TY - JOUR
T1 - Coronary Risk Prediction by Logical Analysis of Data
AU - Alexe, Sorin
AU - Blackstone, Eugene
AU - Hammer, Peter L.
AU - Ishwaran, Hemant
AU - Lauer, Michael S.
AU - Pothier Snader, Claire E.
N1 - Funding Information:
Drs. Lauer, Blackstone, and Ishwaran and Ms. Snader receive support from the National Heart, Lung, and Blood Institute (Grant RO1 HL-66004-1). Dr. Lauer, Dr. Blackstone, and Ms. Snader receive additional support from the American Heart Association (Established Investigator Grant 0040244N). Dr. Hammer and Mr. Alexe receive support from the National Science Foundation (Grant NSF-DMS-9806389) and the Office of Naval Research (Grant N00014-92-J-1375). We gratefully acknowledge all the support which made this study possible.
Copyright:
Copyright 2013 Elsevier B.V., All rights reserved.
PY - 2003/3
Y1 - 2003/3
N2 - The objective of this study was to distinguish within a population of patients with known or suspected coronary artery disease groups at high and at low mortality rates. The study was based on Cleveland Clinic Foundation's dataset of 9454 patients, of whom 312 died during an observation period of 9 years. The Logical Analysis of Data method was adapted to handle the disproportioned size of the two groups of patients, and the inseparable character of this dataset - characteristic to many medical problems. As a result of the study, we have identified a high-risk group of patients representing 1/5 of the population, with a mortality rate 4 times higher than the average, and including 3/4 of the patients who died. The low-risk group identified in the study, representing approximately 4/5 of the population, had a mortality rate 3 times lower than the average. A Prognostic Index derived from the LAD model is shown to have a 83.95% correlation with the mortality rate of patients. The classification given by the Prognostic Index was also shown to agree in 3 out of 4 cases with that of the Cox Score, widely used by cardiologists, and to outperform it slightly, but consistently. An example of a highly reliable risk stratification system using both indicators is provided.
AB - The objective of this study was to distinguish within a population of patients with known or suspected coronary artery disease groups at high and at low mortality rates. The study was based on Cleveland Clinic Foundation's dataset of 9454 patients, of whom 312 died during an observation period of 9 years. The Logical Analysis of Data method was adapted to handle the disproportioned size of the two groups of patients, and the inseparable character of this dataset - characteristic to many medical problems. As a result of the study, we have identified a high-risk group of patients representing 1/5 of the population, with a mortality rate 4 times higher than the average, and including 3/4 of the patients who died. The low-risk group identified in the study, representing approximately 4/5 of the population, had a mortality rate 3 times lower than the average. A Prognostic Index derived from the LAD model is shown to have a 83.95% correlation with the mortality rate of patients. The classification given by the Prognostic Index was also shown to agree in 3 out of 4 cases with that of the Cox Score, widely used by cardiologists, and to outperform it slightly, but consistently. An example of a highly reliable risk stratification system using both indicators is provided.
KW - Classification
KW - Data mining
KW - Logical Analysis of Data
KW - Partially defined Boolean functions
KW - Risk indices
KW - Risk prediction
UR - http://www.scopus.com/inward/record.url?scp=0037245469&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0037245469&partnerID=8YFLogxK
U2 - 10.1023/A:1022970120229
DO - 10.1023/A:1022970120229
M3 - Article
AN - SCOPUS:0037245469
VL - 119
SP - 15
EP - 42
JO - Annals of Operations Research
JF - Annals of Operations Research
SN - 0254-5330
IS - 1-4
ER -