
浏览全部资源
扫码关注微信
1.重庆医科大学附属第一医院神经外科,重庆 400016
2.重庆科技学院智能技术与工程学院,重庆 401331
夏宇隆,Email:2010473582@qq.com, 研究方向:神经外科。
但 炜,Email:1187403442@qq.com。
收稿:2023-01-04,
修回:2023-06-27,
录用:2023-08-04,
纸质出版:2023-09-28
移动端阅览
夏宇隆,蒋理,但炜,等.基于人工智能的高血压性脑出血医疗文本信息自动识别系统[J].重庆医科大学学报,2023,48(9):1122-1127.
Xia Yulong,Jiang Li,Dan Wei,et al.AI-based automatic recognition system of medical text for hypertensive intracerebral hemorrhage[J].Journal of Chongqing Medical University,2023,48(9):1122-1127.
夏宇隆,蒋理,但炜,等.基于人工智能的高血压性脑出血医疗文本信息自动识别系统[J].重庆医科大学学报,2023,48(9):1122-1127. DOI: 10.13406/j.cnki.cyxb.003332.
Xia Yulong,Jiang Li,Dan Wei,et al.AI-based automatic recognition system of medical text for hypertensive intracerebral hemorrhage[J].Journal of Chongqing Medical University,2023,48(9):1122-1127. DOI: 10.13406/j.cnki.cyxb.003332.
目的
2
构建基于人工智能的高血压性脑出血医疗文本信息自动识别系统,快速识别和分析患者临床信息,高效地输出正确的诊疗方案。
方法
2
基于国内外最新高血压性脑出血诊疗指南,经多位高年资神经外科医生和专业人工智能团队共同讨论,构建基于语言表征模型和专家模块的高血压性脑出血医疗文本信息自动识别及决策系统(即H系统)。随后将收集到的高血压性脑出血病例分为训练集、测试集和验证集,以数据库中病例的真实治疗方案为金标准,先总体评价H系统的准确性,再将其与神经外科医生进行对比,分析H系统的判读效率。
结果
2
在测试集中,H系统所输出的治疗方案的准确率为94.0%(91.5%~96.5%),特异度为91.8%(86.3%~97.3%),灵敏度为95.5%(89.3%~98.2%),曲线下面积(area under the curve,AUC)值为0.936(0.922~0.950)(
P
=0.000);在验证集中,H系统所输出的治疗方案的准确率为93.3%(89.5%~97.1%),特异度为 89.9%(83.4%~96.4%),灵敏度为95.8%(92.3%~99.3%),AUC值为0.928(0.891~0.966)(
P
=0.000)。在处理同样的70例病例时,H系统用时(334.60±4.46)s,而神经外科医生用时(12 550.28±95.45)s;在50 min内,H系统处理的病例数为(383±3)例,而神经外科医生处理的病例数为(11±4)例。
结论
2
本研究所构建的H系统能够对高血压性脑出血患者的急诊病例进行自动识别和分析,并快速输出准确的诊疗方案,可协助医生对高血压脑出血进行急诊诊疗。
Objective
2
To design an automatic medical text recognition system based on artificial intelligence(AI), which can quickly spot and analyze patients’ clinical information then output accurate treatment plans.
Methods
2
After discussions by senior neurosurgeons and professional AI teams,we designed the automatic recognition and decision-making system of medical text information for hypertensive cerebral hemorrhage(namely H-system) based on the language representation model and the expert mode. Taking the real treatment plans in the database as the gold standard, the accuracy of the H-system was evaluated as a whole,and then it was compared with the senior neurosurgery to analyze the efficiency of the H-system.
Results
2
In the testing sets,the accuracy of the output by H-system was 94.0%(91.5%-96.5%),the specificity was 91.8%(86.3%-97.3%),the sensitivity was 95.5%(89.3%-98.2%),and
the AUC was 0.936(0.922-0.950)(
P
=0.000). Meanwhile,in the validation sets,the accuracy of the output by H-system was 93.3%(89.5%-97.1%),the specificity was 89.9%(83.4%-96.4%),the sensitivity was 95.8%(92.3%-99.3%),and the AUC was 0.928(0.891-0.966)(
P
=0.000). In processing the same 70 cases,the H-system took(334.60±4.46) s compared to (12 550.28±95.45) s for the neurosurgeon;in 50 minutes, the H-system processed(383±3) cases compared to (11±4) cases for the neurosurgeon.
