CLIN CHEM LAB MED:使用机器学习模型对样本混淆进行高精度且可解释的检测

2020-03-19 MedSci原创 MedSci原创

数据校验(增量检查)广泛用于混合样品检测。由于混淆的绝对发生率的特异性和稀疏性不足,因此增量检查的正预测值(PPV)相当低,因为要在大量错误警报中识别出真正的混淆错误会很费力。

数据校验(增量检查)广泛用于混合样品检测。由于混淆的绝对发生率的特异性和稀疏性不足,因此增量检查的正预测值(PPV)相当低,因为要在大量错误警报中识别出真正的混淆错误会很费力。为了克服这个问题,我们通过机器学习开发了一种新的精确检测模型。

受delta增量检查检查的启发,研究人员决定与过去的检查进行比较,并拓宽时间范围。从完整的血细胞计数和生化测试中选择15个常见项目。我们考虑了在我院同时进行的15项检查中≥11项检查。 我们创建了滑动窗口大小为4的连续检查的单个局部时间序列数据。对局部时间序列数据的最后一次检查进行了混洗,以生成人为混淆的案例。将数据集分为开发集和验证集后,然后使用梯度启动决策树(gradient-boosting-decision-tree, GBDT)模型来学习,以检测部分时间序列数据的最后检查结果是否是人为混合结果 。在验证集上对模型的性能进行了评估。

本模型的受试者工作特征曲线(ROC AUC)下面积为0.9983 (bootstrap置信区间[bsCI]: 0.9983 - 0.9985)。

研究结果表明,GBDT模型在检测样品混杂方面更有效。准确性提高将使更多机构能够进行更有效和集中的混合检测,从而提高患者的安全性。

原始出处:

Tomohiro Mitani,Shunsuke Doi, Highly accurate and explainable detection of specimen mix-up using a machine learning model

