Patient Perspectives on Conversational Artificial Intelligence for Atrial Fibrillation Self-Management: Qualitative Analysis.

Background: Conversational artificial intelligence (AI) allows for engaging interactions, however, its acceptability, barriers, and enablers to support patients with atrial fibrillation (AF) are unknown.

Objective: This work stems from the Coordinating Health care with AI-supported Technology for patients with AF (CHAT-AF) trial and aims to explore patient perspectives on receiving support from a conversational AI support program.

Methods: Patients with AF recruited for a randomized controlled trial who received the intervention were approached for semistructured interviews using purposive sampling.

Improving Cardiovascular Outcomes in the Psoriasis Cohort. Psoriasis and Cardiovascular Disease-Clinician Knowledge, Practice and Perceptions.

Background: Psoriasis is a risk factor for cardiovascular disease (CVD). This risk is independent and incremental to traditional cardiovascular (CV) risk factors, but clinician and patient perspectives on this risk are unclear. This study aims to assess the knowledge, perceptions, and practice of clinicians and patients with respect to psoriasis and CVD.

Machine-learning versus traditional approaches to predict all-cause mortality for acute coronary syndrome: a systematic review and meta-analysis.

Background: Acute coronary syndrome (ACS) remains one of the leading causes of death globally. Accurate and reliable mortality risk prediction of ACS patients is essential for developing targeted treatment strategies and improve prognostication. Traditional models for risk stratification such as the GRACE and TIMI risk scores offer moderate discriminative value, and do not incorporate contemporary predictors of ACS prognosis.

A qualitative exploration of the educational needs of people living with heart failure: BANDAIDD-Explore study.

This is an exploratory qualitative study of cardiovascular clinicians, people living with heart failure (HF), and their caregivers. The aim was to understand the unmet educational needs in self-management for adults living with HF. Four focus groups were conducted face-to-face or via videoconference, recorded, and transcribed verbatim for thematic analysis.

Machine-learning based risk prediction of outcomes in patients hospitalised with COVID-19 in Australia: the AUS-COVID score.

Objective: We aimed to develop a highly interpretable and effective, machine-learning based risk prediction algorithm to predict in-hospital mortality, intubation and adverse cardiovascular events in patients hospitalised with COVID-19 in Australia (AUS-COVID Score).

Materials And Methods: This prospective study across 21 hospitals included 1714 consecutive patients aged ≥ 18 in their index hospitalization with COVID-19. The dataset was separated into training (80%) and test sets (20%).

Machine learning approaches for risk prediction after percutaneous coronary intervention: a systematic review and meta-analysis.

Aims: Accurate prediction of clinical outcomes following percutaneous coronary intervention (PCI) is essential for mitigating risk and peri-procedural planning. Traditional risk models have demonstrated a modest predictive value. Machine learning (ML) models offer an alternative risk stratification that may provide improved predictive accuracy.

Biologic Therapy and Cardiometabolic Risk in Psoriasis: A Retrospective Review.

Introduction: Psoriasis is a systemic inflammatory disease with increased cardiometabolic risk including dyslipidaemia and diabetes. Biologic therapy effectively treats the cutaneous inflammatory burden of psoriasis and evolving evidence suggests potential to reduce systemic inflammatory sequalae that can elevate cardiovascular risk. This study aimed to assess the change in cardiometabolic risk markers in a cohort of patients with psoriasis treated with 1 year of continuous biologic treatment.

Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis.

Background: Accurate mortality prediction following transcatheter aortic valve implantation (TAVI) is essential for mitigating risk, shared decision-making and periprocedural planning. Surgical risk models have demonstrated modest discriminative value for patients undergoing TAVI and are typically poorly calibrated, with incremental improvements seen in TAVI-specific models. Machine learning (ML) models offer an alternative risk stratification that may offer improved predictive accuracy.

Detection of hypertension and blood pressure phenotypes using ambulatory blood pressure monitoring in women with past hypertensive disorders of pregnancies.

