Utilizing natural language processing and large language models in the diagnosis and prediction of infectious diseases: A systematic review

BACKGROUND

Natural Language Processing (NLP) and Large Language Models (LLMs) hold largely untapped potential in infectious disease management. This review explores their current use and uncovers areas needing more attention.

METHODS

This analysis followed systematic review procedures, registered with the Prospective Register of Systematic Reviews. We conducted a search across major databases including PubMed, Embase, Web of Science, and Scopus, up to December 2023, using keywords related to NLP, LLM, and infectious diseases. We also employed the Quality Assessment of Diagnostic Accuracy Studies-2 tool for evaluating the quality and robustness of the included studies.

RESULTS

Our review identified 15 studies with diverse applications of NLP in infectious disease management. Notable examples include GPT-4's application in detecting urinary tract infections and BERTweet's use in Lyme Disease surveillance through social media analysis. These models demonstrated effective disease monitoring and public health tracking capabilities. However, the effectiveness varied across studies. For instance, while some NLP tools showed high accuracy in pneumonia detection and high sensitivity in identifying invasive mold diseases from medical reports, others fell short in areas like bloodstream infection management.

CONCLUSIONS

This review highlights the yet-to-be-fully-realized promise of NLP and LLMs in infectious disease management. It calls for more exploration to fully harness AI's capabilities, particularly in the areas of diagnosis, surveillance, predicting disease courses, and tracking epidemiological trends.

Does machine learning have a high performance to predict obesity among adults and older adults? A systematic review and meta-analysis

AIM

Machine learning may be a tool with the potential for obesity prediction. This study aims to review the literature on the performance of machine learning models in predicting obesity and to quantify the pooled results through a meta-analysis.

DATA SYNTHESIS

A systematic review and meta-analysis were conducted, including studies that used machine learning to predict obesity. Searches were conducted in October 2023 across databases including LILACS, Web of Science, Scopus, Embase, and CINAHL. We included studies that utilized classification models and reported results in the Area Under the ROC Curve (AUC) (PROSPERO registration: CRD42022306940), without imposing restrictions on the year of publication. The risk of bias was assessed using an adapted version of the Transparent Reporting of a multivariable prediction model for individual Prognosis or Diagnosis (TRIPOD). Meta-analysis was conducted using MedCalc software. A total of 14 studies were included, with the majority demonstrating satisfactory performance for obesity prediction, with AUCs exceeding 0.70. The random forest algorithm emerged as the top performer in obesity prediction, achieving an AUC of 0.86 (95%CI: 0.76-0.96; I2: 99.8%), closely followed by logistic regression with an AUC of 0.85 (95%CI: 0.75-0.95; I2: 99.6%). The least effective model was gradient boosting, with an AUC of 0.77 (95%CI: 0.71-0.82; I2: 98.1%).

CONCLUSION

Machine learning models demonstrated satisfactory predictive performance for obesity. However, future research should utilize more comparable data, larger databases, and a broader range of machine learning models.

Shaping the future of healthcare in British Columbia: Establishing provincial clinical governance for responsible deployment of artificial intelligence tools

As healthcare embraces the transformative potential of Artificial Intelligence (AI), it is imperative to safeguard patient and provider safety, equity, and trust in the healthcare system. This article outlines the approach taken by the British Columbia (BC) Provincial Health Services Authority (PHSA) to establish clinical governance for the responsible deployment of AI tools in healthcare. Leveraging its province-wide mandate and expertise, PHSA establishes the infrastructure and processes to proactively and systematically intake, assess, prioritize, and evaluate AI tools. PHSA proposes a coordinated approach in AI tool deployment in collaboration with regional health authorities to prevent duplication of efforts and ensure equitable access to existing and emerging AI tools across the province of BC, incorporating principles of anti-Indigenous racism, cultural safety, and humility. The proposed governance structure underscores the identification of clinical needs, proactive ethics review, rigorous risk assessment, data validation, transparent communication, provider training, and ongoing evaluation to ensure success.

Large language models and generative AI in telehealth: a responsible use lens

OBJECTIVE

This scoping review aims to assess the current research landscape of the application and use of large language models (LLMs) and generative Artificial Intelligence (AI), through tools such as ChatGPT in telehealth. Additionally, the review seeks to identify key areas for future research, with a particular focus on AI ethics considerations for responsible use and ensuring trustworthy AI.

MATERIALS AND METHODS

Following the scoping review methodological framework, a search strategy was conducted across 6 databases. To structure our review, we employed AI ethics guidelines and principles, constructing a concept matrix for investigating the responsible use of AI in telehealth. Using the concept matrix in our review enabled the identification of gaps in the literature and informed future research directions.

RESULTS

Twenty studies were included in the review. Among the included studies, 5 were empirical, and 15 were reviews and perspectives focusing on different telehealth applications and healthcare contexts. Benefit and reliability concepts were frequently discussed in these studies. Privacy, security, and accountability were peripheral themes, with transparency, explainability, human agency, and contestability lacking conceptual or empirical exploration.

CONCLUSION

The findings emphasized the potential of LLMs, especially ChatGPT, in telehealth. They provide insights into understanding the use of LLMs, enhancing telehealth services, and taking ethical considerations into account. By proposing three future research directions with a focus on responsible use, this review further contributes to the advancement of this emerging phenomenon of healthcare AI.

Patient Factors Associated with Missed Otolaryngology Appointments at an Urban Safety-Net Hospital

OBJECTIVE

To determine if patient factors related to ethnicity, socioeconomic status (SES), medical comorbidities, or appointment characteristics increase the risk of missing an initial adult otolaryngology appointment.

METHODS

This study is a retrospective case control study at Boston Medical Center (BMC) in Boston, Massachusetts, that took place in 2019. Patient demographic and medical comorbidity data as well as appointment characteristic data were collected and compared between those that attended their initial otolaryngology appointment versus those who missed their initial appointment. Chi-square and ANOVA tests were used to calculate differences between attendance outcomes. Multivariate analysis was used to compare the odds of missing an appointment based on various patient- and appointment-related factors.

RESULTS

Patients who were more likely to miss their appointments were more often female, of lower education, disabled, not employed, Black or Hispanic, and Spanish-speaking. Spring and Fall appointments were more likely to be missed. When a multivariate regression was conducted to control for social determinants of health (SDOH) such as race, insurance status, employment, and education status, the odds of females, Spanish-speaking, students, and disabled patients missing their appointment were no longer statistically significant.

CONCLUSION

A majority of patients at BMC come from lower SES backgrounds and have multiple medical comorbidities. Those who reside closer to BMC, often areas of lower average income, had higher rates of missed appointments. Interventions such as decreasing lag time, providing handicap-accessible free transportation, and increasing accessibility of telemedicine for patients could help improve attendance rates at BMC.

LEVEL OF EVIDENCE

IV Laryngoscope, 134:4003-4010, 2024.

Exploring potential drivers of patient engagement with their health data through digital platforms: A scoping review

BACKGROUND

Patient engagement when providing patient access to health data results from an interaction between the available tools and individual capabilities. The recent digital advancements of the healthcare field have altered the manifestation and importance of patient engagement. However, a comprehensive assessment of what factors contribute to patient engagement remain absent. In this review article, we synthesised the most frequently discussed factors that can foster patient engagement with their health data.

METHODS

A scoping review was conducted in MEDLINE, Embase, and Google Scholar. Relevant data were synthesized within 7 layers using a thematic analysis: (1) social and demographic factors, (2) patient ability factors, (3) patient motivation factors, (4) factors related to healthcare professionals' attitudes and skills, (5) health system factors, (6) technological factors, and (7) policy factors.

RESULTS

We identified 5801 academic and 200 Gy literature records, and included 292 (4.83%) in this review. Overall, 44 factors that can affect patient engagement with their health data were extracted. We extracted 6 social and demographic factors, 6 patient ability factors, 12 patient motivation factors, 7 factors related to healthcare professionals' attitudes and skills, 4 health system factors, 6 technological factors, and 3 policy factors.

CONCLUSIONS

Improving patient engagement with their health data enables the development of patient-centered healthcare, though it can also exacerbate existing inequities. While expanding patient access to health data is an important step towards fostering shared decision-making in healthcare and subsequently empowering patients, it is important to ensure that these developments reach all sectors of the community.

