ARCH PATHOL LAB MED:利用机器学习简化临床实验室中质谱数据的质量审查

2019-10-22 gladiator MedSci原创

临床质谱仪(MS)检测的周转时间和工作效率会影响将检测结果通知给病人的时间,这主要是由于MS数据分析质量手工核查时间的影响。

临床质谱仪(MS)检测的周转时间和工作效率会影响将检测结果通知给病人的时间,这主要是由于MS数据分析质量手工核查时间的影响。

本研究的目的是确定使用标准机器学习算法创建的分类模型是否可以验证分析上可接受的MS结果,从而减少手工核查的需求。

研究人员通过气相色谱-质谱分析1267份尿液样本中的THC-COOH获得回顾性数据。这些样本的数据之前都被标记为分析上不可接受或人工审核可以接受。研究人员将数据集随机分成训练数据和测试数据(分别包括848419个样本),在每组结果中维持可接受(90%)和不可接受(10%)的比例。使用分层10倍交叉验证评估6个监督机器学习算法的能力区分不可接受的和可以接受的分析训练数据集的结果。使用召回率最高的分类器构建最终模型,并根据测试数据集评估其性能。

6个分类器的比较测试中,基于支持向量机算法的模型的查全率和可接受精度最高。优化后,该模型能够正确识别测试数据集(100%召回率)中所有不可接受的结果,准确率为81%

研究表明,自动数据核查确定了测试数据集中所有分析上不可接受的分析,同时将手动核查要求降低了大约87%。这种自动化策略可以将手工核查集中在可能有问题的分析上,从而在不降低质量的情况下提高处理量和周转时间。

原始出处:

Min Yu, MD, PhD; Lindsay A. L. Bazydlo, PhD;Streamlining Quality Review of Mass Spectrometry Data in the Clinical Laboratory by Use of Machine Learning

本文系梅斯医学(MedSci)原创编译整理,转载需授权!


