[This corrects the article DOI: 10.3389/fvets.2024.1327081.].

BACKGROUND: The presence of bias in artificial intelligence has garnered increased attention, with inequities in algorithmic performance being exposed across the fields of criminal justice, education, and welfare services. In health care, the inequitable performance of algorithms across demographic groups may widen health inequalities.
OBJECTIVE: Here, we identify and characterize bias in cardiology algorithms, looking specifically at algorithms used in the management of heart failure.
METHODS: Stage 1 involved a literature search of PubMed and Web of Science for key terms relating to cardiac machine learning (ML) algorithms. Papers that built ML models to predict cardiac disease were evaluated for their focus on demographic bias in model performance, and open-source data sets were retained for our investigation. Two open-source data sets were identified: (1) the University of California Irvine Heart Failure data set and (2) the University of California Irvine Coronary Artery Disease data set. We reproduced existing algorithms that have been reported for these data sets, tested them for sex biases in algorithm performance, and assessed a range of remediation techniques for their efficacy in reducing inequities. Particular attention was paid to the false negative rate (FNR), due to the clinical significance of underdiagnosis and missed opportunities for treatment.
RESULTS: In stage 1, our literature search returned 127 papers, with 60 meeting the criteria for a full review and only 3 papers highlighting sex differences in algorithm performance. In the papers that reported sex, there was a consistent underrepresentation of female patients in the data sets. No papers investigated racial or ethnic differences. In stage 2, we reproduced algorithms reported in the literature, achieving mean accuracies of 84.24% (SD 3.51%) for data set 1 and 85.72% (SD 1.75%) for data set 2 (random forest models). For data set 1, the FNR was significantly higher for female patients in 13 out of 16 experiments, meeting the threshold of statistical significance (-17.81% to -3.37%; P<.05). A smaller disparity in the false positive rate was significant for male patients in 13 out of 16 experiments (-0.48% to +9.77%; P<.05). We observed an overprediction of disease for male patients (higher false positive rate) and an underprediction of disease for female patients (higher FNR). Sex differences in feature importance suggest that feature selection needs to be demographically tailored.
CONCLUSIONS: Our research exposes a significant gap in cardiac ML research, highlighting that the underperformance of algorithms for female patients has been overlooked in the published literature. Our study quantifies sex disparities in algorithmic performance and explores several sources of bias. We found an underrepresentation of female patients in the data sets used to train algorithms, identified sex biases in model error rates, and demonstrated that a series of remediation techniques were unable to address the inequities present.

Cardiovascular disease (CVD) and mental health disorders contribute to significant healthcare expenses. Lifestyle approaches that empower and enable patients to participate in their recovery are needed with the increasing complexity of cardiac patients. Traditional Tamil medical practice of Siddha self-inquiry meditation targets holistic health through intuitive lifestyle transformation. We describe 4 complex cardiac patients who explored Siddha based Hunger Gratitude Experience (HUGE) mindful eating and reported elevated levels of optimism and deeper experience of life as outlined by the 5000-year-old secular Siddha medical tradition. We cannot exclude the role of suggestion and placebo effect in descriptive series. However, the simultaneous improvement in physical health and emotional wellbeing along with demonstrated resilience against unforeseen adversities suggests this is Uvagai, the true essence of Siddha higher consciousness. Uvagai is extreme happiness and may be accessible universally with little formal training and targets positive psychology to improve wellbeing. While flow and bliss states are transient transcendental experiences, Uvagai may be more profound and therapeutic in CVD despite age and comorbidities. Seeking Uvagai can potentially overcome health disparities, including rural, minority, and underprivileged populations for better health. HUGE allows CVD patients to safely engage in Uvagai, experience higher consciousness and intuitively sustain lifestyle transformation.