Identifying Patterns of Primary Care In-Person and Telemedicine Use in the Veterans Health Administration: A Latent Class Analysis

BACKGROUND

The Veterans Health Administration increased synchronous telemedicine (video and telephone visits) in primary care in response to the COVID-19 pandemic.

OBJECTIVE

Our objective was to determine veteran use patterns of in-person and telemedicine primary care when all modalities were available.

DESIGN

A retrospective cohort analysis. We performed a latent class analysis of primary care visits over a 1-year period to identify veteran subgroup (i.e., class) membership based on amount of primary care use and modality used. Then, we used multinomial logistic regression with a categorical outcome to identify patient characteristics associated with class identification.

PARTICIPANTS

A random national sample consisting of 564,580 primary care empaneled veterans in June 2021.

MAIN MEASURES

Latent class membership.

KEY RESULTS

We identified three latent classes: those with few primary care visits that were predominantly telephone-based (45%), intermediate number of visits of all modalities (50%), and many visits of all modalities (5%). In an adjusted model, characteristics associated with the "few" visits class, compared to the intermediate class, were older age, male sex, White race, further driving distance to primary care, higher Gagne, optimal internet speed, and unmarried status (OR 1.002, 1.52, 1.13, 1.004, 1.04, 1.05, 1.06, respectively; p < .05). Characteristics associated with membership in the "many" visits class, compared to the intermediate class, were Hispanic race, higher JEN Frailty Index and Gagne (OR 1.12, 1.11, 1.02, respectively; p < .05), and higher comorbidity by Care Assessment Need score quartile (Q2 1.73, Q3 2.80, Q4 4.12; p < 0.05).

CONCLUSIONS

Veterans accessing primary care in-person or via telemedicine do so primarily in three ways: (1) few visits, predominantly telephone; (2) intermediate visits, all modalities, (3) many visits, all modalities. We found no groups of veterans receiving a majority of primary care through video.

Cost of Carbon in the Total Cost of Healthcare Procedures: A Methodological Challenge

Economic evaluations aim to compare the costs and the results of health strategies to guide the public decision-making process. Cost estimation is, thus, a cornerstone of this approach. At present, few national evaluation agencies recommend incorporating the cost of greenhouse gas (GHG) emissions from healthcare actions into the calculation of healthcare costs. Our main goal is to describe and discuss the methodology for integrating the cost of GHG emissions into the field of applied economic evaluations. To estimate this cost, three steps are required: (1) identifying and quantifying the physical flows linked to the production and management of the outputs of healthcare interventions, (2) estimating the quantity of GHG that can be attributed to each physical flow, and (3) valuing these GHG emissions in monetary terms. Integrating the cost of GHG emissions into the calculation of the costs of healthcare interventions is both useful and relevant from a perspective of collective intergenerational well-being. This approach has been made possible thanks to the existence of accounting and monetary valuation methods for emissions. Agencies specialized in health economic evaluations could take up this issue to resolve ongoing questions, thus providing researchers with a methodological framework and public decision-makers with some key insights.

Effectiveness of telemedicine in outpatient parenteral antimicrobial therapy (Tele-OPAT): A systematic review

INTRODUCTION

Telemedicine is increasingly used to deliver healthcare in many clinical specialities. However, the adoption of telemedicine in the delivery of outpatient parenteral antimicrobial therapy (OPAT) has been relatively slow and limited. This study aims to collate current evidence for telemedicine in OPAT regarding clinical efficacy, safety, acceptability and cost-effectiveness.

METHODS

We systematically searched the Cochrane Library, CINAHL, EMCARE, EMBASE and MEDLINE databases through 24 July 2022, for relevant studies published in English. Research articles and conference abstracts were included if they involved any form of telephone or video consultation in delivering parenteral antibiotics in the home or outpatient setting. Study findings were synthesised into three main themes: patient outcomes and safety, patient and provider satisfaction and cost-effectiveness. The mixed methods appraisal tool was used to review the methodological quality of the studies. PROSPERO CRD42022342874.

RESULTS

The literature search yielded 311 articles, of which 12 (five full-length articles and seven conference abstracts) reporting over 1245 telemedicine interventions were reviewed. The reported outcomes were heterogeneous. Telemedicine was cost-effective and associated with high patient satisfaction and comparable complication rates compared to conventional OPAT. Considering six comparative studies, rehospitalisation risk was lower for telemedicine than conventional OPAT (risk ratio, 0.58; 95% confidence interval, 0.38-0.88; I2  =  31%).

DISCUSSION

The results of this review demonstrate that telemedicine has a role in delivering safe and cost-effective OPAT care, especially for patients residing in remote and geographically isolated locations. Nevertheless, high-quality studies and publication of existing data and experiences are needed to further validate this model of care delivery.

The Role of Artificial Intelligence and Machine Learning in Cardiovascular Imaging and Diagnosis

Cardiovascular diseases remain the leading cause of global mortality, underscoring the critical need for accurate and timely diagnosis. This narrative review examines the current applications and future potential of artificial intelligence (AI) and machine learning (ML) in cardiovascular imaging. We discuss the integration of these technologies across various imaging modalities, including echocardiography, computed tomography, magnetic resonance imaging, and nuclear imaging techniques. The review explores AI-assisted diagnosis in key areas such as coronary artery disease detection, valve disorders assessment, cardiomyopathy classification, arrhythmia detection, and prediction of cardiovascular events. AI demonstrates promise in improving diagnostic accuracy, efficiency, and personalized care. However, significant challenges persist, including data quality standardization, model interpretability, regulatory considerations, and clinical workflow integration. We also address the limitations of current AI applications and the ethical implications of their implementation in clinical practice. Future directions point towards advanced AI architectures, multimodal imaging integration, and applications in precision medicine and population health management. The review emphasizes the need for ongoing collaboration between clinicians, data scientists, and policymakers to realize the full potential of AI in cardiovascular imaging while ensuring ethical and equitable implementation. As the field continues to evolve, addressing these challenges will be crucial for the successful integration of AI technologies into cardiovascular care, potentially revolutionizing diagnostic capabilities and improving patient outcomes.

Characteristics of Patients Receiving Complex Case Management in an Acute Care Hospital

BACKGROUND

Improving transitions in care is a major focus of health care planning. In the research team's prior intervention study, the length of stay (LOS) was reduced when patients at high risk for readmission were identified early in their acute care stay and received complex management.

OBJECTIVE

This study will describe the characteristics of patients receiving complex case management in an urban acute care hospital.

PRIMARY PRACTICE SETTING

Acute care hospital.

METHODOLOGY AND SAMPLE

This was a retrospective chart review of patients in a previous quality assurance study. A random selection of patients who previously underwent high-risk screening using the LACE (Length of stay; Acuity of the admission; Comorbidity of the patient; Emergency department use) index and received complex case management (the intervention group) were reviewed. The charts of a random selection of patients from the previous comparison group were also reviewed. Patient characteristics were collected and compared using descriptive statistics.

RESULTS

In the intervention group, more patients had their family physicians (FPs) documented (93.1% [81/87] vs. 89.2% [66/74]). More patients in the intervention group (89.7% [77/87] vs. 85.1% [63/74]) lived at home prior to admission. More patients in the intervention group had a family caregiver involved (44.8% [39/87] vs. 41.9% [31/74]). At discharge, more patients in the intervention group (87.1% [74/85]) were discharged home compared with the comparison group (78.4% [58/74]).

IMPLICATIONS FOR CASE MANAGEMENT PRACTICE

(1) Having an identified FP, living at home, and having family caregiver(s) characterized those with lower LOS and discharged home. (2) Case management, risk screening, and discharge planning improve patient outcomes. (3) This study identified the importance of having a FP and engaged family caregivers in improving care outcomes.

Navigating the future of health care with AI-driven digital therapeutics

Digital therapeutics (DTx) is a recently conceived idea in health care that aims to cure ailments and modify patient behavior by employing a range of digital technologies. Notably, when traditional medication is not entirely efficacious, DTx offers an innovative avenue for treatments linked to dysfunctional behaviors and lifestyle management. DTx involves extremely adaptable therapeutic devices that empower greater patient engagement in treating illness, using algorithms to collect, transfer and analyze the patient's data. Efficient clinical monitoring and supervision at the individual level by remote access and algorithms for a range of diseases is made possible by integrating machine learning and artificial intelligence with DTx. There is a potentially large worldwide market for DTx owing to its convenient, personalized therapies.

