Cardiovascular disorders (heart diseases) are the most prevalent cause of death on a global scale. So early detection and classification increase the likelihood of survival. In the context of machine learning techniques, there is always a need for an accurate and explainable predictive model for detecting various diseases, such as cardiac disorders. The work carried out in this paper stacks bidirectional long short-term memory with deep learning to propose two models. The first model is used to detect cardiac disease with a binary label classification, while the second one classifies cardiac disease, which is a multi-label classification problem. Bidirectional LSTM is used as an approximate algorithm for feature extraction. Deep learning is used for classification purposes. The proposed models are trained and validated over the PTB-XL dataset. The performance of these models is evaluated and compared against state-of-the-art methods. The comparison shows the proposed model outperforms other methods in terms of accuracy, precision, f1-score, and recall. SHAP is used to make these models explainable, which in turn helps to annotate different diseases on the ECG report.

Background Increasing utilisation of hospice services has been a major focus in oncology, while only recently have cardiologists realised the similar needs of dying patients with heart failure (HF). We examined recent trends in locations of deaths in these two patient populations to gain further insight.Methods Complete population-level data were obtained from the Mortality Multiple Cause-of-Death Public Use Record from the National Center for Health Statistics database, from 2013 to 2017. Location of death was categorised as hospital, home, hospice facility or nursing facility. Demographic characteristics evaluated by place of death included age, sex, race, ethnicity, marital status and education, and a multivariable logistic regression analysis was performed to analyse possible associations.Results Among 2 780 715 deaths from cancer, 27% occurred in-hospital and 14% in nursing facilities; while among 335 350 HF deaths, 27% occurred in-hospital and 30% in nursing facilities. Deaths occurred at hospice facilities in 14% of patients with cancer, compared with just 8.7% in HF (p=0.001). For both patients with HF and cancer, the proportion of at-home and in-hospice deaths increased significantly over time, with majority of deaths occurring at home. In both cancer and HF, patients of non-Hispanic ethnicity (cancer: OR 1.29, (1.27 to 1.31), HF: OR 1.14, (1.07 to 1.22)) and those with some college education (cancer: OR 1.10, (1.09 to 1.11); HF: OR 1.06, (1.04 to 1.09)) were significantly more likely to die in hospice.Conclusion Deaths in hospital or nursing facilities still account for nearly half of cancer or HF deaths. Although positive trends were seen with utilisation of hospice facilities in both groups, usage remains low and much remains to be achieved in both patient populations.

BACKGROUND:Ischemic heart disease (IHD) is a major contributor to mortality in low-and middle-income-countries (LMICs). However, trends in IHD in females in LMICs are not well described. METHODS:We analyzed the Global Burden of Disease (GBD) Study from 1990 to 2019 for males and females with IHD from the ten most-populous LMICs (India, Indonesia, Pakistan, Nigeria, Ethiopia, Philippines, Egypt, Vietnam, Iran, and Afghanistan). RESULTS:In females, IHD incidence increased from 950,000 cases/year to 1.6 million/year, IHD prevalence increased from 8 million to 22.5 million (181% increase) and IHD mortality from 428,320 to 1,040,817 (143% increase). IHD accounted for 6.2% of all deaths among females in 1990, doubling to 13.2% in 2019. IHD mortality for each country increased with the greatest shift in AAPC seen in the Philippines (5.8%, 95% CI 5.4-6.1) and India (3.7%, 95% CI 3.0-4.4). Notably, reductions in ASMR were greater for males than females in Afghanistan, Iran, Egypt, Ethiopia and Nigeria. (all p < 0.001). CONCLUSIONS:The burden of IHD among females in LMIC has increased considerably in LMICs from 1990 to 2019. While the ASMR from IHD across most countries is declining, this was not uniformly noted. Furthermore, several countries noted lesser improvement in ASMR among females compared to males.

