Russian version English version
Volume 11   Issue 1   Year 2016
The use of optimal partitionings for multiparameter data analysis in clinical trials

Guliev R.R., Senko O.V., Zateyshchikov D.A., Nosikov V.V., Uporov I.V., Kuznetsova A.V., Evdokimova M.A., Tereshchenko S.N., Akatova E.V., Glaser M.G., Galyavich A.S., Koziolova N.A., Yagoda A.V., Boeva O.I., Shlyk S.V., Levashov S.Y., Konstantinov V.O., Brazhnik V.A.,Varfolomeev S.D., Kurochkin I.N.

Emanuel Institute of Biochemical Physics of Russian Academy of Science, Moscow, Russia
Central State Medical Academy of Department of Presidential Affairs, Moscow, Russia
Computer Center of Russian Academy of Science, Moscow, Russia
Lomonosov Moscow State University, Moscow, Russia
City Clinical Hospital No. 51, Moscow, Russia
Institute of Cardiology, Russian Cardiology Scientific and Production Center, Moscow, Russia
Moscow State University of Medicine and Dentistry named after A.I. Evdokimov, Moscow, Russia
Sechenov Moscow Medical Academy, Moscow, Russia
Kazan State Medical University, Kazan, Russia
Perm State Medical University named after E.A. Vagner, Perm, Russia
Stavropol State Medical University, Stavropol, Russia
Rostov State Medical University, Rostov-on-Don, Russia
Chelyabinsk state medical academy, Chelyabinsk, Russia
North-Western State Medical University named after Mechnikov, St. Petersburg, Russia
 
Abstract. A predictive model is presented which allows estimating six-month-risk of cardiovascular disease in patients discharged from hospital after acute coronary syndrome. A database, that has been collected from 16 medical centers in seven Russian cities during seven years, was used to create the model. The database contains a wide range of clinical, biochemical and genetic characteristics. The approaches based on the use of optimal partitioning, such as the method of optimal valid partitioning (OVD) and the modified method of statistically weighted syndromes (MSWS), were used in order to create the  predictive model. The accuracy of the model is quite well and is estimated by the value of  AUC=0.72. This model  shows the better predictive ability in comparison with the most widely used methods such as logistic regression, usage  of decision trees, neural networks et.
 
Key words: acute coronary disease, ischemic heart disease, recognition, collective decision making, optimal partition, prognosis.
 

  

Table of Contents Original Article
Math. Biol. Bioinf.
2016;11(1):46-63
doi: 10.17537/2016.11.46
published in Russian

Abstract (rus.)
Abstract (eng.)
Full text (rus., pdf)
References

 

  Copyright IMPB RAS © 2005-2024