No more government-imposed societal-level COVID-19 control measures but still significant self-experienced burden for severely immunocompromised individuals - A cross-sectional survey in the Netherlands

Objectives

In March 2023, all societal-level COVID-19 control measures were lifted by the Dutch government. This study was performed to understand the self-experienced burden of this new phase of COVID-19 on the perspectives and behaviors of severely immunocompromised individuals.

Methods

This is an observational, descriptive, cross-sectional study in The Netherlands. An online survey was completed by severely immunocompromised individuals, to capture their general well-being (score from 1 = worst to 10 = best), mental and physical health, and daily and social activities during survey conduct and retrospectively for before onset of COVID-19. The survey was open for completion from May 24th until August 7nd, 2023.

Results

Of the 236 respondents, 96.6 % had been vaccinated against COVID-19 and 24.6 % were shielding to avoid COVID-19 during survey conduct. The general well-being score for all respondents was 7.5 (±1.2 SD) before onset of the COVID-19 pandemic and 6.9 (±1.6 SD) during survey conduct (P<0.001). For the shielding group (n = 58), these scores were 7.6 (±1.0 SD) and 5.7 (±1.6 SD), respectively (P<0.001). Generally, for all questions about mental and physical health and daily and social activities, there was a trend towards more negative answers during survey conduct, compared with before onset of the COVID-19 pandemic, which was more pronounced for the shielding group.

Conclusions

Despite absence of government-imposed societal measures, COVID-19 avoidance still had a self-experienced burden on perspectives and behaviors of immunocompromised individuals in The Netherlands, with a significantly lower general well-being during survey conduct, compared with before onset of COVID-19.

On spillovers in economic evaluations: definition, mapping review and research agenda

An important issue in economic evaluations is determining whether all relevant impacts are considered, given the perspective chosen for the analysis. Acknowledging that patients are not isolated individuals has important implications in this context. Increasingly, the term "spillovers" is used to label consequences of health interventions on others. However, a clear definition of spillovers is lacking, and as a result, the scope of the concept remains unclear. In this study, we aim to clarify the concept of spillovers by proposing a definition applicable in health economic evaluations. To illustrate the implications of this definition, we highlight the diversity of potential spillovers through an expanded impact inventory and conduct a mapping review that outlines the evidence base for the different types of spillovers. In the context of economic evaluations of health interventions, we define spillovers as all impacts from an intervention on all parties or entities other than the users of the intervention under evaluation. This definition encompasses a broader range of potential costs and effects, beyond informal caregivers and family members. The expanded impact inventory enables a systematic approach to identifying broader impacts of health interventions. The mapping review shows that the relevance of different types of spillovers is context-specific. Some spillovers are regularly included in economic evaluations, although not always recognised as such, while others are not. A consistent use of the term "spillovers", improved measurement of these costs and effects, and increased transparency in reporting them are still necessary. To that end, we propose a research agenda.

Revolutionizing urogynecology: Machine learning application with patient-centric technology: Promise, challenges, and future directions

In an epoch where digital innovation is redefining the medical landscape, electronic health records (EHRs) stand out as a pivotal transformative force. Urogynecology, a discipline anchored in intricate patient histories and meticulous follow-ups, is on the brink of profound transformation due to these digital strides. While EHRs have unified patient data, challenges related to data privacy, interoperability, and access persist. In response, we present Pelvic Health Place (PHPlace) - a multilingual, patient-centric application. Purposefully designed to bolster patient engagement, PHPlace provides clinicians with essential pre-consultation insights, streamlines the consent process, vividly delineates surgical pathways, and assures comprehensive long-term monitoring. This platform also establishes a foundation for global data amalgamation, promising to invigorate research and potentially harness artificial intelligence (AI) capabilities. With AI integration, we anticipate a more tailored treatment approach and enriched patient education, signaling a pivotal shift in urogynecology and emphasizing the imperative for ongoing academic inquiry.

Artificial intelligence-driven transformations in diabetes care: a comprehensive literature review

Artificial intelligence (AI) has been applied in healthcare for diagnosis, treatments, disease management, and for studying underlying mechanisms and disease complications in diseases like diabetes and metabolic disorders. This review is a comprehensive overview of various applications of AI in the healthcare system for managing diabetes. A literature search was conducted on PubMed to locate studies integrating AI in the diagnosis, treatment, management and prevention of diabetes. As diabetes is now considered a pandemic now so employing AI and machine learning approaches can be applied to limit diabetes in areas with higher prevalence. Machine learning algorithms can visualize big datasets, and make predictions. AI-powered mobile apps and the closed-loop system automated glucose monitoring and insulin delivery can lower the burden on insulin. AI can help identify disease markers and potential risk factors as well. While promising, AI's integration in the medical field is still challenging due to privacy, data security, bias, and transparency. Overall, AI's potential can be harnessed for better patient outcomes through personalized treatment.

Legal and Ethical Considerations of Artificial Intelligence for Residents in Post-Acute and Long-Term Care

This article proposes a framework for examining the ethical and legal concerns for using artificial intelligence (AI) in post-acute and long-term care (PA-LTC). It argues that established frameworks on health, AI, and the law should be adapted to specific care contexts. For residents in PA-LTC, their social, psychological, and mobility needs should act as a gauge for examining the benefits and risks of integrating AI into their care. Using those needs as a gauge, 4 areas of particular concern are identified. First, the threat that AI poses to the autonomy of residents can undermine their core needs. Second, how discrimination and bias in algorithmic decision-making can undermine Medicare coverage for PA-LTC, causing doctors' recommendations to be ignored and denying residents the care they are entitled to. Third, privacy rules concerning data use may undermine developers' ability to train accurate AI systems, limiting their usefulness in PA-LTC contexts. Fourth, the importance of obtaining consent before AI is used and discussions about how that care should continue if there are concerns about an ongoing decline in cognition. Together, these considerations elevate existing frameworks and adapt them to the context-specific case of PA-LTC. It is hoped that future research will examine the legal implications of these matters in each of these specific cases.

Framework of the strengths and challenges of clinically integrated trials: An expert panel report

The limitations of the explanatory clinical trial framework include the high expense of implementing explanatory trials, restrictive entry criteria for participants, and redundant logistical processes. These limitations can result in slow evidence generation that is not responsive to population health needs, yielding evidence that is not generalizable. Clinically integrated trials, which integrate clinical research into routine care, represent a potential solution to this challenge and an opportunity to support learning health systems. The operational and design features of clinically integrated trials include a focused scope, simplicity in design and requirements, the leveraging of existing data structures, and patient participation in the entire trial process. These features are designed to minimize barriers to participation and trial execution and reduce additional research burdens for participants and clinicians alike. Broad adoption and scalability of clinically integrated trials are dependent, in part, on continuing regulatory, healthcare system, and payer support. This analysis presents a framework of the strengths and challenges of clinically integrated trials and is based on a multidisciplinary expert "Think Tank" panel discussion that included representatives from patient populations, academia, non-profit funding agencies, the U.S. Food and Drug Administration, and industry.

Effects of Activities on the Psychological Well-Being of Caregivers of Older Adults: A Systematic Review

Given that approximately 41.8 million Americans provide unpaid care to older adults and caregiving roles are often associated with decreased well-being, it is critical to identify strategies to maximize their well-being. The purpose of this review was to explore which activities significantly improve well-being among caregivers of older adults. A systematic literature review was conducted using PsycINFO and 24 research articles met inclusion criteria and were included in the final analysis. Eight cohesive activity categories were identified: Social (n = 5), Psychoeducation (n = 3), Arts/entertainment in the home (n = 2), Psychotherapy (n = 5), Religious/Spiritual (n = 4), Multimodal (n = 4), Physical (n = 5), and Arts/entertainment outside the home (n = 2). Findings suggest that caregivers of older adults should seek opportunities for engagement in meaningful activities, particularly social, psychoeducational activities, arts/entertainment activities in the home, which showed positive impacts, as well as psychotherapy, religious/spiritual, multimodal, and physical activities, which showed mixed impacts on caregivers' psychological well-being.