BACKGROUND:Left ventricular assist device (LVAD) implantation is frequently employed in patients with end-stage heart failure. The outcomes of addressing the repair of all substantial aortic valvular disease at the time of LVAD implantation remain unclear. We sought to assess the clinical outcomes in patients undergoing LVAD implantation concomitant with aortic valve procedures (AVPs) compared with isolated LVAD implantation.METHODS:A literature search was performed using PubMed, Embase, and Cochrane library from inception till June 2022. Primary outcomes included short-term mortality and long-term survival. Random effects models were used to compute mean differences and odds ratios with 95% confidence intervals (CIs).RESULTS:A total of 14 observational studies (N = 52 693) met our inclusion criteria. Concomitant LVAD implantation and AVPs were associated with higher short-term mortality (OR = 1.61 [95% CI, 1.06-2.42]; p = 0.02) and mean CPBt (MD = 43.25 [95% CI, 22.95-63.56]; p < 0.0001), and reduced long-term survival (OR = 0.70 [95% CI, 0.55-0.88]; p = 0.003) compared with isolated LVAD implantation. No difference in the odds of cerebrovascular accident (OR = 1.05 [95% CI, 0.79-1.39]; p = 0.74) and mean length of hospital stay (MD = 2.89 [95% CI, -4.04 to 9.82]; p = 0.41) was observed between the two groups. On adjusted analysis, short-term mortality was significantly higher in the LVAD group with concurrent AVPs when compared with the isolated LVAD group (aHR = 1.50 [95% CI, 1.20-1.87]; p = 0.0004).CONCLUSIONS:Concurrent AVPs were associated with higher short-term mortality and reduced long-term survival in patients undergoing LVAD implantation compared with isolated LVAD implantation.

The prevalence of different cancers after heart transplant (HT) is unclear due to small and conflicting prior studies. Herein, we report a systematic review and meta-analysis to highlight the prevalence and pattern of malignancies post-HT. We conducted an extensive literature search on PubMed, Scopus, Cochrane databases for prospective or retrospective studies reporting malignancies after HT. The proportions from each study were subjected to random effects model that yielded the pooled estimate with 95% confidence intervals (CI). Fifty-five studies comprising 60,684 HT recipients reported 7759 total cancers during a mean follow-up of 9.8 ± 5.9 years, with an overall incidence of 15.3% (95% CI = 12.7%-18.1%). Mean time from HT to cancer diagnosis was 5.1 ± 4 years. The most frequent cancers were gastrointestinal (7.6%), skin (5.7%), and hematologic/blood (2.5%). Meta-regression showed no association between incidence of cancer and mean age at HT (coeff: -0.008; P = 0.25), percentage of male recipients (coeff: -0.001; P = 0.81), donor age (coeff: -0.011; P = 0.44), 5-year (coeff: 0.003; P = 0.12) and 10-year (coeff: 0.02; P = 0.68) post-transplant survival. There is a substantial risk of malignancies in HT recipients, most marked for gastrointestinal, skin, and hematologic. Despite their occurrence, survival is not significantly impacted.

Abstract Objective To assess recent trends in age adjusted mortality rates (AAMRs) in the United States based on county level presidential voting patterns. Design Cross sectional study. Setting USA, 2001-19. Participants 99.8% of the US population. Main outcome measures AAMR per 100 000 population and average annual percentage change (APC). Methods The Centers for Disease Control and Prevention WONDER database was linked to county level data on US presidential elections. County political environment was classified as either Democratic or Republican for the four years that followed a November presidential election. Additional sensitivity analyses analyzed AAMR trends for counties that voted only for one party throughout the study, and county level gubernatorial election results and state level AAMR trends. Joinpoint analysis was used to assess for an inflection point in APC trends. Results The study period covered five presidential elections from 2000 to 2019. From 2001 to 2019, the AAMR per 100 000 population decreased by 22% in Democratic counties, from 850.3 to 664.0 (average APC −1.4%, 95% confidence interval −1.5% to −1.2%), but by only 11% in Republican counties, from 867.0 to 771.1 (average APC −0.7%, −0.9% to −0.5%). The gap in AAMR between Democratic and Republican counties therefore widened from 16.7 (95% confidence interval 16.6 to 16.8) to 107.1 (106.5 to 107.7). Statistically significant inflection points in APC occurred for Democratic counties between periods 2001-09 (APC −2.1%, −2.3% to −1.9%) and 2009-19 (APC −0.8%, −1.0% to −0.6%). For Republican counties between 2001 and 2008 the APC was −1.4% (−1.8% to −1.0%), slowing to near zero between 2008 and 2019 (APC −0.2%, −0.4% to 0.0%). Male and female residents of Democratic counties experienced both lower AAMR and twice the relative decrease in AAMR than did those in Republican counties. Black Americans experienced largely similar improvement in AAMR in both Democratic and Republican counties. However, the AAMR gap between white residents in Democratic versus Republican counties increased fourfold, from 24.7 (95% confidence interval 24.6 to 24.8) to 101.3 (101.0 to 101.6). Rural Republican counties experienced the highest AAMR and the least improvement. All trends were similar when comparing counties that did not switch political environment throughout the period and when gubernatorial election results were used. The greatest contributors to the widening AAMR gap between Republican and Democratic counties were heart disease (difference in AAMRs 27.6), cancer (17.3), and chronic lower respiratory tract diseases (8.3), followed by unintentional injuries (3.3) and suicide (3.0). Conclusion The mortality gap in Republican voting counties compared with Democratic voting counties has grown over time, especially for white populations, and that gap began to widen after 2008.

