1School of pharmacy, Yonsei university, South Korea
2ANSORP, CHA Bio Group at CHA Bio complex, South Korea
*Corresponding author:Hyunjo Kim, School of pharmacy, Yonsei university, Campus town, Songdo techno park, Incheon city, South Korea
Submission: June 13, 2019; Published: June 24, 2019
ISSN: 2578-0190 Volume2 Issue5
Infection disease is a major cause of morbidity and mortality in the developing world. Antibiotics resistance, which is predicted to rise in many countries worldwide, threatens infection treatment and control. The machine learning can help to identify patients at higher risk of treatment failure in infection diseases Closer monitoring of these patients may decrease treatment failure rates and prevent emergence outbreak of antibiotic resistance. To identify features associated with treatment failure and to predict which patients are at highest risk of antibiotics resistance this study was designed. The most predictive model was forward stepwise selection, although most models performed at or above targeted value. We employed a range of powerful machine learning tools to predict antibiotic resistance from whole genome sequencing data for model strain. We used the presence or absence of genes, population structure and isolation year of isolates as predictors, and could attain average precision and recall without prior knowledge about the causal mechanisms. These results demonstrate the potential application of machine learning methods as a diagnostic tool in healthcare settings.
Keywords: Infection disease; Antibiotics resistance; Machine learning model algorithm; Genome analysis; Antibiotics resistance genes (ARGs); PK/PD analysis