Conclusion
2
The H-system constructed in this study can automatically recognize and analyze the medical text data of patients, and quickly output an accurate treatment plan. In clinical practice, it may assist doctors to provide an efficient and reliable treatment for patients with hypertensive intracerebral hemorrhage.
Ikram MA , Wieberdink RG , Koudstaal PJ . International epidemiology of intracerebral hemorrhage [J ] . Curr Atheroscler Rep , 2012 , 14 ( 4 ): 300 - 306 .
刘卫东 . 高血压性脑出血的诊治进展 [J ] . 上海医学 , 2017 , 40 ( 11 ): 646 - 649 .
Liu WD . Progress of diagnosis and therapy in hypertensive intracerebral hemorrhage [J ] . Shanghai Med J , 2017 , 40 ( 11 ): 646 - 649 .
丁贤彬 , 焦 艳 , 毛德强 , 等 . 2012—2018年重庆市脑出血发病及死亡趋势分析 [J ] . 重庆医学 , 2021 , 50 ( 1 ): 133 - 137,141 .
Ding XB , Jiao Y , Mao DQ , et al . Trend analysis of intracerebral hemorrhage from 2012 to 2018 in Chongqing Municipality [J ] . Chongqing Med , 2021 , 50 ( 1 ): 133 - 137,141 .
王陇德 , 刘建民 , 杨 弋 , 等 . 我国脑卒中防治仍面临巨大挑战:《中国脑卒中防治报告2018》概要 [J ] . 中国循环杂志 , 2019 , 34 ( 2 ): 105 - 119 .
Wang LD , Liu JM , Yang Y , et al . The prevention and treatment of stroke still face huge challenges—brief report on stroke prevention and treatment in China,2018 [J ] . Chin Circ J , 2019 , 34 ( 2 ): 105 - 119 .
杨 帆 , 杨国军 , 杨 哲 . 北京地区3139例首发脑出血患者流行特征及预后情况分析 [J ] . 华南预防医学 , 2022 , 48 ( 1 ): 46 - 49,54 .
Yang F , Yang GJ , Yang Z . Epidemic characteristics and prognosis of 3 139 patients with first-episode cerebral hemorrhage in Beijing [J ] . South China J Prev Med , 2022 , 48 ( 1 ): 46 - 49,54 .
Ramesh AN , Kambhampati C , Monson J , et al . Artificial intelligence in medicine [J ] . Ann R Coll Surg Engl , 2004 , 86 ( 5 ): 334 - 338 .
Al-masni MA , Kim WR , Kim EY , et al . Automated detection of cerebral microbleeds in MR images:a two-stage deep learning approach [J ] . Neuroimage Clin , 2020 , 28 : 102464 .
Soun JE , Chow DS , Nagamine M , et al . Artificial intelligence and acute stroke imaging [J ] . AJNR Am J Neuroradiol , 2021 , 42 ( 1 ): 2 - 11 .
Yasaka K , Akai H , Kunimatsu A , et al . Deep learning with convolutional neural network in radiology [J ] . Jpn J Radiol , 2018 , 36 ( 4 ): 257 - 272 .
骆明涛 , 伍 聪 , 陶传元 , 等 . 《高血压性脑出血中国多学科诊治指南》急救诊治解读 [J ] . 中国急救医学 , 2021 , 41 ( 3 ): 185 - 190 .
Luo MT , Wu C , Tao CY , et al . Interpretation of emergency treatment of Chinese multidisciplinary guideline for management of hypertensive intracerebral hemorrhage [J ] . Chin J Crit Care Med , 2021 , 41 ( 3 ): 185 - 190 .
游 潮 , 刘 鸣 , 于学忠 , 等 . 高血压性脑出血中国多学科诊治指南 [J ] . 中国急救医学 , 2020 , 40 ( 8 ): 689 - 702 .
