DIGITAL HEALTH最新文献

Background: Switzerland's healthcare system is known for its quality but faces challenges such as slow digitalization and fragmentation, especially in perinatal care. This study investigates Swiss women's use, needs, and attitudes in respect of digital health tools during pregnancy and postpartum, focusing on any differences between rural and urban populations.

Methods: A web-based cross-sectional survey targeted pregnant women and those who had given birth in the last 12 months. Participants were recruited through social media, and the data were analyzed using principal component analysis and multivariable regressions to explore factors affecting the use of digital tools and attitudes toward eHealth.

Results: A total of 1160 participants completed the survey. Healthcare professionals (92%) and private networks (77%) were the primary sources of information. Women expressed a strong preference for app features such as data access (73%), prescription management (73%), and scheduling appointments with healthcare professionals (71%). However, they also raised concerns about the impersonal nature of digital healthcare interactions (71%). Overall, rural women had more negative attitudes toward online health information seeking, which can be attributed to differences in education levels.

Conclusion: The findings indicate that while Swiss women in the perinatal period do utilize digital tools, they focus more on nonmedical topics such as tracking physiological development. The study underscores the importance of adapting digital health solutions to the specific needs of women in the perinatal period. Emphasis should be placed on developing applications that are not only informative but also empower women on their healthcare journey while ensuring data privacy and supporting personal interactions with healthcare providers.

Objective: Given the complex nature of preterm birth, interventions to reduce rates of preterm birth should be multifaceted. This analysis aimed to explore the association between the duration of using Maven, a digital health platform for women's and family health, and the odds of preterm birth.

Methods: Data came from 3326 pregnant, nulliparous Maven users who enrolled in Maven during their pregnancy between January 2020 and September 2022. Chi-square and Fisher's exact tests compared characteristics between users who developed gestational conditions and users who did not. This retrospective cohort study used logistic regression models to estimate the association between the duration of Maven use and odds of preterm birth, stratified by the presence of gestational conditions.

Results: Compared to those without gestational conditions, individuals who developed gestational conditions were more likely to have a preterm birth (8.7% vs. 3.4%; p < 0.001). For every 1 h of Maven use, users experienced a 2% reduction in their odds of experiencing a preterm birth [adjusted odds ratio (AOR) (95% confidence interval (CI)) = 0.98 (0.95, 0.998), p = 0.04]. Among individuals who developed gestational conditions, every 1 h increase in Maven use was associated with a 5% reduction in the odds of experiencing a preterm birth [AOR (95% CI) = 0.95 (0.91, 0.99), p = 0.037]. There was no statistically significant association between Maven use and preterm birth in individuals without gestational conditions.

Conclusion: Among those who developed gestational conditions, use of a digital health platform was associated with a decreased likelihood of preterm birth.

Background and objective: The rapid development of computer technology has led to a revolutionary transformation in artificial intelligence (AI)-assisted healthcare. The integration of whole-slide imaging technology with AI algorithms has facilitated the development of digital pathology for lung cancer (LC). However, there is a lack of comprehensive scientometric analysis in this field.

Methods: A bibliometric analysis was conducted on 197 publications related to digital pathology in LC from 502 institutions across 39 countries, published in 97 academic journals in the Web of Science Core Collection between 2004 and 2023.

Results: Our analysis has identified the United States and China as the primary research nations in the field of digital pathology in LC. However, it is important to note that the current research primarily consists of independent studies among countries, emphasizing the necessity of strengthening academic collaboration and data sharing between nations. The current focus and challenge of research related to digital pathology in LC lie in enhancing the accuracy of classification and prediction through improved deep learning algorithms. The integration of multi-omics studies presents a promising future research direction. Additionally, researchers are increasingly exploring the application of digital pathology in immunotherapy for LC patients.

Conclusions: In conclusion, this study provides a comprehensive knowledge framework for digital pathology in LC, highlighting research trends, hotspots, and gaps in this field. It also provides a theoretical basis for the application of AI in clinical decision-making for LC patients.

Background: Digital testing services for sexually transmitted and blood-borne infections (STBBIs), such as GetCheckedOnline, experience significant user drop-offs. For example, 32% of GetCheckedOnline users needing testing at account creation do not test, constituting missed opportunities. We explored the influence of users' expectations and experiences of GetCheckedOnline's web design and implementation on missed opportunities.

Methods: This interpretive description purposively sampled 14 GetCheckedOnline users who created accounts between April 2022 and February 2023, indicated needed testing at account creation but did not test. We conducted semi-structured interviews and cognitive walkthroughs of GetCheckedOnline on Zoom, exploring participants' expectations and experiences, including problems using the service. Interviews were audio recorded, transcribed verbatim, and analyzed using reflexive thematic analyses.

