Page 115 - 《中国药房》2021年10期
P. 115
·药物与临床·
干扰素治疗慢性乙型肝炎疗效预测人工神经网络模型的建立与
应用 Δ
傅晓华 ,罗 纯 ,高思明 ,傅晓霞 ,卢荣奎 ,容海鹰(1.广州新海医院药剂科,广州 510300;2.广州市第八
1*
1
2
1
2
3
人民医院中医科,广州 510060;3.广州新海医院消化内科,广州 510300)
+
中图分类号 R512.6 2;R975 文献标志码 A 文章编号 1001-0408(2021)10-1257-05
DOI 10.6039/j.issn.1001-0408.2021.10.17
摘 要 目的:建立预测干扰素治疗慢性乙型肝炎(CHB)疗效的人工神经网络(ANN)模型,以期为临床选择适宜的CHB治疗方
案提供依据。方法:回顾性分析2011年7月-2019年11月广州市第八人民医院接受干扰素治疗的92例CHB患者的临床资料,收
集其基本信息、生化指标、血常规指标、病毒学标志物等。按干扰素疗效分为应答组(73例)和无应答组(19例),采用Minitab 18.0
统计软件进行多因素Logistic 回归分析以筛选影响干扰素疗效的因素;采用Neurosolutions 5.0软件随机抽取约30%的CHB患者
(27例)作为测试组建立ANN模型并进行验证。结果:患者的平均血小板体积、血小板分布宽度、直接胆红素、乙肝e抗原水平、乙
7
肝病毒DNA大于4×10 IU/mL对干扰素应答有显著影响(P<0.05)。ANN测试组应答预测的准确率、特异性、工作特征曲线下面
积均显著高于Logistic回归(P<0.05)。结论:ANN模型预测干扰素治疗CHB疗效的准确性较好。
关键词 干扰素;慢性乙型肝炎;人工神经网络;疗效;预测
Establishment and Application of Artificial Neural Network Model in Predicting Clinical Efficacy of
Interferon for Chronic Hepatitis B
1
3
2
FU Xiaohua ,LUO Chun ,GAO Siming ,FU Xiaoxia ,LU Rongkui ,RONG Haiying(1. Dept. of Pharmacy,
1
2
1
Guangzhou Xinhai Hospital,Guangzhou 510300,China;2. Dept. of Traditional Chinese Medicine,Guangzhou
Eighth People’s Hospital, Guangzhou 510060, China; 3. Dept. of Gastroenterology, Guangzhou Xinhai
Hospital,Guangzhou 510300,China)
ABSTRACT OBJECTIVE:To establish artificial neural networks (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 4×10 IU/mL had significant effect on interferon response(P<0.05).
7
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.
KEYWORDS Interferon;Chronic hepatitis B;Artificial neural network;Therapeutic efficacy;Prediction
慢性乙型肝炎(CHB)是一个严重危害人类健康的 苷(酸)类似物 。其中,核苷(酸)类似物是常规治疗
[2]
公共卫生问题。我国属乙型肝炎病毒(HBV)感染高流 CHB 的一线抗病毒药物,其抗病毒效果好且耐药率低,
[3]
行区,2020 年我国 CHB 感染 902 476 例、死亡 464 例 。 但治疗周期较长,停药后易复发 。相较于核苷(酸)类
[1]
目前,临床治疗 CHB 的抗病毒药物主要有干扰素和核 似物,干扰素具有良好的免疫调节作用和抗病毒作用,
可以特异性地增强患者体内T淋巴细胞的功能,具有疗
Δ 基金项目:广东省医学科学技术研究基金项目(No.B2018132)
[4]
程短、应答持久、无病毒变异和耐药等优点 。但研究者
*副主任药师,硕士。研究方向:医院药学、药事管理。电话:
020-84105080。E-mail:fuxiaohua3118@sina.com 在临床工作中发现,干扰素的总体有效率较低,这可能
中国药房 2021年第32卷第10期 China Pharmacy 2021 Vol. 32 No. 10 ·1257 ·