Abstract
Stratifying individuals at risk for developing diabetes could enable targeted delivery of interventional programs to those at highest risk, while avoiding the effort and costs of prevention and treatment in those at low risk. The objective of this study was to explore the potential role of a Hidden Markov Model (HMM), a machine learning technique, in validating the performance of the Framingham Diabetes Risk Scoring Model (FDRSM), a well-respected prognostic model. Can HMM predict 8-year risk of developing diabetes in an individual effectively? To our knowledge, no study has attempted use of HMM to validate the performance of FDRSM. We used Electronic Medical Record (EMR) data, of 172,168 primary care patients to derive the 8-year risk of developing diabetes in an individual using HMM. The Area Under Receiver Operating Characteristic Curve (AROC) in our study sample of 911 individuals for whom all risk factors and follow up data were available is 86.9% compared to AROCs of 78.6% and 85% reported in a previously conducted validation study of FDRSM in the same Canadian population and the Framingham study respectively. These results demonstrate that the discrimination capability of our proposed HMM is superior to the validation study conducted using the FDRSM in a Canadian population and in the Framingham population. We conclude that HMM is capable of identifying patients at increased risk of developing diabetes within the next 8-years.
Highlights
The prevalence of type 2 diabetes (T2DM) has increased dramatically across the globe to 8.5% of the population in 2014, incurring tremendous human, economic and social costs
In 2007, a risk scoring model was published by the Framingham offspring study to identify individuals most likely to develop T2DM in the future[14]
With the exception of parental history of diabetes that were not available in our source database, the same physical and blood biochemical examinations that were addressed by the FDRSM15 were chosen in this study for follow up including BP, sex, body mass index (BMI), fasting blood glucose (FBG) levels, age, high density lipoprotein (HDL) and triglycerides (TG)
Summary
The prevalence of type 2 diabetes (T2DM) has increased dramatically across the globe to 8.5% of the population in 2014, incurring tremendous human, economic and social costs. Given that diabetes and its complications are preventable, the rising rate of T2DM and the complications that result from metabolic deterioration necessitate efforts to improve early detection of T2DM risk In this context, there is a dire need for alternative approaches that: (1) are aimed at pre-emptive risk stratification and prevention, (2) provide insights needed for healthcare providers, patients, providers and health policy makers, and (3) are based on aggregated knowledge obtained from interpreting massive amount of healthcare data[10]. Dekker et al.[16], for instance, report, in their 2017 paper, that “most clinical risk scores are useless” and that “assuming linearity of predictors” is an example of methodological mistakes frequently made by researchers In their 2018 paper, Steyerberg et al.[17] add that these mistakes are “quite common in current scientific practice and lead to prediction models that cannot be trusted”. We should consider and test alternative approaches to develop and validate risk models with the objective of better predicting disease risk and progression, prevent disease and allow patients to make better decisions about their health
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
