Full
Outline
The clinical symptoms and ultrasound images of gallstone disease (GSD) and gallbladder polyps (GP) overlap, yet they have distinct prognoses and management strategies. Misdiagnosis can lead to excessive or delayed intervention. This study aims to develop and validate a differential diagnostic model based on multidimensional clinical indicators to enhance the differentiation between GSD and GP.
We included 371 518 individuals from health check-ups at a hospital in Kaizhou District, Chongqing, from 2015 to 2020, selecting 24 307 GSD or GP patients. These were split into a training set (19 445 cases) and an internal validation set (4 862 cases) at an 8:2 ratio. Variables were selected using Lasso regression and XGBoost algorithm, and a diagnostic model was built with Logistic regression. The model’s calibration, discrimination, and clinical applicability were evaluated using the calibration curve, the area under the ROC curve (AUC), and decision curve analysis, respectively.For external validation, 14 341 GSD and GP patients undergoing health checkups during the same period at a hospital in the Liangjiang New Area, Chongqing, were included to assess the model’s discriminative performance.
Women, older individuals, those with high BMI, central obesity, elevated GGT and ALT levels, high blood glucose levels, and fatty liver were more likely to be diagnosed with GSD. Individuals with high HDL-C and LDL-C levels were more likely to have GP. The model demonstrated good calibration and discrimination, with an ROC AUC of 69.4% (95% CI: 67.8%-70.9%). Decision curve analysis further indicated that the model had good clinical applicability, and external validation further confirmed its discriminatory performance. An online tool (https://yitingxu129.shinyapps.io/logisticmodel/) was created to aid in differentiating GSD and GP.
This study shows that gender, age, BMI, and blood biochemistry indicators are valuable in differentiating GSD and GP.The developed model has good predictive performance and clinical applicability and is expected to assist radiologists in making accurate differential diagnoses of GSD and GP, reduce misdiagnoses, and lower the disease burden.
43
20
| 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
010-62662699(Operation and Technical Support)
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
