AUTHOR=Zhao Yanjie , Chen Chaoyue , Huang Zhouyang , Wang Haoxiang , Tie Xin , Yang Jinhao , Cui Wenyao , Xu Jianguo 

TITLE=Prediction of upcoming urinary tract infection after intracerebral hemorrhage: a machine learning approach based on statistics collected at multiple time points

JOURNAL=Frontiers in Neurology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2023.1223680

DOI=10.3389/fneur.2023.1223680

ISSN=1664-2295

ABSTRACT=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 aims to propose a machine learning method to predict the upcoming UTI by using multi-time-point statistics.
Methods A total of 110 patients were identified from neuro-intensive care unit in this research. Laboratory test results at two time points were chosen: Lab 1st collected at the time of admission, and Lab 2nd collected at the time of 48 hours after admission. Univariate analysis was performed to investigate if there was statistical differences between UTI group and non-UTI group. Machine learning models were bulit with various combination 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 differences in laboratory test results between UTI group and non-UTI group either 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 model test, respectively.
Conclusion The combination of clinical information and multi-time-point laboratory data can effectively predict upcoming UTIs after ICH in neurocritical care.