Establishment and evaluation of screening model of minimal hepatic encephalopathy in patients with liver cirrhosis

doi:10.3969/j.issn.1674-8115.2021.09.014

Abstract

Abstract: Objective

·To establish and evaluate a screening model of liver cirrhosis patients complicated with minimal hepatic encephalopathy (MHE).

Methods

·A total of 404 patients with liver cirrhosis who were hospitalized from June 2017 to November 2019 were selected as the research subjects, and the clinical data of them were collected. Based on Logistic regression analysis and artificial neural network (ANN), the MHE screening models were established, and the discriminant ability of the two models was evaluated and compared.

Results

·The Logistic regression model showed that age, history of diabetes mellitus, infection, renal insufficiency, nutritional risk, total bilirubin>24 μmol/L, blood ammonia>47 μmol/L and international normalized ratio (INR)≥1.5 were the significant risk factors (all P<0.05). The area under the curve (AUC) of receiver operator characteristic curve (ROC curve) of ANN model and Logistic regression model were 0.814 and 0.737 (Z=4.208, P=0.000), respectively. The sensitivities were 72.4% and 69.9%, and the specificities were 76.7% and 67.8%, respectively.

Conclusion

·The ANN model is more effective than the Logistic regression model in MHE screening.

Key words: minimal hepatic encephalopathy (MHE), artificial neural network (ANN), screening model

CLC Number:

R575.2

Zhu-ping QIAN, Yan YANG. Establishment and evaluation of screening model of minimal hepatic encephalopathy in patients with liver cirrhosis[J]. JOURNAL OF SHANGHAI JIAOTONG UNIVERSITY (MEDICAL SCIENCE), 2021, 41(9): 1228-1232.

Figures/Tables 5

TrendMD

References 17

1	中华医学会消化病学分会, 中华医学会肝病学分会. 中国肝性脑病诊治共识意见(2013年,重庆)[J]. 中国医学前沿杂志(电子版), 2014, 6(2): 81-93.
2	Thomsen KL, Macnaughtan J, Tritto G, et al. Clinical and pathophysiological characteristics of cirrhotic patients with grade 1 and minimal hepatic encephalopathy[J]. PLoS One, 2016, 11(1): e0146076.
3	Ampuero J, Montoliú C, Simón-Talero M, et al. Minimal hepatic encephalopathy identifies patients at risk of faster cirrhosis progression[J]. J Gastroenterol Hepatol, 2018, 33(3): 718-725.
4	Bajaj JS, Thacker LR, Heuman DM, et al. The Stroop smartphone application is a short and valid method to screen for minimal hepatic encephalopathy[J]. Hepatology, 2013, 58(3): 1122-1132.
5	Sharma P, Sharma BC. A survey of patterns of practice and perception of minimal hepatic encephalopathy: a nationwide survey in India[J]. Saudi J Gastroenterol, 2014, 20(5): 304-308.
6	马瑜, 嵇承栋, 赵静, 等. 筛查模型与效果评价的研究进展[J]. 公共卫生与预防医学, 2014, 25(4): 70-74.
7	中华医学会肝病学分会, 中华医学会感染病学分会. 慢性乙型肝炎防治指南(2015年版)[J]. 实用肝脏病杂志, 2015, 19(3): 5-16.
8	Yuan LT, Chuah SK, Yang SC, et al. Multiple bacterial infections increase the risk of hepatic encephalopathy in patients with cirrhosis[J]. PLoS One, 2018, 13(5): e0197127.
9	朱彬, 邹聪聪, 郑昕. 终末期肝病的营养不良评价体系和营养支持治疗[J]. 临床肝胆病杂志, 2017, 33(9): 1699-1706.
10	Pang Y, Kartsonaki C, Turnbull I, et al. Diabetes, plasma glucose, and incidence of fatty liver, cirrhosis, and liver cancer: a prospective study of 0.5 million people[J]. Hepatology, 2018, 68(4): 1308-1318.
11	佘倩, 陈明锴. 不同血糖代谢状态患者肝硬化的临床特征[J]. 武汉大学学报(医学版), 2019, 40(6): 982-986.
12	张浩彬, 周伟珠. IBM SPSS Modeler18.0数据挖掘权威指南[M]. 北京: 人民邮电出版社, 2019.
13	秦平, 张镏琢, 赵晓雯, 等. BP神经网络在代谢综合征影响因素分析中的应用[J]. 实用预防医学, 2011, 18(10): 1819-1822.
14	陈杰, 周勤, 陈进, 等. 人工神经网络在疾病预后研究中的应用进展[J]. 中国胸心血管外科临床杂志, 2013, 20(1): 95-99.
15	许人, 石张镇, 张文龙, 等. Logistic多元回归和人工神经网络在判断进展期胃癌淋巴结转移中的应用[J]. 中国老年学杂志, 2016,36(16): 3980-3982.
16	中华医学会肝病学分会. 肝硬化肝性脑病诊疗指南[J]. 传染病信息, 2018, 31(5): 403-420.
17	李倩倩, 牛小霞, 徐碧海,等. 肝硬化失代偿期患者主要照顾者对延续性护理需求的质性研究[J]. 解放军护理杂志, 2018, 35(1): 25-28.

