Leveraging the Electronic Health Record to Create an Automated Real-Time Prognostic Tool for Peripheral Arterial...

Area of Science:

• Cardiovascular Medicine
• Health Informatics
• Biostatistics

Background:

• Automated, individualized risk prediction tools integrated with electronic health records (EHRs) are lacking for peripheral arterial disease (PAD) management.
• Current management relies on non-real-time, generalized risk assessments.
• Point-of-care decision support for PAD is needed.

Purpose of the Study:

• To develop a prognostic tool for PAD patients using automatically extracted EHR data.
• To enable real-time, individualized risk prediction at the point of care.
• To improve clinical decision-making in PAD management.

Main Methods:

• A validated phenotyping algorithm was deployed to an EHR linked to the Rochester Epidemiology Project.
• Peripheral arterial disease (PAD) cases were identified from Olmsted County, MN (1998-2011).
• A Cox proportional hazards model was used to derive risk prediction equations.

Main Results:

• The study included 1676 PAD patients; 593 died within 5 years.
• The risk calculator achieved a c-statistic of 0.76 (95% CI, 0.74-0.78) for survival.
• Risk stratification showed significantly increasing mortality across subgroups (P<0.0001).

Conclusions:

• Electronic tools can be deployed within EHRs to create automated, real-time risk calculators for PAD survival.
• The developed prognostic model can be translated into clinical practice as an automated, individualized risk assessment tool.
• This technology supports point-of-care decision-making for patients with peripheral arterial disease.