Strontianite-rich carbonatite,containing over 30 vol%carbonate minerals predominantly composed of strontianite(SrCO3),is identified in the Zhengjialiangzi ore segment of the Muluozhai rare earth element(REE)deposit,we...Strontianite-rich carbonatite,containing over 30 vol%carbonate minerals predominantly composed of strontianite(SrCO3),is identified in the Zhengjialiangzi ore segment of the Muluozhai rare earth element(REE)deposit,western Sichuan Province,China.It exhibits a unique mineral assemblage dominated by strontianite,fluorite,bastnäsite,barite,calcite and dolomite,distinguishing it from conventional calcio-,magnesio-,ferro-,or natro-carbonatites.The rock shows extreme enrichment in REEs(ΣREE=47335-64367 ppm),with strong LREE/HREE fractionation[(La/Yb)N=1151-2119]and notably high concentrations of high-value critical REEs(e.g.,Pr,Nd,Tb,Dy),5-10 times greater than those in local calcite-dominated carbonatites.Trace element patterns indicate significant enrichment in REEs,Sr,and Ba,along with depletion in high-field-strength elements(HFSEs;e.g.,Nb,Ta,Zr,Hf).In-situ Sr isotopes of strontianite[(^(87)Sr/^(86)Sr)i=0.706190-0.707305]indicate an enriched mantle source(EMI-EMII).Sr enrichment is attributed to initial mantle source enrichment and extensive fractional crystallization,possibly accompanied by minor wall-rock assimilation.We propose that the strontianite-rich carbonatite formed from a highly evolved,Sr-and REEs-rich carbonatitic magma that intruded into shallow structural breccias,followed by rapid cooling.Its formation is associated with a continuous melt-fluid evolutionary process that is characteristic of carbonatitic systems.展开更多
目的:基于机器学习算法构建人类免疫缺陷病毒/获得性免疫缺陷综合征(human immunodeficiency virus and acquired immunodeficiency syndrome,HIV/AIDS)患者合并马尔尼菲篮状菌(Talaromyces marneffei,TM)感染的诊断模型,以实现辅助早...目的:基于机器学习算法构建人类免疫缺陷病毒/获得性免疫缺陷综合征(human immunodeficiency virus and acquired immunodeficiency syndrome,HIV/AIDS)患者合并马尔尼菲篮状菌(Talaromyces marneffei,TM)感染的诊断模型,以实现辅助早期诊断和提升诊断灵敏度。方法:回顾性收集2020年1月至2023年9月在重庆市公共卫生医疗救治中心共201例HIV/AIDS-Mp1p抗原阳性患者实验室数据,筛选得到确诊TM(TM组)91例和未感染TM(非TM组)110例。将数据通过统计学分析获得2组间差异性指标,并构建logistic回归、随机森林分类器、决策树分类器模型。再通过最小绝对收缩和选择算子(least absolute shrinkage and selection operator,Lasso)回归筛选差异变量,并构建Lasso-logistic回归、随机森林和决策树分类器模型。分析所有模型筛选的高贡献特征指标,采用正确率、精确率、受试者工作特征(receiver operating characteristic,ROC)曲线和曲线下面积(area under the curve,AUC)评价模型的诊断性能。结果:通过TM组与非TM组检验指标比较,删除了白细胞计数和性别2个差异无统计学意义的指标(P>0.05),纳入红细胞计数、血小板计数、血红蛋白含量、C-反应蛋白、白细胞介素-6、降钙素原、年龄、CD4^(+)T淋巴细胞计数、HIV-RNA含量、(1-3)-β-D葡聚糖检测、曲霉半乳甘露聚糖抗原检测11个差异有统计学意义(P<0.05)的指标构建logistic回归模型、决策树和随机森林分类模型。进一步通过Lasso回归分析删除了CD4^(+)T淋巴细胞计数和红细胞计数指标,剩余9个变量纳入构建了Lasso-logistic回归、决策树和随机森林分类模型,其AUC均大于纳入11个变量构建的同种模型,其中随机森林分类模型(n=9)的诊断性能最佳,正确率为0.797、精确率为0.794、AUC=0.822(95%CI=0.719~0.924)。结论:在不同诊断模型中实验室检验指标特征重要性不同,经Lasso回归筛选变量后再构建模型能提高诊断性能,构建的所有模型中随机森林分类模型诊断性能最好。基于机器学习算法和临床检验数据建立诊断模型,有利于辅助临床早期诊断HIV/AIDS合并TM感染。展开更多
基金the National Natural Science Foundation of China(Grant No.42203073 and 41472072)Basic Scientific Research Fund of the Institute of Geology,CAGS(Grant No.J2317)Sichuan Science and Technology Program(Grant No.2023NSFSC0272).
