DIGITAL HEALTH最新文献

Purpose: Chat Generative Pre-trained Transformer (ChatGPT) is now utilized in various fields of healthcare in order to obtain answers to questions related to healthcare-related problems and to evaluate available information. Primary hyperparathyroidism is a common endocrine disorder. We aimed to evaluate the accuracy and quality of ChatGPT's responses to questions specific to hyperparathyroidism cases discussed at multidisciplinary endocrinology meetings.

Methods: ChatGPT-4 was asked to respond to 10 hyperparathyroidism cases evaluated at multidisciplinary endocrinology meetings. The accuracy, completeness, and quality of the responses were scored independently by two endocrinologists. Accuracy and completeness were evaluated on the Likert scale, and quality was evaluated on the global quality scale (GQS).

Results: No misleading information was detected in the responses. In terms of diagnosis, the mean accuracy scores (ranging from 1 to 5) were 4.9 ± 0.1 and the mean completeness scores (ranging from 1 to 3) were 3.0. In the responses given in terms of further examination, the mean accuracy and completeness scores were 4.8 ± 0.13 and 2.6 ± 0.16, respectively. The mean accuracy and completeness scores for treatment recommendations were 4.9 ± 0.1 and 2.4 ± 0.16, respectively. The GQS evaluation result was 80% high quality and 20% medium quality.

Conclusion: In this study, the accuracy and quality rates of ChatGPT-4 were generally high in responding to questions as to hyperparathyroidism patients. It can be concluded that artificial intelligence may serve as a valuable tool in healthcare. However, the limitations and risks of ChatGPT should also be evaluated.

About one-third of stroke survivors experience aphasia, i.e., language dysfunction caused by brain damage. Aphasia affects not only a person's ability to communicate, but it often leads to the inability to return to work, loss of close relationships, diminished quality of life, negative self-perception, and depression. Yet persons with aphasia are globally underserved due to limited access to resources, which limits their chance for recovery. Immersive virtual reality (VR) has the potential to solve this problem and deliver efficient, personalized treatments to millions of people worldwide who need access to rehabilitation services or more flexibility in treatment delivery. To reduce the global burden of stroke experts recommend taking bold, pragmatic actions across all four pillars of stroke quadrangle-surveillance, prevention, acute care, and rehabilitation. Embracing immersive VR-based rehabilitation of poststroke aphasia would be one step in that direction.

Background: Professional opinion polling has become a popular means of seeking advice for complex nephrology questions in the #AskRenal community on X. ChatGPT is a large language model with remarkable problem-solving capabilities, but its ability to provide solutions for real-world clinical scenarios remains unproven. This study seeks to evaluate how closely ChatGPT's responses align with current prevailing medical opinions in nephrology.

Methods: Nephrology polls from X were submitted to ChatGPT-4, which generated answers without prior knowledge of the poll outcomes. Its responses were compared to the poll results (inter-rater) and a second set of responses given after a one-week interval (intra-rater) using Cohen's kappa statistic (κ). Subgroup analysis was performed based on question subject matter.

Results: Our analysis comprised two rounds of testing ChatGPT on 271 nephrology-related questions. In the first round, ChatGPT's responses agreed with poll results for 163 of the 271 questions (60.2%; κ = 0.42, 95% CI: 0.38-0.46). In the second round, conducted to assess reproducibility, agreement improved slightly to 171 out of 271 questions (63.1%; κ = 0.46, 95% CI: 0.42-0.50). Comparison of ChatGPT's responses between the two rounds demonstrated high internal consistency, with agreement in 245 out of 271 responses (90.4%; κ = 0.86, 95% CI: 0.82-0.90). Subgroup analysis revealed stronger performance in the combined areas of homeostasis, nephrolithiasis, and pharmacology (κ = 0.53, 95% CI: 0.47-0.59 in both rounds), compared to other nephrology subfields.

Conclusion: ChatGPT-4 demonstrates modest capability in replicating prevailing professional opinion in nephrology polls overall, with varying performance levels between question topics and excellent internal consistency. This study provides insights into the potential and limitations of using ChatGPT in medical decision making.

Objective: Health programs for Indigenous people are most effective, acceptable, and sustainable when Indigenous perspectives are prioritized. Codesign builds on Indigenous people's creativity and propensity to experiment with new technologies and ensures research is designed and implemented in a culturally safe and respectful manner. Limited research has focused on older Indigenous people as partners in digital health. No research has focused on the acceptability and feasibility of older Indigenous people using wearables for heart health monitoring. This study provides insights into the acceptability and feasibility for ≥55-year-old Indigenous people living in remote locations to use wearables (watches and patches) to detect atrial fibrillation (AF) and high blood pressure.

