J Gen Intern Med:机器学习模型能准确预测多病患者1年死亡率

2018-08-03 王淳 环球医学

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。

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。

背景:预测临床多样化的多病住院患者队列的死亡非常困难。基于电子病历记录(EMR)数据研发1年死亡风险预后模型可改善临终关怀计划并对研究的风险进行调整。

目的:旨在考察患者住院末期人口统计学、生命体征和实验室数据集是否可准确用于量化其1年死亡风险。

设计:使用与国家死亡注册登记相连的电子病历记录数据进行的回顾性研究。

参与者:共计纳入4年期间6家医院的59848名住院患者。

主要测量:住院末期生命体征、全血细胞计数、基本和完整代谢组、人口统计学信息、ICD编码。首要结局指标为1年内死亡率。

结果:在验证数据集上检测模型性能。随机森林(RF)比逻辑回归(LR)模型在鉴别能力上更具优势。使用住院最终48小时的人口统计学、生命体征和实验室数据的最终数据集建立的用于预测1年内死亡的RF模型,其曲线下面积(AUC)为0.86(0.85~0.87)。年龄、血尿素氮、血小板计数、血红蛋白、肌酐是RF模型中最重要的变量。仅使用合并症变量的模型具有最低的AUC。具有较高死亡概率的患者中,RF模型低估率不超过10%。

结论:患者住院末期EMR数据集能准确用于评估多病住院患者的1年死亡风险。

原始出处:


评论区 (4)
#插入话题
  1. [GetPortalCommentsPageByObjectIdResponse(id=1688357, encodeId=f6c9168835e44, 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=154, 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=Sat Oct 20 00:02:00 CST 2018, time=2018-10-20, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583148, encodeId=fa74158314879, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=176, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1609016, encodeId=9f9e16090163e, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=159, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047595, encodeId=cb68104e595fd, 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=144, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Fri Aug 03 22:02:00 CST 2018, time=2018-08-03, status=1, ipAttribution=)]
  2. [GetPortalCommentsPageByObjectIdResponse(id=1688357, encodeId=f6c9168835e44, 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=154, 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=Sat Oct 20 00:02:00 CST 2018, time=2018-10-20, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583148, encodeId=fa74158314879, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=176, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1609016, encodeId=9f9e16090163e, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=159, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047595, encodeId=cb68104e595fd, 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=144, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Fri Aug 03 22:02:00 CST 2018, time=2018-08-03, status=1, ipAttribution=)]
    2018-08-05 ms6279672939590805

    #机器#

    0

  3. [GetPortalCommentsPageByObjectIdResponse(id=1688357, encodeId=f6c9168835e44, 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=154, 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=Sat Oct 20 00:02:00 CST 2018, time=2018-10-20, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583148, encodeId=fa74158314879, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=176, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1609016, encodeId=9f9e16090163e, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=159, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047595, encodeId=cb68104e595fd, 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=144, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Fri Aug 03 22:02:00 CST 2018, time=2018-08-03, status=1, ipAttribution=)]
    2018-08-05 ms3994565386320060

    #Med#

    0

  4. [GetPortalCommentsPageByObjectIdResponse(id=1688357, encodeId=f6c9168835e44, 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=154, 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=Sat Oct 20 00:02:00 CST 2018, time=2018-10-20, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1583148, encodeId=fa74158314879, content=<a href='/topic/show?id=f6e1611840d' target=_blank style='color:#2F92EE;'>#机器#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=176, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1609016, encodeId=9f9e16090163e, content=<a href='/topic/show?id=eb6b1145939' target=_blank style='color:#2F92EE;'>#Med#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=159, 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=Sun Aug 05 10:02:00 CST 2018, time=2018-08-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1047595, encodeId=cb68104e595fd, 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=144, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=f0620, createdName=CHANGE, createdTime=Fri Aug 03 22:02:00 CST 2018, time=2018-08-03, status=1, ipAttribution=)]
    2018-08-03 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