PDF
Full
Outline
Objective To construct a prediction model based on machine learning algorithm for cirrhosis-related hepatic encephalopathy. Methods A cross-sectional survey was conducted in 1498 patients from 7 medical institutions in Chongqing from June 2019 to June 2020, who were divided into hepatic encephalopathy group (n=285) and non-hepatic encephalopathy group(n=1213) according to whether hepatic encephalopathy occurred. 70% (1048 in total) of the data collected from 1498 patients was randomly chosen as the training set for establishing the prediction model and the rest 30% (450 in total) was used for internal verification. Univariate logistic regression was used to filter input indicators. Logistic regression, random forest, decision tree and XGBoost algorithm based on machine learning were used to construct a diagnostic predictive model. The models constructed by the four methods were compared for predictive and diagnostic value of cirrhosis-related hepatic encephalopathy. Results Logistic regression, random forest, decision tree and XGBoost models all suggested prothrombin activity (OR=0.933, 95%CI 0.921-0.946), age (OR=1.045, 95%CI 1.029-1.061), blood sodium (OR=0.964, 95%CI 0.928-1.000) and urea nitrogen (OR=1.063, 95%CI 1.022-1.105) are important influencing factors of hepatic encephalopathy. The sensitivities of the four models were 0.843, 0.904, 0.759 and 0.892; the specificities were 0.785, 0.695, 0.717 and 0.706; the area under the curve (AUC) were 0.875, 0.883, 0.767 and 0.847 respectively. Conclusions The risk prediction model of cirrhosis-related hepatic encephalopathy established based on machine learning has high diagnostic value. The diagnostic effects of logistic and random forest models are better than those of decision tree and XGBoost models.
PDF
129
47
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