Methods: This mixed methods study was codesigned and coimplemented with the local Aboriginal Controlled Health Service in a remote area of New South Wales, Australia. It included active involvement and codesign with the participants. The devices used in this study included a Withings Scan watch and a Biobeat patch.

Results: Despite challenging conditions (>36°C) and variable internet connectivity, 11 Indigenous older adults participated in a five-day wearables program in a remote location. Participants indicated that using digital health devices was acceptable and feasible for older Indigenous users. They described high levels of comfort, safety and convenience when using wearables (patches and watches) to detect AF. They were active participants in codesigning the program.

Conclusion: Older Indigenous Australians are motivated to use wearable health devices. They are keen to participate in codesign innovative health tech programs to ensure new health technologies are acceptable to Indigenous people and feasible for remote locations.

Objective: As the world faces an aging population, the complexities of care management become increasingly pronounced. While technological solutions hold promise in addressing the dynamic demands of care, many nuances are to be considered in the design and implementation of active and assisted living technologies (AAL) for older adult care. This qualitative study, set in southern Spain, is positioned at the crossroads of healthcare challenges, as seen by the different actors involved in the care process and the technological solutions developed in response to these challenges. By investigating the complex landscape of caregiving and by examining the experiences and challenges faced by caregivers, healthcare professionals, and older adults, we aim to guide the development of vision-based AAL technologies that are responsive to the genuine needs of older adults and those requiring care.

Methods: A qualitative research methodology was used in the study. In total15 in-depth interviews and five focus groups were conducted with a diverse group of stakeholders involved in the process of care provision and reception.

Results: While the results demonstrate that there is a readiness for technological solutions, concerns over privacy and trust highlight the need for a carefully integrated, human-centric approach to technology in caregiving.

Conclusion: This research serves as a compass, guiding future discussions on the intersection of aging, technology, and care, with the ultimate goal of transforming caregiving into a collaborative and enriching journey for all stakeholders involved.

Objective: Explainable machine learning (XAI) was introduced in this study to improve the interpretability, explainability and transparency of the modelling results. The survex package in R was used to interpret and compare two survival models - the Cox proportional hazards regression (coxph) model and the random survival forest (rfsrc) model - and to estimate overall survival (OS) and its determinants in heart failure (HF) patients using these models.

Methods: We selected 1159 HF patients hospitalised at the First Affiliated Hospital of Kunming Medical University. First, the performance of the two models was investigated using the C-index, the integrated C/D AUC, and the integrated Brier score. Second, a global explanation of the whole cohort was carried out using the time-dependent variable importance and the partial dependence survival profile. Finally, the SurvSHAP(t) and SurvLIME plots and the ceteris paribus survival profile were used to obtain a local explanation for each patient.

Results: By comparing the C-index, the C/D AUC, and the Brier score, this study showed that the model performance of rfsrc was better than coxph. The global explanation of the whole cohort suggests that the C-reactive protein, lg BNP (brain natriuretic peptide), estimated glomerular filtration rate, albumin, age and blood chloride were significant unfavourable predictors of OS in HF patients in both the cxoph and the rfsrc models. By including individual patients in the model, we can provide a local explanation for each patient, which guides the clinician in individualising the patient's treatment.

Conclusion: By comparison, we conclude that the model performance of rfsrc is better than that of coxph. These two predictive models, which address not only the whole population but also selected patients, can help clinicians personalise the treatment of each HF patient according to his or her specific situation.

Objective: This study describes a research protocol for a behavioral marker-based predictive model that examines the functional status of older adults with subjective cognitive decline and mild cognitive impairment.

Methods: A total of 130 older adults aged ≥65 years with subjective cognitive decline or mild cognitive impairment will be recruited from the Dementia Relief Centers or the Community Service Centers. Data on behavioral and psychosocial markers (e.g. physical activity, mobility, sleep/wake patterns, social interaction, and mild behavioral impairment) will be collected using passive wearable actigraphy, in-person questionnaires, and smartphone-based ecological momentary assessments. Two follow-up assessments will be performed at 12 and 24 months after baseline. Mixed-effect machine learning models: MErf, MEgbm, MEmod, and MEctree, and standard machine learning models without random effects [random forest, gradient boosting machine] will be employed in our analyses to predict functional status over time.

Results: The results of this study will be fundamental for developing tailored digital interventions that apply deep learning techniques to behavioral data to predict, identify, and aid in the management of functional decline in older adults with subjective cognitive decline and mild cognitive impairment. These older adults are considered the optimal target population for preventive interventions and will benefit from such tailored strategies.

Conclusions: Our study will contribute to the development of self-care interventions that utilize behavioral data and machine learning techniques to provide automated analyses of the functional decline of older adults who are at risk for dementia.