版权声明:
本网站所有内容来源注明为“梅斯医学”或“MedSci原创”的文字、图片和音视频资料,版权均属于梅斯医学所有。非经授权,任何媒体、网站或个人不得转载,授权转载时须注明来源为“梅斯医学”。其它来源的文章系转载文章,或“梅斯号”自媒体发布的文章,仅系出于传递更多信息之目的,本站仅负责审核内容合规,其内容不代表本站立场,本站不负责内容的准确性和版权。如果存在侵权、或不希望被转载的媒体或个人可与我们联系,我们将立即进行删除处理。
在此留言
评论区 (5)
#插入话题
  1. [GetPortalCommentsPageByObjectIdResponse(id=1941563, encodeId=f0b9194156311, content=<a href='/topic/show?id=108022e76b3' target=_blank style='color:#2F92EE;'>#临床实验#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=38, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=22776, encryptionId=108022e76b3, topicName=临床实验)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=6779163, createdName=liuhuangbo, createdTime=Sat Jun 06 17:34:00 CST 2020, time=2020-06-06, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1786295, encodeId=575c1e86295e7, content=<a href='/topic/show?id=569f13e9045' target=_blank style='color:#2F92EE;'>#Pathol#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=13790, encryptionId=569f13e9045, topicName=Pathol)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=4b65161, createdName=yb6560, createdTime=Thu Nov 07 08:34:00 CST 2019, time=2019-11-07, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1553371, encodeId=1e2815533e116, content=<a href='/topic/show?id=81bd923e559' target=_blank style='color:#2F92EE;'>#质谱#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=35, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=92375, encryptionId=81bd923e559, topicName=质谱)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=96fd14366106, createdName=jeanqiuqiu, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583210, encodeId=780515832103b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=33, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61184, encryptionId=f6e1611840d, topicName=机器)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=13dc16973127, createdName=ms6279672939590805, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610046, encodeId=7dc01610046b2, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=11459, encryptionId=eb6b1145939, topicName=Med)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=552a19396740, createdName=ms3994565386320060, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=)]
  2. [GetPortalCommentsPageByObjectIdResponse(id=1941563, encodeId=f0b9194156311, content=<a href='/topic/show?id=108022e76b3' target=_blank style='color:#2F92EE;'>#临床实验#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=38, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=22776, encryptionId=108022e76b3, topicName=临床实验)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=6779163, createdName=liuhuangbo, createdTime=Sat Jun 06 17:34:00 CST 2020, time=2020-06-06, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1786295, encodeId=575c1e86295e7, content=<a href='/topic/show?id=569f13e9045' target=_blank style='color:#2F92EE;'>#Pathol#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=13790, encryptionId=569f13e9045, topicName=Pathol)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=4b65161, createdName=yb6560, createdTime=Thu Nov 07 08:34:00 CST 2019, time=2019-11-07, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1553371, encodeId=1e2815533e116, content=<a href='/topic/show?id=81bd923e559' target=_blank style='color:#2F92EE;'>#质谱#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=35, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=92375, encryptionId=81bd923e559, topicName=质谱)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=96fd14366106, createdName=jeanqiuqiu, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583210, encodeId=780515832103b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=33, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61184, encryptionId=f6e1611840d, topicName=机器)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=13dc16973127, createdName=ms6279672939590805, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610046, encodeId=7dc01610046b2, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=11459, encryptionId=eb6b1145939, topicName=Med)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=552a19396740, createdName=ms3994565386320060, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=)]
    2019-11-07 yb6560
  3. [GetPortalCommentsPageByObjectIdResponse(id=1941563, encodeId=f0b9194156311, content=<a href='/topic/show?id=108022e76b3' target=_blank style='color:#2F92EE;'>#临床实验#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=38, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=22776, encryptionId=108022e76b3, topicName=临床实验)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=6779163, createdName=liuhuangbo, createdTime=Sat Jun 06 17:34:00 CST 2020, time=2020-06-06, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1786295, encodeId=575c1e86295e7, content=<a href='/topic/show?id=569f13e9045' target=_blank style='color:#2F92EE;'>#Pathol#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=13790, encryptionId=569f13e9045, topicName=Pathol)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=4b65161, createdName=yb6560, createdTime=Thu Nov 07 08:34:00 CST 2019, time=2019-11-07, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1553371, encodeId=1e2815533e116, content=<a href='/topic/show?id=81bd923e559' target=_blank style='color:#2F92EE;'>#质谱#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=35, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=92375, encryptionId=81bd923e559, topicName=质谱)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=96fd14366106, createdName=jeanqiuqiu, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583210, encodeId=780515832103b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=33, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61184, encryptionId=f6e1611840d, topicName=机器)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=13dc16973127, createdName=ms6279672939590805, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610046, encodeId=7dc01610046b2, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=11459, encryptionId=eb6b1145939, topicName=Med)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=552a19396740, createdName=ms3994565386320060, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=)]
    2019-10-24 jeanqiuqiu
  4. [GetPortalCommentsPageByObjectIdResponse(id=1941563, encodeId=f0b9194156311, content=<a href='/topic/show?id=108022e76b3' target=_blank style='color:#2F92EE;'>#临床实验#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=38, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=22776, encryptionId=108022e76b3, topicName=临床实验)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=6779163, createdName=liuhuangbo, createdTime=Sat Jun 06 17:34:00 CST 2020, time=2020-06-06, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1786295, encodeId=575c1e86295e7, content=<a href='/topic/show?id=569f13e9045' target=_blank style='color:#2F92EE;'>#Pathol#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=13790, encryptionId=569f13e9045, topicName=Pathol)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=4b65161, createdName=yb6560, createdTime=Thu Nov 07 08:34:00 CST 2019, time=2019-11-07, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1553371, encodeId=1e2815533e116, content=<a href='/topic/show?id=81bd923e559' target=_blank style='color:#2F92EE;'>#质谱#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=35, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=92375, encryptionId=81bd923e559, topicName=质谱)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=96fd14366106, createdName=jeanqiuqiu, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583210, encodeId=780515832103b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=33, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61184, encryptionId=f6e1611840d, topicName=机器)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=13dc16973127, createdName=ms6279672939590805, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610046, encodeId=7dc01610046b2, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=11459, encryptionId=eb6b1145939, topicName=Med)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=552a19396740, createdName=ms3994565386320060, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=)]
  5. [GetPortalCommentsPageByObjectIdResponse(id=1941563, encodeId=f0b9194156311, content=<a href='/topic/show?id=108022e76b3' target=_blank style='color:#2F92EE;'>#临床实验#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=38, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=22776, encryptionId=108022e76b3, topicName=临床实验)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=6779163, createdName=liuhuangbo, createdTime=Sat Jun 06 17:34:00 CST 2020, time=2020-06-06, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1786295, encodeId=575c1e86295e7, content=<a href='/topic/show?id=569f13e9045' target=_blank style='color:#2F92EE;'>#Pathol#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=13790, encryptionId=569f13e9045, topicName=Pathol)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=4b65161, createdName=yb6560, createdTime=Thu Nov 07 08:34:00 CST 2019, time=2019-11-07, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1553371, encodeId=1e2815533e116, content=<a href='/topic/show?id=81bd923e559' target=_blank style='color:#2F92EE;'>#质谱#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=35, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=92375, encryptionId=81bd923e559, topicName=质谱)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=96fd14366106, createdName=jeanqiuqiu, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583210, encodeId=780515832103b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=33, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61184, encryptionId=f6e1611840d, topicName=机器)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=13dc16973127, createdName=ms6279672939590805, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610046, encodeId=7dc01610046b2, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=11459, encryptionId=eb6b1145939, topicName=Med)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=552a19396740, createdName=ms3994565386320060, createdTime=Thu Oct 24 12:34:00 CST 2019, time=2019-10-24, status=1, ipAttribution=)]