Machine Learning Models for Predicting Mortality in Patients with Cirrhosis and Acute Upper Gastrointestinal Bleeding at an Emergency Department: A Retrospective Cohort Study

BACKGROUND

Cirrhosis is a major global cause of mortality, and upper gastrointestinal (GI) bleeding significantly increases the mortality risk in these patients. Although scoring systems such as the Child-Pugh score and the Model for End-stage Liver Disease evaluate the severity of cirrhosis, none of these systems specifically target the risk of mortality in patients with upper GI bleeding. In this study, we constructed machine learning (ML) models for predicting mortality in patients with cirrhosis and upper GI bleeding, particularly in emergency settings, to achieve early intervention and improve outcomes.

METHODS

In this retrospective study, we analyzed the electronic health records of adult patients with cirrhosis who presented at an emergency department (ED) with GI bleeding between 2001 and 2019. Data were divided into training and testing sets at a ratio of 90:10. The ability of three ML models-a linear regression model, an XGBoost (XGB) model, and a three-layer neural network model-to predict mortality in the patients was evaluated.

RESULTS

A total of 16,025 patients with cirrhosis and 32,826 ED visits for upper GI bleeding were included in the study. The in-hospital and ED mortality rates were 11.2% and 2.2%, respectively. The XGB model exhibited the highest performance in predicting both in-hospital and ED mortality (area under the receiver operating characteristic curve: 0.866 and 0.861, respectively). International normalized ratio, renal function, red blood cell distribution width, age, and white blood cell count were the strongest predictors in all the ML models. The median ED length of stay for the ED mortality group was 17.54 h (7.16-40.01 h).

CONCLUSIONS

ML models can be used to predict mortality in patients with cirrhosis and upper GI bleeding. Of the three models, the XGB model exhibits the highest performance. Further research is required to determine the actual efficacy of our ML models in clinical settings.

Predictors of Medical and Dental Clinic Closure by Machine Learning Methods: Cross-Sectional Study Using Empirical Data

BACKGROUND

Small clinics are important in providing health care in local communities. Accurately predicting their closure would help manage health care resource allocation. There have been few studies on the prediction of clinic closure using machine learning techniques.

OBJECTIVE

This study aims to test the feasibility of predicting the closure of medical and dental clinics (MCs and DCs, respectively) and investigate important factors associated with their closure using machine running techniques.

METHODS

The units of analysis were MCs and DCs. This study used health insurance administrative data. The participants of this study ran and closed clinics between January 1, 2020, and December 31, 2021. Using all closed clinics, closed and run clinics were selected at a ratio of 1:2 based on the locality of study participants using the propensity matching score of logistic regression. This study used 23 and 19 variables to predict the closure of MCs and DCs, respectively. Key variables were extracted using permutation importance and the sequential feature selection technique. Finally, this study used 5 and 6 variables of MCs and DCs, respectively, for model learning. Furthermore, four machine learning techniques were used: (1) logistic regression, (2) support vector machine, (3) random forest (RF), and (4) Extreme Gradient Boost. This study evaluated the modeling accuracy using the area under curve (AUC) method and presented important factors critically affecting closures. This study used SAS (version 9.4; SAS Institute Inc) and Python (version 3.7.9; Python Software Foundation).

RESULTS

The best-fit model for the closure of MCs with cross-validation was the support vector machine (AUC 0.762, 95% CI 0.746-0.777; P<.001) followed by RF (AUC 0.736, 95% CI 0.720-0.752; P<.001). The best-fit model for DCs was Extreme Gradient Boost (AUC 0.700, 95% CI 0.675-0.725; P<.001) followed by RF (AUC 0.687, 95% CI 0.661-0.712; P<.001). The most significant factor associated with the closure of MCs was years of operation, followed by population growth, population, and percentage of medical specialties. In contrast, the main factor affecting the closure of DCs was the number of patients, followed by annual variation in the number of patients, year of operation, and percentage of dental specialists.

CONCLUSIONS

This study showed that machine running methods are useful tools for predicting the closure of small medical facilities with a moderate level of accuracy. Essential factors affecting medical facility closure also differed between MCs and DCs. Developing good models would prevent unnecessary medical facility closures at the national level.

Prevalence of alcohol use disorders documented in electronic health records in primary care across intersections of race or ethnicity, sex, and socioeconomic status

BACKGROUND

Diagnosis of alcohol use disorder (AUD) in primary care is critical for increasing access to alcohol treatment. However, AUD is underdiagnosed and may be inequitably diagnosed due to societal structures that determine access to resources (e.g., structural racism that limits opportunities for some groups and influences interpersonal interactions in and beyond health care). This study described patterns of provider-documented AUD in primary care across intersections of race, ethnicity, sex, and community-level socioeconomic status (SES).

METHODS

This cross-sectional study used EHR data from a regional healthcare system with 35 primary care clinics that included adult patients who completed alcohol screenings between 3/1/2015 and 9/30/2020. The prevalence of provider-documented AUD in primary care based on International Classification of Diseases-9 (ICD-9) and ICD-10 diagnoses was compared across intersections of race, ethnicity, sex, and community-level SES.

RESULTS

Among 439,375 patients, 6.6% were Latine, 11.0% Asian, 5.4% Black, 1.3% Native Hawaiian/Pacific Islander (NH/PI), 1.5% American Indian/Alaska Native (AI/AN), and 74.2% White, and 58.3% women. The overall prevalence of provider-documented AUD was 1.0% and varied across intersecting identities. Among women, the prevalence was highest for AI/AN women with middle SES, 1.5% (95% CI 1.0-2.3), and lowest for Asian women with middle SES, 0.1% (95% CI 0.1-0.2). Among men, the prevalence was highest for AI/AN men with high and middle SES, 2.0% (95% CI 1.1-3.4) and 2.0% (95% CI 1.2-3.2), respectively, and lowest for Asian men with high SES, 0.5% (95% CI 0.3-0.7). Black and Latine patients tended to have a lower prevalence of AUD than White patients, across all intersections of sex and SES except for Black women with high SES. There were no consistent patterns of the prevalence of AUD diagnosis that emerged across SES.

CONCLUSION

The prevalence of provider-documented AUD in primary care was highest in AI/AN men and women and lowest in Asian men and women. Findings of lower prevalence of provider-documented AUD in Black and Hispanic than White patients across most intersections of sex and SES differed from prior studies. Findings may suggest that differences in access to resources, which vary in effects across these identity characteristics and lived experiences, influence the diagnosis of AUD in clinical care.

Experiences and impacts of psychological support following adverse neonatal experiences or perinatal loss: a qualitative analysis

BACKGROUND

Poor parental mental health in the perinatal period has detrimental impacts on the lives and relationships of parents and their babies. Parents whose babies are born premature and/or sick and require neonatal care or those who experience perinatal loss are at increased risk of adverse mental health outcomes. In 2021 a North-West charity received funding to offer psychological support to service users of infants admitted to neonatal care or those who had experienced perinatal loss, named the Family Well-being Service (FWS). The FWS offered three different types of support - ad hoc support at the neonatal units or specialist clinics; one-to-one person-centred therapy; or group counselling. Here we report the qualitative findings from an independent evaluation of the FWS.

METHODS

Thirty-seven interviews took place online or over the phone with 16 service users (of whom two took part in a follow-up interview), eight FWS providers and 11 healthcare professionals. Interviews were coded and analysed using thematic analysis.

RESULTS

The analysis revealed two themes. 'Creating time and space for support' detailed the informational, contextual, and relational basis of the service. This theme describes the importance of tailoring communications and having a flexible and proactive approach to service user engagement. Service users valued being listened to without judgement and having the space to discuss their own needs with a therapist who was independent of healthcare. Communication, access, and service delivery barriers are also highlighted. The second theme - 'making a difference' - describes the cognitive, emotional, and interpersonal benefits for service users. These included service users being provided with tools for positive coping, and how the support had led to enhanced well-being, improved relationships, and confidence in returning to work.

CONCLUSION

The findings complement and extend the existing literature by offering new insights into therapeutic support for service users experiencing adverse neonatal experiences or perinatal loss. Key mechanisms of effective support, irrespective of whether it is provided on a one-to-one or group basis were identified. These mechanisms include clear information, flexibility (in access or delivery), being independent of statutory provision, focused on individual needs, active listening, the use of therapeutic tools, and positive relationships with the therapist. Further opportunities to engage with those less willing to take up mental health support should be developed.