There have been concerns that Black patients may be at risk for poorer outcomes after an acute myocardial infarction (AMI), compared with White patients, because of decreased access to quality care and a lower likelihood of receiving evidence-based cardiovascular interventions. 1 Blackston JW Safford MM Mefford MT Freeze E Howard G Howard VJ Naftel DC Brown TM Levitan EB. Cardiovascular disease events and mortality after myocardial infarction among Black and White adults: REGARDS study. Circ Cardiovasc Qual Outcomes. 2020; 13e006683 Crossref PubMed Scopus (6) Google Scholar , 2 Mathews R Chen AY Thomas L Wang TY Chin CT Thomas KL Roe MT Peterson ED. Differences in short-term versus long-term outcomes of older black versus white patients with myocardial infarction: findings from the Can Rapid Risk Stratification of Unstable Angina Patients Suppress Adverse Outcomes with Early Implementation of American College of Cardiology/American Heart Association Guidelines (CRUSADE). Circulation. 2014; 130: 659-667 Crossref PubMed Scopus (21) Google Scholar , 3 Singh JA Lu X Ibrahim S Cram P. Trends in and disparities for acute myocardial infarction: an analysis of Medicare claims data from 1992 to 2010. BMC Med. 2014; 12: 190 Crossref PubMed Scopus (49) Google Scholar However, individual studies have shown conflicting results, with some demonstrating poorer outcomes after AMI in Black patients, 1 Blackston JW Safford MM Mefford MT Freeze E Howard G Howard VJ Naftel DC Brown TM Levitan EB. Cardiovascular disease events and mortality after myocardial infarction among Black and White adults: REGARDS study. Circ Cardiovasc Qual Outcomes. 2020; 13e006683 Crossref PubMed Scopus (6) Google Scholar ,4 Skinner J Chandra A Staiger D Lee J McClellan M. Mortality after acute myocardial infarction in hospitals that disproportionately treat black patients. Circulation. 2005; 112: 2634-2641 Crossref PubMed Scopus (195) Google Scholar whereas others suggest no difference between the 2 racial groups. 2 Mathews R Chen AY Thomas L Wang TY Chin CT Thomas KL Roe MT Peterson ED. Differences in short-term versus long-term outcomes of older black versus white patients with myocardial infarction: findings from the Can Rapid Risk Stratification of Unstable Angina Patients Suppress Adverse Outcomes with Early Implementation of American College of Cardiology/American Heart Association Guidelines (CRUSADE). Circulation. 2014; 130: 659-667 Crossref PubMed Scopus (21) Google Scholar ,5 Ng DK Brotman DJ Lau B Young JH. Insurance status, not race, is associated with mortality after an acute cardiovascular event in Maryland. J Gen Intern Med. 2012; 27: 1368-1376 Crossref PubMed Scopus (23) Google Scholar ,6 Huckfeldt P Escarce J Sood N Yang Z Popescu I Nuckols T. Thirty-day postdischarge mortality among black and white patients 65 years and older in the Medicare Hospital Readmissions Reduction Program. JAMA Netw Open. 2019; 2e190634 Crossref PubMed Scopus (12) Google Scholar It is essential to identify racial disparities in outcomes to develop policies designed to ensure equity and delivery of care and outcomes. Therefore, we sought to conduct a meta-analysis of available studies to examine whether mortality after AMI differs between Black and White patients.

