BMC digital health最新文献

{"title":"Machine learning-based prediction of COVID-19 mortality using immunological and metabolic biomarkers.","authors":"Thomas Wetere Tulu, Tsz Kin Wan, Ching Long Chan, Chun Hei Wu, Peter Yat Ming Woo, Cee Zhung Steven Tseng, Asmir Vodencarevic, Cristina Menni, Kei Hang Katie Chan","doi":"10.1186/s44247-022-00001-0","DOIUrl":"10.1186/s44247-022-00001-0","url":null,"abstract":"<p><p><b>COVID-19 mortality prediction</b> <b>Background</b> COVID-19 has become a major global public health problem, despite prevention and efforts. The daily number of COVID-19 cases rapidly increases, and the time and financial costs associated with testing procedure are burdensome. <b>Method</b> To overcome this, we aim to identify immunological and metabolic biomarkers to predict COVID-19 mortality using a machine learning model. We included inpatients from Hong Kong's public hospitals between January 1, and September 30, 2020, who were diagnosed with COVID-19 using RT-PCR. We developed three machine learning models to predict the mortality of COVID-19 patients based on data in their electronic medical records. We performed statistical analysis to compare the trained machine learning models which are Deep Neural Networks (DNN), Random Forest Classifier (RF) and Support Vector Machine (SVM) using data from a cohort of 5,059 patients (median age = 46 years; 49.3% male) who had tested positive for COVID-19 based on electronic health records and data from 532,427 patients as controls. <b>Result</b> We identified top 20 immunological and metabolic biomarkers that can accurately predict the risk of mortality from COVID-19 with ROC-AUC of 0.98 (95% CI 0.96-0.98). Of the three models used, our result demonstrate that the random forest (RF) model achieved the most accurate prediction of mortality among COVID-19 patients with age, glomerular filtration, albumin, urea, procalcitonin, c-reactive protein, oxygen, bicarbonate, carbon dioxide, ferritin, glucose, erythrocytes, creatinine, lymphocytes, PH of blood and leukocytes among the most important biomarkers identified. A cohort from Kwong Wah Hospital (131 patients) was used for model validation with ROC-AUC of 0.90 (95% CI 0.84-0.92). <b>Conclusion</b> We recommend physicians closely monitor hematological, coagulation, cardiac, hepatic, renal and inflammatory factors for potential progression to severe conditions among COVID-19 patients. To the best of our knowledge, no previous research has identified important immunological and metabolic biomarkers to the extent demonstrated in our study.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1186/s44247-022-00001-0.</p>","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":" ","pages":"6"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9896457/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45453724","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":"Acceptability and feasibility of a mobile health application for enhancing public private mix for TB care among healthcare Workers in Southwestern Uganda.","authors":"Wilson Tumuhimbise, Daniel Atwine, Fred Kaggwa, Angella Musiimenta","doi":"10.1186/s44247-023-00009-0","DOIUrl":"10.1186/s44247-023-00009-0","url":null,"abstract":"<p><strong>Background: </strong>Mobile health interventions can potentially enhance public-private linkage for tuberculosis care. However, evidence about their acceptability and feasibility is lacking. This study sought to assess the initial acceptability and feasibility of a mobile health application for following up on presumptive tuberculosis patients referred from private to public hospitals. Twenty-two healthcare workers from three private hospitals and a public hospital in southwestern Uganda received the Tuuka mobile application for 1 month for testing. Testing focused on referring patients by healthcare workers from private hospitals and receiving referred patients by public healthcare workers and sending SMS reminders to the referred patients by filling out the digital referral forms inbuilt within the app. Study participants participated in qualitative semi-structured in-depth interviews on the acceptability and feasibility of this app. An inductive, content analytic approach, framed by the unified theory of acceptance and use of technology model, was used to analyze qualitative data. Quantitative feasibility metrics and the quantitative assessment of acceptability were analyzed descriptively using STATA.</p><p><strong>Results: </strong>Healthcare workers found the Tuuka application acceptable and feasible, with a mean total system usability scale score of 98 (SD 1.97). The majority believed that the app would help them make quicker medical decisions (91%), communicate with other healthcare workers (96%), facilitate partnerships with other hospitals (100%), and enhance quick TB case notification (96%). The application was perceived to be useful in reminding referred patients to adhere to referral appointments, notifying public hospital healthcare workers about the incoming referred patients, facilitating communication across facilities, and enhancing patient-based care.