文摘Strontianite-rich carbonatite,containing over 30 vol%carbonate minerals predominantly composed of strontianite(SrCO3),is identified in the Zhengjialiangzi ore segment of the Muluozhai rare earth element(REE)deposit,western Sichuan Province,China.It exhibits a unique mineral assemblage dominated by strontianite,fluorite,bastnäsite,barite,calcite and dolomite,distinguishing it from conventional calcio-,magnesio-,ferro-,or natro-carbonatites.The rock shows extreme enrichment in REEs(ΣREE=47335-64367 ppm),with strong LREE/HREE fractionation[(La/Yb)N=1151-2119]and notably high concentrations of high-value critical REEs(e.g.,Pr,Nd,Tb,Dy),5-10 times greater than those in local calcite-dominated carbonatites.Trace element patterns indicate significant enrichment in REEs,Sr,and Ba,along with depletion in high-field-strength elements(HFSEs;e.g.,Nb,Ta,Zr,Hf).In-situ Sr isotopes of strontianite[(^(87)Sr/^(86)Sr)i=0.706190-0.707305]indicate an enriched mantle source(EMI-EMII).Sr enrichment is attributed to initial mantle source enrichment and extensive fractional crystallization,possibly accompanied by minor wall-rock assimilation.We propose that the strontianite-rich carbonatite formed from a highly evolved,Sr-and REEs-rich carbonatitic magma that intruded into shallow structural breccias,followed by rapid cooling.Its formation is associated with a continuous melt-fluid evolutionary process that is characteristic of carbonatitic systems.
文摘目的:基于机器学习算法构建人类免疫缺陷病毒/获得性免疫缺陷综合征(human immunodeficiency virus and acquired immunodeficiency syndrome,HIV/AIDS)患者合并马尔尼菲篮状菌(Talaromyces marneffei,TM)感染的诊断模型,以实现辅助早期诊断和提升诊断灵敏度。方法:回顾性收集2020年1月至2023年9月在重庆市公共卫生医疗救治中心共201例HIV/AIDS-Mp1p抗原阳性患者实验室数据,筛选得到确诊TM(TM组)91例和未感染TM(非TM组)110例。将数据通过统计学分析获得2组间差异性指标,并构建logistic回归、随机森林分类器、决策树分类器模型。再通过最小绝对收缩和选择算子(least absolute shrinkage and selection operator,Lasso)回归筛选差异变量,并构建Lasso-logistic回归、随机森林和决策树分类器模型。分析所有模型筛选的高贡献特征指标,采用正确率、精确率、受试者工作特征(receiver operating characteristic,ROC)曲线和曲线下面积(area under the curve,AUC)评价模型的诊断性能。结果:通过TM组与非TM组检验指标比较,删除了白细胞计数和性别2个差异无统计学意义的指标(P>0.05),纳入红细胞计数、血小板计数、血红蛋白含量、C-反应蛋白、白细胞介素-6、降钙素原、年龄、CD4^(+)T淋巴细胞计数、HIV-RNA含量、(1-3)-β-D葡聚糖检测、曲霉半乳甘露聚糖抗原检测11个差异有统计学意义(P<0.05)的指标构建logistic回归模型、决策树和随机森林分类模型。进一步通过Lasso回归分析删除了CD4^(+)T淋巴细胞计数和红细胞计数指标,剩余9个变量纳入构建了Lasso-logistic回归、决策树和随机森林分类模型,其AUC均大于纳入11个变量构建的同种模型,其中随机森林分类模型(n=9)的诊断性能最佳,正确率为0.797、精确率为0.794、AUC=0.822(95%CI=0.719~0.924)。结论:在不同诊断模型中实验室检验指标特征重要性不同,经Lasso回归筛选变量后再构建模型能提高诊断性能,构建的所有模型中随机森林分类模型诊断性能最好。基于机器学习算法和临床检验数据建立诊断模型,有利于辅助临床早期诊断HIV/AIDS合并TM感染。