Objective: To evaluate the incidence of hypertension and blood pressure (BP) phenotypes using 24-hour ambulatory BP (24hr-ABP) in women with past pregnancy complications who were recruited into a Women's Heart Clinic (WHC).

Study Design: We recruited 156 women aged 30-55 years with past hypertensive disorders of pregnancy (HDP) and/or gestational diabetes (GDM) to a multidisciplinary six-month WHC that provided cardiovascular risk management in Melbourne, Australia. Women were referred for 24 hr-ABP monitoring if clinic BP was ≥130/80 mmHg.

Determinants of medication adherence in patients with acute coronary syndrome: a secondary analysis of a randomised clinical trial.

Background: Coronary heart disease (CHD) remains a leading cause of mortality and disability worldwide. Approximately half of the patients who have had a prior hospital admission for CHD will have a recurrent coronary event, with the majority of these occurring within 12 months. Despite well-established evidence-based therapies, medication non-adherence is highly prevalent and reasons for medication non-adherence are poorly understood.

Implementation of a data-driven quality improvement program in primary care for patients with coronary heart disease: a mixed methods evaluation of acceptability, satisfaction, barriers and enablers.

Background The study aimed to understand the acceptability, satisfaction, uptake, utility and feasibility of a quality improvement (QI) intervention to improve care for coronary heart disease (CHD) patients in Australian primary care practices and identify barriers and enablers, including the impact of COVID-19. Methods Within the QUality improvement for Effectiveness of care for people Living with heart disease (QUEL) study, 26 Australian primary care practices, supported by five Primary Health Networks (PHN) participated in a 1-year QI intervention (November 2019 - November 2020). Data were collected from practices and PHNs staff via surveys and semi-structured interviews.

Preoperative estimated glomerular filtration rate to predict cardiac events in major noncardiac surgery: a secondary analysis of two large international studies.

Background: Optimised use of kidney function information might improve cardiac risk prediction in noncardiac surgery.

Methods: In 35,815 patients from the VISION cohort study and 9219 patients from the POISE-2 trial who were ≥45 yr old and underwent nonurgent inpatient noncardiac surgery, we examined (by age and sex) the association between continuous nonlinear preoperative estimated glomerular filtration rate (eGFR) and the composite of myocardial injury after noncardiac surgery, nonfatal cardiac arrest, or death owing to a cardiac cause within 30 days after surgery. We estimated contributions of predictive information, C-statistic, and net benefit from eGFR and other common patient and surgical characteristics to large multivariable models.

Atrial fibrillation status and associations with adverse clinical outcomes in patients hospitalised with COVID-19: a large unselected statewide population-linkage study.

Background: Atrial fibrillation (AF) is common in COVID-19 patients. The impact of AF on major-adverse-cardiovascular-events (MACE defined as all-cause mortality, myocardial infarction, ischemic stroke, cardiac failure or coronary revascularisation), recurrent AF admission and venous thromboembolism in hospitalised COVID-19 patients is unclear.

Methods: Patients admitted with COVID-19 (1-January-2020 to 30-September-2021) were identified from the New South Wales Admitted-Patient-Data-Collection database, stratified by AF status (no-AF vs prior-AF or new-AF during index COVID-19 admission) and followed-up until 31-Mar-2022.

Perioperative aspirin and coronary artery bypass graft surgery: An updated meta-analysis of randomized controlled trials.

Background: The decision to continue aspirin before elective coronary artery bypass graft surgery remains contentious because of competing thrombotic and bleeding risks. We performed a contemporary systematic review and meta-analysis to compare outcomes between patients undergoing coronary artery bypass grafting who stopped and continued aspirin before surgery.

Methods: PubMed, MEDLINE, and CENTRAL databases were searched from inception to 4 October 2023 for randomized controlled trials comparing patients undergoing coronary artery bypass grafting who continued preoperative aspirin with those who discontinued before surgery.

Age of menopause, healthy lifestyle and cardiovascular disease in women: a prospective cohort study.

