| Category |
Gastroenterology & Hepatology |
| Manuscript Type |
Retrospective Cohort Study |
| Article Title |
Machine learning as a decision-support tool for spontaneous bacterial empyema and spontaneous bacterial peritonitis in cirrhosis
|
| Manuscript Source |
Unsolicited Manuscript |
| All Author List |
Zhi-Ji Chen, Xin Ge, Jia-Yao Xu, Yu-Hong Zhang, Mei Yang, Lin-Hong Mao, Yu-Mei Wang, Ping Chen, Zhen Zhu, Fang Tang, Chun-Yan Luo, Jin-Fang Liu, Bo-Yi Wu, Xing-Shun Qi, Trevor Kwan-Hung Wu, Lung-Yi Mak, Li Zhou, Liang-Zhi Wen, Song He, Hao-Lin Wang and Zhi-Hang Zhou |
| Funding Agency and Grant Number |
| Funding Agency |
Grant Number |
| National Natural Science Foundation of China |
82373003, 82573112, and 82570664 |
| New Chongqing Youth Innovation Talents |
CSTB2024NSCQ-QCXMX0010 |
| Chongqing Science and Health Joint Key Project |
2024ZDXM031 |
| Chongqing Medical University Major Science and Technology Talent Project |
|
|
| Corresponding Author |
Zhi-Hang Zhou, MD, Department of Gastroenterology, The Second Affiliated Hospital of Chongqing Medical University, No. 76 Linjiang Road, Yuzhong District, Chongqing 400010, China. zhouzhihang@cqmu.edu.cn |
| Key Words |
Spontaneous bacterial empyema; Spontaneous bacterial peritonitis; Cirrhosis; Machine learning; Diagnosis |
| Core Tip |
Bacterial infections are common and are associated with high mortality in patients with cirrhosis. In this multicenter retrospective study, a Neural Additive Model- retrieval-augmented tabular deep learning (NAM-TABR) model was developed as a decision-support tool for spontaneous bacterial empyema (SBE) and spontaneous bacterial peritonitis (SBP). For SBE, the traditional polymorphonuclear leukocyte (PMN) cutoff showed limited sensitivity, whereas the NAM-TABR model increased the Youden index from 0.480 to 0.618, achieving area under the curves (AUCs) of 0.865 (internal) and 0.925 (external), respectively. For SBP, PMN > 50 × 106/L improved the Youden index compared to PMN > 250 × 106/L (0.534 vs 0.429), and the NAM-TABR model further increased it to 0.635, with AUCs of 0.885 (internal) and 0.823 (external), respectively. |
| Citation |
Chen ZJ, Ge X, Xu JY, Zhang YH, Yang M, Mao LH, Wang YM, Chen P, Zhu Z, Tang F, Luo CY, Liu JF, Wu BY, Qi XS, Wu TKH, Mak LY, Zhou L, Wen LZ, He S, Wang HL, Zhou ZH. Machine learning as a decision-support tool for spontaneous bacterial empyema and spontaneous bacterial peritonitis in cirrhosis. World J Gastroenterol 2026; In press
|
| PDF |
127625-in-press.pdf
|
