Developing an Ontology Representing Fall Risk Management Domain Knowledge

Ontologies serve as comprehensive frameworks for organizing domain-specific knowledge, offering significant benefits for managing clinical data. This study presents the development of the Fall Risk Management Ontology (FRMO), designed to enhance clinical text mining, facilitate integration and interoperability between disparate data sources, and streamline clinical data analysis. By representing major entities within the fall risk management domain, the FRMO supports the unification of clinical language and decision-making processes, ultimately contributing to the prevention of falls among older adults. We used Ontology Web Language (OWL) to build the FRMO in Protégé. Of the seven steps of the Stanford approach, six steps were utilized in the development of the FRMO: (1) defining the domain and scope of the ontology, (2) reusing existing ontologies when possible, (3) enumerating ontology terms, (4) specifying the classes and their hierarchy, (5) defining the properties of the classes, and (6) defining the facets of the properties. We evaluated the FRMO using four main criteria: consistency, completeness, accuracy, and clarity. The developed ontology comprises 890 classes arranged in a hierarchical structure, including six top-level classes with a total of 43 object properties and 28 data properties. FRMO is the first comprehensively described semantic ontology for fall risk management. Healthcare providers can use the ontology as the basis of clinical decision technology for managing falls among older adults.

'Super boots' for soldiers: theoretical ergogenic and thermoprotective benefits of energetically optimised military combat boots

Soldiers typically perform physically demanding tasks while wearing military uniforms and tactical footwear. New research has revealed a substantial increase of ~10% in energetic cost of walking when wearing modern combat boots versus running shoes. One approach to mitigating these costs is to follow in the footsteps of recent innovations in athletic footwear that led to the development of 'super shoes', that is, running shoes designed to lower the energetic cost of locomotion and maximise performance. We modelled the theoretical effects of optimised combat boot construction on physical performance and heat strain with the intent of spurring similarly innovative research and development of 'super boots' for soldiers. We first assessed the theoretical benefits of super boots on 2-mile run performance in a typical US Army soldier using the model developed by Kipp and colleagues. We then used the Heat Strain Decision Aid thermoregulatory model to determine the metabolic savings required for a physiologically meaningful decrease in heat strain in various scenarios. Combat boots that impart a 10% improvement in running economy would result in 7.9%-15.1% improvement in 2-mile run time, for faster to slower runners, respectively. Our thermal modelling revealed that a 10% metabolic savings would more than suffice for a 0.25°C reduction in heat strain for the vast majority of work intensities and durations in both hot-dry and hot-humid environments. These findings highlight the impact that innovative military super boots would have on physical performance and heat strain in soldiers, which could potentially maximise the likelihood of mission success in real-world scenarios.

Inference of drug off-target effects on cellular signaling using interactome-based deep learning

Many diseases emerge from dysregulated cellular signaling, and drugs are often designed to target specific signaling proteins. Off-target effects are, however, common and may ultimately result in failed clinical trials. Here we develop a computer model of the cell's transcriptional response to drugs for improved understanding of their mechanisms of action. The model is based on ensembles of artificial neural networks and simultaneously infers drug-target interactions and their downstream effects on intracellular signaling. With this, it predicts transcription factors' activities, while recovering known drug-target interactions and inferring many new ones, which we validate with an independent dataset. As a case study, we analyze the effects of the drug Lestaurtinib on downstream signaling. Alongside its intended target, FLT3, the model predicts an inhibition of CDK2 that enhances the downregulation of the cell cycle-critical transcription factor FOXM1. Our approach can therefore enhance our understanding of drug signaling for therapeutic design.

A focus group interview

BACKGROUND

As healthcare and especially health technology evolve rapidly, new challenges require healthcare professionals to take on new roles. Consequently, the demand for health informatics competencies is increasing, and achieving these competencies using frameworks, such as Technology Informatics Guiding Reform (TIGER), is crucial for future healthcare.

AIM

The study examines essential health informatics and educational competencies and health informatics challenges based on TIGER Core Competency Areas. Rather than examine each country independently, the focus is on uncovering commonalities and shared experiences across diverse contexts.

METHODS

Six focus group interviews were conducted with twenty-one respondents from three different countries (Germany (n = 7), Portugal (n = 6), and Finland (n = 8)). These interviews took place online in respondents' native languages. All interviews were transcribed and then summarized by each country. Braun and Clarke's thematic analysis framework was applied, which included familiarization with the data, generating initial subcategories, identifying, and refining themes, and conducting a final analysis to uncover patterns within the data.

RESULTS

Agreed upon by all three countries, competencies in project management, communication, application in direct patient care, digital literacy, ethics in health IT, education, and information and knowledge management were identified as challenges in healthcare. Competencies such as communication, information and communication technology, project management, and education were identified as crucial for inclusion in educational programs, emphasizing their critical role in healthcare education.

CONCLUSIONS

Despite working with digital tools daily, there is an urgent need to include health informatics competencies in the education of healthcare professionals. Competencies related to application in direct patient care, IT-background knowledge, IT-supported and IT-related management are critical in educational and professional settings are seen as challenging but critical in healthcare.

Modelling of physicians' clinical information-seeking behaviour in Iran: a grounded theory study

OBJECTIVES

Exploring clinical information-seeking behaviour (CISB) and its associated factors contributes to its theoretical advancement and offers a valuable framework for addressing physicians' information needs. This study delved into the dimensions, interactions, strategies and determinants of CISB among physicians at the point of care.

DESIGN

A grounded theory study was developed based on Strauss and Corbin's approach. Data were collected by semistructured interviews and then analysed through open, axial and selective coding.

SETTING

The study was conducted at academic centres affiliated with Isfahan University of Medical Sciences.

PARTICIPANTS

This investigation involved recruiting 21 specialists and subspecialists from the academic centres.

RESULTS

The findings revealed that physicians' CISB encompassed multiple dimensions when addressing clinical inquiries. Seven principal themes emerged from the analysis: 'clinical information needs', 'clinical question characteristics', 'clinical information resources', 'information usability', 'factors influencing information seeking', 'action/interaction encountering clinical questions' and 'consequences of CISB'. The core category identified in this study was 'focused attention'.

CONCLUSIONS

The theoretical explanation demonstrated that the CISB process was interactive and dynamic. Various stimuli, including causal, contextual and intervening conditions, guide physicians in adopting information-seeking strategies and focusing on resolving clinical challenges. However, insufficient stimuli may hinder physicians' engagement in CISB. Understanding CISB helps managers, policy-makers, clinical librarians and information system designers optimally implement several interventions, such as suitable training methods, reviewing monitoring and evaluating information systems, improving clinical decision support systems, electronic medical records and electronic health records, as well as monitoring and evaluating these systems. Such measures facilitate focused attention on clinical issues and promote CISB among physicians.

Missed nursing care and its associated factors in public hospitals of Bahir Dar City, Northwest Ethiopia: a cross-sectional study

OBJECTIVES

The aim of this study was to investigate the prevalence of missed nursing care and its associated factors among public hospitals in Bahir Dar City, Northwest Ethiopia.

DESIGN

An institution-based cross-sectional study was conducted among 369 randomly selected nurses.

SETTING

The study was conducted in primary and secondary-level public hospitals in Bahir Dar City.

PARTICIPANTS

Nurses who had worked in hospitals in Bahir Dar City were included.

INTERVENTION

No intervention was needed in this study.

PRIMARY AND SECONDARY OUTCOME MEASURES

A binary logistic regression model was used for statistical analysis. Statistical significance of the association between outcome variables and independent variables was declared at a p value of <0.05 with a 95% CI.

RESULTS

The prevalence of missed nursing care in this study was 46.3% (95% CI: 41.7% to 50.9%). The activities most frequently missed were physical examination (56.4%), patient discharge planning and teaching (50.9%), providing emotional support to the patient and family (50.8%), monitoring input and output (50.2%), assisting with patient ambulation (48.5%) and documentation (48%). Factors associated with missed nursing care include: male professionals (adjusted OR (AOR): 2.9, 95% CI: 1.8 to 4.8), those who had not received on-the-job training (AOR: 2.2, 95% CI: 1.4 to 3.6), those who worked full 24-hour shifts (AOR: 3.7, 95% CI: 2.0 to 6.5), those who were dissatisfied with the level of teamwork (AOR: 4.6, 95% CI: 2.8 to 7.6) and those who had an intention to leave the nursing profession (AOR: 1.8, 95% CI: 1.1 to 2.9). These factors were statistically associated with missed nursing care.

CONCLUSION

A significant proportion of nurses missed essential nursing care activities. Efforts should be made to enhance training, improve teamwork among nurses, provide stability and adjust work shifts to mitigate this issue.

Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts

RATIONALE

Intensive care units (ICUs) admit the most severely ill patients. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff, with Early Warning Score (EWS) systems being used to identify those at risk of deterioration.

OBJECTIVES

We report the development and validation of an enhanced continuous scoring system for predicting adverse events, which combines vital signs measured routinely on acute care wards (as used by most EWS systems) with a risk score of a future adverse event calculated on discharge from the ICU.