相关资讯

CELL:机器学习揭示抗生素作用机制

最近,研究人员开发了一个集成的“白盒子”生化筛选,网络建模和机器学习方法,以揭示因果机制,并应用这种方法来理解抗生素的功效。

机器学习:准确率(Precision)、召回率(Recall)、F值(F-Measure)、ROC曲线、PR曲线

在机器学习、数据挖掘、推荐系统完成建模之后,需要对模型的效果做评价。 业内目前常常采用的评价指标有准确率(Precision)、召回率(Recall)、F值(F-Measure)等,下图是不同机器学习算法的评价指标。下文讲对其中某些指标做简要介绍。 本文针对二元分类器! 本文针对二元分类器!! 本文针对二元分类器!!! 对分类的分类器的评价指标将在以后文章中介绍。 在介绍指标前

Radiology:MRI放射组学机器学习与ADC值在评价前列腺病变的价值

本研究旨在比较术前MRI阅片中比较双参数非对比放射组学机器学习(RML)平均表观扩散系数和放射科医生评价前列腺病变特点的差异。

Sci Rep:肌肉侵入性膀胱癌预后中,机器学习自动化肿瘤芽殖定量能够改善TNM分期

肿瘤芽殖在一些肿瘤类型中是一个独立的预后特征。最近,有研究人员在肌肉侵入性膀胱癌患者中首次报道了肿瘤芽殖与生存评估之间的关系。研究人员利用基于机器学习的方法学来精确的对肿瘤芽进行定量,具体是100名肌肉浸润性膀胱癌患者的所有免疫荧光标签的整张图片分析。更多的是,肿瘤芽殖与TNM(p=0.00089)和pT(p=0.0078)阶段相关。研究人员还基于疾病特异性生存,建立了一个新的分类和回归树模型来对

JACC:经导管主动脉瓣置换术后院内死亡率的机器学习预测模型

机器学习方法可以生成强大的模型来预测TAVR的院内死亡率。

Circulation:采用机器学习预测心肌梗死风险的可能性

目前,心肌肌钙蛋白浓度随患者的年龄、性别和样本时间的变化在诊断方法中尚未得到解释。Than等人计划通过机器学习将这些变量结合起来,以提高患者个体的风险评估。采用机器学习算法(心肌-缺血-损伤-指数[MI3]),将年龄、性别和匹配的心肌肌钙蛋白I浓度综合起来,在3013位患者中进行测试,在7998位疑诊心肌梗死的患者中进行验证。MI3采用梯度增强计算一个值(0-100)来反映个人诊断为1型心肌梗死的