Page 115 - 《中国药房》2023年19期
P. 115

·药师与药学服务·


          药物性肝损伤自动监测与评估系统的研发与应用
                                                                                     Δ

                                                  2
                 1*
                                          1
                                  1
                                                                   2 #
                                                           2
                          1
          艾 超 ,冀召帅 ,张雅鑫 ,刘 岸 ,周学思 ,陈忠昊 ,吴 及 (1.清华大学附属北京清华长庚医院/清华大学
          临床医学院药学部,北京 102218;2.清华大学电子工程系,北京 100084)
          中图分类号  R975+.5      文献标志码  A      文章编号  1001-0408(2023)19-2409-05
          DOI  10.6039/j.issn.1001-0408.2023.19.18
          摘  要  目的  建立药物性肝损伤(DILI)自动监测与评估系统(DILI-SAS),提升临床DILI的诊断效率。方法  利用自然语言处理
          技术对全部住院病历数据进行挖掘和利用,并结合 Roussel Uclaf 因果关系评价法(RUCAM)构建 DILI-SAS。对 2022 年 8 月-
          2023年1月期间在清华大学附属北京清华长庚医院住院的19 445例患者病历进行检测,验证系统性能并人工分析DILI患者基本
          资料及第一怀疑药物分布情况。结果  DILI-SAS整体准确率为91.95%,召回率为93.20%;共监测出75例DILI病例,DILI发生率
          为385.70/10万人;通过人机耦合的方式开展DILI监测效率比人工独立监测约提高了60倍;75例DILI中主要以男性(61.33%)、60
          岁以上(56.00%)患者为主,肝损伤临床分型主要是肝细胞损伤型(69.33%),潜伏期主要集中在用药后5~90 d(62.67%),RUCAM
          评分在3~5分之间最多(66.67%);第一怀疑药物的药理分布主要为二氢吡啶类、羟甲基戊二酸单酰辅酶A还原酶抑制剂、质子泵
          抑制剂等,具体药物有阿托伐他汀、奥美拉唑、头孢曲松、甲硝唑等。结论  建立的DILI-SAS在保障系统准确度的基础上,能提升
          DILI评价时效性,可为临床DILI的早期识别、诊断、评价提供解决方案。
          关键词  药物性肝损伤;自然语言处理技术;自动监测与评估系统;不良反应;因果关系评价


          Development and application of drug-induced liver injury surveillance and assessment system
                                                         1
                                                                                         2
                                                                       2
                                                                                                 2
                               1
                 1
                                               1
          AI Chao ,JI Zhaoshuai ,ZHANG Yaxin ,LIU An ,ZHOU Xuesi ,CHEN Zhonghao ,WU Ji [1.  Dept.  of
          Pharmacy,  Beijing  Tsinghua  Changgung  Hospital (BTCH) Affiliated  to  Tsinghua  University/School  of  Clinical
          Medicine,  Tsinghua  University,  Beijing  102218,  China;2.  Dept.  of  Electronic  Engineering,  Tsinghua
          University, Beijing 100084, China]
          ABSTRACT   OBJECTIVE  To  establish  the  drug-induced  liver  injury (DILI)  surveillance  and  assessment  system (DILI-SAS),
          and  to  improve  the  diagnostic  efficiency  of  clinical  DILI.  METHODS  The  DILI-SAS  was  constructed  by  using  natural  language
          processing  technology  to  mine  and  utilize  all  inpatient  medical  record  data,  and  combined  with  Roussel Uclaf causality  assessment
          method (RUCAM). The medical records of 19 445 hospitalized patients from August 2022 to January 2023 were detected to verify
          the performance of the system and manually analyze the basic data of patients with DILI and the distribution of the first suspected
          drugs.  RESULTS  The  overall  accuracy  rate  of  the  DILI-SAS  system  was  91.95%,  and  the  recall  rate  was  93.20%.  Seventy-five
          DILI  cases  were  detected,  and  the  DILI  incidence  rate  was  385.70/100  000  people. The  efficiency  of  DILI  monitoring  by  human-
          computer  coupling  was  increased  by  about  60  times  of  manual  monitoring;  males (61.33%)  and  patients  over  60  years  old
         (56.00%)  were  the  most  common  in  the  75  cases  of  DILI.  The  clinical  type  of  liver  injury  was  hepatocyte  injury (69.33%),  the
          incubation period was mainly 5-90 days after treatment (62.67%), and the RUCAM score between 3 and 5 was the most common
         (66.67%); pharmacological distribution of the first suspected drugs was mainly dihydropyridines, HMG CoA reductase inhibitors,
          proton  pump  inhibitors,  etc.  The  specific  drugs  were  atorvastatin,  omeprazole,  ceftriaxone,  metronidazole  and  other  drugs.
          CONCLUSIONS  The  establishment  of  DILI-SAS  can  improve  the  evaluation  efficiency  on  the  basis  of  ensuring  the  accuracy
          degree, and provide a solution for the early identification, diagnosis and evaluation of clinical DILI.
          KEYWORDS    drug-induced  liver  injury;  natural  language  processing;  surveillance  and  assessment  system;  adverse  drug
          reactions; causality evaluation


             Δ 基金项目 中国工程院研究课题(No. 12019C9001)                    药物性肝损伤(drug-induced liver injury,DILI)是临
             *第一作者 副主任药师,硕士。研究方向:医工交叉、智慧药学、
                                                             床常见的药物不良反应之一;严重的DILI可进展至急性
          药事管理。E-mail:aichao@btch.edu.cn
                                                                                 [1]
                                                             肝衰竭,甚至发生死亡 ,是药物研发失败、增加警示和
             # 通信作者 教授,博士。研究方向:人工智能、机器学习、自然语
          言处理、模式识别数据挖掘。E-mail:wuji_ee@tsinghua.edu.cn        撤市的重要原因,受到医药行业的高度重视                      [2―3] 。据

          中国药房  2023年第34卷第19期                                              China Pharmacy  2023 Vol. 34  No. 19    · 2409 ·
   110   111   112   113   114   115   116   117   118   119   120