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

Authors:
Elisa Cuadrado-Godia
Elisa Cuadrado-Godia
Hospital del Mar
Spain
Ankush D Jamthikar
Ankush D Jamthikar
Department of Electronics and Communication Engineering
Narendra N Khanna
Narendra N Khanna
Indraprastha Apollo Hospitals
Tadashi Araki
Tadashi Araki
Toho University Ohashi Medical Center
Japan
Md Md Maniruzzaman, M.Sc.
Md Md Maniruzzaman, M.Sc.
Statistics Discipline, Khulna University, Khulna-9208, Bangladesh
Lecturer
Khulna, Khulna | Bangladesh
Luca Saba
Luca Saba
Azienda Ospedaliero Universitaria (A.O.University)
Roma | Italy
Andrew Nicolaides
Andrew Nicolaides
Imperial College
United Kingdom

Comput Biol Med 2019 May 25;108:182-195. Epub 2019 Mar 25.

Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA. Electronic address:

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 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 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 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 demonstrated the best performance due to presence of CUSIP and ranked at the first place with highest AUC.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiomed.2019.03.020DOI Listing
May 2019
1 Read
1.240 Impact Factor

Publication Analysis

Top Keywords

cardiovascular risk
12
risk
9
risk factors
8
logistic regression
8
risk calculator
8
cvr factors
8
risk cvr
8
optimal risk
8
cusip ranked
8
odds ratio
4
regression compute
4
multivariate logistic
4
ratio second
4
compute odds
4
receiver operating
4
evaluate performance
4
performance types
4
types cvr
4
curves evaluate
4
characteristic curves
4

Similar Publications