Tuberculosis caused by Mycobacterium tuberculosis is the leading infectious killer posing a major public health threat. The clinical manifestations of ocular tuberculosis are highly heterogeneous. Currently, the diagnosis of ocular tuberculosis still heavily relies on comprehensive clinical judgment and response to anti-tuberculosis therapy. Tuberculosis-specific T-cell detection quantifies the intensity of antigen-specific T-cell responses, providing indirect evidence for the diagnosis of tuberculosis infection. It has become a key auxiliary examination in the diagnosis and management of ocular tuberculosis but must be closely integrated with clinical manifestations and imaging features. A positive result suggests the involvement of a tuberculous immune response but cannot alone confirm a diagnosis of ocular tuberculosis. Future efforts should integrate T-SPOT.TB testing with other diagnostic tools, standardize diagnostic procedures, and explore the mechanisms linking T-cell subset functions with the intraocular immune microenvironment. Further elucidation of the relationship between T-cell responses and ocular tuberculosis phenotypes will help advance personalized treatment.
With the rapid improvement of the perception and computing capacity of mobile devices such as smart phones, human activity recognition using mobile devices as the carrier has been a new research hot-spot. The inertial information collected by the acceleration sensor in the smart mobile device is used for human activity recognition. Compared with the common computer vision recognition, it has the following advantages: convenience, low cost, and better reflection of the essence of human motion. Based on the WISDM data set collected by smart phones, the inertial navigation information and the deep learning algorithm-convolutional neural network (CNN) were adopted to build a human activity recognition model in this paper. The K nearest neighbor algorithm (KNN) and the random forest algorithm were compared with the CNN network in the recognition accuracy to evaluate the performance of the CNN network. The classification accuracy of CNN model reached 92.73%, which was much higher than KNN and random forest. Experimental results show that the CNN algorithm model can achieve more accurate human activity recognition and has broad application prospects in predicting and promoting human health.