The population of adults with congenital heart disease (ACHD) is rapidly increasing. There is limited understanding of location of death and associated disparities in these patients. From 2005-2018, a trend-level analysis was performed using death certificate data from the Centers for Disease Control and Prevention Wide-ranging Online Data for Epidemiologic Research Database, with individual-level mortality data obtained from National Center for Health Statistics. Places of death were classified as hospital, home, hospice facility, nursing home/long-term care and other. A total of 15,507 total deaths were identified in ACHD from 2005-2018 (54% Male, 84% White). ACHD patients were more likely to die in the hospital (64%) compared to general population (41%). Younger decedents (20-34) with ACHD were more likely to die in the hospital, while older decedents (≥65) were more likely to die at Hospice/Nursing facilities. Black and Hispanic patients with ACHD were more likely to die in the hospital compared to White and non-Hispanic patients. A significantly large proportion of ACHD deaths are observed in younger patients and occur in inpatient facilities. End-of-life planning among socially vulnerable populations should be prioritized.

1364 Objectives: Increased serum alkaline phosphatase (SAP) in an asymptomatic patient may pose a diagnostic dilemma for the clinician. Major sources of SAP are bone and liver. A retrospective review was done to assess the value of routine bone scan (BS) to identify occult bone pathology such as Paget’s disease (PD) or metastatic disease as the source of elevated SAP. Methods: 87 BS were performed because of increased SAP (range 126-986 U/L, mean 222 U/L, reference range 25-125 U/L). There were 59 men and 28 women, age 29-87 years (mean 64 years). Patients with elevated SAP and known malignancy or PD were excluded. Whole-body (and where necessary spot/SPECT) Tc-99m HDP BS was performed in all patients. Diagnosis was based on characteristic scintigraphic patterns and radiographic/pathologic correlation. Results: In 67/87 (77%), no significant bone abnormality was identified other than age-related degenerative change (Table). PD was found in 11/87 (13%), including the lowest SAP (126). In three (SAP 136, 138, 293), the major abnormalities were lumbar vertebral body, sacral insufficiency and multiple rib fractures, respectively. In one (SAP 356), abnormal liver uptake on BS led to the diagnosis of colon cancer with extensive lymph node and liver metastases (the likely source of elevated SAP). 5 cases of previously undiagnosed metastatic cancer (4 prostate, 1 lung) (SAP range 215-986, including the 2 highest) were identified. In general, it appeared that for either PD or metastases, the higher the SAP, the greater the bone involvement. Conclusions: Metabolic bone disease and metastases are present over a wide range of SAP levels, reflecting the degree of active metabolism. In general, minor elevations in SAP have a lower incidence of PD or other significant pathology and BS may be better reserved for SAP > 200. Correlation with serum calcium, SAP fractionation and serum PSA (where clinically appropriate) may be alternative approaches to routine BS.

The population of adults with congenital heart disease (ACHD) is rapidly increasing. There is limited understanding of location of death and associated disparities in these patients. From 2005-2018, a trend-level analysis was performed using death certificate data from the Centers for Disease Control and Prevention Wide-ranging Online Data for Epidemiologic Research Database, with individual-level mortality data obtained from National Center for Health Statistics. Places of death were classified as hospital, home, hospice facility, nursing home/long-term care and other. A total of 15,507 total deaths were identified in ACHD from 2005-2018 (54% Male, 84% White). ACHD patients were more likely to die in the hospital (64%) compared to general population (41%). Younger decedents (20-34) with ACHD were more likely to die in the hospital, while older decedents (≥65) were more likely to die at Hospice/Nursing facilities. Black and Hispanic patients with ACHD were more likely to die in the hospital compared to White and non-Hispanic patients. A significantly large proportion of ACHD deaths are observed in younger patients and occur in inpatient facilities. End-of-life planning among socially vulnerable populations should be prioritized.