Health Informatics Journal最新文献

Objective: The aim of this study was to evaluate and compare the impressions of older adults with mild dementia/MCI (mild cognitive impairment) and people with schizophrenia towards the usability of GRADIOR (version 4.5) and their user experience (UX) with this computerized cognitive rehabilitation program.

Methods: The impressions towards the usability of GRADIOR and the UX of 41 older adults with mild dementia/MCI and 41 people with schizophrenia were obtained using the User Experience Questionnaire.

Results: Older adults with dementia/MCI had more positive impressions than people with schizophrenia. Both agreed that its quality was lower in Dependability.

Conclusion: GRADIOR meets users' needs and preferences but needs improvements to ensure they feel more in control when interacting with it. For people with schizophrenia, other aspects of usability and UX need improvement. Usability and UX evaluation allow the verification of technological acceptability and functionality, and to identifying specific improvements for each user group.

Research indicates that recording medical consultations benefits patients by helping them recall information pertinent to their care. Cancer Care Alberta set out to develop a mobile recording app to enable patients to safely and securely record appointments and take notes. Stakeholder engagement was conducted with patients, healthcare providers, and the Alberta Health Services Legal & Privacy team. App testing was completed with patient and family advisors. The app was piloted in a clinic to assess workflow impacts before moving to a public launch. The app launched in late November 2018 and continues to be used by patients in the cancer program and beyond. Earlier in 2024, the app underwent additional testing with advisors and user-friendly improvements were made based on feedback and previous user reviews. This article summarizes the development, implementation, and sustainment of the My Care Conversations app. Implementation challenges and effective strategies are highlighted.

Objective: A large number of people with obstructive sleep apnea (OSA) also suffer from major depressive disorder (MDD), leading to underdiagnosis due to overlapping symptoms. Polysomnography has been considered to identify MDD. However, limited access to sleep clinics makes this challenging. In this study, we propose a model to detect MDD in people with OSA using an electrocardiogram (ECG) during sleep. Methods: The single-lead ECG data of 32 people with OSA (OSAD-) and 23 with OSA and MDD (OSAD+) were investigated. The first 60 min of their recordings after sleep were segmented into 30-s segments and 13 parameters were extracted: PR, QT, ST, QRS, PP, and RR; mean heart rate; two time-domain HRV parameters: SDNN, RMSSD; and four frequency heart rate variability parameters: LF_power, HF_power, total power, and the ratio of LF_power/HF_power. The mean and standard deviation of these parameters were the input to a support vector machine which was trained to separate OSAD- and OSAD+. Results: The proposed model distinguished between OSAD+ and OSAD- groups with an accuracy of 78.18%, a sensitivity of 73.91%, a specificity of 81.25%, and a precision of 73.91%. Conclusion: This study shows the potential of using only ECG for detecting depression in OSA patients.

Objective: Despite the documented beneficial effects of computerized physician order entry (CPOE) systems and despite numerous incentives for their adoption in various countries around the globe implementation teams encounter unexpected difficulties when launching CPOE systems. This survey aimed at gathering users' opinions on CPOE implementation. Additional factors that can be influenced by CPOE implementation were equally considered, namely workplace satisfaction, interprofessional collaboration, patient safety climate, system usability, and organisational readiness to implement change. Methods: We performed a mixed-mode survey at a tertiary care university hospital that introduced a commercial CPOE system. The survey consisted of validated questionnaires, self-developed, and socio-demographic questions. It was distributed both before and after CPOE implementation. Answers were descriptively analysed, compared between time-points, and assessed in relation to socio-demographic characteristics. Results: Users showed very diverse and only cautiously optimistic opinions towards CPOE implementation, which remained mainly unchanged during the post-survey. Respondents rated the system usability, organisational readiness for implementing change, and patient safety climate rather poorly, while workplace satisfaction and interprofessional collaboration were rated positively. Conclusion: This survey contributes to understanding user perspectives by providing valuable insights into user opinions before and after CPOE implementation, taking into account a range of associated factors.

Objective: The current study aims to understand how Apple Watch helped users maintain wellness routines during the COVID-19 lockdown period, where access to public gyms and spaces was curtailed. We explore the effectiveness of biofeedback engagement aspects of Apple Watch: goals, alerts and notifications, and sociability aspects of the device or social interaction with other users. Methods: We report the results of a 2-week digital diary study based in the United States with 10 adults with 6 months or longer exposure to Apple Watch, followed by online survey responses gathered from 330 additional users. Results: The study findings show how Apple Watch transforms notifications from distractions into positive wellness tools. Data suggests that personal context (custom goals and supported intent) combined with motivational nudges from alerts and notifications as well as contextually triggered nudges contribute to Apple Watch user adoption and satisfaction. Conclusion: This study highlights how Apple Watch transforms notifications from distractions into positive wellness tools; emphasizing the importance of balancing nudging with customization with user control. Sociability and privacy remain crucial, especially with biofeedback-enabled fitness trackers. We conclude that Apple Watch enhances user engagement by triggering context-relevant interactions, nudging users to achieve their goals through small, motivated behaviors.

