In this paper, a deep learning method has been raised to build an automatic classification algorithm of severity of chronic obstructive pulmonary disease. Large sample clinical data as input feature were analyzed for their weights in classification. Through feature selection, model training, parameter optimization and model testing, a classification prediction model based on deep belief network was built to predict severity classification criteria raised by the Global Initiative for Chronic Obstructive Lung Disease (GOLD). We get accuracy over 90% in prediction for two different standardized versions of severity criteria raised in 2007 and 2011 respectively. Moreover, we also got the contribution ranking of different input features through analyzing the model coefficient matrix and confirmed that there was a certain degree of agreement between the more contributive input features and the clinical diagnostic knowledge. The validity of the deep belief network model was proved by this result. This study provides an effective solution for the application of deep learning method in automatic diagnostic decision making.
To study the effect of microgravity on peripheral oxygen saturation (SpO2) in rats, tail-suspended rats were applied to simulate microgravity environment. SpO2 and arterial oxygen saturation (SaO2) were measured by pulse oximeter and arterial blood gas analyzer (ABGA) respectively on the 14th day, 21st day and 28th day in tail-suspended group and control group. Paired t-test shows that SpO2 was significantly lower than SaO2 in tail-suspended group on the 14th day (P < 0.05), the 21st day ( P < 0.05) and the 28th day ( P < 0.01). The ANOVA results shows that modeling time had significant effect on SpO 2 value but no effect on SaO2 value in tail-suspended group. These results indicate that pulse oximeter may be not suitable for oxygen saturation test in microgravity environment.