Health Informatics Journal最新文献

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.

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.

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.

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.

Background: The efficacy of mHealth apps in managing hypertension has been proven; however, low usage intention remains a significant challenge, warranting an in-depth exploration of the influencing factors. Objectives: This study aimed to examine the factors influencing hypertensive new users' intention to use mobile health applications through a cross-sectional survey. Methods: Fuzzy-set qualitative comparative analysis (fsQCA) was employed to investigate the combinations of various determinants, including technology acceptance, adoption factors, compliance behavior initiation factors, and time motivation factors for decision making. Results: A total of 100 middle-aged and elderly hypertensive individuals participated in the survey, with 98 responses included in the final statistical analysis. The analysis identified four distinct configurations that contribute to high usage intentions, with solution consistency and coverage values of 0.93 and 0.36, respectively. Conclusion: The findings suggest that intervention strategies should account for the various pathways leading to usage intentions.

Objective: This paper describes Victoria, an empirically built data pipeline for SNDS to: - Build an automated, scalable pipeline supporting changes to the data model inherent to the use of large databases, - Deliver a documented pipeline with clear processes, enabling scientific, epidemiological researches, - Ease access to SNDS data in compliance with regulatory requirements. Methods: This paper describes the 2-steps process of the Victoria pipeline and its final output. The initial cleaning step consists in formatting, deleting empty, error or duplicate records and renaming variables without changing their values, accordingly with the official SNDS documentation. The second step consists in creating 2 linearised data models: every line of each table is an event, and each table is indexed with a unique patient identifier, without the need for a central patient or identifier table. These 2 models are: - the epidemiological model, used for answering most of the research questions requiring population phenotyping (demography, diagnosis, procedures characteristics). - the medico-economic model is used for costs and healthcare consumption analyses. It contains more complex information about reimbursements rates and the data quality assessment is focused on costs rather than medico-administrative information. Results: The pipeline was executed on 2 different datasets representing ∼85 000 and ∼870 000 beneficiaries with the following configuration: one master with 4 cores and 16Go of RAM and respectively 4 and 6 workers. The total execution time for the smaller dataset was 25 h and 96 h for the larger one. The longest part of those times is represented by the format conversion to parquet. The cleaning step took only 4 h in both cases. The epidemiological model took 344 min for the smaller dataset and 1934 min for the larger one. The medico-economic model took the longest time with 704 min and 2145 min, respectively. Conclusion: Victoria pipeline is a successfully implemented SNDS pipeline. Compared to previous pipelines, reviewability is part of its design as unit tests and quality assessments can natively be developed to ensure data and analysis quality. The pipeline has been used for 2 published studies. The recent work toward OMOP conversion will be integrated in upcoming versions and, as Victoria is set to run on a CD platform, the potential evolution if SNDS format can be considered.

Prompt administration of radiotherapy (RT) is one of the most effective treatments against cancer. Each day, the radiotherapy departments of large hospitals must plan numerous irradiation sessions, considering the availability of human and material resources, such as healthcare professionals and linear accelerators. With the increasing number of patients suffering from different types of cancers, manually establishing schedules following each patient's treatment protocols has become an extremely difficult and time-consuming task. We propose an optimization algorithm that automatically schedules and generates patient appointments. The model can rearrange fixed appointments to accommodate urgent cases, enabling hospitals to schedule appointments more efficiently. It respects the different treatment protocols and should increase staff and patient satisfaction. The optimization algorithm can be connected to a mobile application allowing patients to accept or refuse appointment changes for rescheduling radiotherapy treatments.

Background: Gestational diabetes mellitus (GDM) is one of the risk factors for postpartum urinary incontinence. Pelvic floor muscle training (PFMT) improves pelvic floor dysfunction in puerperal women, but patient compliance is low. Mobile Health (mHealth) is a promising solution. Objective: To investigate PFMT compliance and effects on pelvic floor muscles in GDM puerperal women guided by the mobile fitness app Keep. Methods: This randomized controlled trial included puerperal women with GDM (n = 72) who were delivered at a tertiary general hospital, selected from November 2021 to April 2022 using convenience sampling, and randomly divided into control (n = 36) and experimental (n = 36) groups. The control group performed PFMT based on routine postpartum PFMT training instruction. The experimental group performed PFMT based on Keep. Both groups had a 4-week intervention period. The PFMT compliance, International Consultation on Incontinence Questionnaire Short Form (ICIQ-SF), Pelvic Muscle Self-efficacy Scale, and the Knowledge, Attitude, Belief, and Practice (KAP) scores of PFMT in puerperal women in the groups were compared pre- and post-intervention. Pelvic floor surface electromyographic biofeedback was used to compare the post-intervention pelvic floor muscle strength between the two groups. Results: Compared with the control group, the test group had higher post-intervention maternal PFMT compliance, pelvic floor muscle strength, pelvic floor muscle self-efficacy, and KAP scores (p < 0.05); incontinence scores were lower (p < 0.05). Pelvic floor muscles in both groups recovered better post-intervention (p < 0.05). Conclusion: The Keep app can improve PFMT adherence, urinary incontinence, KAP scores, self-efficacy, and pelvic floor muscle strength in GDM puerperal women and promote pelvic floor rehabilitation after delivery.