Risk prediction models for mortality in patients with cardiovascular disease: The BioBank Japan project
نویسندگان
چکیده
BACKGROUND Cardiovascular disease (CVD) is a leading cause of death in Japan. The present study aimed to develop new risk prediction models for long-term risks of all-cause and cardiovascular death in patients with chronic phase CVD. METHODS Among the subjects registered in the BioBank Japan database, 15,058 patients aged ≥40 years with chronic ischemic CVD (ischemic stroke or myocardial infarction) were divided randomly into a derivation cohort (n = 10,039) and validation cohort (n = 5019). These subjects were followed up for 8.55 years in median. Risk prediction models for all-cause and cardiovascular death were developed using the derivation cohort by Cox proportional hazards regression. Their prediction performances for 5-year risk of mortality were evaluated in the validation cohort. RESULTS During the follow-up, all-cause and cardiovascular death events were observed in 2962 and 962 patients from the derivation cohort and 1536 and 481 from the validation cohort, respectively. Risk prediction models for all-cause and cardiovascular death were developed from the derivation cohort using ten traditional cardiovascular risk factors, namely, age, sex, CVD subtype, hypertension, diabetes, total cholesterol, body mass index, current smoking, current drinking, and physical activity. These models demonstrated modest discrimination (c-statistics, 0.703 for all-cause death; 0.685 for cardiovascular death) and good calibration (Hosmer-Lemeshow χ2-test, P = 0.17 and 0.15, respectively) in the validation cohort. CONCLUSIONS We developed and validated risk prediction models of all-cause and cardiovascular death for patients with chronic ischemic CVD. These models would be useful for estimating the long-term risk of mortality in chronic phase CVD.
منابع مشابه
C-reactive protein and other markers of inflammation in hemodialysis patients
Background: Hemodialysis patients are at greater risk of cardiovascular disease. Higher than expected cardiovascular morbidity and mortality in this population has been attributed to dislipidemia as well as inflammation. The causes of inflammation in hemodialysis patients are multifactorial. Several markers were used for the detection of inflammatory reaction in patients with chronic renal dise...
متن کاملInvestigation on the risk factores for mortality of patients with COVID-19 and prioritization these factores using neural network in some southern cities of Iran
Background: The coronavirus disease 2019 (COVID-19 the seventh human coronavirus) was discovered in Wuhan, Hubei province of China, in January 2020. COVID-19 virus caused six million deads in the world to date and cussed infection of more than seven million of cases in Iran(1). This infectious disease caused by the SARS-CoV-2 virus. This virus was contagious and fast-spread. Despite the aquaran...
متن کاملHEART RATE: A PREDICTOR OF EARLY MORTALITY IN PATIENTS WITH MYOCARDIAL INFARCTION
A number of epidemiologic studies have reported a positive relationship between heart rate, cardiovascular disease and mortality. To examine the correlation between heart rate and mortality after acute myocardial infarction (AMI), 2147 patients hospitalized in coronary care units in Isfahan were investigated in a cross-sectional study. Their heart rate was measured according to an electroca...
متن کاملPrediction of Emotional Repression based on Alexithymia and Type D Personality in Cardiovascular Patients
Introduction: Cardiovascular disease is one of the causes of mortality in the world, which psychological factors play an important role in its occurrence and exacerbation. This study aimed to investigate the prediction of emotional repression based on alexithymia and type D personality in cardiovascular patients. Methods: Participants were 100 patients with coronary artery disease selected thr...
متن کاملProposing an Intelligent Monitoring System for Early Prediction of Need for Intubation among COVID-19 Hospitalized Patients
Introduction: Predicting acute respiratory insufficiency due to coronavirus disease 2019 (COVID-19) can diminish the severe complications and mortality associated with the disease. This study aimed to develop an intelligent system based on machine learning (ML) models for frontline clinicians to effectively triage high-risk patients and prioritize who needs mechanical intubation (MI). Material...
متن کامل