</p><p><strong>Conclusion: </strong>The Tuuka mobile health application is acceptable and feasible for following up on referred presumptive tuberculosis patients referred from private to public hospitals in southwestern Uganda. Future efforts should focus on incorporating incentives to motivate and enable sustained use among healthcare workers.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1186/s44247-023-00009-0.</p>","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":" ","pages":"9"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9982777/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45221681","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":"Non-inferiority of a hybrid outpatient rehabilitation: a randomized controlled trial (HIRE, DRKS00028770).","authors":"Richard Albers, Stella Lemke, Sebastian Knapp, Gert Krischak, Matthias Bethge","doi":"10.1186/s44247-023-00013-4","DOIUrl":"10.1186/s44247-023-00013-4","url":null,"abstract":"<p><strong>Background: </strong>Physiotherapeutic telerehabilitation in various musculoskeletal and internal diseases, including back pain, might be comparable to face-to-face rehabilitation or better than non-rehabilitation. In Germany, a standardized back school for patients with chronic back pain is provided in outpatient rehabilitation centers. The effectiveness of this standardized back school was shown in a randomized controlled trial in face-to-face rehabilitation. This study examines non-inferiority of a hybrid rehabilitation applying a digital version of the standardized back school against a rehabilitation applying the face-to-face back school.</p><p><strong>Methods/design: </strong>We recruit 320 patients in eight German outpatient rehabilitation centers. Patients are randomized equally to the intervention and control groups. Patients aged 18 to 65 years with back pain are included. Patients lacking a suitable private electronic device and German language skills are excluded. Both groups receive the standardized back school as part of the 3-week rehabilitation program. The control group receives the back school conventionally in face-to-face meetings within the outpatient rehabilitation center. The intervention group receives the back school online using a private electronic device. Besides the back school, the patients participate in rehabilitation programs according to the German rehabilitation guideline for patients with chronic back pain. Hence, the term \"hybrid\" rehabilitation for the intervention group is used. The back school consists of seven modules. We assess data at four time points: start of rehabilitation, end of rehabilitation, 3 months after the end of rehabilitation and, 12 months after the end of rehabilitation. The primary outcome is pain self-efficacy. Secondary outcomes are, amongst others, motivational self-efficacy, cognitive and behavioral pain management, and disorder and treatment knowledge. Guided interviews with patients, physicians, physiotherapists and other health experts supplement our study with qualitative data.</p><p><strong>Discussion/aim: </strong>Our randomized controlled trial aims to demonstrate non-inferiority of the online back school, compared to conventional implementation of the back school.</p><p><strong>Trial registration: </strong>German Clinical Trials Register (DRKS00028770, April 05, 2022).</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1186/s44247-023-00013-4.</p>","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":" ","pages":"15"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10125254/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45972639","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":"Mobile applications in the Philippines during the COVID-19 pandemic: systematic search, use case mapping, and quality assessment using the Mobile App Rating Scale (MARS).","authors":"Aldren Gonzales, Razel Custodio, Marie Carmela Lapitan, Mary Ann Ladia","doi":"10.1186/s44247-023-00007-2","DOIUrl":"10.1186/s44247-023-00007-2","url":null,"abstract":"<p><strong>Background: </strong>In the Philippines, various mobile health apps were implemented during the COVID-19 pandemic with very little knowledge in terms of their quality. The aims of this paper were 1) to systemically search for mobile apps with COVID-19 pandemic use case that are implemented in the Philippines; 2) to assess the apps using Mobile App Rating Scale (MARS); and 3) to identify the critical points for future improvements of these apps.