Beyond the incubator: applying a "one health" approach in the NICU

A "one health" approach recognises that human health, animal health and planetary health are closely interlinked and that a transdisciplinary approach is required to fully understand and maintain global health. While, by necessity, Neonatal Intensive Care has traditionally focused on the acutely unwell newborn, the avoidance of long-term harm is core to many management decisions. The COVID 19 pandemic and climate crisis have brought into sharp relief the importance of a "one health" approach as part of long-term health promotion in the holistic care of neonates, who may survive to experience the burden of future environmental crises. This narrative review seeks to integrate what we know about "one health" issues in the neonatal intensive care unit, notably antimicrobial resistance and climate change, and suggest "everyday changes" which can be utilised by practitioners to minimise the impact of neonatal intensive care on these global health issues. Many of the changes suggested not only represent important improvements for planetary health but are also core to good neonatal practice. IMPACT: Neonatal patients are likely to bear the burden of future environmental crises including pandemics and climate related disasters. While the focus of intensive care practitioners is acute illness, awareness of "one health" problems are important for our smallest patients as part of preventing long-term harm. High quality neonatal care can benefit both the planet and our patients.

Barriers to and Facilitators of Artificial Intelligence Adoption in Health Care: Scoping Review

BACKGROUND

Artificial intelligence (AI) use cases in health care are on the rise, with the potential to improve operational efficiency and care outcomes. However, the translation of AI into practical, everyday use has been limited, as its effectiveness relies on successful implementation and adoption by clinicians, patients, and other health care stakeholders.

OBJECTIVE

As adoption is a key factor in the successful proliferation of an innovation, this scoping review aimed at presenting an overview of the barriers to and facilitators of AI adoption in health care.

METHODS

A scoping review was conducted using the guidance provided by the Joanna Briggs Institute and the framework proposed by Arksey and O'Malley. MEDLINE, IEEE Xplore, and ScienceDirect databases were searched to identify publications in English that reported on the barriers to or facilitators of AI adoption in health care. This review focused on articles published between January 2011 and December 2023. The review did not have any limitations regarding the health care setting (hospital or community) or the population (patients, clinicians, physicians, or health care administrators). A thematic analysis was conducted on the selected articles to map factors associated with the barriers to and facilitators of AI adoption in health care.

RESULTS

A total of 2514 articles were identified in the initial search. After title and abstract reviews, 50 (1.99%) articles were included in the final analysis. These articles were reviewed for the barriers to and facilitators of AI adoption in health care. Most articles were empirical studies, literature reviews, reports, and thought articles. Approximately 18 categories of barriers and facilitators were identified. These were organized sequentially to provide considerations for AI development, implementation, and the overall structure needed to facilitate adoption.

CONCLUSIONS

The literature review revealed that trust is a significant catalyst of adoption, and it was found to be impacted by several barriers identified in this review. A governance structure can be a key facilitator, among others, in ensuring all the elements identified as barriers are addressed appropriately. The findings demonstrate that the implementation of AI in health care is still, in many ways, dependent on the establishment of regulatory and legal frameworks. Further research into a combination of governance and implementation frameworks, models, or theories to enhance trust that would specifically enable adoption is needed to provide the necessary guidance to those translating AI research into practice. Future research could also be expanded to include attempts at understanding patients' perspectives on complex, high-risk AI use cases and how the use of AI applications affects clinical practice and patient care, including sociotechnical considerations, as more algorithms are implemented in actual clinical environments.

Gap analysis of strategies for promoting interprofessional teams in healthcare units

PURPOSE

A healthcare unit's effectiveness largely depends on how well its interprofessional teams work together. Unfortunately, the strategies used to improve these teams often lack substance. This study analyzed these strategies and found a performance gap.

DESIGN/METHODOLOGY/APPROACH

This study took a unique mixed-method approach, systematically reviewing both qualitative and quantitative studies that identified strategies to enhance interprofessional teams in healthcare units. To gauge the effectiveness of these strategies, the researcher utilized an Importance-Performance Analysis (IPA) in four specialized clinical training centers in Hamadan province, Iran. The analysis of the IPA involved 35 experts from these centers as the statistical population.

FINDINGS

Based on a systematic review, there are seven categories: contextual, strategic, communication, organizational, individual, Human Resources Management (HRM), and environmental for promoting interprofessional teams with a total of 36 sub-indicator. Based on the IPA, the HRM aspect shows the most extensive performance gap. The individual and organizational aspects fall under resource wastage, and the environmental aspect is within the indifferent zone. Also, some critical sub-indicators, such as incentives/rewards, roles and responsibilities, financial resources, team-initiated innovation, the culture of respect, partner resources, humility, data availability, set expectations, and team availability, are in the weak areas.

PRACTICAL IMPLICATIONS

This research has identified critical areas for improvement in promoting teamwork in clinical training centers through a comprehensive gap analysis. It also presents practical policy solutions to address these weak points, providing a clear roadmap for enhancing interprofessional teams in healthcare units.

ORIGINALITY/VALUE

Improving teamwork in healthcare can be challenging, but it is possible with proper strategies and tools. One of the highlights of the recent study was the combination of systematic review studies with IPA to identify areas for improving interprofessional teamwork in clinical training centers.

Effectiveness of ChatGPT 4.0 in Telemedicine-Based Management of Metastatic Prostate Carcinoma

The recent rise in telemedicine, notably during the COVID-19 pandemic, highlights the potential of integrating artificial intelligence tools in healthcare. This study assessed the effectiveness of ChatGPT versus medical oncologists in the telemedicine-based management of metastatic prostate cancer. In this retrospective study, 102 patients who met inclusion criteria were analyzed to compare the competencies of ChatGPT and oncologists in telemedicine consultations. ChatGPT's role in pre-charting and determining the need for in-person consultations was evaluated. The primary outcome was the concordance between ChatGPT and oncologists in treatment decisions. Results showed a moderate concordance (Cohen's Kappa = 0.43, p < 0.001). The number of diagnoses made by both parties was not significantly different (median number of diagnoses: 5 vs. 5, p = 0.12). In conclusion, ChatGPT exhibited moderate agreement with oncologists in management via telemedicine, indicating the need for further research to explore its healthcare applications.

The essential role of dual-energy x-ray absorptiometry in the prediction of subclinical cardiovascular disease

Subclinical cardiovascular disease (Sub-CVD) is an early stage of cardiovascular disease and is often asymptomatic. Risk factors, including hypertension, diabetes, obesity, and lifestyle, significantly affect Sub-CVD. Progress in imaging technology has facilitated the timely identification of disease phenotypes and risk categorization. The critical function of dual-energy x-ray absorptiometry (DXA) in predicting Sub-CVD was the subject of this research. Initially used to evaluate bone mineral density, DXA has now evolved into an indispensable tool for assessing body composition, which is a pivotal determinant in estimating cardiovascular risk. DXA offers precise measurements of body fat, lean muscle mass, bone density, and abdominal aortic calcification, rendering it an essential tool for Sub-CVD evaluation. This study examined the efficacy of DXA in integrating various risk factors into a comprehensive assessment and how the application of machine learning could enhance the early discovery and control of cardiovascular risks. DXA exhibits distinct advantages and constraints compared to alternative imaging modalities such as ultrasound, computed tomography, magnetic resonance imaging, and positron emission tomography. This review advocates DXA incorporation into cardiovascular health assessments, emphasizing its crucial role in the early identification and management of Sub-CVD.

Metrics used in quality improvement publications addressing environmental sustainability in healthcare: A scoping review protocol

Quality improvement approaches are increasingly being used to address the problem of healthcare's climate and ecological impact. While sustainability is increasingly recognized as a domain of quality, consensus is lacking on the most appropriate measures and metrics for those looking to reduce ecological impacts through quality improvement initiatives. We propose a scoping review to summarize approaches for selecting and quantifying ecological impacts in the published quality improvement literature. We will search multiple electronic databases (MEDLINE, EMBASE, CINAHL, and Scopus) from 2000 onwards, to identify published quality improvement initiatives in the human healthcare setting intended to address ecological impact with at least one quantitative measure of ecological impact, such as kilograms of carbon dioxide equivalent greenhouse gas. Two independent reviewers working in parallel will screen studies for inclusion and abstract study data, including publication, study, and ecological impact characteristics. Charted data will be synthesized narratively as well as with descriptive tables, figures, and summary statistics. In doing so, we will map areas of relative focus as well as gaps in the measurement of ecological impact across quality improvement initiatives. This map can in turn be used to raise awareness of ecological impacts requiring broader consideration, encouraging holistic and clinically relevant approaches to measuring ecological impact in future quality improvement work.