Objective: The Internet of Medical Things (IoMT) is transforming healthcare systems, but concerns about device integrity and sensitive data are growing. The study aims to develop a framework for evaluating and prioritizing integrity schemes in healthcare for IoT-based medical sensor devices, addressing the challenges of selecting the right authentication solution due to its complexity and intricacy. Methods: A unified health-hesitant fuzzy expert system for IoMT sensor integrity assessment in Saudi Arabia is described in this paper. Medical sensor integrity literature and professionals are contacted first. Delphi is used to gather attributes of integrity approaches while an Internet of Things medical sensor integrity specialist supervises the operation. After collecting characteristics, good assessment criteria are created and the hesitant fuzzy analytic network procedure is used to assess integrity. Results: Functional integrity and measurement accuracy are the biggest factors in IoMT sensor security and integrity, according to assessment. The framework achieves 93%, 94%, and 95% precision, accuracy, and recall compared to current approaches. The framework helps healthcare integrity security professionals and stakeholders assess and resolve IoT medical sensor authentication issues. Conclusion: This health-hesitant fuzzy expert system will let Saudi Arabian and international healthcare stakeholders safely deploy IoMT sensors in the changing healthcare landscape.

Objective: Faced with the challenges of differential diagnosis caused by the complex clinical manifestations and high pathological heterogeneity of pituitary adenomas, this study aims to construct a high-quality annotated corpus to characterize pituitary adenomas in clinical notes containing rich diagnosis and treatment information. Methods: A dataset from a pituitary adenomas neurosurgery treatment center of a tertiary first-class hospital in China was retrospectively collected. A semi-automatic corpus construction framework was designed. A total of 2000 documents containing 9430 sentences and 524,232 words were annotated, and the text corpus of pituitary adenomas (TCPA) was constructed and analyzed. Its potential application in large language models (LLMs) was explored through fine-tuning and prompting experiments. Results: TCPA had 4782 medical entities and 28,998 tokens, achieving good quality with the inter-annotator agreement value of 0.862-0.986. The LLMs experiments showed that TCPA can be used to automatically identify clinical information from free texts, and introducing instances with clinical characteristics can effectively reduce the need for training data, thereby reducing labor costs. Conclusion: This study characterized pituitary adenomas in clinical notes, and the proposed method were able to serve as references for relevant research in medical natural language scenarios with highly specialized language structure and terminology.

Objectives: Our study analyzed dental nurses' use and use behavior determinants of electronic patient IS modules in telephone triage. The modules were implemented in public oral healthcare organizations' patient ISs to digitalize the national waiting time monitoring system.

Methods: For the cross-sectional survey, we collected data from dental nurses using convenience sampling and applied a modified UTAUT as the theoretical framework.

Results: The results indicate that using the module for different purposes varied, and the nurses used it sparsely in recording data for monitoring national waiting times. Using the module was laborious, and triage work was busy.

Conclusion: Dental nurses' low system usage resulted in poor-quality data for waiting time monitoring. As healthcare data is increasingly used for purposes other than clinical decision making, we must ensure that healthcare professionals performing clinical tasks perceive data recording for non-clinical purposes as meaningful and have time for proper data entry.

Objectives: Smartphone apps can be highly effective in supporting young people experiencing mood disorders, but an appealing visual design is a key predictor of engagement with such apps. However, there has been little research about the interaction between visual design, mood and wellbeing in young people using a mental health app. This study aimed to explore young people's perspectives on colour and visual design in the development of a music-based app for mood management. Methods: Workshops were conducted with 24 participants (aged 13-25 years) with data analysis following a general inductive approach. Results: Results indicated that colour could impact wellbeing in both positive and negative ways. Participants favoured a subtle use of colour within sophisticated, dark palettes and were influenced by a complex interplay of common semiotic values, experiences with other apps, and mood. Conclusions: These findings highlight the highly contextual nature of the relationship between colour and mood, emphasising the importance of co-design in app development.

Objective: We analyzed a natural language processing (NLP) toolkit's ability to classify unstructured EHR data by psychiatric diagnosis. Expertise can be a barrier to using NLP. We employed an NLP toolkit (CLARK) created to support studies led by investigators with a range of informatics knowledge. Methods: The EHR of 652 patients were manually reviewed to establish Depression and Substance Use Disorder (SUD) labeled datasets, which were split into training and evaluation datasets. We used CLARK to train depression and SUD classification models using training datasets; model performance was analyzed against evaluation datasets. Results: The depression model accurately classified 69% of records (sensitivity = 0.68, specificity = 0.70, F1 = 0.68). The SUD model accurately classified 84% of records (sensitivity = 0.56, specificity = 0.92, F1 = 0.57). Conclusion: The depression model performed a more balanced job, while the SUD model's high specificity was paired with a low sensitivity. NLP applications may be especially helpful when combined with a confidence threshold for manual review.