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

Abstract

Background Automated individualized risk prediction tools linked to electronic health records ( EHR s) are not available for management of patients with peripheral arterial disease. The goal of this study was to create a prognostic tool for patients with peripheral arterial disease using data elements automatically extracted from an EHR to enable real‐time and individualized risk prediction at the point of care. Methods and Results A previously validated phenotyping algorithm was deployed to an EHR linked to the Rochester Epidemiology Project to identify peripheral arterial disease cases from Olmsted County, MN, for the years 1998 to 2011. The study cohort was composed of 1676 patients: 593 patients died over 5‐year follow‐up. The c‐statistic for survival in the overall data set was 0.76 (95% confidence interval [CI], 0.74–0.78), and the c‐statistic across 10 cross‐validation data sets was 0.75 (95% CI, 0.73–0.77). Stratification of cases demonstrated increasing mortality risk by subgroup (low: hazard ratio, 0.35 [95% CI, 0.21–0.58]; intermediate‐high: hazard ratio, 2.98 [95% CI, 2.37–3.74]; high: hazard ratio, 8.44 [95% CI, 6.66–10.70], all P <0.0001 versus the reference subgroup). An equation for risk calculation was derived from Cox model parameters and β estimates. Big data infrastructure enabled deployment of the real‐time risk calculator to the point of care via the EHR . Conclusions This study demonstrates that electronic tools can be deployed to EHR s to create automated real‐time risk calculators to predict survival of patients with peripheral arterial disease. Moreover, the prognostic model developed may be translated to patient care as an automated and individualized real‐time risk calculator deployed at the point of care.

Editor's Choice – The GermanVasc Score: A Pragmatic Risk Score Predicts Five Year Amputation Free Survival in Patients with Peripheral Arterial Occlusive Disease

“…5 y risk of amputation or death * HR (95% CI) Amputation or death after 5 y e % Range 0e49 2003e2007, one year follow up), 20 the ERICVA simplified score (672 patients with CLTI, 2005e2010, one year follow up), 21 the COPART (COhorte de Patients ARTériopathes) risk score (184 patients with IC, 2002e2004, five year follow up), 22 Arruda-Olsen et al (1 676 patients with PAOD, 1998e2011, five year follow up), 23 or the SMART (Second Manifestations of Arterial Disease) risk score (5 788 patients with PAOD, 1996e2010, five year follow up). 24 and van Walraven et al 25 who developed a comorbidity score using a large administrative database from Canada to predict in hospital mortality (345 795 patients, 1996e2008, in hospital follow up).…”

Artificial Intelligence in Cardiology: Present and Future

“…17 We are also able to display relevant laboratory test results and automated prognostic estimation for patients with peripheral artery disease using structured data elements and an automated risk calculator derived from models generated by a communitybased study. 88 In principle, similar approaches will be possible for a wide range of other cardiovascular health disorders. Improved knowledge delivery for health care professionals at the point of care facilitated by NLP-enabled CDS holds promise for revolutionary new approaches to health care that will bring the right information for the right patient at the right time and be portable to any EHR regardless of vendor, thereby enabling standardization and documentation of highest-quality care across health care systems.…”

Usability of a Digital Registry to Promote Secondary Prevention for Peripheral Artery Disease Patients

“…ethnicity and geocode), (2) mortality risk score estimated by automated calculator, 18 (3) comorbidities used for calculation of risk score, (4) status of PAD guidelinerecommended strategies (treatment with antiplatelet agents, statins, ACEIs or ARBs, and smoking abstention), (5) selected laboratory test results (total cholesterol, low-density lipoprotein and high-density lipoprotein cholesterol), and (6) blood pressure values (systolic and diastolic). The algorithm used to design the mortality risk calculator was derived from a community-based cohort of PAD patients from Olmsted County, Minnesota, using a Cox model for 5-year all-cause mortality.…”

“…The algorithm used to design the mortality risk calculator was derived from a community-based cohort of PAD patients from Olmsted County, Minnesota, using a Cox model for 5-year all-cause mortality. 18 Data elements such as demographic characteristics, status of guideline recommended strategies, laboratory test results, comorbidities (using billing codes), and blood pressure values included in the PAD-CKS tool were…”