DESIGN

A modified Delphi process identified candidate variables commonly available in electronic records as the basis for a 'static' score of the patient's condition immediately after discharge from the ICU. L1-regularised logistic regression was used to estimate the in-hospital risk of future adverse event. We then constructed a model of physiological normality using vital sign data from the day of hospital discharge. This is combined with the static score and used continuously to quantify and update the patient's risk of deterioration throughout their hospital stay.

SETTING

Data from two National Health Service Foundation Trusts (UK) were used to develop and (externally) validate the model.

PARTICIPANTS

A total of 12 394 vital sign measurements were acquired from 273 patients after ICU discharge for the development set, and 4831 from 136 patients in the validation cohort.

RESULTS

Outcome validation of our model yielded an area under the receiver operating characteristic curve of 0.724 for predicting ICU readmission or in-hospital death within 24 hours. It showed an improved performance with respect to other competitive risk scoring systems, including the National EWS (0.653).

CONCLUSIONS

We showed that a scoring system incorporating data from a patient's stay in the ICU has better performance than commonly used EWS systems based on vital signs alone.

TRIAL REGISTRATION NUMBER

ISRCTN32008295.

Design considerations for the migration from paper to screen-based media in current health education for older adults: a scoping review

OBJECTIVES

To map the current use of paper-based and/or screen-based media for health education aimed at older people.

DESIGN

A scoping review was reported following the Preferred Reporting Items of Systematic Reviews and Meta-analyses for Scoping Reviews checklist.

DATA SOURCES

The search was carried out in seven databases (Scopus, Web of Science, Embase, Medline, CINAHL, ACM Guide to Computing Literature, PsycINFO), with studies available from 2012 to the date of the search in 2022, in English, Portuguese, Italian or Spanish. In addition, Google Scholar was searched to check the grey literature. The terms used in the search strategy were older adults, health education, paper and screen-based media, preferences, intervention and other related terms.

ELIGIBILITY CRITERIA

Studies included were those that carried out health education interventions for older individuals using paper and/or screen-based media and that described barriers and/or facilitators to using these media.

DATA EXTRACTION AND SYNTHESIS

The selection of studies was carried out by two reviewers. A data extraction form was developed with the aim of extracting and recording the main information from the studies. Data were analysed descriptively using Bardin's content analysis.

RESULTS

The review included 21 studies that carried out health education interventions with different purposes, the main ones being promotion of physical activity, hypertension prevention and psychological health. All 21 interventions involved screen-based media on computers, tablets, smartphones and laptops, while only 4 involved paper-based media such as booklets, brochures, diaries, flyers and drawings. This appears to reflect a transition from paper to screen-based media for health education for the older population, in research if not in practice. However, analysis of facilitators and barriers to using both media revealed 10 design factors that could improve or reduce their use, and complementarity in their application to each media type. For example, screen-based media could have multimedia content, additional functionality and interactivity through good interaction design, but have low accessibility and require additional learning due to complex interface design. Conversely, paper-based media had static content and low functionality but high accessibility and availability and a low learning cost.

CONCLUSIONS

We recommend having improved screen-based media design, continued use of paper-based media and the possible combination of both media through the new augmented paper technology.

REGISTRATION NUMBER

Open Science Framework (DOI: 10.17605/OSF.IO/GKEAH).

Reporting form and content of research priorities identified in knee osteoarthritis clinical practice guidelines: a methodological literature analysis

OBJECTIVES

Clinical practice guideline (CPG) developers conduct systematic summaries of research evidence, providing them great capacity and ability to identify research priorities. We systematically analysed the reporting form and content of research priorities in CPGs related to knee osteoarthritis (KOA) to provide a valuable reference for guideline developers and clinicians.

DESIGN

A methodological literature analysis was done and the characteristics of the reporting form and the content of the research priorities identified in KOA CPGs were summarised.

DATA SOURCES

Six databases (PubMed, Embase, China National Knowledge Infrastructure, VIP Database for Chinese Technical Periodicals, Wanfang and Chinese Biomedical Literature Database) were searched for CPGs published from 1 January 2017 to 4 December 2022. The official websites of 40 authoritative orthopaedic societies, rheumatology societies and guideline development organisations were additionally searched.

ELIGIBILITY CRITERIA

We included all KOA CPGs published in English or Chinese from 1 January 2017 that included at least one recommendation for KOA. We excluded duplicate publications, older versions of CPGs as well as guidance documents for guideline development.

DATA EXTRACTION AND SYNTHESIS

Reviewers worked in pairs and independently screened and extracted the data. Descriptive statistics were used, and absolute frequencies and proportions of related items were calculated.

RESULTS

187 research priorities reported in 41 KOA CPGs were identified. 24 CPGs reported research priorities, of which 17 (41.5%) presented overall research priorities for the entire guideline rather than for specific recommendations. 110 (58.8%) research priorities were put forward due to lack of evidence. Meanwhile, more than 70% of the research priorities reflected the P (population) and I (intervention) structural elements, with 135 (72.2%) and 146 (78.1%), respectively. More than half of the research priorities (118, 63.8%) revolved around evaluating the efficacy of interventions. Research priorities primarily focused on physical activity (32, 17.3%), physical therapy (30, 16.2%), surgical therapy (27, 14.6%) and pharmacological treatment (26, 14.1%).

CONCLUSIONS

Research priorities reported in KOA CPGs mainly focused on evaluating non-pharmacological interventions. There exists considerable room for improvement for a comprehensive and standardised generation and reporting of research priorities in KOA CPGs.

Supporting the decision to perform molecular profiling for cancer patients based on routinely collected data through the use of machine learning

BACKGROUND

Personalized medicine offers targeted therapy options for cancer treatment. However, the decision whether to include a patient into next-generation sequencing (NGS) testing is not standardized. This may result in some patients receiving unnecessary testing while others who could benefit from it are not tested. Typically, patients who have exhausted conventional treatment options are of interest for consideration in molecularly targeted therapy. To assist clinicians in decision-making, we developed a decision support tool using routine data from a precision oncology program.

METHODS

We trained a machine learning model on clinical data to determine whether molecular profiling should be performed for a patient. To validate the model, the model's predictions were compared with decisions made by a molecular tumor board (MTB) using multiple patient case vignettes with their characteristics.

RESULTS

The prediction model included 440 patients with molecular profiling and 13,587 patients without testing. High area under the curve (AUC) scores indicated the importance of engineered features in deciding on molecular profiling. Patient age, physical condition, tumor type, metastases, and previous therapies were the most important features. During the validation MTB experts made the same decision of recommending a patient for molecular profiling only in 10 out of 15 of their previous cases but there was agreement between the experts and the model in 9 out of 15 cases.

CONCLUSION

Based on a historical cohort, our predictive model has the potential to assist clinicians in deciding whether to perform molecular profiling.

Predicting pressure injury risk in hospitalised patients using machine learning with electronic health records: a US multilevel cohort study

OBJECTIVE

To predict the risk of hospital-acquired pressure injury using machine learning compared with standard care.

DESIGN

We obtained electronic health records (EHRs) to structure a multilevel cohort of hospitalised patients at risk for pressure injury and then calibrate a machine learning model to predict future pressure injury risk. Optimisation methods combined with multilevel logistic regression were used to develop a predictive algorithm of patient-specific shifts in risk over time. Machine learning methods were tested, including random forests, to identify predictive features for the algorithm. We reported the results of the regression approach as well as the area under the receiver operating characteristics (ROC) curve for predictive models.

SETTING

Hospitalised inpatients.

PARTICIPANTS

EHRs of 35 001 hospitalisations over 5 years across 2 academic hospitals.

MAIN OUTCOME MEASURE

Longitudinal shifts in pressure injury risk.

RESULTS

The predictive algorithm with features generated by machine learning achieved significantly improved prediction of pressure injury risk (p<0.001) with an area under the ROC curve of 0.72; whereas standard care only achieved an area under the ROC curve of 0.52. At a specificity of 0.50, the predictive algorithm achieved a sensitivity of 0.75.

CONCLUSIONS

These data could help hospitals conserve resources within a critical period of patient vulnerability of hospital-acquired pressure injury which is not reimbursed by US Medicare; thus, conserving between 30 000 and 90 000 labour-hours per year in an average 500-bed hospital. Hospitals can use this predictive algorithm to initiate a quality improvement programme for pressure injury prevention and further customise the algorithm to patient-specific variation by facility.

Qualitative study exploring the design of a patient-reported symptom-based risk stratification system for suspected head and neck cancer referrals: protocol for work packages 1 and 2 within the EVEREST-HN programme

INTRODUCTION

Between 2009/2010 and 2019/2020, England witnessed an increase in suspected head and neck cancer (sHNC) referrals from 140 to 404 patients per 100 000 population. 1 in 10 patients are not seen within the 2-week target, contributing to patient anxiety. We will develop a pathway for sHNC referrals, based on the Head and Neck Cancer Risk Calculator. The evolution of a patient-reported symptom-based risk stratification system to redesign the sHNC referral pathway (EVEREST-HN) Programme comprises six work packages (WPs). This protocol describes WP1 and WP2. WP1 will obtain an understanding of language to optimise the SYmptom iNput Clinical (SYNC) system patient-reported symptom questionnaire for sHNC referrals and outline requirements for the SYNC system. WP2 will codesign key elements of the SYNC system, including the SYNC Questionnaire, and accompanying behaviour change materials.