Results: Three themes were identified: (a) transitioning between GetCheckedOnline and laboratory services is a major testing barrier; (b) users' appraisal of their health and social contexts is a determinant of testing through GetCheckedOnline; and (c) tailoring GetCheckedOnline's design and implementation to accommodate varying user needs can promote equitable testing. Health equity issues occurred along sociodemographic gradients as the GetCheckedOnline-laboratory transition was more onerous for older users. Users' appraisal of their testing needs which varied by age and gender, and their assessment of time, and travel requirements for testing in remote communities influenced testing. Learning about GetCheckedOnline from healthcare providers improved testing compared with learning about the service through Google search which raised trust concerns regarding GetCheckedOnline's authenticity. Suggested improvements to promote health equity include personalized education, mail-in testing options, and simpler seamless web experiences.

Conclusions: To promote equitable access to digital STBBI testing services such as GetCheckedOnline, we can adapt web-design and implementation to suit user needs and contexts, ensuring simplicity and options for testing that reduce user burdens.

Objective: Convolutional neural networks (CNNs) have achieved state-of-the-art results in various medical image segmentation tasks. However, CNNs often assume that the source and target dataset follow the same probability distribution and when this assumption is not satisfied their performance degrades significantly. This poses a limitation in medical image analysis, where including information from different imaging modalities can bring large clinical benefits. In this work, we present an unsupervised Structure Aware Cross-modality Domain Adaptation (StAC-DA) framework for medical image segmentation.

Methods: StAC-DA implements an image- and feature-level adaptation in a sequential two-step approach. The first step performs an image-level alignment, where images from the source domain are translated to the target domain in pixel space by implementing a CycleGAN-based model. The latter model includes a structure-aware network that preserves the shape of the anatomical structure during translation. The second step consists of a feature-level alignment. A U-Net network with deep supervision is trained with the transformed source domain images and target domain images in an adversarial manner to produce probable segmentations for the target domain.

Results: The framework is evaluated on bidirectional cardiac substructure segmentation. StAC-DA outperforms leading unsupervised domain adaptation approaches, being ranked first in the segmentation of the ascending aorta when adapting from Magnetic Resonance Imaging (MRI) to Computed Tomography (CT) domain and from CT to MRI domain.

Conclusions: The presented framework overcomes the limitations posed by differing distributions in training and testing datasets. Moreover, the experimental results highlight its potential to improve the accuracy of medical image segmentation across diverse imaging modalities.

Objective: Readmission to the coronary care unit (CCU) has significant implications for patient outcomes and healthcare expenditure, emphasizing the urgency to accurately identify patients at high readmission risk. This study aims to construct and externally validate a predictive model for CCU readmission using machine learning (ML) algorithms across multiple hospitals.

Methods: Patient information, including demographics, medical history, and laboratory test results were collected from electronic health record system and contributed to a total of 40 features. Five ML models: logistic regression, random forest, support vector machine, gradient boosting, and multilayer perceptron were employed to estimate the readmission risk.

Results: The gradient boosting model was selected demonstrated superior performance with an area under the receiver operating characteristic curve (AUC) of 0.887 in the internal validation set. Further external validation in hold-out test set and three other medical centers upheld the model's robustness with consistent high AUCs, ranging from 0.852 to 0.879.

Conclusion: The results endorse the integration of ML algorithms in healthcare to enhance patient risk stratification, potentially optimizing clinical interventions, and diminishing the burden of CCU readmissions.

Background: Levodopa-carbidopa intestinal gel (LCIG) is a continuously delivered Parkinson's disease therapy intended to stabilize plasma levodopa levels. Patients receiving LCIG require education and follow-up. Some LCIG support programs use video-assisted telenursing.

Objective: To examine how videoconferencing impacts satisfaction with LCIG support programs.

Methods: FACILITATE CARE (Feasibility of video-Assisted Care for Intestinal Levodopa Infusion with Telenursing - observAtional Trial Evaluating patient and Caregiver Acceptance in REal life) was a 12-week, prospective, open-label, 2-arm, parallel-group, observational study assessing satisfaction with LCIG support in patients who self-assigned to video or audio-only arms. Patients aged 18-85 years had completed LCIG titration and owned a videoconferencing device (video arm only). A visual analog scale measured satisfaction (1-10, 10 being most satisfied).

Results: Patients' mean (standard deviation) ages were 67.9 (7.4, n = 26) and 71.1 (6.2, n = 15) years in the video and audio arms, respectively. Patients, caregivers, and physicians in both groups reported satisfaction scores of 8-10 with LCIG support personnel, communication access, and assistance with becoming independent. At week 12, the Modified Caregiver Strain Index least square means change from baseline was lower in the video vs. audio arm (-2.3 [1.0] vs. 1.6 [1.2]). LCIG support personnel travel time was lower in the video vs. audio arm (125.7 [70.2] vs. 203.0 [70.0] minutes).

Conclusions: LCIG support programs are associated with high patient, caregiver, and physician satisfaction; video and audioconferencing satisfaction are similarly high. Video-assisted telenursing may be a convenient communication avenue and may reduce caregiver burden.

Registration: ClinicalTrials.gov; NCT04500106.

