Assessing the Efficacy of ChatGPT Versus Human Researchers in Identifying Relevant Studies on mHealth Interventions for Improving Medication Adherence in Patients With Ischemic Stroke When Conducting Systematic Reviews: Comparative Analysis.

BACKGROUND: ChatGPT by OpenAI emerged as a potential tool for researchers, aiding in various aspects of research. One such application was the identification of relevant studies in systematic reviews. However, a comprehensive comparison of the efficacy of relevant study identification between human researchers and ChatGPT has not been conducted. OBJECTIVE: This study aims to compare the efficacy of ChatGPT and human researchers in identifying relevant studies on medication adherence improvement using mobile health interventions in patients with ischemic stroke during systematic reviews. METHODS: This study used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Four electronic databases, including CINAHL Plus with Full Text, Web of Science, PubMed, and MEDLINE, were searched to identify articles published from inception until 2023 using search terms based on MeSH (Medical Subject Headings) terms generated by human researchers versus ChatGPT. The authors independently screened the titles, abstracts, and full text of the studies identified through separate searches conducted by human researchers and ChatGPT. The comparison encompassed several aspects, including the ability to retrieve relevant studies, accuracy, efficiency, limitations, and challenges associated with each method. RESULTS: A total of 6 articles identified through search terms generated by human researchers were included in the final analysis, of which 4 (67%) reported improvements in medication adherence after the intervention. However, 33% (2/6) of the included studies did not clearly state whether medication adherence improved after the intervention. A total of 10 studies were included based on search terms generated by ChatGPT, of which 6 (60%) overlapped with studies identified by human researchers. Regarding the impact of mobile health interventions on medication adherence, most included studies (8/10, 80%) based on search terms generated by ChatGPT reported improvements in medication adherence after the intervention. However, 20% (2/10) of the studies did not clearly state whether medication adherence improved after the intervention. The precision in accurately identifying relevant studies was higher in human researchers (0.86) than in ChatGPT (0.77). This is consistent with the percentage of relevance, where human researchers (9.8%) demonstrated a higher percentage of relevance than ChatGPT (3%). However, when considering the time required for both humans and ChatGPT to identify relevant studies, ChatGPT substantially outperformed human researchers as it took less time to identify relevant studies. CONCLUSIONS: Our comparative analysis highlighted the strengths and limitations of both approaches. Ultimately, the choice between human researchers and ChatGPT depends on the specific requirements and objectives of each review, but the collaborative synergy of both approaches holds the potential to advance evidence-based research and decision-making in the health care field.

A Systematic Review of the Application of Artificial Intelligence in Nursing Care: Where are We, and What's Next?

Background: Integrating Artificial Intelligence (AI) into healthcare has transformed the landscape of patient care and healthcare delivery. Despite this, there remains a notable gap in the existing literature synthesizing the comprehensive understanding of AI's utilization in nursing care. Objective: This systematic review aims to synthesize the available evidence to comprehensively understand the application of AI in nursing care. Methods: Studies published between January 2019 and December 2023, identified through CINAHL Plus with Full Text, Web of Science, PubMed, and Medline, were included in this review. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines guided the identification, screening, exclusion, and inclusion of articles. The convergent integrated analysis framework, as proposed by the Joanna Briggs Institute, was employed to synthesize data from the included studies for theme generation. Results: A total of 337 records were identified from databases. Among them, 35 duplicates were removed, and 302 records underwent eligibility screening. After applying inclusion and exclusion criteria, eleven studies were deemed eligible and included in this review. Through data synthesis of these studies, six themes pertaining to the use of AI in nursing care were identified: 1) Risk Identification, 2) Health Assessment, 3) Patient Classification, 4) Research Development, 5) Improved Care Delivery and Medical Records, and 6) Developing a Nursing Care Plan. Conclusion: This systematic review contributes valuable insights into the multifaceted applications of AI in nursing care. Through the synthesis of data from the included studies, six distinct themes emerged. These findings not only consolidate the current knowledge base but also underscore the diverse ways in which AI is shaping and improving nursing care practices.

Social determinants of health and emergency department visits among older adults with multimorbidity: insight from 2010 to 2018 National Health Interview Survey.

