BACKGROUND
Diabetes, one of the most serious and fast-growing chronic health conditions, often leads to other serious complications such as neurological, renal, ophthalmic, and heart diseases. Research has shown that more than 85% of diabetic patients develop at least one of these complications. Unfortunately, patients in rural markets are less likely to undergo preventative screenings, particularly for diabetic retinopathy (requiring a dilated pupil eye examination). Therefore, studying co-morbidities among diabetic patients using association analysis is a worthy research endeavor. However, ordinary association analysis has a tradeoff between setting levels of support and its ability to detect rarer association rules. Thus is an unmet need of current analytical techniques addressing the likelihood and patterning of diabetic complications.
SUMMARY OF TECHNOLOGY
Researchers at OSU have developed a novel algorithm for detecting associations between diabetes complications and various patient data. This novel assessment metric can retrieve rare patterns without over-generating association rules. Initial tests of the algorithm have been run using a dataset of 492,025 patients with diabetes and related complications. This algorithm revealed interesting associations between complications such as (but not limited to) renal manifestations with retinopathy, and gastroparesis with ketoacidosis and retinopathy. Additionally, information pertaining to different demographic groups and comorbidities of patients was ascertained from the analyses. This novel technology provides a non-invasive, and easily accessible tool that allows at-risk patients to be informed of potential risks, helping increase the rate of patient compliance to treatment and reducing the cost of treating this disease.
POTENTIAL AREAS OF APPLICATION
- Accountable care organizations
- Insurance companies
- Closed healthcare systems (e.g., the Cherokee Nation)
- Self-insured employers
MAIN ADVANTAGES
- Increased compliance with healthcare guidelines through early warning
- Reduces cost of care by identifying most at-risk individuals
- Increased quality of life for patients
STAGE OF DEVELOPMENT
This technology is available as a prototype.