北京生物醫(yī)學(xué)工程

基于數(shù)據(jù)挖掘的HIV感染者CD4細(xì)胞計(jì)數(shù)預(yù)測(cè)模型

Data mining models for predicting CD4+T lymphocyte count of HIV-infected patients

作者：陳婕卿朱碧云陳卉黃曉婕

單位：首都醫(yī)科大學(xué)生物醫(yī)學(xué)工程學(xué)院(北京100069)

關(guān)鍵詞： HIV；CD4+T淋巴細(xì)胞計(jì)數(shù)；外周血組分；數(shù)據(jù)挖掘；預(yù)測(cè)模型

分類(lèi)號(hào)：

出版年·卷·期（頁(yè)碼）：2013·32·5（479-484）

摘要：

目的探索利用數(shù)據(jù)挖掘技術(shù)預(yù)測(cè)CD4+ T淋巴細(xì)胞計(jì)數(shù)<350個(gè)/μL和<500個(gè)/μL的可能性和效果，從而為CD4+ T淋巴細(xì)胞計(jì)數(shù)預(yù)測(cè)模型的選取提供參考依據(jù)。方法收集345名HIV感染男男性接觸者的2837例總淋巴細(xì)胞計(jì)數(shù)、血紅蛋白、血小板計(jì)數(shù)、白細(xì)胞計(jì)數(shù)和紅細(xì)胞計(jì)數(shù)，分別建立基于Logistic回歸、線(xiàn)性判別分析、決策樹(shù)、反向傳播多層感知機(jī)和徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)模型，并對(duì)預(yù)測(cè)效果進(jìn)行10折交叉驗(yàn)證。利用敏感度、特異度、陽(yáng)性預(yù)測(cè)值、陰性預(yù)測(cè)值和受試者操作特征(ROC)曲線(xiàn)下面積對(duì)5種預(yù)測(cè)模型的性能進(jìn)行評(píng)價(jià)。結(jié)果上述5種模型預(yù)測(cè)CD4<350個(gè)/μL的ROC曲線(xiàn)下面積(Az)分別為0.698、0.697、0.706、0.746和0.745，預(yù)測(cè)CD4<500個(gè)/μL的Az值分別為0.735、0.737、0.724、0.707和0.714，均高于單獨(dú)使用總淋巴細(xì)胞計(jì)數(shù)(Az值分別為0.657和0.691)進(jìn)行預(yù)測(cè)的效果。結(jié)論數(shù)據(jù)挖掘模型在預(yù)測(cè)CD4+T淋巴細(xì)胞計(jì)數(shù)方面具有一定水平，不同模型在完成不同預(yù)測(cè)任務(wù)時(shí)表現(xiàn)出了不同性能。

Objective To investigate the feasibility and performance of data mining technology for predicting a CD4+ T lymphocyte count of less than 350 cells/μL and 500 cells/μL in HIV-infected patients，respectively，so as to provide a reference for the selection of model for predicting CD4 + T lymphocyte count.Methods Total lymphocyte counts (TLC)，hemoglobin，platelet count，white blood cell count and red blood cell count of 2 837 samples，collected from 345 HIV-infected men who have sex with men，were used to build five predictive models，including Logistic regression model，linear discriminate analysis model，decision tree，BP-based multi-layer perceptron and radial basis function neural network，which were then tested by the method of 10-fold cross validation.The predictive performances of the five models were assessed and compared by measures of sensitivity，specificity，positive predictive value，negative predictive value and area under the receiver operating characteristic (ROC) curve. Results Areas under the ROC curves (Az) of the five models for predicting a CD4+T lymphocyte count<350 cells/ μL were 0.698，0.697，0.706，0.746 and 0.745，respectively，and those for predicting a CD4+T lymphocyte count<500 cells/ μL were 0.735，0.737，0.724，0.707 and 0.714，respectively.All of them were greater than those (0.657 and 0.691，respectively) for TLC as a stand-alone predictor.Conclusions The data mining models for predicting CD4+T lymphocyte count have a high performance，and different models for different prediction tasks may have different performances.

參考文獻(xiàn)：

［1］World Health Organization.Scaling up antiretroviral therapy in resource-limited settings: Treatment guidelines for a public health approach［EB/OL］.(2012-7-24)http://www.who.int/.
［2］中華醫(yī)學(xué)會(huì)感染病學(xué)分會(huì)艾滋病學(xué)組．艾滋病診療指南（2011版）［J］．中華臨床感染病雜志，2011，4（6）：321-330.
AIDS Group，Society of Infectious Diseases，Chinese Medical Association.Guideline of diagnosis and treatment for AIDS(2011)［J］.Chinese Journal of Infectious Diseases，2011，4(6): 321-330.
［3］Thompson MA，Aberg JA，Cahn P，et al.2010 Recommendations of the International AIDS Society-USA Panel［J］.JAMA，2010，304(3): 321-333.
［4］Gupta A，Gupte N，Bhosale R，et al.Low sensitivity of total lymphocyte count as a surrogate marker to identify antepartum and postpartum Indian women who require antiretroviral therapy［J］.JAIDS，2007，46: 338-342.
［5］Chen RY，Westfall AO，Hardin JM，et al.Complete blood cell count as a surrogate CD4 cell marker for HIV monitoring in resource-limited settings［J］.JAIDS，2007，44(5): 525-530.
［6］Singh Y，Mars M.Support vector machines to forecast changes in CD4 count of HIV-1 positive patients［J］.Scientific Research and Essays，2010，5(17): 2384-2390.
［7］王景泉，沈成利，郭彩萍，等．成人HIV/AIDS患者CD4+T淋巴細(xì)胞與淋巴細(xì)胞總數(shù)的關(guān)系及其意義［J］．中國(guó)全科醫(yī)學(xué),2006,9(22):1859-1861.
Wang Jingquan，Shen Chengli，Guo Caiping，et al.Relationship and significance of CD4+ T cells and total lymphocytes in adult HIV/AIDS patients［J］.Chinese General Practice，2006，9(22): 1859-1861.
［8］韓揚(yáng)，邱志峰，李太生，等．艾滋病患者淋巴細(xì)胞數(shù)和CD4+T細(xì)胞計(jì)數(shù)的相關(guān)性研究［J］．中華檢驗(yàn)醫(yī)學(xué)雜志，2006，29（7）：596-600.
Han Yang，Qiu Zhifeng，Li Taisheng，et al.Study on the correlation between total lymphocyte counts and CD4+ T cell counts in HIV/AIDS patients［J］.Chinese Journal of Laboratory Medicine，2006，29(7): 596-600.
［9］WANG Yuming，LIANG Shuying，YU Erman，et al.Correlation analysis on total lymphocyte count and CD4 count in HIV-infected patients: a retrospective evaluation［J］.Journal of Huazhong University of Science Technology ［Medical Science］，2011，31: 712-716.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频