BACKGROUND: Multimorbidity is prevalent among older adults and is associated with adverse health outcomes, including high emergency department (ED) utilization. Social determinants of health (SDoH) are associated with many health outcomes, but the association between SDoH and ED visits among older adults with multimorbidity has received limited attention. This study aimed to examine the association between SDoH and ED visits among older adults with multimorbidity. METHODS: A cross-sectional analysis was conducted among 28,917 adults aged 50 years and older from the 2010 to 2018 National Health Interview Survey. Multimorbidity was defined as the presence of two or more self-reported diseases among 10 common chronic conditions, including diabetes, hypertension, asthma, stroke, cancer, arthritis, chronic obstructive pulmonary disease, and heart, kidney, and liver diseases. The SDoH assessed included race/ethnicity, education level, poverty income ratio, marital status, employment status, insurance status, region of residence, and having a usual place for medical care. Logistic regression models were used to examine the association between SDoH and one or more ED visits. RESULTS: Participants' mean (± SD) age was 68.04 (± 10.66) years, and 56.82% were female. After adjusting for age, sex, and the number of chronic conditions in the logistic regression model, high school or less education (adjusted odds ratio [AOR]: 1.10, 95% confidence interval [CI]: 1.02-1.19), poverty income ratio below the federal poverty level (AOR: 1.44, 95% CI: 1.31-1.59), unmarried (AOR: 1.19, 95% CI: 1.11-1.28), unemployed status (AOR: 1.33, 95% CI: 1.23-1.44), and having a usual place for medical care (AOR: 1.46, 95% CI 1.18-1.80) was significantly associated with having one or more ED visits. Non-Hispanic Black individuals had higher odds (AOR: 1.28, 95% CI: 1.19-1.38), while non-Hispanic Asian individuals had lower odds (AOR: 0.71, 95% CI: 0.59-0.86) of one or more ED visits than non-Hispanic White individuals. CONCLUSION: SDoH factors are associated with ED visits among older adults with multimorbidity. Systematic multidisciplinary team approaches are needed to address social disparities affecting not only multimorbidity prevalence but also health-seeking behaviors and emergent healthcare access.

Heterogeneity in the Prevalence of Cardiovascular Risk Factors by Ethnicity and Birthplace Among Asian Subgroups: Evidence From the 2010 to 2018 National Health Interview Survey.

BACKGROUND: Asian people in the United States have different sociodemographic and health-related characteristics that might affect cardiovascular disease (CVD) risk by ethnicity and birthplace. However, they are often studied as a monolithic group in health care research. This study aimed to examine heterogeneity in CVD risk factors on the basis of birthplace among the 3 largest Asian subgroups (Chinese, Asian Indian, and Filipino) compared with US-born non-Hispanic White (NHW) adults. METHODS AND RESULTS: A cross-sectional analysis was conducted using the 2010 to 2018 National Health Interview Survey data from 125 008 US-born and foreign-born Chinese, Asian Indian, Filipino, and US-born NHW adults. Generalized linear models with Poisson distribution were used to examine the prevalence and prevalence ratios of self-reported hypertension, diabetes, high cholesterol, physical inactivity, smoking, and overweight/obesity among Asian subgroups compared with US-born NHW adults. The study included 118 979 US-born NHW and 6029 Asian adults who self-identified as Chinese (29%), Asian Indian (33%), and Filipino (38%). Participants' mean (±SD) age was 49±0.1 years, and 53% were females. In an adjusted analysis, foreign-born Asian Indians had significantly higher prevalence of diabetes, physical inactivity, and overweight/obesity; foreign-born Chinese had higher prevalence of physical inactivity, and foreign-born Filipinos had higher prevalence of all 5 CVD risk factors except smoking compared with NHW adults. CONCLUSIONS: This study revealed significant heterogeneity in the prevalence of CVD risk factors among Asian subgroups by ethnicity and birthplace, stressing the necessity of disaggregating Asian subgroup data. Providers should consider this heterogeneity in CVD risk factors and establish tailored CVD prevention plans for Asian subgroups.

Utilizing Social Determinants of Health Model to Understand Barriers to Medication Adherence in Patients with Ischemic Stroke: A Systematic Review.

