Health Informatics Journal最新文献

Introduction: Emerging technologies, particularly artificial intelligence (AI), offer the potential to personalize healthcare for pediatric developmental disorders, but their development presents challenges. Methods: This study introduces IVORY, a mobile AI platform for managing personal health records (PHRs) in children with developmental disorders. IVORY integrates advanced optical character recognition (OCR)-based text recognition models optimized for diverse medical document types and template-matching algorithms, ensuring standardized data processing. The primary features include digitizing medical records, symptom interpretation, and AI-driven health recommendations. Results: Using pretrained OCR algorithms with 126 diverse medical report types, the platform achieved an OCR success rate of 81%. Input data include fMRI interpretations, psychological assessments, and laboratory findings, whereas outputs offer percentile-based insights and treatment recommendations. Caregivers (3.44 ± 0.67) and professionals (3.50 ± 0.63) highly rated the platform for usability. Conclusions: Despite OCR limitations for low-resolution data, IVORY has the potential to enhance data consolidation, accuracy, and scalability in personalized pediatric healthcare.

Objective: Smart healthcare devices provide essential support for elderly health management, yet adoption barriers remain. This study investigates how technology readiness influences intention to use smart healthcare devices among Chinese seniors through technology interactivity, moderated by subjective norms. Methods: A cross-sectional survey involving 552 older participants from Wuxi, China, was analyzed using multiple linear regression and moderated mediation models. Results: The results showed that technology readiness significantly predicted usage intention and was fully mediated by technology interactivity. Subjective norms moderated the relationship between technology interactivity and usage intention, strengthening the indirect effect of technology readiness when subjective norms were high. Conclusion: The findings underscore the crucial role of technology interactivity in linking technology readiness to adoption, while subjective norms further reinforce this mechanism. To promote the adoption of smart healthcare devices, interventions should focus on enhancing technological literacy, fostering interactive user experiences, and leveraging community-driven social support. These findings contribute to resource conservation theory and provide policy insights to reduce digital disparities among aging populations.

This study aims to explore patient perceptions and interactions with virtual consultation (VC) systems to understand the factors influencing their adoption and satisfaction. We analyzed 21,839 patient reviews from four major virtual consultation platforms-MDLive, Doctor on Demand, Maple, and HealthTap-collected from publicly accessible sources. Sentiment analysis, word frequency analysis, topic modeling using Latent Dirichlet Allocation (LDA), and association rule mining were used to extract insights. The findings reveal a generally positive sentiment among patients, with recurring themes focusing on app functionality and the important role of doctors in the virtual consultation experience. Virtual consultation systems were found to play a dual role: as a communicator during initial interactions and as a medium facilitating patient-doctor communication. The analysis also identified key doctor-related factors, categorized by the Theory of Planned Behavior, including attitudes (e.g., empathy), subjective norms (e.g., cultural competence), and perceived behavioral control (e.g., time management). The study provides valuable insights for enhancing healthcare system design and improving virtual consultation quality. However, limitations include potential bias in patient reviews, limited platform focus, and the lack of demographic data. Future research should explore advanced machine learning techniques and investigate relationships between different factors to improve virtual healthcare.

Objective: This study aimed to evaluate the presentation suitability and readability of ChatGPT's responses to common patient questions, as well as its potential to enhance readability. Methods: We initially analyzed 30 ChatGPT responses related to knee osteoarthritis (OA) on March 20, 2023, using readability and presentation suitability metrics. Subsequently, we assessed the impact of detailed and simplified instructions provided to ChatGPT for same responses, focusing on readability improvement. Results: The readability scores for responses related to knee OA significantly exceeded the recommended sixth-grade reading level (p < .001). While the presentation of information was rated as "adequate," the content lacked high-quality, reliable details. After the intervention, readability improved slightly for responses related to knee OA; however, there was no significant difference in readability between the groups receiving detailed versus simplified instructions. Conclusions: Although ChatGPT provides informative responses, they are often difficult to read and lack sufficient quality. Current capabilities do not effectively simplify medical information for the general public. Technological advancements are needed to improve user-friendliness and practical utility.

Background: Uniform interpretation of digital health messages is important to achieve semantic interoperability of electronic health information systems (eHIS). Whereas international digital health terminologies such as ICD, LOINC and SNOMED-CT exist, their design considerations regarding health processes, data collected, and technologies, among others do not necessarily match Uganda's eHIS contextual needs. Objective: This research aimed to design a process that could be used to contextualise international digital health terminologies for Uganda's eHIS. Methods: The Design Science approach was used in designing the contextualisation process while utilising a foundation contextualisation approach for mapping terminologies. Results: The contextualisation process constitutes six major phases; assessing the national digital health information system context, extracting data elements in the national digital health information system, mapping existing national data elements to international terminologies, identifying and coding unmatched data elements, validating contextualised terminologies and digitising the validated terminologies. The terminology standards contextualisation process was validated using the Delphi technique and the HIV Information Management Services use case. The validation results showed that the contextualisation process was relevant, usable, adaptable and interoperable to Uganda's eHIS. Conclusion: Accordingly, this study demonstrated how international digital health terminologies could be contextualised for Uganda's health information systems. The contextualisation process could also be applied to other disease information management services in Uganda.

