including healthcare professionals and policymakers. New technologies like machine learning are remarkably reshaping the healthcare landscape, especially in HIV testing. However, their implementation from the stakeholders' point of view remains unclear. This study explored the perspectives of key stakeholders in Gauteng Province on the status of machine learning applications in HIV testing in South Africa.</p><p><strong>Methods: </strong>The study used an exploratory qualitative approach to recruit 15 stakeholders working in government and non-government institutions rendering HIV testing services. The study participants were healthcare professionals such as public health experts, lab scientists, medical doctors, nurses, HIV testing services, and retention counselors. Individual-based in-depth interviews were conducted using open-ended questions. Thematic content analysis was used, and results were presented in themes and sub-themes.</p><p><strong>Results: </strong>Three main themes were determined, namely awareness level, existing applications, and perceived potential of machine learning in HIV testing interventions. A total of nine sub-themes were discussed in the study: limited knowledge among frontline workers, research vs. implementation gap, need for education, self-testing support, data analysis tools, counseling aids, youth engagement, system efficiency, and data-driven decisions. The study shows that integration of machine learning would enhance HIV risk prediction, individualized testing through HIV self-testing, and youth engagement. This is crucial for reducing HIV transmission, addressing stigma, and optimizing resource allocation. Despite the potential, machine learning is underutilized in HIV testing services beyond statistical analysis in South Africa. Key gaps identified were a lack of implementation of research findings and a lack of awareness among frontline workers and end-users.</p><p><strong>Conclusion: </strong>Policymakers should design educational programs to improve awareness of existing machine learning initiatives and encourage the implementation of research findings into HIV testing services. A follow-up study should assess the feasibility, structural challenges, and design implementation strategies for the integration of machine learning in HIV testing in South Africa.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1618781"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12354530/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877049","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}

{"title":"eHealth literacy assessment as a promoter of user adherence in using digital health systems and services. A case study for balance physiotherapy in the TeleRehaB DSS project.","authors":"Konstantinos Georgas, Konstantinos Bromis, Theodoros P Vagenas, Olympia Giannakopoulou, Nikolaos Vasileiou, Ioannis Kouris, Maria Haritou, George K Matsopoulos","doi":"10.3389/fdgth.2025.1535582","DOIUrl":"10.3389/fdgth.2025.1535582","url":null,"abstract":"<p><p>Improving patient adherence and compliance with digital health interventions requires the creation of eHealth literacy resources. This study examines the creation and application of a novel eHealth literacy tool for home-based balance physiotherapy as part of the TeleRehaB DSS project. This tool evaluates patients' digital literacy, in particular their ability to use the Internet of Things (IoT), Augmented Reality (AR) and smart device technologies. The tool addresses the challenge of low treatment adherence by utilizing models to monitor compliance in real time and adjust treatment recommendations accordingly. The TeleRehaB DSS integrates this literacy tool to maximize resource allocation and improve patient engagement. Testing and validation has shown the system's ability to improve therapeutic outcomes and increase patient involvement. This strategy not only addresses the real-world difficulties of implementing digital health systems, but also advances the growing body of knowledge on improving treatment adherence through customized digital literacy assessments. When developing effective health technologies, the capabilities of users must be taken into account, especially for older people or those with limited digital literacy, as this study highlights.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1535582"},"PeriodicalIF":3.2,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12350259/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877048","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}

{"title":"The effects of internet self-health management on patients with chronic disease multimorbidity: a 4-year longitudinal study.","authors":"Yuyang Wang, Qiang Hu, Botian Chen, Defu Ma","doi":"10.3389/fdgth.2025.1568743","DOIUrl":"10.3389/fdgth.2025.1568743","url":null,"abstract":"<p><strong>Background: </strong>The escalating global burden of chronic diseases has given rise to a growing population affected by multimorbidity, defined as the co-occurrence of two or more chronic conditions. This health phenomenon is exacerbating disease burden through compounded clinical complications and increased healthcare demands. This study evaluates the effectiveness of internet-based self-health management in improving health behaviors and clinical indicators in patients with multimorbidity.</p><p><strong>Methods: </strong>A total of 30,745 adults aged ≥18 years from five northwestern Chinese provinces were enrolled. Following baseline data collection in 2013, participants received structured online health guidance covering diet nutrition, physical activity, and mental well-being. A follow-up assessment was conducted in 2017, involving questionnaire surveys and clinical measurements. Changes in health behaviors and clinical indicators of 2,535 patients with multimorbidity were analyzed. Binary logistic regression models were employed to identify factors influencing multimorbidity management outcomes.</p><p><strong>Results: </strong>The prevalence of multimorbidity at baseline in this study was 7.9%. After four years of health management, significant improvements were observed: smoking cessation rates increased from 8.2% to 10.2%, while low physical activity decreased from 29.0% to 24.6%. Both healthy individuals and multimorbid patients showed an increase in soybeans and nuts intake from 2013 to 2017. The fasting plasma glucose of the multimorbidity subjects decreased from 9.33 mmol/L in 2013 to 8.28 mmol/L in 2017, and the total cholesterol level decreased from 6.97 mmol/L to 6.26 mmol/L (<i>P</i> < 0.001). Significant reductions were also observed in triglycerides and low-density lipoprotein cholesterol levels (<i>P</i> < 0.001). The binary logistic regression results showed that being 40 years or older, male, having a family history of chronic diseases, changes in smoking status and sleep quality under health management guidance were influencing factors for effective control of multimorbidity.</p><p><strong>Conclusion: </strong>Internet-based self-health management effectively improves health behaviors and clinical indicators in patients with chronic disease multimorbidity.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1568743"},"PeriodicalIF":3.2,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12343493/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144849918","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}