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=1688359, encodeId=bc7f16883592c, content=<a href='/topic/show?id=fab46121efa' target=_blank style='color:#2F92EE;'>#机器学习模型#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61217, encryptionId=fab46121efa, topicName=机器学习模型)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=2bea28558433, createdName=ms2694732865965676, createdTime=Fri Nov 13 20:33:48 CST 2020, time=2020-11-13, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1669432, encodeId=4d7f16694326f, content=<a href='/topic/show?id=9d7b620395d' target=_blank style='color:#2F92EE;'>#样本#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=62039, encryptionId=9d7b620395d, topicName=样本)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f33226554040, createdName=zhzhxiang, createdTime=Wed Sep 02 12:33:48 CST 2020, time=2020-09-02, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583232, encodeId=d67115832325b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610367, encodeId=46ef161036e10, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=26, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047784, encodeId=3267104e7845e, content=梅斯里提供了很多疾病的模型计算公式,赞一个!, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Thu Mar 19 18:33:48 CST 2020, time=2020-03-19, status=1, ipAttribution=)]
  2. [GetPortalCommentsPageByObjectIdResponse(id=1688359, encodeId=bc7f16883592c, content=<a href='/topic/show?id=fab46121efa' target=_blank style='color:#2F92EE;'>#机器学习模型#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61217, encryptionId=fab46121efa, topicName=机器学习模型)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=2bea28558433, createdName=ms2694732865965676, createdTime=Fri Nov 13 20:33:48 CST 2020, time=2020-11-13, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1669432, encodeId=4d7f16694326f, content=<a href='/topic/show?id=9d7b620395d' target=_blank style='color:#2F92EE;'>#样本#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=62039, encryptionId=9d7b620395d, topicName=样本)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f33226554040, createdName=zhzhxiang, createdTime=Wed Sep 02 12:33:48 CST 2020, time=2020-09-02, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583232, encodeId=d67115832325b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610367, encodeId=46ef161036e10, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=26, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047784, encodeId=3267104e7845e, content=梅斯里提供了很多疾病的模型计算公式,赞一个!, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Thu Mar 19 18:33:48 CST 2020, time=2020-03-19, status=1, ipAttribution=)]
    2020-09-02 zhzhxiang
  3. [GetPortalCommentsPageByObjectIdResponse(id=1688359, encodeId=bc7f16883592c, content=<a href='/topic/show?id=fab46121efa' target=_blank style='color:#2F92EE;'>#机器学习模型#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61217, encryptionId=fab46121efa, topicName=机器学习模型)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=2bea28558433, createdName=ms2694732865965676, createdTime=Fri Nov 13 20:33:48 CST 2020, time=2020-11-13, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1669432, encodeId=4d7f16694326f, content=<a href='/topic/show?id=9d7b620395d' target=_blank style='color:#2F92EE;'>#样本#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=62039, encryptionId=9d7b620395d, topicName=样本)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f33226554040, createdName=zhzhxiang, createdTime=Wed Sep 02 12:33:48 CST 2020, time=2020-09-02, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583232, encodeId=d67115832325b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610367, encodeId=46ef161036e10, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=26, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047784, encodeId=3267104e7845e, content=梅斯里提供了很多疾病的模型计算公式,赞一个!, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Thu Mar 19 18:33:48 CST 2020, time=2020-03-19, status=1, ipAttribution=)]
  4. [GetPortalCommentsPageByObjectIdResponse(id=1688359, encodeId=bc7f16883592c, content=<a href='/topic/show?id=fab46121efa' target=_blank style='color:#2F92EE;'>#机器学习模型#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61217, encryptionId=fab46121efa, topicName=机器学习模型)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=2bea28558433, createdName=ms2694732865965676, createdTime=Fri Nov 13 20:33:48 CST 2020, time=2020-11-13, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1669432, encodeId=4d7f16694326f, content=<a href='/topic/show?id=9d7b620395d' target=_blank style='color:#2F92EE;'>#样本#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=62039, encryptionId=9d7b620395d, topicName=样本)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f33226554040, createdName=zhzhxiang, createdTime=Wed Sep 02 12:33:48 CST 2020, time=2020-09-02, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583232, encodeId=d67115832325b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610367, encodeId=46ef161036e10, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=26, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047784, encodeId=3267104e7845e, content=梅斯里提供了很多疾病的模型计算公式,赞一个!, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Thu Mar 19 18:33:48 CST 2020, time=2020-03-19, status=1, ipAttribution=)]
  5. [GetPortalCommentsPageByObjectIdResponse(id=1688359, encodeId=bc7f16883592c, content=<a href='/topic/show?id=fab46121efa' target=_blank style='color:#2F92EE;'>#机器学习模型#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=61217, encryptionId=fab46121efa, topicName=机器学习模型)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=2bea28558433, createdName=ms2694732865965676, createdTime=Fri Nov 13 20:33:48 CST 2020, time=2020-11-13, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1669432, encodeId=4d7f16694326f, content=<a href='/topic/show?id=9d7b620395d' target=_blank style='color:#2F92EE;'>#样本#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=62039, encryptionId=9d7b620395d, topicName=样本)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f33226554040, createdName=zhzhxiang, createdTime=Wed Sep 02 12:33:48 CST 2020, time=2020-09-02, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583232, encodeId=d67115832325b, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1610367, encodeId=46ef161036e10, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=26, 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=Sat Mar 21 06:33:48 CST 2020, time=2020-03-21, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047784, encodeId=3267104e7845e, content=梅斯里提供了很多疾病的模型计算公式,赞一个!, beContent=null, objectType=article, channel=null, level=null, likeNumber=34, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Thu Mar 19 18:33:48 CST 2020, time=2020-03-19, status=1, ipAttribution=)]
    2020-03-19 CHANGE

    梅斯里提供了很多疾病的模型计算公式,赞一个!

    0

相关资讯

Clin Otolaryngol:通过机器学习模型来预测突发性感官听力损失患者的听力结果

突发性感官听力损失(SSHL)是一种多因子障碍疾病且伴随着高度的异质性,因此,结果具有很大的不同。最近,有研究人员基于4种SSHL机器学习模型来开发预测模型,从而鉴定最好的模型来用于临床。研究包括了1220名SSHL患者,时间为2008年6月到2015年12月。研究发现,在包括149个变量的原生数据测试中,深度信念网络(DBN)模型具有最好的预测能力,预测准确性为77.58%,AUC为0.84。然

J Gen Intern Med:机器学习模型能准确预测多病患者1年死亡率

2018年6月,发表在《J Gen Intern Med》的一项由美国学者进行的概念验证研究,利用多病患者现有的住院末期电子病历记录数据开发和验证用于预测患者1年死亡率的机器学习模型。