This article proposes a clinical decision support system that processes biomedical data. For this purpose a bionic model has been designed based on neural networks, genetic algorithms and immune systems. The developed system has been tested on data from pregnant women. The paper focuses on the approach to enable selection of control actions that can minimize the risk of adverse outcome. The control actions (hyperparameters of a new type) are further used as an additional input signal. Its values are defined by a hyperparameter optimization method. A software developed with Python is briefly described.
|Journal||Journal of Physics: Conference Series|
|Publication status||Published - 2017|
|Event||International Conference on Information Technologies in Business and Industry 2016 - Tomsk, Russian Federation|
Duration: 21 Sep 2016 → 23 Sep 2016
ASJC Scopus subject areas
- Physics and Astronomy(all)