METHODS AND ANALYSIS

WP1 will be conducted at three acute National Health Service (NHS) trusts with variation in service delivery models and ensuring a broad mixture of social, economic and cultural backgrounds of participants. Up to 150 patients with sHNC (n=50 per site) and 15 clinicians (n=5 per site) will be recruited. WP1 will use qualitative methods including interviews, observation and recordings of consultations. Rapid qualitative analysis and inductive thematic analysis will be used to analyse the data. WP2 will recruit lay patient representatives to participate in online focus groups (n=8 per focus group), think-aloud technique and experience-based codesign and will be analysed using qualitative and quantitative approaches.

ETHICS AND DISSEMINATION

The committee for clinical research at The Royal Marsden, a research ethics committee and the Health Research Authority approved this protocol. All participants will give informed consent. Ethical issues of working with patients on an urgent cancer diagnostic pathway have been considered. Findings will be disseminated via journal publications, conference presentations and public engagement activities.

Identifying provider, patient and practice factors that shape long-term opioid prescribing for cancer pain: a qualitative study of American and Australian providers

INTRODUCTION

Prescribing long-term opioid therapy is a nuanced clinical decision requiring careful consideration of risks versus benefits. Our goal is to understand patient, provider and context factors that impact the decision to prescribe opioids in patients with cancer.

METHODS

We conducted a secondary analysis of the raw semistructured interview data gathered from 42 prescribers who participated in one of two aligned concurrent qualitative studies in the USA and Australia. We conducted a two-part analysis of the interview: first identifying all factors influencing long-term prescribing and second open coding-related content for themes.

RESULTS

Factors that influence long-term opioid prescribing for cancer-related pain clustered under three key domains (patient-related, provider-related and practice-related factors) each with several themes. Domain 1: Patient factors related to provider-patient continuity, patient personality, the patient's social context and patient characteristics including racial/ethnic identity, housing and socioeconomic status. Domain 2: Provider-related factors centred around provider 'personal experience and expertise', training and time availability. Domain 3: Practice-related factors included healthcare interventions to promote safer opioid practices and accessibility of quality alternative pain therapies.

CONCLUSION

Despite the differences in the contexts of the two countries, providers consider similar patient, provider and practice-related factors when long-term prescribing opioids for patients with cancer. Some of these factors may be categorised as cognitive biases that may intersect in an already disadvantaged patient and exacerbate disparities in the treatment of their pain. A more systematic understanding of these factors and how they impact the quality of care can inform appropriate interventions.

SCALE-UP II: protocol for a pragmatic randomised trial examining population health management interventions to increase the uptake of at-home COVID-19 testing in community health centres

INTRODUCTION

SCALE-UP II aims to investigate the effectiveness of population health management interventions using text messaging (TM), chatbots and patient navigation (PN) in increasing the uptake of at-home COVID-19 testing among patients in historically marginalised communities, specifically, those receiving care at community health centres (CHCs).

METHODS AND ANALYSIS

The trial is a multisite, randomised pragmatic clinical trial. Eligible patients are >18 years old with a primary care visit in the last 3 years at one of the participating CHCs. Demographic data will be obtained from CHC electronic health records. Patients will be randomised to one of two factorial designs based on smartphone ownership. Patients who self-report replying to a text message that they have a smartphone will be randomised in a 2×2×2 factorial fashion to receive (1) chatbot or TM; (2) PN (yes or no); and (3) repeated offers to interact with the interventions every 10 or 30 days. Participants who do not self-report as having a smartphone will be randomised in a 2×2 factorial fashion to receive (1) TM with or without PN; and (2) repeated offers every 10 or 30 days. The interventions will be sent in English or Spanish, with an option to request at-home COVID-19 test kits. The primary outcome is the proportion of participants using at-home COVID-19 tests during a 90-day follow-up. The study will evaluate the main effects and interactions among interventions, implementation outcomes and predictors and moderators of study outcomes. Statistical analyses will include logistic regression, stratified subgroup analyses and adjustment for stratification factors.

ETHICS AND DISSEMINATION

The protocol was approved by the University of Utah Institutional Review Board. On completion, study data will be made available in compliance with National Institutes of Health data sharing policies. Results will be disseminated through study partners and peer-reviewed publications.

TRIAL REGISTRATION NUMBER

ClinicalTrials.gov: NCT05533918 and NCT05533359.

Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis

Prognosticating Amyotrophic Lateral Sclerosis (ALS) presents a formidable challenge due to patients exhibiting different onset sites, progression rates, and survival times. In this study, we have developed and evaluated Machine Learning (ML) algorithms that integrate Ensemble and Imbalance Learning techniques to classify patients into Short and Non-Short survival groups based on data collected during diagnosis. We aimed to identify individuals at high risk of mortality within 24 months of symptom onset through analysis of patient data commonly encountered in daily clinical practice. Our Ensemble-Imbalance approach underwent evaluation employing six ML algorithms as base classifiers. Remarkably, our results outperformed those of individual algorithms, achieving a Balanced Accuracy of 88% and a Sensitivity of 96%. Additionally, we used the Shapley Additive Explanations framework to elucidate the decision-making process of the top-performing model, pinpointing the most important features and their correlations with the target prediction. Furthermore, we presented helpful tools to visualize and compare patient similarities, offering valuable insights. Confirming the obtained results, our approach could aid physicians in devising personalized treatment plans at the time of diagnosis or serve as an inclusion/exclusion criterion in clinical trials.

Perceptions of students and faculty on NCAAA-accredited health informatics programs in Saudi Arabia: an evaluative study

BACKGROUND

As the healthcare sector becomes increasingly reliant on technology, it is crucial for universities to offer bachelor's degrees in health informatics (HI). HI professionals bridge the gap between IT and healthcare, ensuring that technology complements patient care and clinical workflows; they promote enhanced patient outcomes, support clinical research, and uphold data security and privacy standards. This study aims to evaluate accredited HI academic programs in Saudi Arabia.

METHODS

This study employed a quantitative, descriptive, cross-sectional design utilising a self-reported electronic questionnaire consisting of predetermined items and response alternatives. Probability-stratified random sampling was also performed.

RESULT

The responses rates were 39% (n = 241) for students and 62% (n = 53) for faculty members. While the participants expressed different opinions regarding the eight variables being examined, the faculty members and students generally exhibited a strong level of consensus on many variables. A notable association was observed between facilities and various other characteristics, including student engagement, research activities, admission processes, and curriculum. Similarly, a notable correlation exists between student engagement and the curriculum in connection to research, attrition, the function of faculty members, and academic outcomes.

CONCLUSION

While faculty members and students hold similar views about the institution and its offerings, certain areas of divergence highlight the distinct perspectives and priorities of each group. The perception disparity between students and faculty in areas such as admission, faculty roles, and internships sheds light on areas of improvement and alignment for universities.

Can ChatGPT pass the MRCP (UK) written examinations? Analysis of performance and errors using a clinical decision-reasoning framework

OBJECTIVE

Large language models (LLMs) such as ChatGPT are being developed for use in research, medical education and clinical decision systems. However, as their usage increases, LLMs face ongoing regulatory concerns. This study aims to analyse ChatGPT's performance on a postgraduate examination to identify areas of strength and weakness, which may provide further insight into their role in healthcare.

DESIGN

We evaluated the performance of ChatGPT 4 (24 May 2023 version) on official MRCP (Membership of the Royal College of Physicians) parts 1 and 2 written examination practice questions. Statistical analysis was performed using Python. Spearman rank correlation assessed the relationship between the probability of correctly answering a question and two variables: question difficulty and question length. Incorrectly answered questions were analysed further using a clinical reasoning framework to assess the errors made.

SETTING

Online using ChatGPT web interface.

PRIMARY AND SECONDARY OUTCOME MEASURES

Primary outcome was the score (percentage questions correct) in the MRCP postgraduate written examinations. Secondary outcomes were qualitative categorisation of errors using a clinical decision-making framework.

RESULTS

ChatGPT achieved accuracy rates of 86.3% (part 1) and 70.3% (part 2). Weak but significant correlations were found between ChatGPT's accuracy and both just-passing rates in part 2 (r=0.34, p=0.0001) and question length in part 1 (r=-0.19, p=0.008). Eight types of error were identified, with the most frequent being factual errors, context errors and omission errors.

CONCLUSION

ChatGPT performance greatly exceeded the passing mark for both exams. Multiple choice examinations provide a benchmark for LLM performance which is comparable to human demonstrations of knowledge, while also highlighting the errors LLMs make. Understanding the reasons behind ChatGPT's errors allows us to develop strategies to prevent them in medical devices that incorporate LLM technology.

