Health Informatics Journal最新文献

Objectives: Complex diseases, like diabetic kidney disease (DKD), often exhibit heterogeneity, challenging accurate risk prediction with machine learning. Traditional global models ignore patient differences, and subgroup learning lacks interpretability and predictive efficiency. This study introduces the Interpretable Subgroup Learning-based Modeling (iSLIM) framework to address these issues.

Methods: iSLIM integrates expert knowledge with a tree-based recursive partitioning approach to identify DKD subgroups within an EHR dataset of 11,559 patients. It then constructs separate models for each subgroup, enhancing predictive accuracy while preserving interpretability.

Results: Five clinically relevant subgroups are identified, achieving an average sensitivity of 0.8074, outperforming a single global model by 0.1104. Post hoc analyses provide pathological and biological evidence supporting subgroup validity and potential DKD risk factors.

Conclusion: The iSLIM surpasses traditional global model in predictive performance and subgroup-specific risk factor interpretation, enhancing the understanding of DKD's heterogeneous mechanisms and potentially increasing the adoption of machine learning models in clinical decision-making.

Objectives: Online health communities (OHCs) facilitate patient-physician interaction and the adoption of online health services. However, few studies explored the impact of network effects on patients' continuance intentions in OHCs. This study aims to explore the determinants affecting OHC patients' continuance intentions based on the network effects theory and expectation confirmation model (ECM). Methods: An integrated research model and relative hypotheses are proposed. A total of 420 valid responses are collected through an online questionnaire survey to test the research framework using structural equation modeling. Results: The results reveal that direct network effect, cross network effect, and indirect network effect all positively affect perceived ease of use, and the latter two also positively affect perceived usefulness that further affect continuance intention. In addition, other results are consistent with the ECM-based hypotheses and the positive impact of perceived e-health literacy on continuance intention is also explained. Conclusion: Patients' continuance intention to use OHCs can be improved by network effects through direct, cross, and indirect formats. ECM-based determinants, including confirmation, perceived usefulness, and satisfaction, provide valuable insights for OHC patients' continuous use. Enhancing e-health literacy helps maintain patients' intention to continue using OHCs.

This study investigates the barriers to implementing electronic health records (EHR) systems for decision support in Tanzanian primary healthcare (PHC) facilities and proposes strategies to address these challenges. A qualitative, inductive approach was used, guided by the Diffusion of Innovations (DOI) theory, the Technology Acceptance Model (TAM), and the Sociotechnical Systems theory. Using snowball sampling, data were collected from 14 participants through semi-structured interviews in Dodoma, Tanzania. Thematic analysis identified key barriers. Critical barriers to EHR implementation include lack of leadership support, poor network infrastructure, increased workload, and resistance to technology due to concerns over professional autonomy. Technical challenges, such as system downtime and lack of skilled personnel, hinder EHR use, resulting in inefficiencies and incomplete system adoption, negatively affecting patient outcomes. This study offers unique insights into barriers to EHR adoption in Tanzanian PHC facilities. Grounded in multiple theoretical frameworks, the findings contribute to health informatics discourse in low-resource settings and provide practical recommendations for improving EHR implementation. The study's implications are relevant for policymakers, healthcare leaders, and IT developers in similar contexts.

Objectives: Dupuytren disease is a common condition that causes progressive finger contractures resulting in impaired hand function and difficulties in performing daily activities. Patient reported outcome measures (PROMs) are commonly used in research and clinical practice to evaluate treatment outcomes. Both general upper extremity PROMs and Dupuytren-specific PROMs are available, typically developed using conventional methodology based on classical test theory. However, most current PROMs have been shown to have low responsiveness and the relevance of included items have been questioned. In this study we aim to develop a new Dupuytren-specific PROM using modern measurement methodology based on item response theory (IRT). Methods: The study will be performed in three phases. In Phase 1, (completed), an expert group developed a questionnaire with a large number of potentially relevant items derived from existing PROMs and patient collaboration. In Phase 2, the questionnaire will be administered to 300 patients with Dupuytren disease, and their responses will be analyzed with IRT methodology to identify the best performing items to be included in the new PROM. In Phase 3, the new PROM will be administered to 300 additional patients for validation. Conclusion: This new Dupuytren-specific patient-reported outcome measure will help advance clinical research on Dupuytren disease.

Background: Healthcare Informatics leaders are the bridge between the information systems and clinical departments. The role has grown to where Health Informatics leaders analyze, design, develop, implement, and evaluate information and communication systems that enhance individual and population health outcomes, improve patient care, and strengthen the clinician-patient relationship. Their role spans across administration, information technology into the clinical realm. Objective: The primary objective of this study was to identify the past, current roles, and responsibilities of Health Informatics leaders while the secondary outcome was to identify the future trends in the responsibilities and roles. Methods: A thirteen-question survey was emailed to recipients through listservs. Results: Respondents cited their roles have evolve in respect to EMR to improve patient outcome and efficiency, overseeing compliance with federal and state regulations, design and customization of information technology systems, quality improvement management, healthcare data analytics (machine learning and artificial intelligence), population health management. Conclusion: The role of CMIO and healthcare informatics leaders have begun to be distinctly delineated, and their positions have had a tremendous impact on the integration of health information technology in healthcare. The role of the CMIO will continue to evolve as technology changes.