Automated dispensing cabinets (ADCs) are decentralized, computer-controlled systems used to store, distribute, and track medications at the point of care in the wards.

Objective: The objective of the current study is to evaluate how healthcare practitioners are satisfied with ADCs and scrutinize some influencing factors that could affect this satisfaction.

Material: A cross-sectional survey study was designed and distributed online to healthcare providers in Al-hasa hospitals.

Results: A total of 166 participants. Regarding the frequency and pattern of ADC use, around 79.5% used ADC and 85.4% were informed about using ADC on a daily basis. As for the level of satisfaction with ADC, an exact 81.9% gave a high rate for overall satisfaction, 81.3% were highly satisfied with the system's accuracy, and 74.7% were highly satisfied with the time it takes to complete the task. Regarding usability of the system, 69.8% thought it was easy whereas 36.8% agreed that the time required for reloading medication is longer than before ADC. Furthermore, 79.5% agreed that ADC allowed them to accomplish their job safely, and 67.4% agreed that it improved their productivity. Regarding challenges, 74.7% agreed that all drawer types assure safe access and removal of medications, and 18.7% agreed that there is a significant potential for loss of data.

Conclusion: This study investigated healthcare staff's perceptions and satisfaction with ADCs in Al-hasa hospitals. The healthcare participants were mostly highly satisfied with the use of the ADCs which translated into better patient care and improved patient safety as well as higher productivity.

Purpose: This study aimed to investigate professional nurses' general attitudes toward artificial intelligence, their knowledge and perceptions of ChatGPT usage, and the influencing factors.

Methods: The population of the research consists of nurses who follow a social media platform account in Turkey. The sample of the study consisted of 288 nurses who participated in the study between December 2023 and March 2024. Data were collected through an account on a social media platform via Google Forms using the Information Identification Questionnaire for ChatGPT and Artificial Intelligence Programs and the General Attitudes to Artificial Intelligence Scale (GAAIS).

Results: The mean scores obtained from the overall GAAIS and its Positive Attitudes subscale from the participants in this study were 67.54 ± 13.14 and 41.89 ± 11.24, respectively. Of the participants, 48.3% knew about ChatGPT and artificial intelligence programs. Of the participants, 27.8% used ChatGPT and artificial intelligence programs. Their scores for the Positive Attitude subscale were higher than were the scores of those who did not use such programs. Of the participants, 84.4% thought that nurses should be made aware of ChatGPT and artificial intelligence programs, 67% thought that the use of these programs would contribute to nurses' professional development, 42.4% thought that the use of these programs would not reduce nurses' workload, and 58.3% thought that the use of these programs would positively affect patient care.

Conclusion: In this study, it can be said that nurses in Turkey have positive attitudes toward integrating ChatGPT and AI programs to improve patient outcomes and add them to nursing practices.

Implications for nursing practice: The present study in which nurses' attitudes toward the implementation of ChatGPT and artificial intelligence programs were investigated is expected to provide information for healthcare institutions, policy makers and artificial intelligence developers on the integration of ChatGPT and artificial intelligence into nursing practice. It is necessary to create environments that use AI technologies that reduce the nursing workload of nurses in the clinical area and positively affect the quality of patient care.

Objective: Parkwood VIP4SCI platform is a virtual e-health solution adapted from a version created for Spinal Cord Injury Ontario (SCIO) that focused on self-management skill development for persons with spinal cord injury (SCI) transitioning between stages of care, in partnership with caregivers and clinicians. This evaluation of the platform informs the usability and feasibility of a model to facilitate service care aims postrehabilitation.

Design: Participants: Inpatients and outpatients admitted to the SCI Rehabilitation Program (n = 31), and a mix of interdisciplinary clinicians on the Rehabilitation Team (n = 20). Caregivers participated at the discretion of the patient.Interventions: Inpatients were randomized into two groups (Platform or Standard Care (i.e., delayed access)). Outpatients were given access at enrollment. Pre-post assessments were completed using surveys, and platform analytics were collected. Weekly check-ins were introduced to increase engagement. Focus groups were held with a subset of participants near study completion.

Results: VIP4SCI was viewed as usable and feasible. Platform satisfaction assessed on a -3 to +3 scale ranged from +0.9 to 2.5, demonstrating positive agreement. Self-efficacy related to self-management ranged from 5.4 to 7.6 out of 10. The educational resource hub was identified as the most beneficial feature. Lack of clinician uptake was a barrier to integration into day-to-day practice.

Conclusions: Platform usage was low among all groups despite the perceived need for facilitating care coordination with consistent and intentional self-management programming. Despite the lack of uptake, partly due to challenges associated with the pandemic, conclusions on platform features and barriers to implementation will help to inform future programming.