Drug-drug interactions prediction based on deep learning and knowledge graph: A review

Drug-drug interactions (DDIs) can produce unpredictable pharmacological effects and lead to adverse events that have the potential to cause irreversible damage to the organism. Traditional methods to detect DDIs through biological or pharmacological analysis are time-consuming and expensive, therefore, there is an urgent need to develop computational methods to effectively predict drug-drug interactions. Currently, deep learning and knowledge graph techniques which can effectively extract features of entities have been widely utilized to develop DDI prediction methods. In this research, we aim to systematically review DDI prediction researches applying deep learning and graph knowledge. The available biomedical data and public databases related to drugs are firstly summarized in this review. Then, we discuss the existing drug-drug interactions prediction methods which have utilized deep learning and knowledge graph techniques and group them into three main classes: deep learning-based methods, knowledge graph-based methods, and methods that combine deep learning with knowledge graph. We comprehensively analyze the commonly used drug related data and various DDI prediction methods, and compare these prediction methods on benchmark datasets. Finally, we briefly discuss the challenges related to drug-drug interactions prediction, including asymmetric DDIs prediction and high-order DDI prediction.

Placental efflux transporters and antiseizure or antidepressant medication use impact birth weight in MoBa cohort

Low birth weight raises neonatal risks and lifelong health issues and is linked to maternal medication use during pregnancy. We examined data from the Norwegian Mother, Father, and Child Cohort Study and the Medical Birth Registry of Norway, including 69,828 offspring with genotype data and 81,189 with maternal genotype data. We identified genetic risk variants in placental efflux transporters, calculated genetic scores based on alleles related to transporter activity, and assessed their interaction with prenatal use of antiseizure or antidepressant medication on offspring birth weight. Our study uncovered possible genetic variants in both offspring (rs3740066) and mothers (rs10248420; rs2235015) in placental efflux transporters (MRP2-ABCC2 and MDR1-ABCB1) that modulated the association between prenatal exposure to antiseizure medication and low birth weight in the offspring. Antidepressant exposure was associated with low birth weight, but there were no gene-drug interactions. The interplay between MRP2-ABCC2 and MDR1-ABCB1 variants and antiseizure medication may impact neonatal birth weight.

Independent prognostic value of CLDN6 in bladder cancer based on M2 macrophages related signature

M2 macrophages are associated with the prognosis of bladder cancer. CLDN6 has been linked to immune infiltration and is crucial for predicting the prognosis in multi-tumor. The effect of CLDN6 on M2 macrophages in bladder cancer remains elusive. Here, we compared a total of 40 machine learning algorithms, then selected optimal algorithm to develop M2 macrophages-related signature (MMRS) based on the identified M2 macrophages related module. MMRS predicted the prognosis better than other models and associated to immunotherapy response. CLDN6, as an important variable in MMRS, was an independent factor for poor prognosis. We found that CLDN6 was highly expressed and affected immune infiltration, immunotherapy response, and M2 macrophages polarization. Meanwhile, CLDN6 promoted the growth of bladder cancer and enhanced the carcinogenic effect by inducing polarization of M2 macrophages. In total, CLDN6 is an independent risk factor in MMRS to predict the prognosis of bladder cancer.

Defining acceptable data collection and reuse standards for queer artificial intelligence research in mental health: protocol for the online PARQAIR-MH Delphi study

INTRODUCTION

For artificial intelligence (AI) to help improve mental healthcare, the design of data-driven technologies needs to be fair, safe, and inclusive. Participatory design can play a critical role in empowering marginalised communities to take an active role in constructing research agendas and outputs. Given the unmet needs of the LGBTQI+ (Lesbian, Gay, Bisexual, Transgender, Queer and Intersex) community in mental healthcare, there is a pressing need for participatory research to include a range of diverse queer perspectives on issues of data collection and use (in routine clinical care as well as for research) as well as AI design. Here we propose a protocol for a Delphi consensus process for the development of PARticipatory Queer AI Research for Mental Health (PARQAIR-MH) practices, aimed at informing digital health practices and policy.

METHODS AND ANALYSIS

The development of PARQAIR-MH is comprised of four stages. In stage 1, a review of recent literature and fact-finding consultation with stakeholder organisations will be conducted to define a terms-of-reference for stage 2, the Delphi process. Our Delphi process consists of three rounds, where the first two rounds will iterate and identify items to be included in the final Delphi survey for consensus ratings. Stage 3 consists of consensus meetings to review and aggregate the Delphi survey responses, leading to stage 4 where we will produce a reusable toolkit to facilitate participatory development of future bespoke LGBTQI+-adapted data collection, harmonisation, and use for data-driven AI applications specifically in mental healthcare settings.

ETHICS AND DISSEMINATION

PARQAIR-MH aims to deliver a toolkit that will help to ensure that the specific needs of LGBTQI+ communities are accounted for in mental health applications of data-driven technologies. The study is expected to run from June 2024 through January 2025, with the final outputs delivered in mid-2025. Participants in the Delphi process will be recruited by snowball and opportunistic sampling via professional networks and social media (but not by direct approach to healthcare service users, patients, specific clinical services, or via clinicians' caseloads). Participants will not be required to share personal narratives and experiences of healthcare or treatment for any condition. Before agreeing to participate, people will be given information about the issues considered to be in-scope for the Delphi (eg, developing best practices and methods for collecting and harmonising sensitive characteristics data; developing guidelines for data use/reuse) alongside specific risks of unintended harm from participating that can be reasonably anticipated. Outputs will be made available in open-access peer-reviewed publications, blogs, social media, and on a dedicated project website for future reuse.

Application of generative language models to orthopaedic practice

OBJECTIVE

To explore whether large language models (LLMs) Generated Pre-trained Transformer (GPT)-3 and ChatGPT can write clinical letters and predict management plans for common orthopaedic scenarios.

DESIGN

Fifteen scenarios were generated and ChatGPT and GPT-3 prompted to write clinical letters and separately generate management plans for identical scenarios with plans removed.

MAIN OUTCOME MEASURES

Letters were assessed for readability using the Readable Tool. Accuracy of letters and management plans were assessed by three independent orthopaedic surgery clinicians.

RESULTS

Both models generated complete letters for all scenarios after single prompting. Readability was compared using Flesch-Kincade Grade Level (ChatGPT: 8.77 (SD 0.918); GPT-3: 8.47 (SD 0.982)), Flesch Readability Ease (ChatGPT: 58.2 (SD 4.00); GPT-3: 59.3 (SD 6.98)), Simple Measure of Gobbledygook (SMOG) Index (ChatGPT: 11.6 (SD 0.755); GPT-3: 11.4 (SD 1.01)), and reach (ChatGPT: 81.2%; GPT-3: 80.3%). ChatGPT produced more accurate letters (8.7/10 (SD 0.60) vs 7.3/10 (SD 1.41), p=0.024) and management plans (7.9/10 (SD 0.63) vs 6.8/10 (SD 1.06), p<0.001) than GPT-3. However, both LLMs sometimes omitted key information or added additional guidance which was at worst inaccurate.

CONCLUSIONS

This study shows that LLMs are effective for generation of clinical letters. With little prompting, they are readable and mostly accurate. However, they are not consistent, and include inappropriate omissions or insertions. Furthermore, management plans produced by LLMs are generic but often accurate. In the future, a healthcare specific language model trained on accurate and secure data could provide an excellent tool for increasing the efficiency of clinicians through summarisation of large volumes of data into a single clinical letter.

Qualitative study of challenges with recruitment of hospitals into a cluster controlled trial of clinical decision support in Australia

OBJECTIVE

To identify barriers to hospital participation in controlled cluster trials of clinical decision support (CDS) and potential strategies for addressing barriers.

DESIGN

Qualitative descriptive design comprising semistructured interviews.

SETTING

Five hospitals in New South Wales and one hospital in Queensland, Australia.

PARTICIPANTS

Senior hospital staff, including department directors, chief information officers and those working in health informatics teams.

RESULTS

20 senior hospital staff took part. Barriers to hospital-level recruitment primarily related to perceptions of risk associated with not implementing CDS as a control site. Perceived risks included reductions in patient safety, reputational risk and increased likelihood that benefits would not be achieved following electronic medical record (EMR) implementation without CDS alerts in place. Senior staff recommended clear communication of trial information to all relevant stakeholders as a key strategy for boosting hospital-level participation in trials.

CONCLUSION

Hospital participation in controlled cluster trials of CDS is hindered by perceptions that adopting an EMR without CDS is risky for both patients and organisations. The improvements in safety expected to follow CDS implementation makes it challenging and counterintuitive for hospitals to implement EMR without incorporating CDS alerts for the purposes of a research trial. To counteract these barriers, clear communication regarding the evidence base and rationale for a controlled trial is needed.

Effectiveness of mHealth interventions to promote physical activity and reduce sedentary behaviours on work-related productivity and performance: a systematic review protocol

INTRODUCTION

Technologies such as health and fitness applications (apps) and wearable activity trackers have recently gained popularity and may play a key role in promoting physical activity and reducing sedentary behaviours. Although several systematic reviews have investigated their efficacy in physical activity and sedentary behaviours, few studies have focused on their impact on work-related outcomes among workers. Here, to explore the effects of mHealth interventions designed to encourage physical activity and decrease sedentary behaviours on work-related outcomes, including absenteeism, presenteeism, productivity, work performance and workability among workers, we will conduct a systematic review based on recent articles and an extensive literature search.