SAFE is a mobile application co-created for and by people who have experienced self-harm, either themselves or as next of kin. This study intended to integrate SAFE into an Emergency Department (ED) to help patients share experiences of self-harm and to support professionals in conducting treatment as usual (TAU). Objective: This study was a part of a Co-operative Inquiry in which a learning intervention was implemented, followed by an interview study exploring ED nurses' reflections and learnings while integrating SAFE into their practice. Methods: Thirteen semi-structured interviews were analysed using reflexive thematic analysis. Results: The nurses imagined that SAFE could be a positive game changer. However, they were hesitant due to uncertainty about the ED context, the value of the app and their skills. Conclusions: Supplying TAU with technology is challenging and future digital solutions must be created in partnership to ensure the solutions are customised to the target group.

Objective: To develop and test an NLP algorithm that accurately detects the presence of information reported from DXA scans containing femoral neck T-scores of the patients scanned. Methods: A rule-based NLP algorithm that iteratively built a collection of regular expressions in testing data consisting of 889 snippets of text pulled from DXA reports. This was manually checked by clinical experts to determine the proportion of manually verified annotations that contained T-score information detected by this algorithm called 'BoneScore'. Testing of 30- and 50-word lengths on each side of the key term 'femoral' were pursued until achievement of adequate accuracy. A separate clinical validation regressed the extracted T-score values on five risk factors with established associations. Results: BoneScore built a set of 20 regular expressions that in concert with a width of 50 words on each side of the key term yielded an accuracy of 98% in the testing data. The extracted T-scores, when modeled with multivariable linear regression, consistently exhibited associations supported by the literature. Conclusion: BoneScore uses regular expressions to accurately extract annotations of T-score values of bone mineral density with a width of 50 words on each side of the key term. The extracted T-scores exhibit clinical face validity.

Objectives: Continued use of a digital health assistant that helps patients living with diabetes to self-manage and deal with complex problems in order to enhance their health status is a healthcare priority. The objective was to explore the barriers related to the use of a mobile personal health assistant for patients with type 2 diabetes.

Methods: Eighty-one participants were offered a personal health assistant through a smartphone application. They completed a questionnaire after initial training (T₀) and after 1 month's experience (T₁).

Results and conclusion: Most had a positive behavioral intention before using it, but the opposite was found after 1 month. There were positive correlations between behavioral intention and the eight related factors. The strongest correlations were with satisfaction and perceived usefulness at T₀ and T₁, respectively. The factors' mean values decreased after 1 month. The best predictors of behavioral intention were satisfaction and performance expectancy at T₀ and T₁, respectively, which predicted the status of 88.4% and 82.7% of the sample. Our findings will help health experts to build better tools that satisfy patients and meet their expectations.

Objective: Integrating artificial intelligence (AI) solutions into clinical practice, particularly in the field of video capsule endoscopy (VCE), necessitates the execution of rigorous clinical studies. Methods: This work introduces a novel software platform tailored to facilitate the conduct of multi-reader multi-case clinical studies in VCE. The platform, developed as a web application, prioritizes remote accessibility to accommodate multi-center studies. Notably, considerable attention was devoted to user interface and user experience design elements to ensure a seamless and engaging interface. To evaluate the usability of the platform, a pilot study is conducted. Results: The results indicate a high level of usability and acceptance among users, providing valuable insights into the expectations and preferences of gastroenterologists navigating AI-driven VCE solutions. Conclusion: This research lays a foundation for future advancements in AI integration within clinical VCE practice.

Background: Children and young people with cancer face barriers when engaging with exercise, such as treatment-related side effects, psychosocial burdens and lack of individualised provisions. Digital health tools, such as smartphone applications, have emerged as a promising driver to support healthcare provisions in exercise prescription among patients. It is vital to explore how such technologies can be developed more effectively in order to strengthen the evidence supporting their use and for more appropriate implementation within healthcare. This study aims to explore user experiences, preferences and suggested improvements from healthy children and young people aged 9-21 years. Methods: An augmented reality (AR) application was specifically developed for children and young people aged 9-21 years undergoing cancer treatment and a protocol for a pilot study was designed. The target sample of this pilot study is 90 healthy children and young people aged 9-21 years. Practical 30-min workshops will be conducted encouraging participants to engage with the smartphone app. Focus groups will explore participant experiences, preferences, and suggested improvements. Data will be analysed deductively with apriori themes derived from the semi-structured interviews. Discussion: Obtaining user experiences, preferences and suggested improvements is especially important for the development of novel apps, such as those prescribing exercise and using algorithms and augmented reality software. Results from this study will directly influence the development of an augmented reality application, which will also be applied within a long-term trial in paediatric oncology.