RESUMO
OBJECTIVE：To establ ish artificial neural netw orks（ANN）model to predict the interferon in the treatment of chronic hepatitis B （CHB），and to provide evidence for selecting suitable CHB therapy plan in clinic. METHODS ：The clinical data of 92 CHB patients treated by interferon ，from Guangzhou Eighth People ’s Hospital were retrospectively analyzed from Jul. 2011 to Dec. 2019. The basic information ，biochemical indexes ，blood routine indexes and virological markers of patients were collected. According to the effect of interferon ，the patients were divided into response group （73 cases）and non-response group （19 cases）. Minitab 18.0 software was used for multivariate Logistic regression analysis to screen the factors influencing the efficacy of interferon. Neurosolutions 5.0 software was used to randomly select 30％ of patients with CHB （27 cases）as the test group to establish and verify the ANN model. RESULTS ：The mean platelet volume ，platelet distribution width ，direct bilirubin ， hepatitis B e antigen and hepatitis B virus DNA more than 4×107 IU/mL had significant effect on interferon response （P＜0.05）. The accuracy ，specificity and area under characteristic curve of ANN test group were significantly higher than those of Logistic regression（P＜0.05）. CONCLUSIONS ：ANN model is accurate in predicting the efficacy of interferon in the treatment of CHB.
RESUMO
Objective:To explore the clinical characteristics of juvenile-onset ankylosing spondylitis.Methods:Clinical data of 350 cases of ankylosing spondylitis diagnosed in Beijing Jishuitan Hospital from January 2014 to December 2019 were collected. There were 75 cases with the symptom onset in age ≤16 years (juvenile-onset ankylosing spondylitis, JoAS), and 275 cases with the symptom onset in age>16 years (adult-onset ankylosing spondylitis, AoAS). The clinical characteristics of two groups were analyzed.Results:Compared with AoAS, JoAS had a higher proportion of males [98.7% (74/75) vs. 79.6% (219/275); χ 2=15.65, P<0.01] and longer course of disease [11(8,15) vs. 8(4,15) years; Z=-3.09, P<0.01]. Compared with AoAS, JoAS was more prone to have peripheral joint swelling and pain [45.3%(34/75) vs. 18.9%(52/275), χ 2=22.20, P<0.01], hip pain [26.7%(20/75) vs. 15.3%(42/275), χ 2=5.25, P=0.03] or heel pain [9.3%(7/75) vs. 2.9%(8/275), χ 2=5.93, P=0.02] as the first clinical manifestation. Compared with AoAS, JoAS had a higher incidence of radiological hip involvement [77.3%(58/75) vs. 43.3%(119/275), OR=4.71, Wald=25.60, P<0.01], lower bone mineral density than peers [34.7%(26/75) vs. 23.3%(64/275), OR=2.23, Wald=7.20, P<0.01], higher incidence of malnutrition [25.3%(19/75) vs. 13.8%(38/275), OR=2.16, Wald=5.84, P=0.02] and higher incidence of acute uveitis [17.3%(13/75) vs. 6.5%(18/275), OR=2.72, Wald=6.24, P=0.01] after adjusting the course of disease. Conclusion:Compared with adult-onset ankylosing spondylitis, juvenile-onset ankylosing spondylitis is more prone to have peripheral joint swelling or hip pain as the first clinical manifestation; the radiological hip involvement, lower bone mineral density than peers, malnutrition and uveitis are more likely to occur.