METHODS AND ANALYSIS

The literature search will be performed using PubMed, Web of Science, the Cochrane Library and the Japan Medical Abstracts Society from inception to 23 September 2023. We will select studies that (1) investigated the impact of mHealth interventions to promote physical activity and reduce sedentary behaviours on work-related outcomes such as absenteeism, presenteeism, productivity, work performance and workability; (2) were designed as a randomised controlled trial (RCT) or non-randomised study of interventions (NRSI); (3) were conducted among workers and (4) were published as full-text original articles in Japanese or English. We will assess the review quality with the AMSTAR 2 tool. The risk of bias will be assessed with the RoB tool 2.0 and ROBINS-I.

ETHICS AND DISSEMINATION

Ethical approval is unnecessary as the study will rely solely on previously published articles. The research results will be submitted for publication in a peer-reviewed scientific journal.

TRIAL REGISTRATION NUMBER

The study protocol has been registered with the UMIN Clinical Trials Registry (ID=UMIN000052290).

Ensemble machine learning reveals key features for diabetes duration from electronic health records

Diabetes is a metabolic disorder that affects more than 420 million of people worldwide, and it is caused by the presence of a high level of sugar in blood for a long period. Diabetes can have serious long-term health consequences, such as cardiovascular diseases, strokes, chronic kidney diseases, foot ulcers, retinopathy, and others. Even if common, this disease is uneasy to spot, because it often comes with no symptoms. Especially for diabetes type 2, that happens mainly in the adults, knowing how long the diabetes has been present for a patient can have a strong impact on the treatment they can receive. This information, although pivotal, might be absent: for some patients, in fact, the year when they received the diabetes diagnosis might be well-known, but the year of the disease unset might be unknown. In this context, machine learning applied to electronic health records can be an effective tool to predict the past duration of diabetes for a patient. In this study, we applied a regression analysis based on several computational intelligence methods to a dataset of electronic health records of 73 patients with diabetes type 1 with 20 variables and another dataset of records of 400 patients of diabetes type 2 with 49 variables. Among the algorithms applied, Random Forests was able to outperform the other ones and to efficiently predict diabetes duration for both the cohorts, with the regression performances measured through the coefficient of determination R2. Afterwards, we applied the same method for feature ranking, and we detected the most relevant factors of the clinical records correlated with past diabetes duration: age, insulin intake, and body-mass index. Our study discoveries can have profound impact on clinical practice: when the information about the duration of diabetes of patient is missing, medical doctors can use our tool and focus on age, insulin intake, and body-mass index to infer this important aspect. Regarding limitations, unfortunately we were unable to find additional dataset of EHRs of patients with diabetes having the same variables of the two analyzed here, so we could not verify our findings on a validation cohort.

German primary care data collection projects: a scoping review

BACKGROUND

The widespread use of electronic health records (EHRs) has led to a growing number of large routine primary care data collection projects globally, making these records a valuable resource for health services and epidemiological and clinical research. This scoping review aims to comprehensively assess and compare strengths and limitations of all German primary care data collection projects and relevant research publications that extract data directly from practice management systems (PMS).

METHODS

A literature search was conducted in the electronic databases in May 2021 and in June 2022. The search string included terms related to general practice, routine data, and Germany. The retrieved studies were classified as applied studies and methodological studies, and categorised by type of research, subject area, sample of publications, disease category, or main medication analysed.

RESULTS

A total of 962 references were identified, with 241 studies included from six German projects in which databases are populated by EHRs from PMS. The projects exhibited significant heterogeneity in terms of size, data collection methods, and variables collected. The majority of the applied studies (n = 205, 85%) originated from one database with a primary focus on pharmacoepidemiological topics (n = 127, 52%) including prescription patterns (n = 68, 28%) and studies about treatment outcomes, compliance, and treatment effectiveness (n = 34, 14%). Epidemiological studies (n = 77, 32%) mainly focused on incidence and prevalence studies (n = 41, 17%) and risk and comorbidity analysis studies (n = 31, 12%). Only 10% (n = 23) of studies were in the field of health services research, such as hospitalisation.

CONCLUSION

The development and durability of primary care data collection projects in Germany is hindered by insufficient public funding, technical issues of data extraction, and strict data protection regulations. There is a need for further research and collaboration to improve the usability of EHRs for health services and research.

Canada's Digital Health Workforce: The Role of Innovation, Research and Policy

The rapid growth of digital health and use of technology has led to an increased demand for qualified professionals in the areas of health informatics (HI) and health information management (HIM). This is reflected by the growth in the number of educational programs and graduates in these areas. However, to develop a culture of digital health innovation in Canada, the role of research needs to be critically examined. In this paper we discuss some of these issues around the relation between research and innovation, and the development of an innovation culture in health informatics, health information management and digital health in Canada. Recommendations for facilitating this development in terms of funding, granting and policy are also explored.

Formative evaluation of an emergency department clinical decision support system for agitation symptoms: a study protocol

INTRODUCTION

The burden of mental health-related visits to emergency departments (EDs) is growing, and agitation episodes are prevalent with such visits. Best practice guidance from experts recommends early assessment of at-risk populations and pre-emptive intervention using de-escalation techniques to prevent agitation. Time pressure, fluctuating work demands, and other systems-related factors pose challenges to efficient decision-making and adoption of best practice recommendations during an unfolding behavioural crisis. As such, we propose to design, develop and evaluate a computerised clinical decision support (CDS) system, Early Detection and Treatment to Reduce Events with Agitation Tool (ED-TREAT). We aim to identify patients at risk of agitation and guide ED clinicians through appropriate risk assessment and timely interventions to prevent agitation with a goal of minimising restraint use and improving patient experience and outcomes.

METHODS AND ANALYSIS

This study describes the formative evaluation of the health record embedded CDS tool. Under aim 1, the study will collect qualitative data to design and develop ED-TREAT using a contextual design approach and an iterative user-centred design process. Participants will include potential CDS users, that is, ED physicians, nurses, technicians, as well as patients with lived experience of restraint use for behavioural crisis management during an ED visit. We will use purposive sampling to ensure the full spectrum of perspectives until we reach thematic saturation. Next, under aim 2, the study will conduct a pilot, randomised controlled trial of ED-TREAT at two adult ED sites in a regional health system in the Northeast USA to evaluate the feasibility, fidelity and bedside acceptability of ED-TREAT. We aim to recruit a total of at least 26 eligible subjects under the pilot trial.

ETHICS AND DISSEMINATION

Ethical approval by the Yale University Human Investigation Committee was obtained in 2021 (HIC# 2000030893 and 2000030906). All participants will provide informed verbal consent prior to being enrolled in the study. Results will be disseminated through publications in open-access, peer-reviewed journals, via scientific presentations or through direct email notifications.

TRIAL REGISTRATION NUMBER

NCT04959279; Pre-results.

Smartwatch detection of new-onset monomorphic ventricular tachycardia in pregnancy

Smartwatches provide health tracking in various ways and there has been a recent rise in reporting cardiac arrhythmias. While original studies focused on atrial fibrillation, fewer reports have been made on other arrhythmias especially in pregnancy. We report a pregnant patient who presented at 34 weeks' gestation with palpitations. An ECG recorded through her Apple Watch showed ventricular tachycardia. Hospital ECG confirmed monomorphic ventricular tachycardia likely caused by increased sympathetic tone from the gravid state. She was admitted to the cardiac intensive care unit for close monitoring with intravenous anti-arrhythmic agents; however, the rhythm persisted. She underwent a caesarean delivery and the arrhythmia resolved post partum. She later underwent a catheter ablation, after which she discontinued all anti-arrhythmic medications with no recurrence. This case highlights the importance of requesting relevant digital health information, if available, from patients in our modern era. Controlled clinical studies are needed to validate such practices.

Evaluation of GPT-4 for 10-year cardiovascular risk prediction: Insights from the UK Biobank and KoGES data

Cardiovascular disease (CVD) remains a pressing global health concern. While traditional risk prediction methods such as the Framingham and American College of Cardiology/American Heart Association (ACC/AHA) risk scores have been widely used in the practice, artificial intelligence (AI), especially GPT-4, offers new opportunities. Utilizing large scale of multi-center data from 47,468 UK Biobank participants and 5,718 KoGES participants, this study quantitatively evaluated the predictive capabilities of GPT-4 in comparison with traditional models. Our results suggest that the GPT-based score showed commendably comparable performance in CVD prediction when compared to traditional models (AUROC on UKB: 0.725 for GPT-4, 0.733 for ACC/AHA, 0.728 for Framingham; KoGES: 0.664 for GPT-4, 0.674 for ACC/AHA, 0.675 for Framingham). Even with omission of certain variables, GPT-4's performance was robust, demonstrating its adaptability to data-scarce situations. In conclusion, this study emphasizes the promising role of GPT-4 in predicting CVD risks across varied ethnic datasets, pointing toward its expansive future applications in the medical practice.