Item	β	S.E.	Wald	P	OR	95% CI
Age	0.028	0.010	8.521	0.004	1.029	1.009‒1.049
Diabetes mellitus	0.595	0.281	4.490	0.034	1.813	1.046‒3.144
Infection	0.547	0.244	5.044	0.025	1.729	1.072‒2.787
Renal dysfunction	0.649	0.273	5.677	0.017	1.914	1.122‒3.266
Nutritional risk	0.745	0.242	9.489	0.002	2.106	1.311‒3.382
Total bilirubin（>24 μmol·L^-1）	0.505	0.248	4.151	0.042	1.657	1.019‒2.692
Ammonia（>47 μmol·L^-1）	0.455	0.225	4.068	0.044	1.575	1.013‒2.450
INR（≥1.5）	0.680	0.325	4.371	0.037	1.973	1.043‒3.731
Constant	-2.975	0.593	25.123	0.000	0.051	‒

Item	β	S.E.	Wald	P	OR	95% CI
Age	0.028	0.010	8.521	0.004	1.029	1.009‒1.049
Diabetes mellitus	0.595	0.281	4.490	0.034	1.813	1.046‒3.144
Infection	0.547	0.244	5.044	0.025	1.729	1.072‒2.787
Renal dysfunction	0.649	0.273	5.677	0.017	1.914	1.122‒3.266
Nutritional risk	0.745	0.242	9.489	0.002	2.106	1.311‒3.382
Total bilirubin（>24 μmol·L^-1）	0.505	0.248	4.151	0.042	1.657	1.019‒2.692
Ammonia（>47 μmol·L^-1）	0.455	0.225	4.068	0.044	1.575	1.013‒2.450
INR（≥1.5）	0.680	0.325	4.371	0.037	1.973	1.043‒3.731
Constant	-2.975	0.593	25.123	0.000	0.051	‒

Model	MHE（diagnosed by PHES）
Model	Positive （n=196）	Negative （n=208）
Logistic regression
High risk	137	67
Low risk	59	141
ANN
High risk	142	49
Low risk	54	159

Model	MHE（diagnosed by PHES）
Model	Positive （n=196）	Negative （n=208）
Logistic regression
High risk	137	67
Low risk	59	141
ANN
High risk	142	49
Low risk	54	159

[1]	GONG Xu-hua1, ZHU Liang2, CHEN Chao3, QIAN Li-jun1. miR-214 promotes the progression of liver fibrosis by activating hepatic stellate cells [J]. JOURNAL OF SHANGHAI JIAOTONG UNIVERSITY (MEDICAL SCIENCE), 2020, 40(06): 776-784.
[2]	SANG Chao1, XIE Guo-xiang2, LIANG Dan-dan1, ZHAO Ai-hua1, JIA Wei1, 2, CHEN Tian-lu1. Improvement of liver fibrosis diagnostic models based on Youden index [J]. , 2019, 39(10): 1156-.