Perspectives of medical imaging professionals about the impact of AI on Swiss radiographers

INTRODUCTION

Artificial Intelligence (AI) is increasingly implemented in medical imaging practice, however, its impact on radiographers practice is not well studied. The aim of this study was to explore the perceived impact of AI on radiographers' activities and profession in Switzerland.

METHODS

A survey conducted in the UK, translated into French and German, was disseminated through professional bodies and social media. The participants were Swiss radiographers (clinical/educators/ researchers/students) and physicians working within the medical imaging profession (radiology/nuclear medicine/radiation-oncology). The survey covered five sections: demographics, AI-knowledge, skills, confidence, perceptions about the AI impact. Descriptive, association statistics and qualitative thematic analysis were conducted.

RESULTS

A total of 242 responses were collected (89% radiographers; 11% physicians). AI is being used by 43% of participants in clinical practice, but 64% of them did not feel confident with AI-terminology. Participants viewed AI as an opportunity (57%), while 19% considered it as a threat. The opportunities were associated with streamlining repetitive tasks, minimizing errors, increasing time towards patient-centered care, research, and patient safety. The significant threats identified were reduction on work positions (23%), decrease of the radiographers' expertise level due to automation bias (16%). Participants (68%) did not feel well trained/prepared to implement AI in their practice, highlighting the non-availability of specific training (88%). 93% of the participants mentioned that AI education should be included at undergraduate education program.

CONCLUSION

Although most participants perceive AI as an opportunity, this study identified areas for improvement including lack of knowledge, educational supports/training, and confidence in radiographers. Customised training needs to be implemented to improve clinical practice and understanding of how AI can benefit radiographers.

"Visualization matters" - stereoscopic visualization of 3D graphic neuroanatomic models through AnaVu enhances basic recall and radiologic anatomy learning when compared with monoscopy

BACKGROUND

The authors had previously developed AnaVu, a low-resource 3D visualization tool for stereoscopic/monoscopic projection of 3D models generated from pre-segmented MRI neuroimaging data. However, its utility in neuroanatomical education compared to conventional methods (specifically whether the stereoscopic or monoscopic mode is more effective) is still unclear.

METHODS

A three-limb randomized controlled trial was designed. A sample (n = 152) from the 2022 cohort of MBBS students at Government Medical College, Thiruvananthapuram (GMCT), was randomly selected from those who gave informed consent. After a one-hour introductory lecture on brainstem anatomy and a dissection session, students were randomized to three groups (S - Stereo; M - Mono and C - Control). S was given a 20-min demonstration on the brainstem lesson module in AnaVu in stereoscopic mode. M was given the same demonstration, but in monoscopic mode. The C group was taught using white-board drawn diagrams. Pre-intervention and post-intervention tests for four domains (basic recall, analytical, radiological anatomy and diagram-based questions) were conducted before and after the intervention. Cognitive loads were measured using a pre-validated tool. The groups were then swapped -S→ M, M →S and C→S, and they were asked to compare the modes.

RESULTS

For basic recall questions, there was a statistically significant increase in the pre/post-intervention score difference of the S group when compared to the M group [p = 0.03; post hoc analysis, Bonferroni corrections applied] and the C group [p = 0.001; ANOVA test; post hoc analysis, Bonferroni corrections applied]. For radiological anatomy questions, the difference was significantly higher for S compared to C [p < 0.001; ANOVA test; post hoc analysis, Bonferroni corrections applied]. Cognitive load scores showed increased mean germane load for S (33.28 ± 5.35) and M (32.80 ± 7.91) compared with C (28.18 ± 8.17). Subjective feedbacks showed general advantage for S and M compared to C. Out of the S and M swap cohorts, 79/102 preferred S, 13/102 preferred M, and 6/102 preferred both.

CONCLUSIONS

AnaVu tool seems to be effective for learning neuroanatomy. The specific advantage seen when taught with stereoscopy in basic recall and radiological anatomy learning shows the importance of how visualization mode influences neuroanatomy learning. Since both S and M are preferred in subjective feedbacks, these results have implications in choosing methods (stereoscopic - needs 3D projectors; monoscopic - needs web based or hand-held devices) to scale AnaVu for anatomy teaching in medical colleges in India. Since stereoscopic projection is technically novel and cost considerations are slightly higher compared to monoscopic projection, the specific advantages and disadvantages of each are relevant in the Indian medical education scenario.

Patient safety during transfers from critical care: developing and assessing a checklist

Critically ill patients often need to be transferred from the intensive care unit (ICU) to the imaging department. This can compromise their safety, not only because of the inherent risk of deterioration but also because of the potential for incidents due to the inadequate preparation of medicines, equipment and monitoring. Using a patient transfer checklist can reduce the risk of human factor errors. This article reports on a quality improvement project conducted at the ICU of an acute hospital trust in the Midlands to develop and evaluate a patient transfer checklist. The checklist was developed based on guidance from the Intensive Care Society and evaluated using retrospective incident reports, an audit of staff compliance and a user survey. Using a transfer checklist in the ICU is likely to reduce patient safety incidents during transfers, but a shift in workplace culture may be needed to enhance incident reporting.

The AI revolution in glaucoma: Bridging challenges with opportunities

Recent advancements in artificial intelligence (AI) herald transformative potentials for reshaping glaucoma clinical management, improving screening efficacy, sharpening diagnosis precision, and refining the detection of disease progression. However, incorporating AI into healthcare usages faces significant hurdles in terms of developing algorithms and putting them into practice. When creating algorithms, issues arise due to the intensive effort required to label data, inconsistent diagnostic standards, and a lack of thorough testing, which often limits the algorithms' widespread applicability. Additionally, the "black box" nature of AI algorithms may cause doctors to be wary or skeptical. When it comes to using these tools, challenges include dealing with lower-quality images in real situations and the systems' limited ability to work well with diverse ethnic groups and different diagnostic equipment. Looking ahead, new developments aim to protect data privacy through federated learning paradigms, improving algorithm generalizability by diversifying input data modalities, and augmenting datasets with synthetic imagery. The integration of smartphones appears promising for using AI algorithms in both clinical and non-clinical settings. Furthermore, bringing in large language models (LLMs) to act as interactive tool in medicine may signify a significant change in how healthcare will be delivered in the future. By navigating through these challenges and leveraging on these as opportunities, the field of glaucoma AI will not only have improved algorithmic accuracy and optimized data integration but also a paradigmatic shift towards enhanced clinical acceptance and a transformative improvement in glaucoma care.

Accuracy of surgical death information: comparison of data held by Victorian Audit of Surgical Mortality and Victorian Agency for Health Information

BACKGROUND

The Victorian Audit of Surgical Mortality (VASM) investigates all surgically related deaths in Victoria. The Victorian Admitted Episodes Database (VAED) is an administrative dataset maintained by the Health Department's Victorian Agency of Health Information (VAHI). We have reviewed clinical records to assess the correlation between deaths reported to the databases.

METHODS

Data July 2019 to June 2020 were compared. All hospitals that had surgical deaths not reported to VASM were asked to provide clinical summaries which were analysed to assess the deaths should have been reported. Case note review of 280 deaths only reported to VAHI through VAED was undertaken to establish whether these should have been reported to VASM.

RESULTS

VASM received 1763 reported surgical deaths with VAHI recording 1907. Using individual patient identifiers, 517 (29.3%) of the VASM deaths were not reported to VAHI but subsequent data analysis revealed they were correctly identified as reportable deaths in 385 (74.5%). There were 914 (47.9%) VAED recorded deaths that were not reported to VASM. 280/914 (30.6%) were reviewed from 21 hospitals. Only 24 (8.6%) of these had a surgical procedure in the patient's final admission and should have been reported. This suggests that the current method of VASM capture of surgical mortality only missed 4% cases for the 2019/20 year.

CONCLUSION

There were major differences between surgical deaths reported to VASM and those reported by health services and recorded in VAED. Less than 5% of cases are not reported to VASM and thus not subjected to peer review.

