Prediction of upcoming urinary tract infection after intracerebral hemorrhage - a machine learning approach based on statistics collected at multiple time points - Original Research

Q: What is the study’s main goal?

To predict upcoming urinary tract infection after intracerebral hemorrhage using a machine learning method based on statistics collected at multiple time points.

Q: Which laboratory time points were used in the analysis?

Laboratory tests were selected at admission (Lab 1) and at 48 hours after admission (Lab 2).

Q: Which factors and model approach showed the best predictive performance?

Corticosteroid usage and daily urinary volume were significant risk factors, and the best model combined clinical information with the rate of change in laboratory parameters.

Aug 5, 2026

Upload by Finn

Accurate prediction of urinary tract infection (UTI) after intracerebral hemorrhage (ICH) supports timely interventions and neurocritical care decisions. This study develops a machine learning approach using multi-time-point statistics derived from laboratory tests at admission and 48 hours post-admission, supported by univariate analysis to compare UTI versus non-UTI groups. Corticosteroid use and daily urinary volume emerge as significant risk factors. A model combining clinical information with laboratory parameter change predicts upcoming UTIs with strong discriminative performance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Purpose

Methods

Study cohort and time-point laboratory data

Feature evaluation and model performance

Results

Identified risk factors

Best-performing predictive model

Conclusion

Keywords

TYPE Original Research PUBLISHED 14 September 2023 DOI 10. 3389/fneur.2023.1223680 OPEN ACCESS EDITED BY Xiangzhi Bai, Beihang University, China REVIEWED BY Ping Hu, Second A􀀈liated Hospital of Nanchang University, China Khan Md Hasib, Bangladesh University of Business and Technology, Bangladesh *CORRESPONDENCE Wenyao Cui [wenyaocui01@gmail.com](wenyaocui01@gmail.com)[ ](wenyaocui01@gmail.com)Jianguo Xu [drjianguoxu@gmail.com](drjianguoxu@gmail.com) †These authors have contributed equally to this work RECEIVED 30 May 2023 ACCEPTED 18 August 2023 PUBLISHED 14 September 2023 CITATION Zhao Y, Chen C, Huang Z, Wang H, Tie X, Yang J, Cui W and Xu J (2023) Prediction of upcoming urinary tract infection after intracerebral hemorrhage: a machine learning approach based on statistics collected at multiple time points. Front. Neurol. 14:1223680 . doi: 10.3389/fneur.2023.1223680 COPYRIGHT © 2023 Zhao, Chen, Huang, Wang, Tie, Yang, Cui and Xu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Prediction of upcoming urinary tract infection after intracerebral hemorrhage: a machine learning approach based on statistics collected at multiple time points Yanjie Zhao1,2†, Chaoyue Chen1,2†, Zhouyang Huang1 , Haoxiang Wang1 , Xin Tie2 , Jinhao Yang1 , Wenyao Cui1,2* and Jianguo Xu1,2* 1 Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, China, 2 Department of Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, China Purpose: Accurate prediction of urinary tract infection (UTI) following intracerebral hemorrhage (ICH) can signiﬁcantly facilitate both timely medical interventions and therapeutic decisions in neurocritical care. Our study aimed to propose a machine learning method to predict an upcoming UTI by using multi-time-point statistics. Methods: A total of 110 patients were identiﬁed from a neuro-intensive care unit in this research. Laboratory test results at two time points were chosen: Lab 1 collected at the time of admission and Lab 2 collected at the time of 48h after admission. Univariate analysis was performed to investigate if there were statistical di􀀀erences between the UTI group and the non-UTI group. Machine learning models were built with various combinations of selected features and evaluated with accuracy (ACC), sensitivity, speciﬁcity, and area under the curve (AUC) values. Results: Corticosteroid usage (p < 0.001) and daily urinary volume (p < 0.001) were statistically signiﬁcant risk factors for UTI. Moreover, there were statistical di􀀀erences in laboratory test results between the UTI group and the non-UTI group at the two time points, as suggested by the univariate analysis. Among the machine learning models, the one incorporating clinical information and the rate of change in laboratory parameters outperformed the others. This model achieved ACC = 0. 773, sensitivity = 0. 785, speciﬁcity = 0. 762, and AUC = 0.868 during training and 0 .682, 0 .685, 0 .673, and 0 . 751 in the model test, respectively. Conclusion: The combination of clinical information and multi-time-point laboratory data can e􀀀ectively predict upcoming UTIs after ICH inneurocritical care. KEYWORDS urinary tract infection, intracerebral hemorrhage, stroke, critical care, machine learning 1. Introduction Manifesting as bacteremia, sepsis, and acute renal failure, urinary tract infection (UTI) is a signi􀀂cant complication linked to unfavorable prognostic outcomes in intracerebral hemorrhage (ICH) patients (1–3) . It can result in readmission with po

FAQs

What is the study’s main goal?

To predict upcoming urinary tract infection after intracerebral hemorrhage using a machine learning method based on statistics collected at multiple time points.

Which laboratory time points were used in the analysis?

Laboratory tests were selected at admission (Lab 1) and at 48 hours after admission (Lab 2).

Which factors and model approach showed the best predictive performance?

Corticosteroid usage and daily urinary volume were significant risk factors, and the best model combined clinical information with the rate of change in laboratory parameters.

Aug 5, 2026

Upload by Finn