Integrative analysis of multimodal patient data identifies personalized predictors of tuberculosis treatment prognosis

Tuberculosis (TB) afflicted 10.6 million people in 2021, and its global burden is increasing due to multidrug-resistant TB (MDR-TB) and extensively resistant TB (XDR-TB). Here, we analyze multi-domain information from 5,060 TB patients spanning 10 countries with high burden of MDR-TB from the NIAID TB Portals database to determine predictors of TB treatment outcome. Our analysis revealed significant associations between radiological, microbiological, therapeutic, and demographic data modalities. Our machine learning model, built with 203 features across modalities outperforms models built using each modality alone in predicting treatment outcomes, with an accuracy of 83% and area under the curve of 0.84. Notably, our analysis revealed that the drug regimens Bedaquiline-Clofazimine-Cycloserine-Levofloxacin-Linezolid and Bedaquiline-Clofazimine-Linezolid-Moxifloxacin were associated with treatment success and failure, respectively, for MDR non-XDR-TB. Drug combinations predicted to be synergistic by the INDIGO algorithm performed better than antagonistic combinations. Our prioritized set of features predictive of treatment outcomes can ultimately guide the personalized clinical management of TB.

Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches

Eosinophilic chronic rhinosinusitis (ECRS) is a distinct subset of chronic rhinosinusitis characterized by heightened eosinophilic infiltration and increased symptom severity, often resisting standard treatments. Traditional diagnosis requires invasive histological evaluation. This study aims to develop predictive models for ECRS based on patient clinical parameters, eliminating the need for invasive biopsy. Utilizing logistic regression with lasso regularization, random forest (RF), gradient-boosted decision tree (GBDT), and deep neural network (DNN), we trained models on common clinical data. The predictive performance was evaluated using metrics such as area under the curve (AUC) for receiver operator characteristics, decision curves, and feature ranking analysis. In a cohort of 437 eligible patients, the models identified peripheral blood eosinophil ratio, absolute peripheral blood eosinophil, and the ethmoidal/maxillary sinus density ratio (E/M) on computed tomography as crucial predictors for ECRS. This predictive model offers a valuable tool for identifying ECRS without resorting to histological biopsy, enhancing clinical decision-making.

Pattern Recognition and Anomaly Detection in fetal morphology using Deep Learning and Statistical learning (PARADISE): protocol for the development of an intelligent decision support system using fetal morphology ultrasound scan to detect fetal congenital anomaly detection

INTRODUCTION

Congenital anomalies are the most encountered cause of fetal death, infant mortality and morbidity. 7.9 million infants are born with congenital anomalies yearly. Early detection of congenital anomalies facilitates life-saving treatments and stops the progression of disabilities. Congenital anomalies can be diagnosed prenatally through morphology scans. A correct interpretation of the morphology scan allows a detailed discussion with the parents regarding the prognosis. The central feature of this project is the development of a specialised intelligent system that uses two-dimensional ultrasound movies obtained during the standard second trimester morphology scan to identify congenital anomalies in fetuses.

METHODS AND ANALYSIS

The project focuses on three pillars: committee of deep learning and statistical learning algorithms, statistical analysis, and operational research through learning curves. The cross-sectional study is divided into a training phase where the system learns to detect congenital anomalies using fetal morphology ultrasound scan, and then it is tested on previously unseen scans. In the training phase, the intelligent system will learn to answer the following specific objectives: (a) the system will learn to guide the sonographer's probe for better acquisition; (b) the fetal planes will be automatically detected, measured and stored and (c) unusual findings will be signalled. During the testing phase, the system will automatically perform the above tasks on previously unseen videos.Pregnant patients in their second trimester admitted for their routine scan will be consecutively included in a 32-month study (4 May 2022-31 December 2024). The number of patients is 4000, enrolled by 10 doctors/sonographers. We will develop an intelligent system that uses multiple artificial intelligence algorithms that interact between themselves, in bulk or individual. For each anatomical part, there will be an algorithm in charge of detecting it, followed by another algorithm that will detect whether anomalies are present or not. The sonographers will validate the findings at each intermediate step.

ETHICS AND DISSEMINATION

All protocols and the informed consent form comply with the Health Ministry and professional society ethics guidelines. The University of Craiova Ethics Committee has approved this study protocol as well as the Romanian Ministry of Research Innovation and Digitization that funded this research. The study will be implemented and reported in line with the STROBE (STrengthening the Reporting of OBservational studies in Epidemiology) statement.

TRIAL REGISTRATION NUMBER

The study is registered under the name 'Pattern recognition and Anomaly Detection in fetal morphology using Deep Learning and Statistical Learning', project number 101PCE/2022, project code PN-III-P4-PCE-2021-0057.

TRIAL REGISTRATION

ClinicalTrials.gov, unique identifying number NCT05738954, date of registration: 2 November 2023.

Pooling of primary care electronic health record (EHR) data on Huntington's disease (HD) and cancer: establishing comparability of two large UK databases

OBJECTIVES

To explore whether UK primary care databases arising from two different software systems can be feasibly combined, by comparing rates of Huntington's disease (HD, which is rare) and 14 common cancers in the two databases, as well as characteristics of people with these conditions.

DESIGN

Descriptive study.

SETTING

Primary care electronic health records from Clinical Practice Research Datalink (CPRD) GOLD and CPRD Aurum databases, with linked hospital admission and death registration data.

PARTICIPANTS

4986 patients with HD and 1 294 819 with an incident cancer between 1990 and 2019.

PRIMARY AND SECONDARY OUTCOME MEASURES

Incidence and prevalence of HD by calendar period, age group and region, and annual age-standardised incidence of 14 common cancers in each database, and in a subset of 'overlapping' practices which contributed to both databases. Characteristics of patients with HD or incident cancer: medical history, recent prescribing, healthcare contacts and database follow-up.

RESULTS

Incidence and prevalence of HD were slightly higher in CPRD GOLD than CPRD Aurum, but with similar trends over time. Cancer incidence in the two databases differed between 1990 and 2000, but converged and was very similar thereafter. Participants in each database were most similar in terms of medical history (median standardised difference, MSD 0.03 (IQR 0.01-0.03)), recent prescribing (MSD 0.06 (0.03-0.10)) and demographics and general health variables (MSD 0.05 (0.01-0.09)). Larger differences were seen for healthcare contacts (MSD 0.27 (0.10-0.41)), and database follow-up (MSD 0.39 (0.19-0.56)).

CONCLUSIONS

Differences in cancer incidence trends between 1990 and 2000 may relate to use of a practice-level data quality filter (the 'up-to-standard' date) in CPRD GOLD only. As well as the impact of data curation methods, differences in underlying data models can make it more challenging to define exactly equivalent clinical concepts in each database. Researchers should be aware of these potential sources of variability when planning combined database studies and interpreting results.

Mobile health biometrics to prescribe immediate remote physical activity for enhancing uptake to cardiac rehabilitation (MOTIVATE-CR+): protocol for a randomised controlled feasibility trial

INTRODUCTION

Cardiac rehabilitation (CR) can reduce cardiovascular mortality and improve health-related quality of life. In the United Kingdom, patient uptake of CR remains low (52%), falling well short of the target in the 2019 National Health Service long-term plan (85%). Mobile health (mHealth) technologies, offering biometric data to patients and healthcare professionals, may bridge the gap between supervised exercise and physical activity advice, enabling patients to engage in regular long-term physically active lifestyles. This randomised controlled trial (RCT) will evaluate the feasibility of mHealth technology when incorporated into a structured home-based walking intervention, in people with recent myocardial infarction.

METHODS AND ANALYSIS

This is a feasibility, assessor blinded, parallel group RCT. Participants will be allocated to either CR standard care (control group) or CR standard care+mHealth supported exercise counselling (mHealth intervention group). Feasibility outcomes will include the number of patients approached, screened and eligible; the percentage of patients who decline CR (including reasons for declining), agree to CR and consent to being part of the study; the percentage of patients who enrol in standard CR and reasons for drop out; and the percentage of participants who complete clinical, physical and psychosocial outcomes to identify a suitable primary outcome for a future definitive trial.

ETHICS AND DISSEMINATION

The trial was approved in the UK by the Northwest-Greater Manchester East Research Ethics Committee (22/NW/0301) and is being conducted in accordance with the Declaration of Helsinki and Good Clinical Practice. Results will be published in peer-reviewed journals and presented at national and international scientific meetings.

TRIAL REGISTRATION NUMBERS

NCT05774587.

Examining behaviour change techniques (BCTs) in technology-based interventions for enhancing social participation in people with mild cognitive impairment (MCI) or dementia: a scoping review protocol

INTRODUCTION

Technology-based interventions have improved the social participation of older adults with mild cognitive impairment (MCI) or dementia. Nevertheless, how these interventions modify social participation remains to be seen, and what efficient behaviour change techniques (BCTs) have been used. As such, this study aims to conduct a scoping review, identifying the features and BCTs behind technology-based interventions that improve social participation for individuals with MCI or dementia.