Role and contribution of the nurse in caring for patients with palliative care needs: A scoping review

BACKGROUND

The provision of high-quality palliative care is important to nursing practice. However, caring for palliative care patients and their families is challenging within a complex everchanging health environment. Nonetheless the caring, artistic role of the nurse is fundamental to the care of the patient and family. However, this role is currently being overshadowed by the technical and scientific elements of nursing.

METHODS

A scoping review was conducted utilising Arksey and O'Malley's framework to identify the role and contribution of nurses in caring for patients with palliative care needs. An open time period search of eight electronic databases (MEDLINE, CINAHL, Academic Search Complete, PsycINFO, EMBASE, Web of Science, Scopus and Cochrane Library) was conducted on the 8th of March 2023 and updated on the 30th of April 2024. Screening was performed independently by two reviewers against eligibility criteria with meetings between authors to discuss included papers and form a consensus. Data was extracted relating to palliative care nursing, methodology, key findings, and recommendations. The analysed and summarised data was mapped onto Oldland et al seven domains framework: (a) medical/nursing and technical competence, (b) person centred care, (c) positive interpersonal behaviours, (d) clinical leadership and governance, (e) promotion of safety, (f) management of the environment, and (g) evidence-based practice.

RESULTS

Fifty-five papers met the criteria for this review which describes the role and contribution of nurses in caring for palliative patients across all domains of professional practice. The review found the leading areas of nurse contribution were person centred, interpersonal and nursing care aspects, with leadership, managing the environment, patient safety and evidence-based practice evident but scoring lower. The contribution of the nurse in palliative care supports a biopsychosocial-educational approach to addressing the physical, emotional and social needs of patients with palliative care needs and their families across the care continuum.

CONCLUSION

Nurses in palliative care engage in a wide range of roles and responsibilities in caring for patients and their families with palliative care needs. However, there remains minimal evidence on the assessment, intervention, and evaluation strategies used by nurses to highlight the importance of their role in caring for patients and their families in this area. The findings of this review suggest that the artistic element of nursing care is being diluted and further research with a focus on evidencing the professional competence and artistic role of the nurse in the provision of palliative care is required. In addition, research is recommended that will highlight the impact of this care on patient and family care outcomes and experiences.

Healthcare-related carbon footprinting-lower impact of a coronary stenting compared to a coronary surgery pathway

Healthcare is a major generator of greenhouse gases, so consideration of this contribution to climate change needs to be quantified in ways that can inform models of care. Given the availability of activity-based financial data, environmentally-extended input-output (EEIO) analysis can be employed to calculate systemic carbon footprints for healthcare activities, allowing comparison of different patient care pathways. We thus quantified and compared the carbon footprint of two common care pathways for patients with stable coronary artery disease, with similar clinical outcomes: coronary stenting and coronary artery bypass surgery (CABG). Healthcare cost data for these two pathways were disaggregated and the carbon footprint associated with this expenditure was calculated by connecting the flow of money within the economy to the greenhouse gases emitted to support the full range of associated activities. The systemic carbon footprint associated with an average stable patient CABG pathway, at a large tertiary referral hospital in Sydney, Australia in 2021-22, was 11.5 tonnes CO2-e, 4.9 times greater than the 2.4 tonnes CO2-e footprint of an average comparable stenting pathway. These data suggest that a stenting pathway for stable coronary disease should be preferred on environmental grounds and introduces EEIO analysis as a practical tool to assist in health-care related carbon footprinting.

Assessing the Readability, Reliability, and Quality of AI-Modified and Generated Patient Education Materials for Endoscopic Skull Base Surgery

BACKGROUND

Despite National Institutes of Health and American Medical Association recommendations to publish online patient education materials at or below sixth-grade literacy, those pertaining to endoscopic skull base surgery (ESBS) have lacked readability and quality. ChatGPT is an artificial intelligence (AI) system capable of synthesizing vast internet data to generate responses to user queries but its utility in improving patient education materials has not been explored.

OBJECTIVE

To examine the current state of readability and quality of online patient education materials and determined the utility of ChatGPT for improving articles and generating patient education materials.

METHODS

An article search was performed utilizing 10 different search terms related to ESBS. The ten least readable existing patient-facing articles were modified with ChatGPT and iterative queries were used to generate an article de novo. The Flesch Reading Ease (FRE) and related metrics measured overall readability and content literacy level, while DISCERN assessed article reliability and quality.

RESULTS

Sixty-six articles were located. ChatGPT improved FRE readability of the 10 least readable online articles (19.7 ± 4.4 vs. 56.9 ± 5.9, p < 0.001), from university to 10th grade level. The generated article was more readable than 48.5% of articles (38.9 vs. 39.4 ± 12.4) and higher quality than 94% (51.0 vs. 37.6 ± 6.1). 56.7% of the online articles had "poor" quality.

CONCLUSIONS

ChatGPT improves the readability of articles, though most still remain above the recommended literacy level for patient education materials. With iterative queries, ChatGPT can generate more reliable and higher quality patient education materials compared to most existing online articles and can be tailored to match readability of average online articles.

Effects of transparent online open procurement on prices, volumes, and costs of medicines: an interrupted time series study in Ningxia, China

Objectives

To assess the effects of the transparent online open procurement arrangement on the prices, volumes, and costs of medicines in Ningxia, China.

Methods

Data were extracted from the Ningxia pharmaceutical procurement platform, covering 16 months of purchase orders (December 2019 to March 2021) prior to the implementation of the transparent online open procurement policy and 20 months of purchase orders after the implementation of the policy (April 2021 to November 2022). Interrupted time series (ITS) analysis was performed to evaluate the effects of the transparent online open procurement policy on the prices, volumes, and total costs of the purchase orders.

Results

After implementation of the transparent online open procurement policy, the average price of purchased medicines showed a declining trend by 0.012 Yuan per month, while the total volume of purchase orders declined at a rate by 1.741 million per month measured by the smallest formulation units and the total costs of the purchase orders decreased at a rate by 5.525 million Yuan per month.

Conclusion

The transparent online open procurement policy resulted in reduced prices, lowered volumes, and lowered total costs of purchased orders of medicines.

Meta-analysis of the human gut microbiome uncovers shared and distinct microbial signatures between diseases

Microbiome studies have revealed gut microbiota's potential impact on complex diseases. However, many studies often focus on one disease per cohort. We developed a meta-analysis workflow for gut microbiome profiles and analyzed shotgun metagenomic data covering 11 diseases. Using interpretable machine learning and differential abundance analysis, our findings reinforce the generalization of binary classifiers for Crohn's disease (CD) and colorectal cancer (CRC) to hold-out cohorts and highlight the key microbes driving these classifications. We identified high microbial similarity in disease pairs like CD vs ulcerative colitis (UC), CD vs CRC, Parkinson's disease vs type 2 diabetes (T2D), and schizophrenia vs T2D. We also found strong inverse correlations in Alzheimer's disease vs CD and UC. These findings, detected by our pipeline, provide valuable insights into these diseases.

IMPORTANCE

Assessing disease similarity is an essential initial step preceding a disease-based approach for drug repositioning. Our study provides a modest first step in underscoring the potential of integrating microbiome insights into the disease similarity assessment. Recent microbiome research has predominantly focused on analyzing individual diseases to understand their unique characteristics, which by design excludes comorbidities in individuals. We analyzed shotgun metagenomic data from existing studies and identified previously unknown similarities between diseases. Our research represents a pioneering effort that utilizes both interpretable machine learning and differential abundance analysis to assess microbial similarity between diseases.

Wider health needs in attention deficit hyperactivity disorder from lived and professional experience: a qualitative framework analysis

OBJECTIVES

This study aimed to explore the perspectives of people with attention deficit hyperactivity disorder (ADHD), their supporters and primary care professionals (PCPs), on the wider physical and mental health needs of people with ADHD and the support currently available.

DESIGN

Qualitative semi-structured interviews, analysed using reflexive thematic analysis.

SETTING

Five general practice surgeries across England.

PARTICIPANTS

Participants with lived experience (people with ADHD and their supporters (n=11)) and PCPs (n=9) (eg, general practitioners and practice managers), recruited via clinical academic networks and previous work packages of this study.

