ABSTRACT
AIM: To develop 10-year cardiovascular disease (CVD) risk prediction models in Chinese patients with type 2 diabetes mellitus (T2DM) managed in primary care using machine learning (ML) methods. METHODS: In this 10-year population-based retrospective cohort study, 141 516 Chinese T2DM patients aged 18 years or above, without history of CVD or end-stage renal disease and managed in public primary care clinics in 2008, were included and followed up until December 2017. Two-thirds of the patients were randomly selected to develop sex-specific CVD risk prediction models. The remaining one-third of patients were used as the validation sample to evaluate the discrimination and calibration of the models. ML-based methods were applied to missing data imputation, predictor selection, risk prediction modelling, model interpretation, and model evaluation. Cox regression was used to develop the statistical models in parallel for comparison. RESULTS: During a median follow-up of 9.75 years, 32 445 patients (22.9%) developed CVD. Age, T2DM duration, urine albumin-to-creatinine ratio (ACR), estimated glomerular filtration rate (eGFR), systolic blood pressure variability and glycated haemoglobin (HbA1c) variability were the most important predictors. ML models also identified nonlinear effects of several predictors, particularly the U-shaped effects of eGFR and body mass index. The ML models showed a Harrell's C statistic of >0.80 and good calibration. The ML models performed significantly better than the Cox regression models in CVD risk prediction and achieved better risk stratification for individual patients. CONCLUSION: Using routinely available predictors and ML-based algorithms, this study established 10-year CVD risk prediction models for Chinese T2DM patients in primary care. The findings highlight the importance of renal function indicators, and variability in both blood pressure and HbA1c as CVD predictors, which deserve more clinical attention. The derived risk prediction tools have the potential to support clinical decision making and encourage patients towards self-care, subject to further research confirming the models' feasibility, acceptability and applicability at the point of care.
Subject(s)
Cardiovascular Diseases , Diabetes Mellitus, Type 2 , Machine Learning , Primary Health Care , Humans , Diabetes Mellitus, Type 2/complications , Male , Female , Cardiovascular Diseases/epidemiology , Cardiovascular Diseases/etiology , Middle Aged , Retrospective Studies , Aged , China/epidemiology , Risk Assessment/methods , Adult , Risk Factors , Follow-Up Studies , East Asian PeopleABSTRACT
BACKGROUND: Hypertension is strongly associated with cardiovascular events. Studies have shown that electrocardiographic (ECG) abnormalities were associated with increased risks for cardiovascular events. However local data is limited. The objectives of this study were: (1) to determine the prevalence of major electrocardiographic abnormalities in patients with hypertension in primary care in Hong Kong, and (2) to determine the association of major electrocardiographic abnormalities with patients' socio-economical background, cardiovascular disease and cardiovascular risk factors. METHODS: This was a cross-sectional study. Subjects were hypertensive patients aged between 18 and 80 who were enrolled in the Risk Assessment and Management Programme (RAMP) in a general outpatient clinic in Hong Kong. Outcome measures were prevalence of probable ischaemic heart disease (IHD), complete left bundle branch block (LBBB), left ventricular hypertrophy (LVH) and atrial fibrillation (AF) in patients with hypertension. The Pearson Chi-square test, independent t-test and Mantel-Haenszel test were used to measure the association between socioeconomic characteristics and cardiovascular risk factors, and ECG abnormalities. RESULTS: 504 hypertensive patients aged 18-80 were recruited in a general outpatient clinic. 6.3% had probable IHD, 0.4% had complete LBBB, 4.0% had LVH and 1.0% had AF. Probable IHD was associated with smoking (P = 0.032), hypercholesterolaemia (P = 0.037) and higher 10-year CV risk (P = 0.04). Complete LBBB was associated with smoking (P = 0.021) and hypercholesterolaemia (P = 0.022). LVH was associated with male gender (P = 0.001) and longer duration of hypertension (P = 0.035). AF was not significantly associated with any of the clinical or sociodemographic parameters. CONCLUSIONS: This study showed that a significant proportion of patients with hypertension at the primary care setting in Hong Kong had probable ischaemic heart disease, left ventricular hypertrophy and atrial fibrillation. This finding is consistent with both overseas data and historic data in Hong Kong. The detection of electrocardiographic abnormalities is helpful in hypertension management by improving risk stratification.
