Diabetes Outcomes Model for the US (DOMUS)
Information last updated: August 2022
Participated in following Mt Hood Diabetes Challenge Meetings: 2022 Malmo.
Publicly accessible?: The model is still in development.
Is the model continuing to be developed?: Yes.
Brief Description:
The diabetes outcomes model for the US (DOMUS) is a microsimulation model that was developed using a multi-ethnic, real-world-data cohort of newly diagnosed Type II diabetics. The model was developed using the Kaiser Permanente Northern California (KPNC) Diabetes Registry, which is a well-described epidemiologic cohort with up to 13 years of follow-up from EMR and claims. We were able to identify over 130,000 newly diagnosed diabetes patients between 2005-2016 with up to 13-year follow-up.
The DOMUS model integrates separate, but interdependent risk equations to predict events for each of the micro and macro-vascular events, hypoglycemia, dementia, depression, and death, and predictive models for eight biomarker levels. The model accounted for static demographic factors (e.g., race), neighbourhood deprivation, smoking and dynamic factors, such as age, duration of diabetes, fifteen-possible glucose–lowering treatment combinations, biomarker levels, and history of diabetes-related events. Moreover, the models explicitly allow for a legacy effect (average A1c in the first year after diagnosis) for all outcomes.
Extensive validation was done on a hold-out sample and model predictions in the validation sample closely aligned with the observed longitudinal trajectory of biomarkers and outcomes. Moreover, we examine the model performance within by age, race/ethnicity, and sex and found excellent predictive performance within subgroups.
Funding source for model development:
Predicting Future Health Disparities for U.S. Adults with Diabetes: Development and Application of the Multi-Ethnic U.S. Diabetes Outcomes Model (NIMHD R01 MD013420)
Key Publications:
The model is still in development, will be submitted by October 2022