METHODS AND ANALYSIS

The scoping review method will be used to search journal articles from electronic databases, such as PsycINFO, PubMed, MEDLINE, Web of Science, Scopus and reference lists. Following the population, concept and context structure, this study focuses on adults over 60 diagnosed with MCI or dementia. It delves into technology-based interventions, specifically focusing on BCTs, features and overall effectiveness for improving social participation. The research considers contextual factors, exploring the diverse settings where these interventions are used, including homes, healthcare facilities and community centres. This approach aims to provide nuanced insights into the impact of technology-based interventions on social participation in the targeted demographic. Two authors will independently screen titles, abstracts and full texts using Covidence software. Disagreements will be resolved through consensus or a third reviewer, and reasons for exclusion will be documented. We will conduct a detailed analysis of BCTs to pinpoint effective strategies applicable to future technology-based intervention designs. Through this scoping review, we aim to provide valuable insights that guide the direction of future research. Specifically, we seek to inform the development of effective technology-based interventions tailored to support social participation for people with MCI or dementia.

ETHICS AND DISSEMINATION

Ethical approval is not necessary, as this review will use available articles from electronic databases. The outcome of the study will be published in a peer-reviewed journal. PROTOCOL REGISTRATION NUMBER: https://osf.io/tkzuf/.

AI-Enhanced Healthcare: Not a new Paradigm for Informed Consent

With the increasing prevalence of artificial intelligence (AI) and other digital technologies in healthcare, the ethical debate surrounding their adoption is becoming more prominent. Here I consider the issue of gaining informed patient consent to AI-enhanced care from the vantage point of the United Kingdom's National Health Service setting. I build my discussion around two claims from the World Health Organization: that healthcare services should not be denied to individuals who refuse AI-enhanced care and that there is no precedence to seeking patient consent to AI-enhanced care. I discus U.K. law relating to patient consent and the General Data Protection Regulation to show that current standards relating to patient consent are adequate for AI-enhanced care. I then suggest that in the future it may not be possible to guarantee patient access to non-AI-enhanced healthcare, in a similar way to how we do not offer patients manual alternatives to automated healthcare processes. Throughout my discussion I focus on the issues of patient choice and veracity in the patient-clinician relationship. Finally, I suggest that the best way to protect patients from potential harms associated with the introduction of AI to patient care is not via an overly burdensome patient consent process but via evaluation and regulation of AI technologies.

Integrated Automatic Examination Assignment Reduces Radiologist Interruptions: A 2-Year Cohort Study of 232,022 Examinations

Radiology departments face challenges in delivering timely and accurate imaging reports, especially in high-volume, subspecialized settings. In this retrospective cohort study at a tertiary cancer center, we assessed the efficacy of an Automatic Assignment System (AAS) in improving radiology workflow efficiency by analyzing 232,022 CT examinations over a 12-month period post-implementation and compared it to a historical control period. The AAS was integrated with the hospital-wide scheduling system and set up to automatically prioritize and distribute unreported CT examinations to available radiologists based on upcoming patient appointments, coupled with an email notification system. Following this AAS implementation, despite a 9% rise in CT volume, coupled with a concurrent 8% increase in the number of available radiologists, the mean daily urgent radiology report requests (URR) significantly decreased by 60% (25 ± 12 to 10 ± 5, t = -17.6, p < 0.001), and URR during peak days (95th quantile) was reduced by 52.2% from 46 to 22 requests. Additionally, the mean turnaround time (TAT) for reporting was significantly reduced by 440 min for patients without immediate appointments and by 86 min for those with same-day appointments. Lastly, patient waiting time sampled in one of the outpatient clinics was not negatively affected. These results demonstrate that AAS can substantially decrease workflow interruptions and improve reporting efficiency.

Facilitators and barriers of digital health technologies implementation in hospital settings in lower-income and middle-income countries since the COVID-19 pandemic: a scoping review protocol

INTRODUCTION

The implementation of digital health technologies (DHTs) in hospitals worldwide has been uneven since the COVID-19 pandemic. Ambiguity in defining the landscape of DHTs adds to the complexity of this process. To address these challenges, this scoping review aims to identify the facilitators and barriers of implementing DHTs in hospitals in lower-income and middle-income countries (LMIC) since COVID-19, describe the DHTs that have been adopted in hospital settings in LMIC during this period, and develop a comprehensive classification framework to define the landscape of DHTs implemented in LMIC.

METHODS AND ANALYSIS

We will conduct a systematic search in PubMed, Scopus, Web of Science and grey literature. Descriptive statistics will be used to report the characteristics of included studies. The facilitators and barriers to DHTs implementation, gathered from both quantitative and qualitative data, will be synthesised using a parallel-results convergent synthesis design. A thematic analysis, employing an inductive approach, will be conducted to categorise these facilitators and barriers into coherent themes. Additionally, we will identify and categorise all available DHTs based on their equipment types and methods of operation to develop an innovative classification framework.

ETHICS AND DISSEMINATION

Formal ethical approval is not required, as primary data collection is not involved in this study. The findings will be disseminated through peer-reviewed publications, conference presentations and meetings with key stakeholders and partners in the field of digital health.

Clinical decision support system for clinical nurses' decision-making on nurse-to-patient assignment: a scoping review protocol

INTRODUCTION

Optimal nurse-to-patient assignment plays a crucial role in healthcare delivery, with direct implications for patient outcomes and the workloads of nursing staff. However, this process is highly intricate, involving a multitude of factors that must be carefully considered. The application of a clinical decision support system (CDSS) to support nursing decision-making can have a positive impact not only on patient outcomes but also on nursing efficiency. This scoping review aims to explore the implementation of CDSS in the decision process of optimal nurse-patient assignment (NPA).

METHODS AND ANALYSIS

This scoping review will follow a stage of the Arksey and O'Malley framework. It will also be based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews' (PRISMA-ScR) guidelines. The research primarily aims to identify studies' findings on applying CDSSs in the NPA process. Hence, academic and grey literature articles from six international bibliographic databases (ie, MEDLINE via PubMed, EMBASE via Ovid, CINAHL via EBSCOhost, IEEE Xplore, Scopus, ProQuest Dissertations and Theses Global) will be considered, where search strategies will be tailored to each database. The literature search will be conducted in February 2024, and the identified studies will be independently screened by two primary reviewers. After extracting data, the qualitative data will be analysed thematically, and the quantitative data will be subjected to descriptive statistics. The research is scheduled to conclude in December 2024.

ETHICS AND DISSEMINATION

Ethical approval is not required as primary data will not be collected in this study. The findings of this study will be disseminated through peer-reviewed publications and conference presentations.

Investigating the characteristics of health-related data collection tools used in randomised controlled trials in low-income and middle-income countries: protocol for a systematic review

INTRODUCTION

Health-related data collection tools, including digital ones, have become more prevalent across clinical studies in the last number of years. However, using digital data collection tools in low-income and middle-income countries presents unique challenges. In this review, we aim to provide an overview of the data collection tools currently being used in randomised controlled trials (RCTs) conducted in low-resource settings and evaluate the tools based on the characteristics outlined in the modified Mobile Survey Tool framework. These include functionality, reliability, usability, efficiency, maintainability, portability, effectiveness, cost-benefit, satisfaction, freedom from risk and context coverage. This evidence may provide a guide to selecting a suitable data collection tool for researchers planning to conduct research in low-income and middle-income countries for future studies.

METHODS AND ANALYSIS

Searches will be conducted in four electronic databases: PubMed, CINAHL, Web of Science and EMBASE. For inclusion, studies must be a RCT, mention a health-related data collection tool and conducted in a low- and middle-income country. Only studies with available full-text and written in English will be included. The search was restricted to studies published between January 2005 and June 2023. This systematic review will use the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) tool. Two review authors will screen the titles and abstracts of search results independently for inclusion. In the initial screening process, the full-text articles will be retrieved if the abstract contains limited information about the study. Disagreements will be resolved through discussion. If the disagreement cannot be resolved, a third author (JO'D) will adjudicate. The study selection process will be outlined in a PRISMA flow-diagram. Data will be analysed using a narrative synthesis approach. The included studies and their outcomes will be presented in a table.

ETHICS AND DISSEMINATION

Formal ethical approval is not required as primary data will not be collected in this study. The findings from this systematic review will be published in a peer-reviewed journal.

PROSPERO REGISTRATION NUMBER

CRD42023405738.

Fighting the Same Battles on a New Battleground: Embedding Technologies in a Virtual Care Environment

The pandemic necessitated the rapid design, development and implementation of technologies to allow remote monitoring of COVID-19 patients at home. This study aimed to explore the environmental barriers and facilitators to the successful development and implementation of virtual care technologies in this fast-paced context. We interviewed eight staff at a virtual hospital in Australia. We found key facilitators to be a learning organizational culture and strong leadership support. Barriers included interoperability issues, legislative constraints and unrealistic clinician expectations. Also, we found that a combination of hot-desking and the lack of single sign on in the virtual care environment, was reported to create additional work for staff. Overall, despite this unique context, our findings are consistent with prior work examining design and implementation of healthcare technologies. The fast pace and high-pressure environment appeared to magnify previously reported barriers, but also cultivate and foster a learning culture.

