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.

Objectives: To explore weather oxygen uptake efficiency slope (OUES) may predict the prognosis in patients with idiopathic pulmonary arterial hypertension (IPAH). Methods: The consecutive newly diagnosed IPAH patients in our hospital from 2010-11 to 2015-06 were prospectively enrolled and regular follow-up study was conducted to record cardiovascular events (death and lung transplantation). Kaplan–Meier curve, uni- and multivariate Cox regression analysis were performed to assess the survival rate in relevant patients. Results: A total of 210 IPAH patients at the mean age of (32±10) years were finished cardiopulmonary exercise test (CPET) and received regular follow-up study including 159 female. There were 31 patients died and 1 received lung transplantation over 41 months follow-up period. OUES was positively related to peak oxygen uptake (VO2)/body weight (r=0.71, P<0.0001). Multivariate analysis demonstrated that OUESI and NT-proBNP could independently predict the prognosis of IPAH patients. The 5-year survival rate in patients with OUESI≤0.52 L/(min?m2) was lower than those with OUESI>0.52 L/(min?m2) (41.9% vs 89.8%), P<0.0001.Conclusion: OUES as a submaximal CPET parameter may well predict the prognosis in IPAH patients.

Cervical spondylosis is a common degenerative spinal disease that severely impacts patients' quality of life and may lead to serious complications. Accurate diagnosis and early intervention are crucial for improving patient outcomes. However,traditional diagnostic methods have limitations in precision and efficiency,primarily relying on clinicians' subjective judgment and experience,which can result in misdiagnosis or missed diagnosis. Recent advancements in artificial intelligence (AI) technology have shown significant potential in the field of medical diagnostics,particularly in medical imaging analysis and lesion identification. AI technologies,through deep learning algorithms such as convolutional neural networks (CNNs),can automatically segment and identify lesion areas in imaging data,significantly enhancing diagnostic accuracy and efficiency. This paper reviews the latest research developments in AI for cervical spondylosis diagnosis,explores its potential in improving diagnostic precision and personalized treatment,and analyzes the current challenges and future research directions to promote further development and clinical application of AI technologies in cervical spondylosis diagnosis.