ABSTRACT
Objective@#To analyze the situation of AIDS knowledge and discrimination among freshmen in Chengdu city, and to explore possible effects of AIDS knowledge on discrimination.@*Methods@#A cluster random sampling was employed to investigate 1 053 college students from 11 universities in Chengdu about their HIV/AIDS knowledge and discrimination. The scores of AIDS knowledge and discrimination of students with different characteristics were analyzed, and the influence path of AIDS knowledge on AIDS discrimination were further analyzed based on different peer relationships.@*Results@#The total scores of AIDS knowledge was negatively correlated to AIDS discrimination( r s =-0.13, P <0.01). After adjusting for confounding factors, the total score of AIDS knowledge was associated with the total score of AIDS discrimination( β =-0.12, P <0.01). AIDS knowledge played a role in AIDS discrimination in intimate, general and unfamiliar peer relationships, with standardized path coefficients of -0.20, -0.24 and -0.18 respectively( P <0.01).@*Conclusion@#AIDS knowledge are correlated with discrimination among freshmen under different peer relationships. More anti-AIDS discrimination courses should be added to AIDS education to reduce the students’ fear and stigma of HIV/AIDS patients and related risk groups.
ABSTRACT
<p><b>OBJECTIVE</b>To evaluate the efficacy of the digital cytopathological lung cancer diagnosing system (DCLCDS) utilizing the latest computer technologies (including reinforcement learning, image segmentation and classifier) and the cytopathological knowledge on lung cancer cells.</p><p><b>METHODS</b>Separate the overlapped lung cancer cells in a slice image applying the improved deBoor-Cox B-Spline algorithm; Segment cell regions in a slice image using an image segmentation algorithm based on reinforcement learning; Ensemble different classifiers, including Decision Tree classifier, Support Vector Machine (SVM) classifier and Bayesian classifier, to achieve an accurate result of cytopathological lung cancer diagnosis.</p><p><b>RESULTS</b>The accurate diagnosis rate for lung cancer identification of 224 images of small lung lesions aspiration biopsy from 120 cases randomly selected was 92.3%. The accurate diagnosis rate for type classification of lung cancer was 82.5%. The identification rate for abnormal nuclear cells was 71.6%.</p><p><b>CONCLUSIONS</b>The DCLCDS achieves a high accuracy on cytopathological lung cancer diagnosis by solving some major problems on the cytology smears, including cell overlapping, uneven coloration and impurity. It provides a relatively objective, standard tool on cytopathological lung cancer diagnosis. It has good efficacy on early diagnosis of lung cancer.</p>