Search

Background The current acute kidney injury (AKI) risk prediction model for patients undergoing percutaneous coronary intervention (PCI) from the American College of Cardiology (ACC) National Cardiovascular Data Registry (NCDR) employed regression techniques. This study aimed to evaluate whether models using machine learning techniques could significantly improve AKI risk prediction after PCI. Methods and findings We used the same cohort and candidate variables used to develop the current NCDR CathPCI Registry AKI model, including 947,091 patients who underwent PCI procedures between June 1, 2009, and June 30, 2011. The mean age of these patients was 64.8 years, and 32.8% were women, with a total of 69,826 (7.4%) AKI events. We replicated the current AKI model as the baseline model and compared it with a series of new models. Temporal validation was performed using data from 970,869 patients undergoing PCIs between July 1, 2016, and March 31, 2017, with a mean age of 65.7 years; 31.9% were women, and 72,954 (7.5%) had AKI events. Each model was derived by implementing one of two strategies for preprocessing candidate variables (preselecting and transforming candidate variables or using all candidate variables in their original forms), one of three variable-selection methods (stepwise backward selection, lasso regularization, or permutation-based selection), and one of two methods to model the relationship between variables and outcome (logistic regression or gradient descent boosting). The cohort was divided into different training (70%) and test (30%) sets using 100 different random splits, and the performance of the models was evaluated internally in the test sets. The best model, according to the internal evaluation, was derived by using all available candidate variables in their original form, permutation-based variable selection, and gradient descent boosting. Compared with the baseline model that uses 11 variables, the best model used 13 variables and achieved a significantly better area under the receiver operating characteristic curve (AUC) of 0.752 (95% confidence interval [CI] 0.749-0.754) versus 0.711 (95% CI 0.708-0.714), a significantly better Brier score of 0.0617 (95% CI 0.0615-0.0618) versus 0.0636 (95% CI 0.0634-0.0638), and a better calibration slope of observed versus predicted rate of 1.008 (95% CI 0.988-1.028) versus 1.036 (95% CI 1.015-1.056). The best model also had a significantly wider predictive range (25.3% versus 21.6%, p < 0.001) and was more accurate in stratifying AKI risk for patients. Evaluated on a more contemporary CathPCI cohort (July 1, 2015-March 31, 2017), the best model consistently achieved significantly better performance than the baseline model in AUC (0.785 versus 0.753), Brier score (0.0610 versus 0.0627), calibration slope (1.003 versus 1.062), and predictive range (29.4% versus 26.2%). The current study does not address implementation for risk calculation at the point of care, and potential challenges include the availability and accessibility of the predictors. Conclusions Machine learning techniques and data-driven approaches resulted in improved prediction of AKI risk after PCI. The results support the potential of these techniques for improving risk prediction models and identification of patients who may benefit from risk-mitigation strategies., Author(s): Chenxi Huang 1, Karthik Murugiah 2, Shiwani Mahajan 1, Shu-Xia Li 1, Sanket S. Dhruva 3,4, Julian S. Haimovich 5, Yongfei Wang 1, Wade L. Schulz 1,6, Jeffrey M. [...]

Our objective was to examine the association between parental immigration status and child health and health care utilization. Using data from a national sample of immigrant adults who had recently [...]

A randomized large scale trial was conducted among 1653 patients with recent history of hospitalization for heart failure to undergo either telemonitoring or usual care to determine possible effect of telemonitoring for improvement of heart-failure outcomes. Telemonitoring which failed to show any outcome improvements among patients recently hospitalized for heart failure indicated the significance of a thorough, independent evaluation of disease-management strategies before their adoption.

The variations in responsiveness to the warnings against the use of the diabetes drug rosiglitazine in the USA are discussed. The Food and Drugs Administration (FDA) has issued a boxed warning as meta-analysis has shown that rosiglitazone is associated with a 43% increase in the risk of myocardial infarction.

The correlation existing between the automated external defibrillators (AEDs) and survival after in-hospital cardiac arrest is analyzed. The application of AEDs is not shown to enhance the survival of such patients.

