scholarly journals Prediction performance of a cardiovascular risk assessment tool using Stanford EHR data repository

2019 ◽  
Author(s):  
Mehrdad Rezaee ◽  
Arsia Takeh ◽  
Igor Putrenko ◽  
Andrea Ganna ◽  
Erik Ingelsson
Keyword(s):  
Type 2 Diabetes ◽  
Risk Assessment ◽  
Prediction Models ◽  
Assessment Tool ◽  
Discrimination Performance ◽  
Data Repository ◽  
Good Prediction ◽  
Effective Prevention ◽  
Medicine Research

AbstractBackgroundStratification of individuals for their risk to develop cardiovascular diseases can be used for effective prevention and intervention. A significant amount of information for risk assessment can be obtained through repurposing electronic health records (EHR). The objective of this study is to derive and assess the performance of prediction models for cardiovascular outcomes by using EHR-derived data.MethodsWe used the Stanford Medicine Research Data Repository (STARR) data from 2000-2017, containing over 2.1 million patients. A subset of 762,372 individuals with complete International Classification of Diseases (ICD) data was used to fit Cox proportional hazard models for prediction of six cardiovascular-related diseases and type 2 diabetes.ResultsThe derived prediction models indicated consistent high discrimination performance (C-index) for all diseases examined: coronary artery disease (0.85), hypertension (0.82), type 2 diabetes (0.77), stroke (0.76), atrial fibrillation (0.82) and abdominal aortic aneurysm (0.77). Lower prediction abilities were observed for deep vein thrombosis (0.67). These results were consistent across age groups and maintained good prediction abilities among individuals with pre-existing diabetes or hypertension. Assessment of model calibration is ongoing.ConclusionsWe proposed new prediction models for the seven diseases using ICD codes derived from EHR data. EHR data can be used for health risk assessment, but challenges related to data quality and model generalizability and calibration remain to be solved.

AUSDRISK: an Australian Type 2 Diabetes Risk Assessment Tool based on demographic, lifestyle and simple anthropometric measures

2010 ◽  
Vol 192 (4) ◽  
pp. 197-202 ◽  
Author(s):  
Lei Chen ◽  
Dianna J Magliano ◽  
Beverley Balkau ◽  
Stephen Colagiuri ◽  
Paul Z Zimmet ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Risk Assessment ◽  
Assessment Tool ◽  
Diabetes Risk ◽  
Risk Assessment Tool ◽  
Anthropometric Measures

scholarly journals TYPE 2 DIABETES MELLITUS PREDICTION IN MALAYSIA USING MODIFIED DIABETES RISK ASSESSMENT TOOL

2020 ◽  
Vol 20 (1) ◽  
pp. 15-21
Author(s):  
Aung Myo Oo ◽  
Al-abed Ali Ahmed Al-abed ◽  
Ohn Mar Lwin ◽  
Sowmya Sham Kanneppady ◽  
Tee Yee Sim ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Risk Assessment ◽  
Type 2 Diabetes Mellitus ◽  
High Risk ◽  
Assessment Tool ◽  
Cost Effective ◽  
Risk Assessment Tool ◽  
Type 2 Dm

Type 2 diabetes mellitus (DM) is becoming major health threat worldwide and it is extremely common in clinical setting. Malaysia is one of the highest diabetic populations among Asian countries and the new cases are increasing day to day. Early detection of people with high risk of Type 2 DM by using simple, easy and cost-effective assessment tool is the better way to identify and prevent the community from this non-communicable disease. The objectives of the study were to identify those are high risk to become type 2DM among Malaysians by using risk scoring form and to educate them how to prevent it. Total 591 subjects were recruited from the health screening programs carried out by the collaboration of Petaling Jaya Development Council (MBPJ) and Lincoln University College, Malaysia. Modified form of Finnish Type 2 Diabetes Risk Assessment Tool was used to identify people at risk of becoming type 2 DM. Descriptive analysis was performed for all included variables in this study by using SPSS version 21. The study found out that almost half of the participants were found to have family history of DM, 60% of them were overweight and obese and 47% were having above normal waist circumference. We observed that nearly 60 % of participants in the study were having moderate to high risk of becoming type 2 DM in next 10 years. To conclude, the result of our study would be helpful in implementation of cost-effective, convenient Type 2 DM risk assessment tool which has yet to be implemented in Malaysia.

scholarly journals 105RANDOM NON-FASTING C-PEPTIDE CAN BE USED AS A RISK ASSESSMENT TOOL FOR HYPOGLYCAEMIA IN ELDERLY NSULIN-TREATED PATIENTS WITH TYPE 2 DIABETES