BACKGROUND: This study aimed to evaluate the burden and impact of cardiac and cerebrovascular disease (CCD) on hospital inpatients with type 1 diabetes mellitus (T1DM).
METHODS: This is a retrospective nationwide cohort study of people with T1DM with or without CCD in the US National Inpatient Sample between 2016 and 2019. The in-hospital mortality rates, length of stay (LoS), and healthcare costs were determined.
RESULTS: A total of 59,860 T1DM patients had a primary diagnosis of CCD and 1,382,934 did not. The median LoS was longer for patients with CCD compared to no CCD (4.6 vs. 3 days). Patients with T1DM and CCD had greater in-hospital mortality compared to those without CCD (4.1% vs. 1.1%, p < 0.001). The estimated total care cost for all patients with T1DM with CCD was approximately USD 326 million. The adjusted odds of mortality compared to patients with non-CCD admission was greatest for intracranial hemorrhage (OR 17.37, 95%CI 12.68-23.79), pulmonary embolism (OR 4.39, 95%CI 2.70-7.13), endocarditis (OR 3.46, 95%CI 1.22-9.84), acute myocardial infarction (OR 2.31, 95%CI 1.92-2.77), and stroke (OR 1.47, 95%CI 1.04-2.09).
CONCLUSIONS: The burden of CCD in patients with T1DM is substantial and significantly associated with increased hospital mortality and high healthcare expenditures.

Over the last four decades, cardiac natriuretic peptides have changed our understanding of patients with chronic heart failure. From the discovery of the heart as an endocrine organ with its own hormones and receptors, the biochemistry and physiology of the system have been translated into useful biomarkers and drug targets in cardiovascular disease. The purpose of this review is to provide medical researchers not working in the field with a simple introduction to the system and its molecular components, its quantitative methods, and its physiology and pathophysiology. The hope is that this overview may help to broaden the knowledge of the endocrine heart with the intent that researchers in other areas of medical research will be inspired to seek new facets of the system, both in translational science and in clinical practice.

Heart attack is a life-threatening condition which is mostly caused due to coronary disease resulting in death in human beings. Detecting the risk of heart diseases is one of the most important problems in medical science that can be prevented and treated with early detection and appropriate medical management; it can also help to predict a large number of medical needs and reduce expenses for treatment. Predicting the occurrence of heart diseases by machine learning (ML) algorithms has become significant work in healthcare industry. This study aims to create a such system that is used for predicting whether a patient is likely to develop heart attacks, by analysing various data sources including electronic health records and clinical diagnosis reports from hospital clinics. ML is used as a process in which computers learn from data in order to make predictions about new datasets. The algorithms created for predictive data analysis are often used for commercial purposes. This paper presents an overview to forecast the likelihood of a heart attack for which many ML methodologies and techniques are applied. In order to improve medical diagnosis, the paper compares various algorithms such as Random Forest, Regression models, K-nearest neighbour imputation (KNN), Naïve Bayes algorithm etc. It is found that the Random Forest algorithm provides a better accuracy of 88.52% in forecasting heart attack risk, which could herald a revolution in the diagnosis and treatment of cardiovascular illnesses.

BACKGROUND: Direct oral anticoagulants (DOACs) have been widely applied in adults for thrombosis prophylaxis. However, the effect of DOACs in pediatric patients with congenital or acquired heart diseases who need anticoagulation therapy remains unclear.
METHODS: We systematically searched the databases of PubMed, Embase, and the Cochrane Library, as well as the ClinicalTrials.gov registry and the World Health Organization\'s International Clinical Trials Registry Platform until June 2024 to identify relevant randomized clinical trials (RCTs). If the number of included studies was less than 5, we performed a narrative review to assess the effect of DOACs in pediatric patients.
RESULTS: Four studies were included. In the UNIVERSE study, thrombotic events occurred in 2% of the rivaroxaban group and 9% of the aspirin group, with bleeding events in 36% and 41%, respectively. The ENNOBLE-ATE study showed no thromboembolic events in the edoxaban group and 1.7% in the SOC group (rate difference: -0.07%, 95% CI: -0.22 to 0.07%). Major bleeding rates were similar (rate difference: -0.03%, 95% CI: -0.18 to 0.12%). The SAXOPHONE trial showed no thromboembolic events in either group and similar major bleeding rates (-0.8%, 95% CI: -8.1 to 3.3%). In the DIVERSITY trial, 81% of dabigatran patients achieved the primary outcome versus 59.3% in the SOC group (Odds ratio: 0.342, 95% CI: 0.081-1.229). No major bleeding occurred in either group.
CONCLUSIONS: Existing studies suggest that the use of DOACs hold promise as an effective and safe alternative for preventing and treating thromboembolism in pediatric patients with heart conditions.

暂无摘要。