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ahj.2010.04.013 Byline: Erica S. Spatz (a), Joseph S. Ross (b)(c), Mayur M. Desai (d), Maureen E. Canavan (d), Harlan M. Krumholz (e)(f)(g) Abstract: Expanding insurance coverage, while necessary, may not be sufficient to ensure high-quality care for adults with cardiovascular disease. We sought to examine the association between having a usual source of care (USOC) and receiving medication treatment of hypertension and hypercholesterolemia. Author Affiliation: (a) Robert Wood Johnson Clinical Scholars Program, Yale University School of Medicine, New Haven, CT (b) Department of Geriatrics and Palliative Medicine, Mount Sinai School of Medicine, New York, NY (c) HSR&D Research Enhancement Award Program and Geriatrics Research, Education, and Clinical Center, James J. Peters VA Medical Center, Bronx, NY (d) Division of Chronic Disease Epidemiology, Yale University School of Public Health, New Haven, CT (e) Robert Wood Johnson Clinical Scholars Program and Section of Cardiolovascular Medicine, Department of Medicine, Yale University School of Medicine, New Haven, CT (f) Section of Health Policy and Administration, Yale University School of Epidemiology and Public Health, New Haven, CT (g) Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT Article History: Received 29 January 2010; Accepted 16 April 2010

A study was conducted to evaluated the association between length of stay and short-term outcomes among Medicare older patients hospitalized for heart failure. Results indicated that with a reduced length of hospital stay 30-day mortality decreased; however, posthospital readmission and mortality risk increased.

A study was conducted to investigate the association between a lack of health insurance and financial constraints on accessing care among those with health insurance and the time taken from onset to hospital admission in acute myocardial infarction (AMI). Results indicated that such factors did contribute to delays in seeking emergency care for AMI.

Cross-sectional analyses of data from Medicare administrative claims for all fee-for-service beneficiaries hospitalized between 2004 and 2006 in acute care hospitals in US was conducted to determine the association between hospital volume threshold and the death rate for patients hospitalized for acute myocardial infarction, heart failure, or pneumonia. Admission to higher-volume hospitals was found to be associated with a reduction in mortality for acute myocardial infarction, heart failure, and pneumonia, but volume threshold above which an increased condition-specific hospital was not significantly associated with reduced mortality.

The study attempts to investigate the profile of US General surgery residents and highlight their attitudes, training experiences and professional expectations as well as differences due to sex and training years. The results indicate that general surgery residents undergo a wide variety of emotions including satisfaction as well as strain and do vary.

The study attempts to estimate racial differences in survival for patients following in-hospital cardiac arrests and the factors associated with it. The results indicate that African-American patients were less likely to survive discharge as compared to white patients and also that most of the racial differences were associated with the hospital in which African-American patients received care.

The study attempts to evaluate the hospital 30-day risk-standardized mortality rates (RSMRs) for those patients that have been discharged with acute myocardial infarction (AMI). The results indicate that there was a significant decrease in hospital mortality rate for patients with AMI.

A study was conducted to evaluate whether patients receiving an implantable cardioverter-defibrillator (ICD) from nonelectrophysiologists had more negative outcomes as compared to implants done by electrophysiologists who were certified for the procedure. Results indicated that implants done by nonelectrophysiologists had a higher risk of procedural complications.

The study aims to compare the mortality risk associated with hypoglycemia among patients with acute myocardial infarction who develop hypoglycemia spontaneously as against those who develop it as a result of insulin therapy. The results indicate that iatrogenic hypoglycemia after insulin therapy had much lower mortality rates as compared to spontaneous hypoglycemia.

A study was conducted to compare the use of the ezetimibe which lowers low-density lipoprotein cholesterol but not recommended as the first option for prevention in the U.S. and Canada. Results showed that despite recommended guidelines for use it was widely prescribed but the clinical outcomes remained indecisive.

A study to evaluate the strategy of Merck and Co Inc. using guest authorship and ghost writers for promotion of rofecoxib was conducted. Results showed that it was difficult to error either guest or ghost writers without determining the extent of research carried out by them on the report.

A study to examine how there is a delay in defibrillation given to patients in hospitals in the U.S. after cardiac arrest, which is ultimately responsible for their death, is conducted. Results conclude that delays in defibrillation after cardiac arrest are common and are associated with lower rate of survival.

The primary percutaneous coronary intervention (PCI) is a reperfusion therapy, which improves the chances of survival of a patient by reestablishing blood flow in the infracted artery.

