目的评价耳穴疗法治疗全膝关节置换术(TKA)术后疼痛的有效性与安全性,为临床提供参考。方法计算机检索中国知识资源总库(CNKI)、中文科技期刊数据库(VIP)、中国学术期刊数据库(万方数据)、中国生物医学文献数据库(CBM)、Cochrane Librar...目的评价耳穴疗法治疗全膝关节置换术(TKA)术后疼痛的有效性与安全性,为临床提供参考。方法计算机检索中国知识资源总库(CNKI)、中文科技期刊数据库(VIP)、中国学术期刊数据库(万方数据)、中国生物医学文献数据库(CBM)、Cochrane Library、PubMed、EMBase、Web of Science建库至2022年7月11日收录的耳穴疗法治疗TKA术后疼痛的随机对照试验文献。2名研究者独立进行文献筛选、数据提取、文献质量评价及交叉核对。采用RevMan5.3软件对静息下视觉模拟量表(VAS)评分、镇痛泵用量及术后不良反应发生率进行统计分析。结果最终纳入7篇文献,共482例患者。Meta分析结果显示:术后12 h VAS[MD=-3.92,95%CI(-6.46,-1.38),P=0.002]、24 h VAS[MD=-1.41,95%CI(-2.17,-0.65),P=0.0003]、36 h VAS[MD=-2.28,95%CI(-3.54,-1.02),P=0.0004]、48 h VAS[MD=-2.63,95%CI(-3.81,-1.46),P<0.0001],2组差异有统计学意义。72 h VAS[MD=-2.91,95%CI(-6.00,0.18),P=0.07],差异无统计学意义。术后12 h镇痛泵用量[MD=-5.64,95%CI(-16.69,-5.41),P=0.32]、72 h镇痛泵用量[MD=-7.29,95%CI(-19.98,5.40),P=0.26],2组差异无统计学意义;术后24 h镇痛泵用量[MD=-3.66,95%CI(-6.35,-0.97),P=0.008]、48 h镇痛泵用量[MD=-3.82,95%CI(-6.22,-1.42),P=0.002],2组差异有统计学意义。膝关节活动度[MD=4.35,95%CI(2.13,6.56),P=0.0001],2组差异有统计学意义。恶心呕吐发生率[OR=0.16,95%CI(0.09,0.26),P<0.00001],头晕嗜睡发生率[OR=0.22,95%CI(0.12,0.43),P<0.00001],尿潴留发生率[OR=0.23,95%CI(0.09,0.57),P=0.002],2组差异有统计学意义;皮肤瘙痒发生率[OR=0.31,95%CI(0.10,0.99),P=0.05]。结论本研究证据显示耳穴疗法可显著改善TKA术后疼痛,减少术后镇痛药物用量,促进术后膝关节活动度恢复,降低术后恶心呕吐、头晕嗜睡、尿潴留的发生风险,对术后皮肤瘙痒有一定程度缓解。展开更多
目的探索可解释机器学习方法在疾病预测中的应用。方法本研究以脓毒血症死亡风险预测为例,从重症监护医学数据库(Medical Information Mart for Intensive Care,MIMIC)-Ⅳ中采集符合纳排标准的19903例脓毒血症(sepsis-3)患者的临床数据...目的探索可解释机器学习方法在疾病预测中的应用。方法本研究以脓毒血症死亡风险预测为例,从重症监护医学数据库(Medical Information Mart for Intensive Care,MIMIC)-Ⅳ中采集符合纳排标准的19903例脓毒血症(sepsis-3)患者的临床数据,利用决策树、逻辑回归、随机森林、XGBoost、轻量梯度提升机(light gradient boosting machine,LightGBM)模型分别构建脓毒血症死亡预测模型。在此基础上,利用全局可解释方法(特征重要性、部分依赖图、个体条件期望、全局代理模型)和局部可解释方法(局部代理模型和Shapely值)对复杂机器学习模型进行解释,探索影响脓毒血症患者预后的危险因素。结果解释性差的机器学习模型的预测性能[模型LightGBM、随机森林、XGBoost的曲线下面积(area under curve,AUC)值分别为0.913、0.892、0.872]高于具有内在解释性的模型(逻辑回归模型AUC=0.779,决策树模型AUC=0.791),并利用全局解释性方法、局部可解释性方法两种类型的解释方法对机器学习模型决策过程进行解释。结论利用全局解释性方法可以解释在整个特征空间内机器学习模型的响应趋势,利用局部可解释性方法可以解释机器学习模型对特定病例的决策过程。展开更多
Land use and land cover(LULC)play a significant role in carbon regulation.South-China accounts for~65%of China’s carbon sink.In Xishuangbanna(South-China),rubber is expanding rapidly creating an urgent need to unders...Land use and land cover(LULC)play a significant role in carbon regulation.South-China accounts for~65%of China’s carbon sink.In Xishuangbanna(South-China),rubber is expanding rapidly creating an urgent need to understand and monitor LULC change and how spatial variation affects carbon storage(CS).This is vital for the formation and implementation of better land use management practices.We studied LULC changes of 22-year period;addressing how these changes have affected the CS.We quantified LULC changes between1988 and 2010 using remote sensing methods and calculated CS changes using InvEST.Results showed that between 1988 and 2010,the rate of deforestation accelerated to 203.2 km^(2)y^(−1)and~23%of forest were lost.Conversion of natural forest to rubber was responsible for 78%of this deforestation.Rubber expansion rate was 153.4 km^(2)y^(−1).Changes to LULC drove a temporal CS reduction 0.223 Tg C/km^(2).Local stakeholders have strong economic interest in converting land to more profitable plantations.Government efforts is required to control land conversion through new policies and incentives to retain natural forest.Assessment of specific potential land use change will be required to avoid promoting the conversion of high carbon storage land uses to low carbon storage land uses.展开更多