Background: Menopause is a timely opportunity to screen for cardiovascular disease (CVD) and intervene with healthier lifestyles. We investigated the association between premature/early menopause and the likelihood of CVD and whether a healthy lifestyle is associated with a lower likelihood of CVD in menopausal woman.

Methods: The Sax Institute's 45 and Up Study prospectively recruited participants aged ≥45 years (n=267 357) between 2005 and 2009 (New South Wales, Australia).

Impact of a Women's Heart Clinic on Cardiovascular Disease Risk Awareness in Women with Past Pregnancy Complications: A Prospective Cohort Study.

Background: Gestational diabetes mellitus (GDM), hypertension during pregnancy (HDP) and/or having small-for-gestational-age (SGA) babies increase cardiovascular disease (CVD) risk. We investigated CVD risk awareness in women with past pregnancy complications and the impact of attending a Women's Heart Clinic (WHC) on this awareness.

Method: Women aged 30-55 years with past GDM, HDP and/or SGA babies were prospectively recruited into a 6-month WHC delivering education and management of CVD risk factors (Melbourne, Australia).

Examining the impact of the QUARTET USA trial using the translational science benefits model.

Evaluation of benefits beyond quantitative academic outputs is essential in determining translational research value. We used the Translational Science Benefits Model (TSBM) to examine the impact of the QUARTET USA trial using 30 benefits across 4 domains: Clinical, Community, Economic, and Policy. We found that the QUARTET USA trial demonstrated impact in six areas within the Clinical, and Community domains and had potential impact in two additional areas within the Community and Economic domains.

Defining a core set of research and development priorities for virtual care in the post-pandemic environment: a call to action.

Objectives: To identify research and development priorities for virtual care following the coronavirus disease 2019 pandemic from the perspective of key stakeholders (patients, clinicians, informaticians and academics).

Design: Qualitative study using a modified nominal group technique.

Setting: Online semi-structured interviews and workshops held in November 2022 and February 2023.

Barriers, facilitators and next steps for sustaining and scaling virtual hospital services in Australia: a qualitative descriptive study.

Objective: To describe the barriers to and facilitators of implementing and delivering virtual hospital (VH) services, and evidence and practice gaps where further research and policy changes are needed to drive continuous improvement.

Study Design: Qualitative descriptive study.

Setting, Participants: Online semi-structured interviews and a focus group were conducted between July 2022 and April 2023 with doctors, nurses and leadership staff involved in VH services at three sites in New South Wales, Australia.

How primary and tertiary care services collaborate in urgent care delivery: an evaluation of general practice advice lines.

Background: To address the rising demand for urgent care and decrease hospital use, health systems are implementing different strategies to support urgent care patients (i.e. patients who would have typically been treated in hospital) in the community, such as general practitioner (GP) advice lines.

A Self-Administered Gamified Mobile Application for Secondary Prevention of Heart Disease in Patients Following a Cardiac Event (MyHeartMate): Process Evaluation from a Randomized Controlled Trial.

This study reports the process evaluation of a randomized controlled trial of the MyHeartMate app for patients with coronary heart disease (CHD). Data were collected on engagement in the intervention group from the app platform logs and self-reported usage and via interviews for perspectives of usefulness and acceptability. Participants' ( = 194) data logs showed 80.

Temporal Trends in the Management Practices of Clinically Important Perioperative Atrial Fibrillation After Noncardiac Surgery.

Background: Clinically important perioperative atrial fibrillation (POAF) is a common cardiac complication after noncardiac surgery. Little is known about how patients with POAF are managed acutely and whether practices have changed over time.

Methods: We conducted an observational substudy of patients who had POAF, were at elevated cardiovascular risk, and were enrolled in the PeriOperative Ischemic Evaluation (POISE)-1, 2 and 3 trials between 2002 and 2021.

Environmental impact of large language models in medicine.

The environmental impact of large language models (LLMs) in medicine spans carbon emission, water consumption and rare mineral usage. Prior-generation LLMs, such as GPT-3, already have concerning environmental impacts. Next-generation LLMs, such as GPT-4, are more energy intensive and used frequently, posing potentially significant environmental harms.