Younts S, Alocilja E, Osburn W, Marquie S, Gray J, Grooms D
Department of Animal Science, Michigan State University, East Lansing, Michigan 48824, USA.
J Food Prot. 2003 Aug;66(8):1455-8. doi: 10.4315/0362-028x-66.8.1455.
The rapid and economical detection of human pathogens in animal and food production systems would enhance food safety efforts. An instrument based on gas sensors coupled with an artificial neural network (ANN) was developed for the detection of and differentiation between laboratory isolates of Escherichia coli O157:H7 and non-O157:H7 E. coli. The purpose of this study was to use field isolates of E. coli to further evaluate the sensor system. This gas sensor-based, computer-controlled detection system was used to monitor gas emissions from 12 isolates of E. coli O157:H7 and 8 non-O157:H7 E. coli isolates. A standard concentration of each isolate was grown in 10 ml of nutrient broth at 37 degrees C for 16 h, and gas sampling was carried out every 5 min. Readings were continuously plotted to generate gas signatures. A back-propagation ANN algorithm was used to interpret the gas patterns. By analysis of the response of the ANN, the sensitivity and specificity of the instrument were calculated. Detectable differences between the gas signatures of the E. coli O157:H7 isolates and the non-O157:H7 isolates were observed. The instruments degree of sensitivity was high for E. coli O157:H7 isolates, but a lower degree of accuracy was observed for non-O157:H7 isolates because of increased strain variation. The sensitivity of the detection system was improved by the normalization of the data generated from the gas sensors. Because of its ability to detect differences in gas patterns, this instrument has a broad range of potential food safety applications.
在动物和食品生产系统中快速、经济地检测人类病原体将加强食品安全工作。开发了一种基于气体传感器并结合人工神经网络（ANN）的仪器，用于检测和区分大肠杆菌O157:H7和非O157:H7大肠杆菌的实验室分离株。本研究的目的是使用大肠杆菌的现场分离株进一步评估该传感器系统。这个基于气体传感器的计算机控制检测系统用于监测12株大肠杆菌O157:H7和8株非O157:H7大肠杆菌分离株的气体排放。将每种分离株的标准浓度在37摄氏度下于10毫升营养肉汤中培养16小时，每5分钟进行一次气体采样。连续绘制读数以生成气体特征图。使用反向传播人工神经网络算法来解释气体模式。通过分析人工神经网络的响应，计算该仪器的灵敏度和特异性。观察到大肠杆菌O157:H7分离株和非O157:H7分离株的气体特征之间存在可检测到的差异。该仪器对大肠杆菌O157:H7分离株的灵敏度较高，但由于菌株变异增加，对非O157:H7分离株的准确度较低。通过对气体传感器产生的数据进行归一化处理，提高了检测系统的灵敏度。由于其能够检测气体模式的差异，该仪器具有广泛的潜在食品安全应用。