Background: Within the rapidly evolving healthcare landscape in Japan, digital marketing innovations are transforming pharmaceutical and medical device marketing. This study explores the emergence of new business models in the digital marketing, highlighting a transition from traditional methods to more dynamic, data-driven strategies.

Methods: InsighTCROSS^® is a business model that qualitatively and quantitatively examines three steps based on stratified persona images: (1) verifying the effectiveness of product marketing promotions, (2) identifying competitors from the users' perspective, and (3) developing marketing strategies to counter competition. To demonstrate the effectiveness of this model, a case study was conducted focusing on the current anticoagulant drugs, including apixaban, dabigatran, edoxaban, rivaroxaban, and warfarin.

Results: Rivaroxaban, the only drug prescribed for the prevention of thrombus and embolism formation in patients with peripheral artery disease after lower limb revascularization, garnered the most interest from interventional cardiologists performing peripheral vascular interventions, as determined by InsighTCROSS^® factor analysis, confirming that the manufacturer's marketing activities have effectively penetrated the market. A survey conducted between 20 September 2023 and 3 October 2023, among members of a cardiology website, identified edoxaban as the market leader with a 39.1% share, followed by apixaban (32.7%) and rivaroxaban (16.8%). The main competitor of edoxaban was warfarin, whereas that of rivaroxaban was apixaban. Decision tree analysis was conducted using InsighTCROSS^®, highlighting the strengths and weaknesses of each anticoagulant, providing strategic approaches to exploit competitive weaknesses. For edoxaban, increased use was driven by elderly and poorly adherent patients; for apixaban, high-volume percutaneous coronary intervention centers; and for rivaroxaban, the influence of medical representative detailing. It is recommended to avoid markets where these drugs have a strong presence and to focus marketing activities on leveraging their specific strengths.

Conclusion: The findings suggest that digital marketing enhances product visibility and patient engagement, providing valuable insights into market behavior and consumer preferences.

Purpose: Breast cancer, the most common cancer in women globally, highlights the need for patient education. Despite many breast cancer discussions on TikTok, their scientific evaluation is lacking. Our study seeks to assess the content quality and accuracy of popular TikTok videos on breast cancer, to improve the dissemination of health knowledge.

Methods: On August 22, 2023, we collected the top 100 trending videos from TikTok's Chinese version using "breast cancer/breast nodule" as keywords. We noted their length, TikTok duration, likes, comments, favorites, reposts, uploader types, and topics. Four assessment tools were used: Goobie's six questions, the Patient Educational Material Assessment Tool (PEMAT), the Video Information and Quality Index (VIQI), and the Global Quality Score (GQS). These instruments evaluate videos based on content, informational integrity, and overall quality.

Results: Among the 100 videos, content quality was low with Goobie's questions mostly scoring 0, except for management at 1.0 (QR 1.0). PEMAT scores were moderate: 54.1 (QR 1.6) for sum, 47.0 (QR 18.8) for PEMAT-A, and 52.3 (QR 11.7) for PEMAT-U. Regarding the quality of information, the VIQI (sum) median was 14.1 (QR 0.2). Additionally, the median GQS score was 3.5 (QR 0.1). Medical professionals' videos focused on breast cancer stages, while patient videos centered on personal experiences. Patient videos had lower content and overall quality compared to those by medical professionals (PEMAT, GQS: P < 0.001, P = 0.004) but received more comments, indicating higher engagement (all P < 0.05).

Conclusion: TikTok's breast cancer content shows educational potential, but while informational quality is moderate, content quality needs improvement. Videos by medical professionals are of higher quality. We recommend increased involvement of healthcare professionals on TikTok to enhance content quality. Non-medical users should share verified information, and TikTok should strengthen its content vetting. Users must scrutinize the credibility of health information on social platforms.

Objective: The internet has become a preferred source for people seeking health information, including diet recommendations which are pivotal in the management of inflammatory bowel disease (IBD). Hence, we aimed to assess the quality of online information in China regarding IBD dietary recommendations.

Methods: The search engines Baidu and Bing were used to screen for their top 25 webpages using the keywords "inflammatory bowel disease diet," "ulcerative colitis diet," "Crohn's disease diet," "inflammatory bowel disease nutrition," "ulcerative colitis nutrition," and "Crohn's disease nutrition." The quality of information was assessed by two physicians according to the Journal of the American Medical Association (JAMA) benchmark, the Global Quality Score (GQS), and the DISCERN instrument.

Results: One hundred and eight webpages were selected for evaluation. The mean scores for JAMA, GQS, and DISCERN were 1.48, 3.11, and 36.20, respectively. Articles from professionals and non-profit organizations demonstrated superior quality compared to those from commercial and health portal websites. Many webpages failed to provide an explicit source of information or support for shared decision-making. The information on several pages lacked comprehensive descriptions of food types for IBD, with some pages even containing inaccuracies. No statistically significant differences in scores were observed between Baidu and Bing.

Conclusions: The quality of online information on IBD dietary recommendations in China is moderate to low and exhibits significant variation across different sources. This warrants joint efforts from online authors, internet platforms, and regulators, to improve the quality of popular medical information.