You C , Liu M , Yu XZ , et al . Multidisciplinary diagnosis and treatment guidelines for hypertensive cerebral hemorrhage in China [J ] . Chin J Crit Care Med , 2020 , 40 ( 8 ): 689 - 702 .
Mouridsen K , Thurner P , Zaharchuk G . Artificial intelligence applications in stroke [J ] . Stroke , 2020 , 51 ( 8 ): 2573 - 2579 .
Zhao K , Zhao Q , Zhou P , et al . Can artificial intelligence be applied to diagnose intracerebral hemorrhage under the background of the fourth industrial revolution? A novel systemic review and Meta-analysis [J ] . Int J Clin Pract , 2022 , 2022 : 9430097 .
牛姗姗 , 钟利平 , 宋腾飞 , 等 . 低密度征和斑点征预测自发性脑出血早期血肿扩大 [J ] . 中山大学学报(医学科学版) , 2022 , 43 ( 3 ): 496 - 503 .
Niu SS , Zhong LP , Song TF , et al . Predictive value of hypodensities and spot sign for hematoma enlargement in early stage of spontaneous cerebral hemorrhage [J ] . J Sun Yat Sen Univ Med Sci , 2022 , 43 ( 3 ): 496 - 503 .
陆 明 , 何卫春 , 党宝齐 , 等 . 高血压脑出血患者的手术时机和手术方式的选择 [J ] . 中国实用神经疾病杂志 , 2014 , 17 ( 1 ): 24 - 26 .
Lu M , He WC , Dang BQ , et al . Observation on the timing of surgery and surgical approach for the patients with hypertensive intracerebral hemorrhage [J ] . Chin J Pract Nerv Dis , 2014 , 17 ( 1 ): 24 - 26 .
马 进 , 曹 臻 , 严明科 . 高血压脑出血患者急诊救治分析 [J ] . 实用心脑肺血管病杂志 , 2017 , 25 ( S1 ): 102 - 103 .
Ma J , Cao Z , Yan MK . Analysis of emergency treatment for hypertensive cerebral hemorrhage patients [J ] . Pract J Cardiac Cereb Pneumal Vasc Dis , 2017 , 25 ( S1 ): 102 - 103 .
Cordonnier C , Demchuk A , Ziai W , et al . Intracerebral haemorrhage:current approaches to acute management [J ] . Lancet , 2018 , 392 ( 10154 ): 1257 - 1268 .
Lee J , Yoon W , Kim S , et al . BioBERT:a pre-trained biomedical language representation model for biomedical text mining [J ] . Bioinformatics , 2020 , 36 ( 4 ): 1234 - 1240 .
李冬梅 , 罗斯斯 , 张小平 , 等 . 命名实体识别方法研究综述 [J ] . 计算机科学与探索 , 2022 , 16 ( 9 ): 1954 - 1968 .
Li DM , Luo SS , Zhang XP , et al . Review on named entity recognition [J ] . J Front Comput Sci Technol , 2022 , 16 ( 9 ): 1954 - 1968 .
张 军 , 邱龙龙 . 一种基于BERT和池化操作的文本分类模型 [J ] . 计算机与现代化 , 2022 ( 6 ): 1 - 7 .
Zhang J , Qiu LL . A text classification model based on BERT and pooling operation [J ] . Comput Mod , 2022 ( 6 ): 1 - 7 .
张晓晓 , 庞 婷 . 浅谈人工智能特点及在医学中应用的几个阶段 [J ] . 福建电脑 , 2017 , 33 ( 3 ): 106 , 161 .
Zhang XX , Pang T . Talking about the characteristics of artificial intelligence and several stages of its application in medicine [J ] . J Fujian Comput , 2017 , 33 ( 3 ): 106 , 161 .
邰 雪 , 赵天祺 , 孙亚茹 , 等 . 人工智能在临床医学的新型优势 [J ] . 内蒙古医科大学学报 , 2021 , 43 ( 3 ): 316 - 319 .
Tai X , Zhao TQ , Sun YR , et al . New advantages of artificial intelligence in clinical medicine [J ] . J Inn Mong Med Univ , 2021 , 43 ( 3 ): 316 - 319 .
0
浏览量
6
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621