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ahj.2007.06.031 Byline: Vivian Ho (a)(b), Joseph S. Ross (c)(d), Brahmajee K. Nallamothu (e), Harlan M. Krumholz (f)(g)(h) Abstract: Many states enforce Certificate of Need (CON) regulations for cardiac procedures, but little is known about how CON affects utilization. We assessed the association between cardiac CON regulations, availability of revascularization facilities, and revascularization rates. Author Affiliation: (a) Baker Institute for Public Policy, Rice University, Houston, TX (b) Department of Medicine, Baylor College of Medicine (c) Department of Geriatrics and Adult Development, Mount Sinai School of Medicine, New York, NY (d) Geriatrics Research, Education and Clinical Center, James J. Peters VA Medical Center, Bronx, NY (e) Health Services Research and Development Center of Excellence, Ann Arbor VA Medical Center, Ann Arbor, MI (f) Department of Medicine, Section of Cardiovascular Medicine and the Robert Wood Johnson Clinical Scholars Program, New Haven, CT (g) Department of Epidemiology and Public Health, Section of Health Policy and Administration, Yale University School of Medicine, New Haven, CT (h) Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT Article History: Received 29 January 2007; Accepted 19 June 2007 Article Note: (footnote) Dr Ross was a scholar in the Robert Wood Johnson Clinical Scholars Program at Yale University sponsored by the Robert Wood Johnson Foundation at times during his involvement in the project., Support was given from a grant awarded to Dr Ho by the National Heart, Lung, and Blood Institute (R01 HL073825-01A1).

Several states have laws mandating disclosure of payments made to physicians by pharmaceutical companies, and an investigation was made to determine the accessibility and quality of the available data, to describe the prevalence and magnitude of disclosed payments. Payments of $100 or more were made to physicians by pharmaceutical companies, but the laws did not provide easy access to public, and the quality of data accessed was not satisfactory.

The financial barriers to health care services or medication among individuals following acute myocardial infarction (AMI) and their association with subsequent health care outcomes are evaluated. The results have shown that the financial barriers to health care services and medications are increasingly associated with worse recovery after AMI, manifested as more angina, poorer quality of life and higher risk of rehospitalization.

A study was conducted among Medicare beneficiaries to determine whether the opening of specialty cardiac hospitals was associated with greater population-based rates of coronary revascularization. Results revealed that opening a specialty cardiac hospital within a hospital referral region (HRR) was associated with increasing use of coronary revascularization among Medic are beneficiaries.

A study evaluated whether the Medicare reimbursement policy changes that provide coverage for screening colonoscopies for all individuals are associated with an increase in either colonoscopy use or early stage colon cancer diagnosis in older patients. Results revealed that expansion of reimbursement to cover colon cancer screening is associated with an increased use of colonoscopy for Medicare beneficiaries and also an increased possibility of early stage diagnosis of colon cancer.

A study is conducted to examine different hospital strategies associated with a faster door-to-balloon time during primary percutaneous coronary intervention. Results show that many specific hospital strategies are associated with a significant reduction in the door-to-balloon time during treatment.

A study was conducted to quantify the representation of patients with renal disease in randomized controlled trials for interventions proven efficacious for cardiovascular disease. It was found that major cardiovascular disease trials frequently exclude patients with renal disease and do not provide adequate information on the renal function of enrollees or the effect of interventions on patients with renal disease.

A study was conducted to determine correlations among acute myocardial infarction (AMI) core process measures and the degree to which they explain the variation in hospital-specific, risk-standardized, 30-day mortality rates. The results indicated that the publicly reported AMI process measures capture a small proportion of the variation in hospital's risk-standardized short-term mortality rates.

ABSTRACT Background Some argue that by precluding individualized treatment, randomized clinical trials (RCTs) provide substandard medical care, while others claim that participation in clinical research is associated with improved patient [...]

A study was conducted to evaluate the effect of blinded peer review on the association between abstract characteristics and likelihood of abstract acceptance at a national research meeting. The study provided evidence of bias in the open review of abstracts, favoring authors from the United States, English-speaking countries outside the U.S. and prestigious academic institutions.