RESULTS

We generated three major themes in relation to ADHD, using reflexive thematic analysis: understanding health, barriers to health and addressing health. Within these, participants reflected on mental and physical health challenges, as well as wider social difficulties and variability in support offered/accessed.

CONCLUSIONS

This study highlights that health problems in ADHD are complex and rooted both in individual factors (eg, mental health) and social factors (eg, support). This study also highlights the differences in expectations and fulfilment of healthcare.

Temporal structures that determine consistency and quality of care: a case study in hyperacute stroke services

BACKGROUND

Temporal structuring is determined by practices and social norms and affects the quality and timing of care. In this case study of hyperacute stroke wards which provide initial stroke investigation, treatment and care, we explored temporal structuring patterns to explain how these may affect quality of care.

METHODS

This paper presents a thematic analysis of qualitative interviews with hyperacute stroke staff (n=76), non-participant observations (n=41, ~102 hours) and documentary analysis of the relevant service standards guidance. We used an inductive coding process to generate thematic findings around the concept of temporal structuring, with graphically illustrated examples.

RESULTS

Five temporal structures influence what-happens-when: (1) clinical priorities and quality assurance metrics motivate rapid activity for the initial life-prolonging assessments and interventions; (2) static features of ward organisation such as rotas and ward rounds impact consistency of care, determining timing and quality of care for patients; (3) some services experimented with staff rotas to try to meet peaks in demand, sometimes unsuccessfully; (4) implicit social norms or heuristics about perceived necessity affected staff motivation to make changes or improvements to consistency of care, particularly around weekend work; and (5) after-effects such as bottlenecks or backlogs affect quality of care, which are hard to measure effectively to drive service improvement.

CONCLUSIONS

Patients need temporally consistent high quality of care. Temporal consistency stems from the design of services, including staffing, targets and patient pathway design as well as cultural attitudes to working patterns. Improvements to consistency of care will be limited without changes to structures such as rotas and ward rounds, but also social norms around weekend work for certain professional groups.

The impact and future of artificial intelligence in medical genetics and molecular medicine: an ongoing revolution

Artificial intelligence (AI) platforms have emerged as pivotal tools in genetics and molecular medicine, as in many other fields. The growth in patient data, identification of new diseases and phenotypes, discovery of new intracellular pathways, availability of greater sets of omics data, and the need to continuously analyse them have led to the development of new AI platforms. AI continues to weave its way into the fabric of genetics with the potential to unlock new discoveries and enhance patient care. This technology is setting the stage for breakthroughs across various domains, including dysmorphology, rare hereditary diseases, cancers, clinical microbiomics, the investigation of zoonotic diseases, omics studies in all medical disciplines. AI's role in facilitating a deeper understanding of these areas heralds a new era of personalised medicine, where treatments and diagnoses are tailored to the individual's molecular features, offering a more precise approach to combating genetic or acquired disorders. The significance of these AI platforms is growing as they assist healthcare professionals in the diagnostic and treatment processes, marking a pivotal shift towards more informed, efficient, and effective medical practice. In this review, we will explore the range of AI tools available and show how they have become vital in various sectors of genomic research supporting clinical decisions.

Doctors' understanding of their learning and learning needs in Kwazulu-Natal district hospitals

BACKGROUND

 Medicine is a self-regulating profession. Doctors must learn how to self-regulate to keep up-to-date with evolving health care needs. This is challenging for those working at District Hospitals (DHs) in rural settings, where limited resources and understaffing may compound a poor approach and understanding of how to become a self-directed learner.

AIM

 To explore perspectives of doctors working in rural DHs, regarding their understanding of learning and learning needs.

SETTING

 This study was conducted in Bethesda and Mseleni DHs, in rural KwaZulu-Natal.

METHODS

 This was a qualitative study. Data was collected through 16 semi-structured interviews and non-participatory observations.

RESULTS

 Four major themes emerged: "Why I learn," "What I need to learn," "How I learn," and our learning environment." This paper focussed on the first three themes. Doctors' learning is influenced by various factors, including their engagement with clinical practice, personal motivation, and their learning process. Deliberate practice and engagement in reflective practice as key principles for workplace learning became evident.

CONCLUSION

 In rural DHs, doctors need to take a proactive self-regulated approach to their learning due to difficulties they encounter. They must build competence, autonomy, a sense of connection in their learning process, thus recognizing the need for continuous learning, motivating themselves, and understanding where they lack knowledge, all essential for achieving success.Contribution: This article contributes towards strengthening medical education in African rural context, by empowering medical educators and facility managers to meet the learning needs of doctors, thus contributing to the provision of quality health care.

A comprehensive study on unraveling the advances of immersive technologies (VR/AR/MR/XR) in the healthcare sector during the COVID-19: Challenges and solutions

The current COVID-19 pandemic has affected almost every aspect of life but its impact on the healthcare landscape is conspicuously adverse. However, digital technologies played a significant contribution in coping with the challenges spawned by this pandemic. In this list of applied digital technologies, the role of immersive technologies in battling COVID-19 is notice-worthy. Immersive technologies consisting of virtual reality (VR), augmented reality (AR), mixed reality (MR), extended reality (XR), metaverse, gamification, etc. have shown enormous market growth within the healthcare system, particularly with the emergence of pandemics. These technologies supplemented interactivity, immersive experience, 3D modeling, touching sensory elements, simulation, and feedback mechanisms to tackle the COVID-19 disease in healthcare systems. Keeping in view the applicability and significance of immersive technological advancement, the major aim of this study is to identify and highlight the role of immersive technologies concerning handling COVID-19 in the healthcare setup. The contribution of immersive technologies in the healthcare domain for the different purposes such as medical education, medical training, proctoring, online surgeries, stress management, social distancing, physical fitness, drug manufacturing and designing, and cognitive rehabilitation is highlighted. A comprehensive and in-depth analysis of the collected studies has been performed to understand the current research work and future research directions. A state-of-the-artwork is presented to identify and discuss the various issues involving the adoption of immersive technologies in the healthcare area. Furthermore, the solutions to these emerging challenges and issues have been provided based on an extensive literature study. The results of this study show that immersive technologies have the considerable potential to provide massive support to stakeholders in the healthcare system during current COVID-19 situation and future pandemics.

Potential vicious cycle between postoperative pain and sleep disorders: A bibliometric analysis

Background

Surgical pain affects postoperative sleep quality, and they jointly form a vicious cycle of mutual influence. The cycle of postoperative pain and sleep disorders could lead to delirium, cardiovascular disease, and hyperalgesia, which significantly affect patients' postoperative recovery. Thus, exploring this phenomenon is of great importance for surgical patients, and warrants further investigation.

Objective

By employing bibliometric methods, this study systematically analyzes the publications on postoperative pain-sleep disorders, identifies research trends and field dynamics, and ultimately provides insights for further progress in this research area.

Methods

In this study, we searched the Web of Science database for studies on postoperative pain and sleep disorders from 2013 to 2023, and analyzed the number of publications, journals, authors, institutions, country regions, and keywords by utilizing CiteSpace, VOSviewer, and Bibliometrix.

Results

The 1894 retrieved publications showed a trend of increasing number of publications and correlations between postoperative pain and sleep disorders from 2013 to 2023. The top countries for publications included the USA, China, etc., establishing a global collaborative network centered around the USA, China, and Europe. The top institutions for publications included University of California System, Harvard University, etc. The top authors include Christine Miaskowski, Steven M. Paul, Qiuling Shi, etc. These publications involved multiple disciplines including surgery, neurology, and anesthesiology, and various research funds including NIH, HHS, NSFC, etc. The top journals for publications included the European Archives of Oto-Rhino-Laryngology, etc. Keywords that appear most frequently in this field include "pain", "surgery", "quality of life", "sleep", "depression", and "outcomes". The thematic map indicated that the hot topics in this area include obstructive sleep apnea, tonsillectomy, children, pain, quality of life, and sleep. The undeveloped topics with research potential included postoperative pain, analgesia and dexmedetomidine, breast cancer, fatigue, and lung cancer.

Conclusion

The increased number of publications and correlations between postoperative pain and sleep disorders, and the collaborative network across the USA, China, and Europe indicate a growing global interest in this area. This study also provides valuable insights into the trend of hot topics and frontiers and shows that this is an evolving and dynamic research area.