Rapid analysis of microbial systems using vibrational spectroscopy and supervised learning methods: application to the discrimination between methicillin-resistant and methicillin-susceptible Staphylococcus aureus.

被引:7
作者
Goodacre, R [1 ]
Rooney, PJ [1 ]
Kell, DB [1 ]
机构
[1] Univ Coll Aberystwyth, Inst Biol Sci, Aberystwyth SY23 3DA, Dyfed, Wales
来源
INFRARED SPECTROSCOPY: NEW TOOL IN MEDICINE, PROCEEDINGS OF | 1998年 / 3257卷
关键词
artificial neural networks; chemometrics; drug resistance; FT-IR; Staphylococcus aureus;
D O I
10.1117/12.306087
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
FT-IR spectra were obtained from 15 methicillin-resistant. and 22 methicillin-susceptible Staphylococcus aureus strains using our DRASTIC (diffuse Reflectance Absorbance Spectroscopy Taking In Chemometrics) approach(1). Cluster analysis showed that the major source of variation between the IR spectra was not due to their resistance or susceptibility to methicillin; indeed early studies using pyrolysis mass spectrometry(2) had shown that this unsupervised analysis gave information on the phage group of the bacteria. By contrast, artificial neural networks, based on supervised learning could be trained to recognize those aspects of the Iia spectra which differentiated methicillin-resistant from methicillin-susceptible strains. These results give the first demonstration that the combination of FT-IR with neural networks can provide a very rapid and accurate antibiotic susceptibility testing technique.
引用
收藏
页码:220 / 229
页数:10
相关论文
empty
未找到相关数据