Chen Zhengguo, Li Ning, Chen Zhu, Zhou Li, Xiao Liming, Zhang Yangsong
NHC Key Laboratory of Nuclear Technology Medical Transformation (MIANYANG CENTRAL HOSPITAL), Mianyang, 621000, China.
School of Computer Science and Technology, Laboratory for Brain Science and Medical Artificial Intelligence, Southwest University of Science and Technology, Mianyang, 621010, China.
Heliyon. 2024 May 16;10(10):e31255. doi: 10.1016/j.heliyon.2024.e31255. eCollection 2024 May 30.
Urinary tract infection (UTI) is one of the most common infectious diseases among children, but there is controversy regarding the use of preventive antibiotics for children first diagnosed with febrile pyelonephritis. To the best of our knowledge, no studies have addressed this issue by the deep learning technology. Therefore, in the current study, we conducted a study using renal static imaging data to investigate the need for preventive antibiotics on children first diagnosed with febrile pyelonephritis under 2 years old. The self-collected dataset comprised 64 children who did not require preventive antibiotic treatments and 112 children who did. Using several classic deep learning models, we verified that it is feasible to screen whether the first diagnosed children with febrile pyelonephritis require preventive antibacterial therapy, achieving a graded diagnosis. With the AlexNet model, we obtained accuracy of 84.05%, sensitivity of 81.71% and specificity of 86.70%, respectively. The experimental results indicate that deep learning technology could provide a new avenue to implement computer-assisted decision support for the diagnosis of the febrile pyelonephritis.
尿路感染（UTI）是儿童中最常见的传染病之一，但对于首次诊断为发热性肾盂肾炎的儿童使用预防性抗生素存在争议。据我们所知，尚无研究通过深度学习技术解决这一问题。因此，在本研究中，我们利用肾脏静态成像数据进行了一项研究，以调查2岁以下首次诊断为发热性肾盂肾炎的儿童是否需要预防性抗生素。自行收集的数据集包括64名不需要预防性抗生素治疗的儿童和112名需要的儿童。使用几种经典的深度学习模型，我们验证了筛查首次诊断为发热性肾盂肾炎的儿童是否需要预防性抗菌治疗并实现分级诊断是可行的。使用AlexNet模型，我们分别获得了84.05%的准确率、81.71%的灵敏度和86.70%的特异性。实验结果表明，深度学习技术可为发热性肾盂肾炎的诊断提供一条实施计算机辅助决策支持的新途径。