Many online health information sources are generic and difficult to understand, but consumers want information to be personalized and understandable. Smartphone health applications (apps) offer personalized information to support health goals and reduce preventable chronic conditions. This study aimed to determine how the HealthyMe/MiSalud personalized app (1) engaged English-speaking African American and Spanish-speaking Hispanic adults, and (2) motivated them to set goals and follow preventive recommendations. Our study adds to the literature on digital health, health information seeking, and prevention. We used a multi-method approach, including community and participatory design principles, to learn about potential African American and Hispanic adult health app users and evaluate the app in two usability tests and a 12-month field test. Ninety-six African American and Hispanic adults downloaded the HealthyMe/MiSalud app and used it for a minimum of 36 weeks. We found they wanted personalized information on core prevention topics, and their health histories and goals affected how they rated topic relevance. African American females ages 18-34 were more likely to save an article aligned with family health history, and African American females aged 35-49, males age 50-64, and African American males overall were more likely to save an article aligned with their health goals. Our study revealed that a prevention app with personalized recommendations can support health information seeking and health literacy. These findings can help app developers, public health practitioners, and researchers when designing apps for groups of varying identities.

Objective: Audit and feedback (A&F) programmes aim to improve patient care by providing summary data on performance to clinicians. They generally have modest, but variable, effects on patient care and questions remain about how best to provide performance feedback. It is not feasible to test all ways of providing feedback in 'real-world' randomised trials. Online screening experiments that screen feedback techniques prior to real-world evaluations of optimised versions offer a systematic approach. User-centred design methodologies can inform the design of such online experiments. Methods: We report the use of an innovative user-centred design approach to create feedback techniques for an online screening experiment and reflect on its usefulness. This approach included the involvement of patients and stakeholders. Results and Conclusion: We highlight lessons on ways to engage with partners, considering the feasibility of online A&F feedback delivery, fidelity, and usability. We demonstrate how the approach was implemented to co-create a set of feedback techniques for an online experiment and could also be applied to the design of other digital interventions.

Objectives: Mechanical ventilator plays a vital role in saving millions of lives. Patients with COVID-19 symptoms need a ventilator to survive during the pandemic. Studies have reported that the mortality rates rise from 50% to 97% in those requiring mechanical ventilation during COVID-19. The pumping of air into the patient's lungs using a ventilator requires a particular air pressure. High or low ventilator pressure can result in a patient's life loss as high air pressure in the ventilator causes the patient lung damage while lower pressure provides insufficient oxygen. Consequently, precise prediction of ventilator pressure is a task of great significance in this regard. The primary aim of this study is to predict the airway pressure in the ventilator respiratory circuit during the breath. Methods: A novel hybrid ventilator pressure predictor (H-VPP) approach is proposed. The ventilator exploratory data analysis reveals that the high values of lung attributes R and C during initial time step values are the prominent causes of high ventilator pressure. Results: Experiments using the proposed approach indicate H-VPP achieves a 0.78 R², mean absolute error of 0.028, and mean squared error of 0.003. These results are better than other machine learning and deep learning models employed in this study. Conclusion: Extensive experimentation indicates the superior performance of the proposed approach for ventilator pressure prediction with high accuracy. Furthermore, performance comparison with state-of-the-art studies corroborates the superior performance of the proposed approach.

Introduction: Current discussions surround whether 'person-first language' (PFL) such as 'patient with autism' and 'identity-first language' (IFL) such as 'autistic patient' is most sensitive and appropriate. There is language guidance when talking about disability and race, ethnicity, and ancestry in genetics research, but not around PFL and IFL. We applied natural language processing (NLP) methods to PFL and IFL in published in genetics research, focussing on Autism Spectrum Disorders (ASD). Methods: Of the approximately 38,000 abstracts accepted in European Society of Human Genetics (ESHG) conference between 2001 and 2021, almost 5000 contained autism keywords. NLP analysis of these explored PFL and IFL use over time, in combination with specific nouns, and in combination with each other. Results: 262 instances of PFL and 264 instances of IFL showed similar, common and consistent use over time. Straightforward matches (e.g. 'patient with ASD' or 'ASD patient') accounted for most uses, with subtle differences in the frequently co-occurring nouns. 50 abstracts used both patterns, typically with one example of each. Conclusions: NLP can quantify use, timing and context for PFL and IFL in research articles. Consequently, NLP can support the development of language style guidelines or to evaluate their effectiveness.

Objectives: Show the generalizability of an ingredient-based method to automatically create an up-to-date, error-free, complete list of medication codes (e.g., opioid medications with at least one opioid ingredient) from an ingredient list (e.g., opioid ingredients). The method, previously evaluated with the RxNorm terminology, was reused and applied in the National Drug Code (NDC) context to create opioid and antidepressant medication lists. Methods: The resulting medication lists were validated through automatic comparisons with curated medication lists (the CDC opioid medication code set and the HEDIS antidepressant medication code set), automatic comparisons with active medication lists (Federal Drug Administration (FDA) databases and RxNorm), and manual physicians' review. Results: The proposed ingredient-based method was validated with two clinical terminologies (RxNorm and NDC) and two use cases (opioid and antidepressant medication code sets), demonstrating generalizability, reusability, and high accuracy. Conclusion: Methodologies for creating lists of sensitive codes are essential to supporting patients' need to restrict access to potentially stigmatizing information. In contrast with data-driven, less accurate, and unexplainable methods to create clinical lists, our study innovated by proposing algorithms to automatically discover correct, complete, up-to-date, and ingredient-based medication lists.