Subject(s)
Atrial Fibrillation , Hypercholesterolemia , Hypertension , Myocardial Ischemia , Adolescent , Adult , Aged , Aged, 80 and over , Atrial Fibrillation/diagnosis , Bundle-Branch Block/complications , Bundle-Branch Block/diagnosis , Bundle-Branch Block/epidemiology , Cross-Sectional Studies , Electrocardiography , Hong Kong/epidemiology , Humans , Hypercholesterolemia/complications , Hypertension/complications , Hypertension/diagnosis , Hypertension/epidemiology , Hypertrophy, Left Ventricular/complications , Hypertrophy, Left Ventricular/diagnosis , Hypertrophy, Left Ventricular/epidemiology , Male , Middle Aged , Myocardial Ischemia/complications , Myocardial Ischemia/diagnosis , Myocardial Ischemia/epidemiology , Prevalence , Primary Health Care , Risk Factors , Young AdultABSTRACT
AIMS: To develop and validate 10-year risk prediction models, nomograms and charts for end-stage renal disease (ESRD) in Chinese patients with type 2 diabetes mellitus (T2DM) in primary care, in order to guide individualized treatment. MATERIALS AND METHODS: This was a 10-year population-based observational cohort study. A total of 141 516 Chinese T2DM patients without history of cardiovascular disease or ESRD who were managed in public primary care clinics in 2008 were included and followed up until December 2017. Two-thirds of these patients were randomly selected to develop sex-specific ESRD risk prediction models using Cox regressions. The validity and accuracy of the models were tested on the remaining third of patients using Harrell's C-index. We selected variables based on their clinical and statistical importance to construct the nomograms and charts. RESULTS: The median follow-up period was 9.75 years. The cumulative incidence of ESRD was 6.0% (men: 6.1%, women: 5.9%). Age, diabetes duration, systolic blood pressure (SBP), SBP variability, diastolic blood pressure, triglycerides, glycated haemoglobin (HbA1c), HbA1c variability, urine albumin to creatinine ratio (UACR), and estimated glomerular filtration rate (eGFR) were significant predictors for both sexes. Smoking and total cholesterol to HDL cholesterol ratio were additional significant predictors for men and women, respectively. The models showed Harrell's C-statistics of 0.889/0.889 (women/men). Age, eGFR, UACR, SBP and HbA1c were selected for both sexes to develop nomograms and charts. CONCLUSIONS: Using routinely available variables, the 10-year ESRD risk of Chinese T2DM patients in primary care can be predicted with approximately 90% accuracy. We have developed different tools to facilitate routine ESRD risk prediction in primary care, so that individualized care can be provided to prevent or delay ESRD in T2DM patients.
Subject(s)
Diabetes Mellitus, Type 2 , Kidney Failure, Chronic , China/epidemiology , Diabetes Mellitus, Type 2/complications , Diabetes Mellitus, Type 2/epidemiology , Female , Glomerular Filtration Rate , Humans , Kidney Failure, Chronic/epidemiology , Kidney Failure, Chronic/etiology , Male , Nomograms , Primary Health Care , Retrospective Studies , Risk FactorsABSTRACT
INTRODUCTION: Diabetes mellitus (DM) is a major disease burden worldwide because it is associated with disabling and lethal complications. DM complication risk assessment and stratification is key to cost-effective management and tertiary prevention for patients with diabetes in primary care. Existing risk prediction functions were found to be inaccurate in Chinese patients with diabetes in primary care. This study aims to develop 10-year risk prediction models for total cardiovascular diseases (CVD) and all-cause mortality among Chinese patients with DM in primary care. METHODS AND ANALYSIS: A 10-year cohort study on a population-based primary care cohort of Chinese patients with diabetes, who were receiving care in the Hospital Authority General Outpatient Clinic on or before 1 January 2008, were identified from the clinical management system database of the Hospital Authority. All patients with complete baseline risk factors will be included and followed from 1 January 2008 to 31 December 2017 for the development and validation of prediction models. The analyses will be carried out separately for men and women. Two-thirds of subjects will be randomly selected as the training sample for model development. Cox regressions will be used to develop 10-year risk prediction models of total CVD and all-cause mortality. The validity of models will be tested on the remaining one-third of subjects by Harrell's C-statistics and calibration plot. Risk prediction models for diabetic complications specific to Chinese patients in primary care will enable accurate risk stratification, prioritisation of resources and more cost-effective interventions for patients with DM in primary care. ETHICS AND DISSEMINATION: The study was approved by the Institutional Review Board of the University of Hong Kong-the Hospital Authority Hong Kong West Cluster (reference number: UW 15-258). TRIAL REGISTRATION NUMBER: NCT03299010; Pre-results.
Subject(s)
Diabetes Complications/epidemiology , Diabetes Mellitus/mortality , Risk Assessment , Adult , China/ethnology , Clinical Protocols , Diabetes Complications/etiology , Diabetes Complications/mortality , Female , Hong Kong/epidemiology , Humans , Male , Models, Statistical , Primary Health Care/statistics & numerical data , Proportional Hazards Models , Retrospective Studies , Risk FactorsABSTRACT
BACKGROUND: A territory-wide diabetes management program (Risk Assessment Management Program - RAMP) was recently established, providing comprehensive management for all diabetics, helping to delineate current level of control and complications prevalence among primary care diabetic patients in Hong Kong. METHOD: This cross-sectional study captured anonymous clinical data from RAMP patients. Data obtained include sociodemographic details, type of diabetes, illness duration, family history, drug usage, coexisting illnesses, diabetic complications and other clinical parameters. RESULTS: Data from 15,856 type 2 diabetic patients were analyzed. 57.1% were above 60 years old, with mean disease duration of 7.3 years. Hypertension was the commonest coexisting chronic illness (57.6%). 30.2% and 61.8% have their systolic and diastolic pressure controlled to below 130 mmHg and 80 mmHg respectively. Over half (51.5%) had an HbA1c level of less than 7.0%. 88.4% did not achieve target lipid level. 15% were on diet control alone. Only 22.2% were on statins. In patients with microalbuminuria and macroalbuminuria, 40.7% and 54.5% were on angiotensin converting enzyme inhibitor (ACEI) or angiotensin receptor blocker (ARB) respectively. 12.9%, 38.8% and 2.4% had diabetic retinopathy, nephropathy and neuropathy respectively. Overall, 37.9%, 7.3% and 0.4% had single, two and three concurrent microvascular complications respectively. CONCLUSION: The level of diabetic control is comparable with other developed countries. We demonstrated a high prevalence of microvascular complications among Chinese primary care patients despite achieving adequate HbA1c levels, highlighting the importance of managing all aspects of diabetes including weight, lipid and blood pressure. Efforts to improve holistic management must be tailored according to the needs of our population, with the challenges that the majority have low educational background and in the older age group.