Introduction: Ischemic strokes and their recurrence create an immense disease burden globally. Therefore, preventing recurrent strokes by promoting medication adherence is crucial to reduce morbidity and mortality. In addition, understanding the barriers to medication adherence related to the social determinants of health (SDoH) could promote equity among persons with ischemic stroke. Objective: To explore the barriers to medication adherence among patients with ischemic stroke through the SDoH. Methods: This systematic review included studies published between January 2018 and December 2022 identified through PubMed, MEDLINE, Web of Science, and CINAHL Plus Full Text. The descriptions of the studies were systematically summarized and discussed based on the SDoH from the US Healthy People 2030 initiative. Results: Eight studies met the inclusion criteria and were included in this review. The most common barrier to adherence was inappropriate medication beliefs, medication side effects, and patient-physician relationship, which relate to the dimensions of healthcare access and quality. Health literacy and health perception, dependent on education access and quality, frequently influenced adherence. Other social determinants, such as financial strain and social and community context, were found to alter adherence behaviors. No study addressed the neighborhood and built environment domain. We found that cognitive impairment is another factor that impacts adherence outcomes among stroke patients. Conclusion: Multifaceted approaches are needed to address the SDoH to improve medication adherence among patients with ischemic stroke. This review emphasized strategies, including patient education, provider-patient communication, social support, health literacy, technology, and policy advocacy to enhance adherence.

Using Neural Networks Algorithm in Ischemic Stroke Diagnosis: A Systematic Review.

Objective: To evaluate the evidence of artificial neural network (NNs) techniques in diagnosing ischemic stroke (IS) in adults. Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) was utilized as a guideline for this review. PubMed, MEDLINE, Web of Science, and CINAHL Plus Full Text were searched to identify studies published between 2018 and 2022, reporting using NNs in IS diagnosis. The Critical Appraisal Checklist for Diagnostic Test Accuracy Studies was adopted to evaluate the included studies. Results: Nine studies were included in this systematic review. Non-contrast computed tomography (NCCT) (n = 4 studies, 26.67%) and computed tomography angiography (CTA) (n = 4 studies, 26.67%) are among the most common features. Five algorithms were used in the included studies. Deep Convolutional Neural Networks (DCNNs) were commonly used for IS diagnosis (n = 3 studies, 33.33%). Other algorithms including three-dimensional convolutional neural networks (3D-CNNs) (n = 2 studies, 22.22%), two-stage deep convolutional neural networks (Two-stage DCNNs) (n = 2 studies, 22.22%), the local higher-order singular value decomposition denoising algorithm (GL-HOSVD) (n = 1 study, 11.11%), and a new deconvolution network model based on deep learning (AD-CNNnet) (n = 1 study, 11.11%) were also utilized for the diagnosis of IS. Conclusion: The number of studies ensuring the effectiveness of NNs algorithms in IS diagnosis has increased. Still, more feasibility and cost-effectiveness evaluations are needed to support the implementation of NNs in IS diagnosis in clinical settings.

Management and Characteristics of Embolism and Thrombosis After COVID-19 Vaccination: Scoping Review.

This scoping review aims to 1) identify characteristics of participants who developed embolism and/or thrombotic event(s) after COVID-19 vaccination and 2) review the management during the new vaccine development of the unexpected event(s). This review was conducted following PRISMA for scoping review guidelines. Peer-reviewed articles were searched for studies involving participants with embolism and/or thrombotic event(s) after COVID-19 vaccination with the management described during the early phase after the approval of vaccines. The 12 studies involving 63 participants were included in this review. The majority of participants' ages ranged from 22 to 49 years. The embolism and/or thrombotic event(s) often occur within 30 days post-vaccination. Five of the included studies reported the event after receiving viral vector vaccines and suggested a vaccine-induced immune thrombotic thrombocytopenia as a plausible mechanism. Cerebral venous sinus thrombosis was the most frequently reported post-vaccination thrombosis complication. In summary, the most frequently reported characteristics and management from this review were consistent with international guidelines. Future studies are recommended to further investigate the incidence and additional potential complications to warrant the benefit and safety after receiving COVID-19 vaccine and other newly developed vaccines.

'Snapshot' cohort study design across multi-site research settings: challenges, strategies, and solutions.