An Exploration of the Certified Health Informatician Australasia (CHIA) Participants

The Certified Health Informatician Australasian (CHIA) is an assessment of a candidate's capabilities measured using a core set of health informatics competencies. The aim of this paper is to describe the outcomes of the first eight years since the program's launch. This paper contributes to the competency framework and certification discourse, and knowledge of the increasing importance and recognition of health informaticians through certification. An analysis of results and possible contributing factors is discussed.

A critical signal for phenotype transition driven by negative feedback loops

The biological rhythms governed by negative feedback loops have undergone extensive investigation. However, developing reliable and versatile warning signals to predict periodic fluctuations in physiological processes and behaviors associated with these rhythms remains a challenge. Here, we monitored the heart rate and tracked ovulation dates of 91 fertile women. The finding strongly links the velocity (derivative) of heart rate with ovulation in menstrual cycles, providing a predictive warning signal. Similarly, an analysis of calcium signaling in the suprachiasmatic nucleus (SCN) of mice reveals that the maximum velocity of rising calcium signal aligns with locomotor activity offsets. To demonstrate the generality of derivative-transitions link, numerical simulations using a negative feedback loop model were conducted. Statistical analysis indicated that over 90% of the oscillations exhibited a correlation between maximum velocity and transition points. Consequently, the maximum velocity derived from oscillatory curves holds significant potential as an early warning signal for critical transitions.

Experimental prognostic model integrating N6-methyladenosine-related programmed cell death genes in colorectal cancer

Colorectal cancer (CRC) intricacies, involving dysregulated cellular processes and programmed cell death (PCD), are explored in the context of N6-methyladenosine (m6A) RNA modification. Utilizing the TCGA-COADREAD/CRC cohort, 854 m6A-related PCD genes are identified, forming the basis for a robust 10-gene risk model (CDRS) established through LASSO Cox regression. qPCR experiments using CRC cell lines and fresh tissues was performed for validation. The CDRS served as an independent risk factor for CRC and showed significant associations with clinical features, molecular subtypes, and overall survival in multiple datasets. Moreover, CDRS surpasses other predictors, unveiling distinct genomic profiles, pathway activations, and associations with the tumor microenvironment. Notably, CDRS exhibits predictive potential for drug sensitivity, presenting a novel paradigm for CRC risk stratification and personalized treatment avenues.

Manifestation and sociodemographic microdata of Brazil's Unified Health System Ombudsman

OBJECTIVES

This article presents the process of extraction and treatment of two datasets from the General Ombudsman of the Brazilian Unified Health System (OUVSUS). The resulting datasets allow the analysis of manifestation characteristics and sociodemographic profile of the citizens that performed these manifestations.

DATA DESCRIPTION

The first dataset depicts the characteristics of the manifestations registered by the General Ombudsman. Each row represents an individual manifestation and contains information such as the registration date, classification, input channel, and subject, among others. The second dataset is constituted of sociodemographic information for each citizen that performed a manifestation, and characteristics such as sexual orientation, race, age, and geographic location of the citizen are presented, among others.

Implementation of a Heparin Infusion Calculator in the Electronic Health Record System as a Risk-Mitigation Strategy in a Community Teaching Hospital Emergency Department

INTRODUCTION

According to the Institute for Safe Medication Practices, unfractionated heparin is a high-risk medication due to the potential for medication errors and adverse events. Unfractionated heparin is often started in the emergency department for patients with acute coronary syndromes or coagulopathies. Risk-mitigation strategies should be implemented to ensure appropriate initiation and monitoring of this high-risk medication. In 2019, an unfractionated heparin calculator was built into the electronic health record at a community medical center. The purpose of this study was to evaluate the impact of the calculator as a risk-mitigation strategy.

METHODS

Patients ≥18 years old admitted between January 1, 2020, and December 31, 2020, were included if they were administered an unfractionated heparin infusion in the emergency department. Patient encounters were excluded if unfractionated heparin order was discontinued before administration. Patient encounters were classified into the unfractionated heparin calculator arm if the unfractionated heparin calculator was used to determine initial dosing, and the remaining patient encounters were classified into the unfractionated heparin no calculator arm. Unfractionated heparin orders were reviewed if a baseline activated partial thromboplastin time was collected and if the correct initial bolus dose and infusion rate were administered. The primary objective is to determine whether the use of unfractionated heparin initiation calculator reduced the rate of medication administration errors. Medication administration errors are defined as baseline activated partial thromboplastin time not collected or incorrectly collected or the administration of incorrect initial bolus dose and infusion rate.

RESULTS

A total of 356 patient encounters with unfractionated heparin orders were included in the primary analysis. There were 13.9% errors (39 of 279) present when the calculator was used and 23.3% (18 of 77) when the calculator was not used (P = .046). There was 86% correct administration of heparin (240 of 279) when the calculator was used and 76% correct administrations (59 of 77) when the calculator was not used.

DISCUSSION

The use of the unfractionated heparin infusion calculator in the emergency department led to decrease in medication administration errors. This is the first study to evaluate the integration of an unfractionated heparin calculator into the electronic health record.

Feature recognition in multiple CNNs using sEMG images from a prototype comfort test

OBJECTIVE

Deep learning-based CNN networks have recently been investigated to solve the problem of body posture recognition based on surface electromyographic signals (sEMG). Influenced by these studies, to develop a combined approach of sEMG and CNNs in the study of human-product interactions and the impact of body comfort, and to compare the advantages and disadvantages of various CNNs networks.

METHODS

In this study, sEMG measurements were carried out by building a prototype usability experiment, and the data were divided into four categories, with two types of datasets: training and testing. Four CNNs, LeNet-5, VGGNet-11, InceptionNet V4, and DenseNet, were used for the recognition of sEMG images.

RESULTS

DenseNet is another type of convolutional neural network with deep layers, which has a unique advantage over other algorithms. unique advantages over other algorithms. DenseNet has fewer layers and better accuracy than InceptionNet V4, but not only does it bypass enhanced feature reuse, but its network is easier to train and has some regularization effects, while also mitigating the problems of gradient disappearance and model degradation.

CONCLUSION

These findings could lead to a more appropriate CNN model and a useful tool for developing comfort judgments of surface EMG signals, furthering the development of products that come into contact with the human body without the need for routine retraining.

Analysis of digital capacity-related factors influencing health promotion participation and active aging of older adults residing in rural areas in South Korea: A structural equation model

Objective

This study aimed to identify the correlation between digital capacity, health promotion participation, and active aging of older people living in rural areas in South Korea to assess the factors influencing participation in programs for health promotion and active aging.

Methods

Data were collected through a 1:1 face-to-face survey using a structured questionnaire from 13 February to 24 February 2023 during the older individuals' visits in the senior citizen welfare centers and senior citizen centers in the region. The Measuring Digital Skills questionnaire used to assess the digital competence of South Korean individuals was employed in this study. To confirm the structural relationship between digital capacity and health promotion participation and active aging in the older population aged 65 years and older based on the collected data, a structural equation modeling analysis was performed.

Results

Active health promotion participation had a positive effect on active aging. The pathway that older adults in Korea can led to participation in health promotion and active aging in the current situation is not mainly through the digital competency whereas mobile internet skill showed positive influneces.

Conclusions

In the digital era and super-aged society, various programs are provided to older individuals to enhance the utilization of smartphones. However, education and programs for strengthening digital capacity should be organized to explain the advantages of digital use and to inform of the dangers of addiction to ensure healthy aging through social participation and exchange both online and offline.

Does Health & Her app use improve menopausal symptoms? A longitudinal cohort study

OBJECTIVES

The Health & Her app provides menopausal women with a means of monitoring their symptoms, symptom triggers and menstrual periods, and enables them to engage in a variety of digital activities designed to promote well-being. This study aimed to examine whether sustained weekly engagement with the app is associated with improvements in menopausal symptoms.

DESIGN

A pre-post longitudinal cohort study.

SETTING

Analysed data collected from Health & Her app users.

PARTICIPANTS

1900 women who provided symptom data via the app across a 2-month period.

PRIMARY AND SECONDARY OUTCOME MEASURES

Symptom changes from baseline to 2 months was the outcome measure. A linear mixed effects model explored whether levels of weekly app engagement influenced symptom changes. Secondary analyses explored whether app-usage factors such as total number of days spent logging symptoms, reporting triggers, reporting menstrual periods and using in-app activities were independently predictive of symptom changes from baseline. Covariates included hormone replacement therapy use, hormonal contraceptive use, present comorbidities, age and dietary supplement use.

RESULTS

Findings demonstrated that greater engagement with the Health & Her app for 2 months was associated with greater reductions in symptoms over time. Daily use of in-app activities and logging symptoms and menstrual periods were each independently associated with symptom reductions.

CONCLUSIONS

This study demonstrated that greater weekly engagement with the app was associated with greater reductions in symptoms. It is recommended that women be made aware of menopause-specific apps, such as that provided by Health & Her, to support them to manage their symptoms.