</p><p><strong>Methods: </strong>To identify existing mobile applications with COVID-19 pandemic use case employed in the Philippines, Google Play and Apple App Stores were systematically searched. Further search was conducted using the Google Search. Data were extracted from the app web store profile and apps were categorized according to use cases. Mobile apps that met the inclusion criteria were independently assessed and scored by two researchers using the MARS-a 23-item, expert-based rating scale for assessing the quality of mHealth applications.</p><p><strong>Results: </strong>A total of 27 apps were identified and assessed using MARS. The majority of the apps are designed for managing exposure to COVID-19 and for promoting health monitoring. The overall MARS score of all the apps is 3.62 points (SD 0.7), with a maximum score of 4.7 for an app used for telehealth and a minimum of 2.3 for a COVID-19 health declaration app. The majority (<i>n</i> = 19, 70%) of the apps are equal to or exceeded the minimum \"acceptable\" MARS score of 3.0. Looking at the categories, the apps for raising awareness received the highest MARS score of 4.58 (SD 0.03) while those designed for managing exposure to COVID-19 received the lowest mean score of 3.06 (SD 0.6).</p><p><strong>Conclusions: </strong>There is a heterogenous quality of mHealth apps implemented during the COVID-19 pandemic in the Philippines. The study also identified areas to better improve the tools. Considering that mHealth is expected to be an integral part of the healthcare system post-pandemic, the results warrant better policies and guidance in the development and implementation to ensure quality across the board and as a result, positively impact health outcomes.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1186/s44247-023-00007-2.</p>","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":" ","pages":"8"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9985954/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44240935","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":"Telehealth in long-term care facilities during the Covid-19 pandemic - Lessons learned from patients, physicians, nurses and healthcare workers.","authors":"Zhaoli Dai","doi":"10.1186/s44247-022-00003-y","DOIUrl":"10.1186/s44247-022-00003-y","url":null,"abstract":"<p><strong>Background: </strong>Telehealth and telecare are particularly important and beneficial to long-term care facilities due to care demands, workforce, and the unique environment. Stemming from the recent findings on telehealth utilisation in residential aged-care facilities in Australia, this commentary seeks to identify lessons and perspectives learned during the Covid-19 pandemic from multiple users, including patients, physicians, nurses, and healthcare workers in long-term care (LTC) settings.</p><p><strong>Main body: </strong>From patients' perspectives, older adults residing in LTC settings often opt not to use virtual care, with the majority preferring in-person visits. This is despite residents expressing their willingness to use telehealth, and virtual care has advantages in LTC settings or in remote areas. Additionally, hearing, vision, or cognitive impairment can limit residents' ability to use information technology to access care, so their preferences for phone or video consultations depend on the health conditions or care requirement. From physicians' perspectives, most healthcare practitioners have a positive attitude toward using telehealth. However, telephone consultations tended to be the dominant mode during the early period of the Covid-19 pandemic. Physicians also raised several major concerns, including technical and equipment-related issues, expanded roles, or additional workloads of LTC staff that could negatively affect clinical decision-making and unequal access in rural, older, and cognitively impaired patients. Most nurses and healthcare workers perceived telehealth positively as a way to enhance patients' care access. However, the majority had concerns about acquiring appropriate knowledge of using the technology for themselves and their patients. In remote areas, nurses expressed higher efficiency and higher care quality when utilising telehealth in caring for older patients than in the regular in-person care mode.</p><p><strong>Conclusion: </strong>Since the beginning of the Covid-19 pandemic, telehealth has continued as an alternative platform in clinical services. However, as a healthcare platform that offers flexibilities of time, location, and improved efficiency, changing the traditional mindset is essential to shift the paradigm to use telehealth when appropriate. Importantly, telehealth needs substantial support in rural or remote long-term care facilities. Doing so will contribute to the reduction of healthcare inequity in long-term care facilities in remote settings and those with social disparities.</p>","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":" ","pages":"2"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9872077/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47031300","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}