Ranking of stroke and cardiovascular risk factors for an optimal risk calculator design: Logistic regression approach

Elisa Cuadrado-Godia; Ankush D Jamthikar; Deep Gupta; Narendra N Khanna; Tadashi Araki; Md Maniruzzaman; Luca Saba; Andrew Nicolaides; Aditya Sharma; Tomaz Omerzu; Harman S Suri; Ajay Gupta; Sophie Mavrogeni; Monika Turk; John R Laird; Athanasios Protogerou; Petros Sfikakis; George D Kitas; Vijay Viswanathan; Jasjit S Suri

doi:10.1016/j.compbiomed.2019.03.020

Ranking of stroke and cardiovascular risk factors for an optimal risk calculator design: Logistic regression approach

Comput Biol Med. 2019 May:108:182-195. doi: 10.1016/j.compbiomed.2019.03.020. Epub 2019 Mar 25.

Authors

Elisa Cuadrado-Godia¹, Ankush D Jamthikar², Deep Gupta², Narendra N Khanna³, Tadashi Araki⁴, Md Maniruzzaman⁵, Luca Saba⁶, Andrew Nicolaides⁷, Aditya Sharma⁸, Tomaz Omerzu⁹, Harman S Suri¹⁰, Ajay Gupta¹¹, Sophie Mavrogeni¹², Monika Turk¹³, John R Laird¹⁴, Athanasios Protogerou¹⁵, Petros Sfikakis¹⁶, George D Kitas¹⁷, Vijay Viswanathan¹⁸, Jasjit S Suri¹⁹

Affiliations

¹ Department of Neurology, IMIM - Hospital Del Mar, Barcelona, Spain.
² Department of ECE, VNIT, Nagpur, Maharashtra, India.
³ Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi, India.
⁴ Division of Cardiovascular Medicine, Toho University, Tokyo, Japan.
⁵ Statistics Discipline, Khulna University, Khulna, Bangladesh.
⁶ Department of Radiology, University of Cagliari, Italy.
⁷ Vascular Screening and Diagnostic Centre, University of Cyprus, Nicosia, Cyprus.
⁸ Cardiovascular Medicine, University of Virginia, VA, USA.
⁹ Department of Neurology, University Medical Centre Maribor, Slovenia.
¹⁰ Brown University, Rhode Island, USA.
¹¹ Department of Radiology, Cornell Medical Center, NY, USA.
¹² Cardiology Clinic, Onassis Cardiac Surgery Center, Athens, Greece.
¹³ Department of Neurology, University Medical Centre Maribor, Maribor, Slovenia.
¹⁴ Heart and Vascular Institute, Adventist Health St. Helena, St Helena, CA, USA.
¹⁵ Department of Cardiovascular Prevention & Research Unit Clinic & Laboratory of Pathophysiology, National and Kapodistrian Univ. of Athens, Greece.
¹⁶ Rheumatology Unit, National Kapodistrian University of Athens, Greece.
¹⁷ Research & Development-Academic Affairs, Dudley Group NHS Foundation Trust, Dudley, United Kingdom.
¹⁸ MV Hospital for Diabetes and Professor M Viswanathan Diabetes Research Centre, Chennai, India.
¹⁹ Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA. Electronic address: jasjit.suri@atheropoint.com.

PMID: 31005010
DOI: 10.1016/j.compbiomed.2019.03.020

Abstract

Purpose: Conventional cardiovascular risk factors (CCVRFs) and carotid ultrasound image-based phenotypes (CUSIP) are independently associated with long-term risk of cardiovascular (CV) disease. In this study, 26 cardiovascular risk (CVR) factors which consisted of a combination of CCVRFs and CUSIP together were ranked. Further, an optimal risk calculator using AtheroEdge composite risk score (AECRS1.0) was designed and benchmarked against seven conventional CV risk (CVR) calculators.

Methods: Two types of ranking were performed: (i) ranking of 26 CVR factors and (ii) ranking of eight types of 10-year risk calculators. In the first case, multivariate logistic regression was used to compute the odds ratio (OR) and in the second, receiver operating characteristic curves were used to evaluate the performance of eight types of CVR calculators using SPSS23.0 and MEDCALC12.0 with validation against STATA15.0.

Results: The left and right common carotid arteries (CCA) of 202 Japanese patients were examined to obtain 404 ultrasound scans. CUSIP ranked in the top 50% of the 26 covariates. Intima-media thickness variability (IMTV) and IMTV_10yr were the most influential carotid phenotypes for left CCA (OR = 250, P < 0.0001 and OR = 207, P < 0.0001 respectively) and right CCA (OR = 1614, P < 0.0001 and OR = 626, P < 0.0001 respectively). However, for the mean CCA, AECRS1.0 and AECRS1.0_10yr reported the most highly significant OR among all the CVR factors (OR = 1.073, P < 0.0001 and OR = 1.104, P < 0.0001). AECRS1.0_10yr also reported highest area-under-the-curve (AUC = 0.904, P < 0.0001) compared to seven types of conventional calculators. Age and glycated haemoglobin reported highest OR (1.96, P < 0.0001 and 1.05, P = 0.012) among all other CCVRFs.

Conclusion: AECRS1.0_10yr demonstrated the best performance due to presence of CUSIP and ranked at the first place with highest AUC.

Keywords: AUC; Cardiovascular risk calculator; Conventional cardiovascular risk factors; Covariates; Image-based phenotypes; Logistic regression; Odds ratio; Performance; Ranking; p-value.

MeSH terms

Age Factors
Aged
Aged, 80 and over
Asian People
Carotid Artery, Common* / diagnostic imaging
Carotid Artery, Common* / metabolism
Carotid Artery, Common* / physiopathology
Female
Humans
Japan
Male
Middle Aged
Models, Cardiovascular*
Risk Assessment
Stroke* / blood
Stroke* / diagnosis
Stroke* / diagnostic imaging
Stroke* / physiopathology
Ultrasonography