Evaluating the performance of the Framingham Diabetes Risk Scoring Model in Canadian electronic medical records.

OBJECTIVE The objective of this study was to evaluate the performance of the Framingham Diabetes Risk Scoring Model (FDRSM) in a Canadian population, using the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) database. METHODS We analyzed the records of 571 631 patients, between the ages of 45 and 64, between 2002 and 2005, by extracting the most recent laboratory and examination results, including age, sex, body mass index, fasting blood glucose, high-density lipoprotein, triglycerides and blood pressure. We calculated the risk scores of these patients based on the FDRSM. We tracked these patients for 8 years to find out whether or not they were diagnosed with diabetes. We used the area under the receiver operating characteristics curve (AROC) to estimate the discrimination capability of the FDRSM on our study sample and compared it with the AROC reported in the original Framingham diabetes study. RESULTS The AROC for our main research sample of 1970 patients for whom all risk factors and follow-up data were available was 78.6% compared to the AROC of 85% reported in the FDRSM. We found that 70.1% of our main sample had risks lower than 3%; 16.3% had risks between 3% and 10%; and 13.6% had risks greater than 10% for diabetes over the following 8-year period. CONCLUSIONS The discrimination capability of the FDRSM Canadian electronic medical records is fair. However, building a more accurate model for predicting diabetes based on the characteristics of Canadian patients is highly recommended.

[1]  R. Birtwhistle,et al.  Canadian Primary Care Sentinel Surveillance Network: a developing resource for family medicine and public health. , 2011, Canadian family physician Medecin de famille canadien.

[2]  Tyler Williamson,et al.  Developing a method to estimate practice denominators for a national Canadian electronic medical record database. , 2013, Family practice.

[3]  C. van Weel,et al.  Identifying people at risk for undiagnosed type 2 diabetes using the GP's electronic medical record. , 2007, Family practice.

[4]  Jaakko Tuomilehto,et al.  The diabetes risk score: a practical tool to predict type 2 diabetes risk. , 2003, Diabetes care.

[5]  Diane Lacaille,et al.  Systematic Review and Meta-Analysis of Validation Studies on a Diabetes Case Definition from Health Administrative Records , 2013, PloS one.

[6]  S. Chamukuttan,et al.  Early diagnosis and prevention of diabetes in developing countries , 2008, Reviews in Endocrine and Metabolic Disorders.

[7]  T. Brennan,et al.  Ambulatory care adverse events and preventable adverse events leading to a hospital admission , 2007, Quality and Safety in Health Care.

[8]  T. Williamson,et al.  Prevalence and epidemiology of diabetes in Canadian primary care practices: a report from the Canadian Primary Care Sentinel Surveillance Network. , 2014, Canadian journal of diabetes.

[9]  Joshua C. Denny,et al.  Type 2 Diabetes Risk Forecasting from EMR Data using Machine Learning , 2012, AMIA.

[10]  Ralph B D'Agostino,et al.  Prediction of incident diabetes mellitus in middle-aged adults: the Framingham Offspring Study. , 2007, Archives of internal medicine.

[11]  Karim Keshavjee,et al.  Who are your patients with diabetes?: EMR case definitions in the Canadian primary care setting. , 2012, Canadian family physician Medecin de famille canadien.

[12]  S. Bornstein,et al.  Validation of a simple clinical diabetes prediction model in a middle-aged, white, German population. , 2007, Archives of internal medicine.

[13]  Ross T Tsuyuki,et al.  Type 2 diabetes mellitus management in Canada: is it improving? , 2013, Canadian journal of diabetes.

[14]  Janet E Hux,et al.  Trends in diabetes prevalence, incidence, and mortality in Ontario, Canada 1995–2005: a population-based study , 2007, The Lancet.

[15]  Karim Keshavjee,et al.  Building a Pan-Canadian Primary Care Sentinel Surveillance Network: Initial Development and Moving Forward , 2009, The Journal of the American Board of Family Medicine.

[16]  C. Bennett,et al.  Ascertainment of chronic diseases using population health data: a comparison of health administrative data and patient self-report , 2013, BMC Public Health.

[17]  Peter Almgren,et al.  Clinical risk factors, DNA variants, and the development of type 2 diabetes. , 2008, The New England journal of medicine.

[18]  Jay R. Desai,et al.  Construction of a Multisite DataLink Using Electronic Health Records for the Identification, Surveillance, Prevention, and Management of Diabetes Mellitus: The SUPREME-DM Project , 2012, Preventing chronic disease.

[19]  T. Peters,et al.  Risk of ovarian cancer in women with symptoms in primary care: population based case-control study , 2009, BMJ : British Medical Journal.

[20]  M. Gulliford,et al.  Selection of Medical Diagnostic Codes for Analysis of Electronic Patient Records. Application to Stroke in a Primary Care Database , 2009, PloS one.

[21]  Amardeep Thind,et al.  Investigating concordance in diabetes diagnosis between primary care charts (electronic medical records) and health administrative data: a retrospective cohort study , 2010, BMC health services research.

[22]  S. Haffner,et al.  Identification of Persons at High Risk for Type 2 Diabetes Mellitus: Do We Need the Oral Glucose Tolerance Test? , 2002, Annals of Internal Medicine.

[23]  G. Nichols,et al.  Validating the Framingham Offspring Study equations for predicting incident diabetes mellitus. , 2008, The American journal of managed care.