文摘目的评价耳穴疗法治疗全膝关节置换术(TKA)术后疼痛的有效性与安全性,为临床提供参考。方法计算机检索中国知识资源总库(CNKI)、中文科技期刊数据库(VIP)、中国学术期刊数据库(万方数据)、中国生物医学文献数据库(CBM)、Cochrane Library、PubMed、EMBase、Web of Science建库至2022年7月11日收录的耳穴疗法治疗TKA术后疼痛的随机对照试验文献。2名研究者独立进行文献筛选、数据提取、文献质量评价及交叉核对。采用RevMan5.3软件对静息下视觉模拟量表(VAS)评分、镇痛泵用量及术后不良反应发生率进行统计分析。结果最终纳入7篇文献,共482例患者。Meta分析结果显示:术后12 h VAS[MD=-3.92,95%CI(-6.46,-1.38),P=0.002]、24 h VAS[MD=-1.41,95%CI(-2.17,-0.65),P=0.0003]、36 h VAS[MD=-2.28,95%CI(-3.54,-1.02),P=0.0004]、48 h VAS[MD=-2.63,95%CI(-3.81,-1.46),P<0.0001],2组差异有统计学意义。72 h VAS[MD=-2.91,95%CI(-6.00,0.18),P=0.07],差异无统计学意义。术后12 h镇痛泵用量[MD=-5.64,95%CI(-16.69,-5.41),P=0.32]、72 h镇痛泵用量[MD=-7.29,95%CI(-19.98,5.40),P=0.26],2组差异无统计学意义;术后24 h镇痛泵用量[MD=-3.66,95%CI(-6.35,-0.97),P=0.008]、48 h镇痛泵用量[MD=-3.82,95%CI(-6.22,-1.42),P=0.002],2组差异有统计学意义。膝关节活动度[MD=4.35,95%CI(2.13,6.56),P=0.0001],2组差异有统计学意义。恶心呕吐发生率[OR=0.16,95%CI(0.09,0.26),P<0.00001],头晕嗜睡发生率[OR=0.22,95%CI(0.12,0.43),P<0.00001],尿潴留发生率[OR=0.23,95%CI(0.09,0.57),P=0.002],2组差异有统计学意义;皮肤瘙痒发生率[OR=0.31,95%CI(0.10,0.99),P=0.05]。结论本研究证据显示耳穴疗法可显著改善TKA术后疼痛,减少术后镇痛药物用量,促进术后膝关节活动度恢复,降低术后恶心呕吐、头晕嗜睡、尿潴留的发生风险,对术后皮肤瘙痒有一定程度缓解。
文摘目的探索可解释机器学习方法在疾病预测中的应用。方法本研究以脓毒血症死亡风险预测为例,从重症监护医学数据库(Medical Information Mart for Intensive Care,MIMIC)-Ⅳ中采集符合纳排标准的19903例脓毒血症(sepsis-3)患者的临床数据,利用决策树、逻辑回归、随机森林、XGBoost、轻量梯度提升机(light gradient boosting machine,LightGBM)模型分别构建脓毒血症死亡预测模型。在此基础上,利用全局可解释方法(特征重要性、部分依赖图、个体条件期望、全局代理模型)和局部可解释方法(局部代理模型和Shapely值)对复杂机器学习模型进行解释,探索影响脓毒血症患者预后的危险因素。结果解释性差的机器学习模型的预测性能[模型LightGBM、随机森林、XGBoost的曲线下面积(area under curve,AUC)值分别为0.913、0.892、0.872]高于具有内在解释性的模型(逻辑回归模型AUC=0.779,决策树模型AUC=0.791),并利用全局解释性方法、局部可解释性方法两种类型的解释方法对机器学习模型决策过程进行解释。结论利用全局解释性方法可以解释在整个特征空间内机器学习模型的响应趋势,利用局部可解释性方法可以解释机器学习模型对特定病例的决策过程。
文摘Land use and land cover(LULC)play a significant role in carbon regulation.South-China accounts for~65%of China’s carbon sink.In Xishuangbanna(South-China),rubber is expanding rapidly creating an urgent need to understand and monitor LULC change and how spatial variation affects carbon storage(CS).This is vital for the formation and implementation of better land use management practices.We studied LULC changes of 22-year period;addressing how these changes have affected the CS.We quantified LULC changes between1988 and 2010 using remote sensing methods and calculated CS changes using InvEST.Results showed that between 1988 and 2010,the rate of deforestation accelerated to 203.2 km^(2)y^(−1)and~23%of forest were lost.Conversion of natural forest to rubber was responsible for 78%of this deforestation.Rubber expansion rate was 153.4 km^(2)y^(−1).Changes to LULC drove a temporal CS reduction 0.223 Tg C/km^(2).Local stakeholders have strong economic interest in converting land to more profitable plantations.Government efforts is required to control land conversion through new policies and incentives to retain natural forest.Assessment of specific potential land use change will be required to avoid promoting the conversion of high carbon storage land uses to low carbon storage land uses.