Multi-site research studies redefine cohort studies by simultaneously providing a cross-sectional snapshot of patients and monitoring them over time, to evaluate outcomes. However, careful design is crucial to minimize potential biases, such as seasonal variations, that may arise during the study period. Addressing snapshot study challenges requires strategic solutions: implementing multi-stage sampling for representativeness, providing rigorous data collection training, using translation techniques and content validation for cultural and linguistic appropriateness, streamlining ethical approval processes, and applying comprehensive data management for follow-up and missing data. These strategies can optimize the efficacy and ethicality of snapshot studies.

Associations between diagnosis with stroke, comorbidities, and activity of daily living among older adults in the United States.

Background: Stroke is the leading cause of mortality. This study aimed to investigate the association between stroke, comorbidities, and activity of daily living (ADL) among older adults in the United States. Methods: Participants were 1165 older adults aged 60 and older from two waves (2016 and 2018) of the Health and Retirement Study who had a stroke. Descriptive statistics were used to describe demographic information and comorbidities. Logistic regressions and multiple regression analyses were used to determine associations between stroke, comorbidities, and ADL. Results: The mean age was 75.32 ± 9.5 years, and 55.6% were female. An adjusted analysis shows that older stroke adults living with diabetes as comorbidity are significantly associated with difficulty in dressing, walking, bedding, and toileting. Moreover, depression was significantly associated with difficulty in dressing, walking, bathing, eating, and bedding. At the same time, heart conditions and hypertension as comorbidity were rarely associated with difficulty in ADL. After adjusting for age and sex, heart condition and depression are significantly associated with seeing a doctor for stroke (odds ratio [OR]: 0.66; 95% confidence interval [CI]: 0.49-0.91; p = 0.01) and stroke therapy (OR: 0.46; 95% CI: 0.25-0.84; p = 0.01). Finally, stroke problem (unstandardized ß [B] = 0.58, p = 0.017) and stroke therapy (B = 1.42, p < 0.001) significantly predict a lower level of independence. Conclusion: This study could benefit healthcare professionals in developing further interventions to improve older stroke adults' lives, especially those with a high level of dependence.

Machine learning-based patient classification system for adults with stroke: A systematic review.

OBJECTIVE: To evaluate the existing evidence of a machine learning-based classification system that stratifies patients with stroke. METHODS: The authors carried out a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations for a review article. PubMed, MEDLINE, Web of Science, and CINAHL Plus Full Text were searched from January 2015 to February 2021. RESULTS: There are twelve studies included in this systematic review. Fifteen algorithms were used in the included studies. The most common forms of machine learning (ML) used to classify stroke patients were the support vector machine (SVM) (n = 8 studies), followed by random forest (RF) (n = 7 studies), decision tree (DT) (n = 4 studies), gradient boosting (GB) (n = 4 studies), neural networks (NNs) (n = 3 studies), deep learning (n = 2 studies), and k-nearest neighbor (k-NN) (n = 2 studies), respectively. Forty-four features of inputs were used in the included studies, and age and gender are the most common features in the ML model. DISCUSSION: There is no single algorithm that performed better or worse than all others at classifying patients with stroke, in part because different input data require different algorithms to achieve optimal outcomes.

The experience of caregivers of chronically ill patients during the COVID-19: A Systematic Review.

OBJECTIVES: This study aimed to identify the difficulties that caregivers of chronically ill patients experienced during the COVID-19 pandemic and to provide directions for future studies. METHODS: Five electronic databases, including PubMed, Web of Science, CINAHL Plus Full Text, EMBASE, and Scopus, were systematically searched from January 2019 to February 2021. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses were employed for the literature screening, inclusion, and exclusion. The Mixed Methods Appraisal Tool was adopted for qualifying appraisal. RESULTS: Six studies met the study criteria, including three quantitative studies, two qualitative studies, and one mixed-method study. Mental health, personal experience, financial problems, physical health, and improvement approaches were the major five themes that participants reported regarding the impact of COVID-19 they encountered during the pandemic. DISCUSSION: The results could heighten healthcare providers, stakeholders, and policy leaders' awareness of providing appropriate support for caregivers. Future research incorporating programs that support caregivers' needs is recommended.