摘 要：儿童急性淋巴细胞白血病等血液病种类繁多，且易出现反复性贫血、出血、感染等不可预期的情况，严重可导致休克及死亡。上海儿童医学中心每年承接近 5 700 名儿童血液病患者，超过全国儿童血液病患者的 1/3，白血病早期预警系统的智能化建设可为医生提前介入提供依据。运用儿童早期预警评分 PEWS，对病区（42 张床位）进行测试，证实发现该方法可提供至少 11 小时的预警，需 381 min。同时，该方案用通过物联及 CNNS 卷积神经网络深度学习的手段实现 PEWS 实时计算。
关键词：儿童早期预警评分；白血病；物联技术；CNNS 神经网络；深度学习
DOI:10.19850/j.cnki.2096-4706.2022.02.030
中图分类号：TP18；R-331 文献标识码：A 文章编号：2096-4706（2022）02-0119-05
Construction and Application of Intelligent Early Warning System for Children with Hematological Diseases
FENG Jiayi, LIU Liping, ZHOU Fen, SHEN Nanping
(Shanghai Children's Medical Center, Shanghai 200127, China)
Abstract: There are many kinds of blood diseases such as acute lymphoblastic leukemia in children, and they are prone to unpredictable situations such as recurrent anemia, bleeding and infection, which can seriously lead to shock and death. Shanghai Children's Medical Center accepts nearly 5 700 children with hematological diseases every year, more than 1/3 of the national children with hematological diseases. The intelligent construction of the early warning system for leukemia can provide a basis for doctors to intervene in advance. Using the Pediatric Early Warning Score (PEWS), testing of the ward (42 beds) confirmed that the method can provide at least 11 hours of early warning, which takes 381 minutes. At the same time, the scheme realizes the real-time calculation of PEWS by means of deep learning of IOT and CNNs convolutional neural network.
Keywords: PEWS; leukemia; IOT technology; CNNS neural network; deep learning
参考文献：
[1] 周芬，潘慈，高怡瑾，等 . 儿童早期预警评分对血液肿瘤患儿病情变化的预测价值及可行性研究 [J]. 解放军护理杂志，2019，36（4）：6-10.
[2] 刘煜，陈历赛，段颖晖，等 . 儿童早期预警评分在 PICU病毒性脑炎患儿病情转归中的预测价值 [J]. 护理学杂志，2017，32（5）：24-26.
[3] 张佳燕，胡菲，张玉侠 . 儿童早期预警评分在留诊观察患儿分流中的应用 [J]. 护理研究，2015，29（30）：3744-3746.
[4] DUNCAN H，HUTCHISON J，PARSHURAM C S. The Pediatric early warning system score： A severity of illness score to predict urgent medical need in hospitalized children [J].Journal of Critical Care，2006，21（3）：271-278.
[5] ASYA A，PETER F，NICOLE S，et al. Validation of a pediatric early warning score in hospitalized pediatric oncology and hematopoietic stem cell transplant patients [J].Pediatric Critical Care Medicine，2016，17（4）：146-153.
[6] 唐慧，杨艳，李映兰，等 . 儿童早期预警评分在急性淋巴细胞白血病患儿中的应用 [J]. 中华护理杂志，2017，52（12）：1422-142.
[7] AGULNIK A，NADKARNI A，ROBLES L N M，et al. Pediatric early warning systems aid in triage to intermediate versus intensive care for pediatric oncology patients in resource-limited hospitals [J/OL].Pediatric Blood & Cancer，2018，65（8）：e27076. [2021-11-03].https://onlinelibrary.wiley.com/doi/10.1002/pbc.27076.
[8] ACKER S N，WATHEN B，ROOSEVELT G E，et al. Rapid response team activation in pediatric surgical patients [J].European journal of pediatric surgery，2017，27（1）：81-85.
[9] AGULNIK A，ACEITUNO A M E，ROBLES L N M，et al. Validation of a pediatric early warning system for hospitalized pediatric oncology patients in a resource-limited setting[J].Cancer，2017，123（24）：4903-4913.
[10] DEMMEL KM， WILLIAMS L， F L E S C H L . Implementation of the Pediatric Early Warning Scoring System on a Pediatric Hematology/Oncology Unit [J].Journal of Pediatric Oncology Nursing，2010，27（4）：229-240.
[11] AGULNIK A，ROBLES L N M，FORBES P W，et al. Improved outcomes after successful implementation of a pediatric early warning system（PEWS）in a resource-limited pediatric oncology hospital [J].Cancer，2017，123（15）：2965-2974.
[12] 王丽，张富强，何伟锋，等 . 儿童早期预警评分在意外伤害急诊患儿病情评估中的应用 [J]. 护理学报，2015，22（16）：56-58.
[13] 董梅德，吴玲，相波，等 . 临床科室护理工作性质调查分析 [J]. 护理学杂志，2015，30（12）：73-75.
[14] 张梅，范媛，朱继红，等 . 儿童早期预警评分系统在小儿普外科中的应用 [J]. 中华现代护理杂志，2014，20（32）：4133-4137.
[15] DONG S Y，LUO G N，TAM C，et al. Deep Atlas Network for Efficient 3D Left Ventricle Segmentation on Echocardiography [J/OL].[2021-12-06].Med Image Analysis，2020，61：101638.https://www.sciencedirect.com/science/article/abs/pii/S1361841520300050.
[16] RONNEBERGER O，FISCHER P，BROX T. U-Net：Convolutional Networks for Biomedical Image Segmentation [C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015. Munich：Springer.2015：234-241.
[17] SZEGEDY C，LIU W，JIA Y Q，et al. Going deeper with convolutions [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Boston：IEEE，2015：1-9.
[18] SZEGEDY C，VANHOUCKE V，IOFFE S，et al. Rethinking the Inception Architecture for Computer Vision [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. Las Vegas：IEEE，2016：2818-2826.
[19] Zhou Z W，Siddiquee M M R，Taibakhsh N，et al. UNet++： A nested U-Net architecture for medical image segmentation [C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Granada：Springer，2018：3-11.
[20] JADERBERG M，SIMONYAN K，ZISSERMAN A，et al. Spatial transformer networks [C]//the 28th International Conference on Neural Information Processing Systems.Montreal：MIT Press，2015:2017-2025.
[21] ALJABAR P，HECKEMANN R A，HAMMERS A，et al. Multi-atlas based segmentation of brain images：Atlas selection and its effect on accuracy [J].Neuroimage，2009，46（3）：726-738.
[22] AWATE S P，ZHU P H，WHITAKER R T. How Many Templates Does It Take for a Good Segmentation?：Error Analysis in Multiatlas Segmentation as a Function of Database Size [C]//MBIA：International Workshop on Multimodal Brain Image Analysis.Nice： Springer，2012，7509：103-114.
[23] BADRINARAYANAN V，KENDALL A，CIPOLLA R. SegNet：A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39：2481-2495.
[24] ZHAO H S，SHI J P，QI X J，et al. Pyramid Scene Parsing Network [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），Honolulu：IEEE，2017：6230-6239.
[25] 王丽嘉，苏新宇，李亚，等 . 基于 COLLATE 融合多图谱的心脏电影 MRI 右心室分割 [J]. 波谱学杂志，2018，35（4）：407-416.
作者简介：冯佳怡（1983.09—），女，汉族，上海人，工程师，硕士，研究方向：可穿戴人工智能、图像处理；通讯作者：柳立平（1983.01—），女，汉族，上海人，研究方向：智慧护理、重症医学、呼吸理疗。