2017 ◽  
Vol 46 (suppl_1) ◽  
pp. i27-i27
Author(s):  
S V Hope ◽  
B A Knight ◽  
B M Shields ◽  
A Hill ◽  
P Choudhary ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Risk Assessment ◽  
Assessment Tool ◽  
Risk Assessment Tool ◽  
C Peptide

A Risk Assessment Tool for Identifying Osteoporosis in Older Women with Type 2 Diabetes Mellitus

2021 ◽  
Author(s):  
Fenghui Pan ◽  
Wenxia Cui ◽  
Lei Gao ◽  
Xiaoting Shi ◽  
Mingrui Zhang ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Risk Assessment ◽  
Type 2 Diabetes Mellitus ◽  
Older Women ◽  
Risk Score ◽  
Assessment Tool ◽  
Risk Assessment Tool ◽  
Characteristic Analysis

Abstract Purpose To develop a simple and clinically useful assessment tool for osteoporosis in older women with type 2 diabetes mellitus (T2DM). Methods A total of 601 women over 60 years of age with T2DM were enrolled in this study. The levels of serum sex hormones and bone metabolism markers were compared between the osteoporosis and non-osteoporosis groups. The least absolute shrinkage and selection operator regularization (LASSO) model was applied to generate a risk assessment tool. The risk score formula was evaluated using receiver operating characteristic analysis and the relationship between the risk score and the bone mineral density (BMD) and T-value were investigated. Results Serum sex hormone-binding globulin (SHBG), cross-linked C-telopeptide of type 1 collagen (CTX), and osteocalcin (OC) were significantly higher in the osteoporosis group. After adjustment for age and body mass index (BMI), SHBG was found to be correlated with the T-value or BMD. Then, a risk score was specifically generated with age, BMI, SHBG, and CTX using the LASSO model. The risk score was significantly negatively correlated with the T-value and BMD of the lumbar spine, femoral neck, and total hip (all P<0.05). Conclusion A risk score using age, BMI, SHBG, and CTX performs well for identifying osteoporosis in older women with T2DM.

scholarly journals Prediction Models for Type 2 Diabetes Risk in the General Population: A Systematic Review of Observational Studies

2021 ◽  
Vol In Press (In Press) ◽  
Author(s):  
Samaneh Asgari ◽  
Davood Khalili ◽  
Farhad Hosseinpanah ◽  
Farzad Hadaegh
Keyword(s):  
Type 2 Diabetes ◽  
Prediction Model ◽  
Prediction Models ◽  
Assessment Tool ◽  
Data Extraction ◽  
External Validation ◽  
Model Development ◽  
Selection Procedure ◽  
Poor Quality

Objectives: This study aimed to provide an overview of prediction models of undiagnosed type 2 diabetes mellitus (U-T2DM) or the incident T2DM (I-T2DM) using the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) checklist and the prediction model risk of the bias assessment tool (PROBAST). Data Sources: Both PUBMED and EMBASE databases were searched to guarantee adequate and efficient coverage. Study Selection: Articles published between December 2011 and October 2019 were considered. Data Extraction: For each article, information on model development requirements, discrimination measures, calibration, overall performance, clinical usefulness, overfitting, and risk of bias (ROB) was reported. Results: The median (interquartile range; IQR) number of the 46 study populations for model development was 5711 (1971 - 27426) and 2457 (2060 - 6995) individuals for I-T2DM and U-T2DM, respectively. The most common reported predictors were age and body mass index, and only the Qrisk-2017 study included social factors (e.g., Townsend score). Univariable analysis was reported in 46% of the studies, and the variable selection procedure was not clear in 17.4% of them. Moreover, internal and external validation was reported in 43% the studies, while over 63% of them reported calibration. The median (IQR) of AUC for I-T2DM models was 0.78 (0.74 - 0.82); the corresponding value for studies derived before October 2011 was 0.80 (0.77 - 0.83). The highest discrimination index was reported for Qrisk-2017 with C-statistics of 0.89 for women and 0.87 for men. Low ROB for I-T2DM and U-T2DM was assessed at 18% and 41%, respectively. Conclusions: Among prediction models, an intermediate to poor quality were reassessed in several aspects of model development and validation, even though there was a comprehensive protocol. Generally, despite its new risk factors or new methodological aspects, the newly developed model did not increase our capability in screening/predicting T2DM, mainly in the analysis part. It was due to the lack of external validation of the prediction models.

Sign in / Sign up

Export Citation Format

Share Document