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ahj.2005.05.010 Byline: Artyom Sedrakyan (a)(b), Heping Zhang (c), Tom Treasure (d), Harlan M. Krumholz (c)(e) Abstract: Knowledge of the risk of atrial fibrillation (AF) for patients undergoing coronary artery bypass graft surgery (CABG) can guide decisions about prophylactic therapy. Accordingly, we sought to use tree-based methods to stratify patients into groups that will have similar risk of AF after CABG and informed decision making regarding aggressive prophylaxis of AF. Author Affiliation: (a) Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD (b) Department of Public Health and Policy, London School of Hygiene and Tropical Medicine, London, United Kingdom (c) Yale University School of Medicine, New Haven, CT (d) Cardiothoracic Unit, Guy's Hospital, London, United Kingdom (e) Center for Outcomes Research and Evaluation, Yale-New Haven Health, New Haven, CT Article History: Received 8 October 2004; Accepted 9 May 2005

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ahj.2005.03.069 Byline: Saif S. Rathore (a), Kevin P. Weinfurt (c), JoAnne M. Foody (a), Harlan M. Krumholz (a)(b)(d)(e)(f) Abstract: The TIMI ST-elevation myocardial infarction (STEMI) score was developed and validated in a randomized controlled trial population. We sought to assess its accuracy in a community-based cohort of elderly patients hospitalized with STEMI. Author Affiliation: (a) Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, Conn (b) Section of Health Policy and Administration, Department of Epidemiology and Public Health, Yale University School of Medicine, New Haven, Conn (c) Center for Clinical and Genetic Economics, Duke Clinical Research Institute, Duke University Medical Center, Durham, NC (d) Qualidigm, Middletown, Conn (e) Yale-New Haven Hospital Center for Outcomes Research and Evaluation, New Haven, Conn (f) The Robert Wood Johnson Clinical Scholars Program, Yale University School of Medicine, New Haven, Conn Article History: Received 18 November 2003; Accepted 29 March 2005 Article Note: (footnote) Saif Rathore was supported by NIH/National Institute of General Medical Sciences Medical Scientist Training Grant GM07205.

Sex and racial differences in the treatment of patients who were deemed to be 'ideal candidates' for particular treatment and in deaths among 598,911 patients hospitalized with myocardial infarction is examined between 1994 and 2002. Rates of reperfusion therapy, coronary angiography, and in-hospital death after myocardial infarction, but not the use of aspirin and beta-blockers, vary according to race and sex.

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ahj.2004.08.018 Byline: Saif S. Rathore (a)(b), Paul D. Frederick (e), Nathan R. Every (e), Hal V. Barron (f), Harlan M. Krumholz (a)(c)(d) Abstract: Racial differences in reperfusion therapy use among patients hospitalized with myocardial infarction (MI) have been previously reported as national phenomenon. However, it is unclear whether racial differences in treatment vary by region. Author Affiliation: (a) Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, Conn (b) MD/PhD Program, Yale University School of Medicine, New Haven, Conn (c) Section of Health Policy and Administration, Department of Epidemiology and Public Health, Yale University School of Medicine, New Haven, Conn (d) Yale-New Haven Hospital Center for Outcomes Research and Evaluation, New Haven, Conn (e) Ovation Research Group, Chicago, Ill (f) Genentech, Incorporated, South San Francisco, Calif Article History: Received 13 January 2004; Accepted 17 August 2004 Article Note: (miscellaneous) The National Registry of Myocardial Infarction-2 and -3 is supported by Genentech, Inc, South San Francisco, Calif. Mr Rathore is supported by National Institutes of Health National Institute of General Medical Sciences Medical Scientist Training Grant GM07205.

Concerns about the rationale for regionalized acute coronary syndromes (ACS) care are presented and some potential unintended consequences are outlined. Proponents contend that regionalized ACXS would save lives by improving access to new technologies, specialist physicians, and higher-quality care not available at other centers.

Race and ethnicity differences in door-to-drug and door-to-balloon times for patients receiving primary reperfusion for ST-segment elevation myocardial infarction are estimated. The results revealed that a substantial portion of the racial and ethnic disparity in time to treatment was accounted for by the specific hospital to which patients were admitted, in contrast to differential treatment by race and ethnicity inside the hospital.

The representation of various groups with regard to race, ethnicity, age, and sex in the cancer trial, despite its diversity in the participants are discussed. The representation of racial and ethnic minorities, the elderly, and women in cancer trials sponsored by the National Cancer Institute are characterized.