Research and applications: Breast cancer survivability prediction using labeled,unlabeled, and pseudo-labeled patient data

Background

Prognostic studies of breast cancer survivability have been aided by machine learning algorithms, which can predict the survival of a particular patient based on historical patient data. However, it is not easy to collect labeled patient records. It takes at least 5 years to label a patient record as ‘survived’ or ‘not survived’. Unguided trials of numerous types of oncology therapies are also very expensive. Confidentiality agreements with doctors and patients are also required to obtain labeled patient records.

Proposed method

These difficulties in the collection of labeled patient data have led researchers to consider semi-supervised learning (SSL), a recent machine learning algorithm, because it is also capable of utilizing unlabeled patient data, which is relatively easier to collect. Therefore, it is regarded as an algorithm that could circumvent the known difficulties. However, the fact is yet valid even on SSL that more labeled data lead to better prediction. To compensate for the lack of labeled patient data, we may consider the concept of tagging virtual labels to unlabeled patient data, that is, ‘pseudo-labels,’ and treating them as if they were labeled.

Results

Our proposed algorithm, ‘SSL Co-training’, implements this concept based on SSL. SSL Co-training was tested using the surveillance, epidemiology, and end results database for breast cancer and it delivered a mean accuracy of 76% and a mean area under the curve of 0.81.     

Research and applications: Learning regular expressions for clinical text classification

Objectives

Natural language processing (NLP) applications typically use regular expressions that have been developed manually by human experts. Our goal is to automate both the creation and utilization of regular expressions in text classification.

Methods

We designed a novel regular expression discovery (RED) algorithm and implemented two text classifiers based on RED. The RED+ALIGN classifier combines RED with an alignment algorithm, and RED+SVM combines RED with a support vector machine (SVM) classifier. Two clinical datasets were used for testing and evaluation: the SMOKE dataset, containing 1091 text snippets describing smoking status; and the PAIN dataset, containing 702 snippets describing pain status. We performed 10-fold cross-validation to calculate accuracy, precision, recall, and F-measure metrics. In the evaluation, an SVM classifier was trained as the control.

Results

The two RED classifiers achieved 80.9–83.0% in overall accuracy on the two datasets, which is 1.3–3% higher than SVM''s accuracy (p<0.001). Similarly, small but consistent improvements have been observed in precision, recall, and F-measure when RED classifiers are compared with SVM alone. More significantly, RED+ALIGN correctly classified many instances that were misclassified by the SVM classifier (8.1–10.3% of the total instances and 43.8–53.0% of SVM''s misclassifications).

Conclusions

Machine-generated regular expressions can be effectively used in clinical text classification. The regular expression-based classifier can be combined with other classifiers, like SVM, to improve classification performance.     

产ESBLs革兰阴性杆菌的检测及耐药性分析

目的：分析革兰阴性杆菌产超广谱β内酰胺酶（ESBLs）的现状和耐药性，指导临床合理使用抗生素。方法：采用美国国家临床实验室标准化委员会（NCCLS）表型筛选和确认试验检测产ESBLs菌株，并采用K—B法对临床常用抗生素进行体外药敏试验。结果：67株革兰阴性杆菌中共检测到ESBLs阳性的菌株19株，阳性率为28．4％。结论：临床分离的革兰阴性杆菌中产ESBLs的菌株分离率较高，而且产酶株多重耐药，碳氢霉烯类为首选抗生素。     

泌尿生殖道支原体检测及药敏结果分析

目的了解疑似非淋菌性尿道炎(NGU)患者解脲支原体(Uu)和人型支原体(Mh)的感染情况和耐药性。方法采用珠海益民生物工程制品厂提供的Uu和Mh试剂盒进行支原体培养、鉴定和药敏试验。结果798份被检标本中,检出支原体阳性275份,总检出率34.5%,男性检出率19.3%,女性检出率45.3%,女性明显高于男性(P<0.001);Uu、Mh、Uu Mh检出率均以女性高于男性。单纯Uu感染以交沙霉素、强力霉素、罗红霉素、克拉霉素和美满霉素的耐药性较低(1.8%~14.3%);Mh感染以交沙霉素、强力霉素和美满霉素的耐药性较低,为11.1%;对Uu Mh混合感染耐药性较高,仅交沙霉素的敏感率较高,为82.2%。结论对NGU患者应作支原体培养和药敏试验,动态监测其耐药性,指导临床医生合理用药,以减少耐药菌株的产生。     

鲍曼不动杆菌的临床分布与药敏分析

目的了解鲍曼不动杆菌的临床分布情况及耐药特点。方法分析我院2008年2月-2009年10月静脉血标本中检出鲍曼不动杆菌的住院患者治疗情况,对鲍曼不动杆菌的科室分布、伴发病原菌情况进行统计学分析;并按临床经验用药与药敏结果是否相符分为两组,各7例;比较两组的治疗有效率。结果重症监护室送检标本阳性率占40.91%,肝胆外科占22.73%;药敏试验显示,鲍曼不动杆菌对头孢哌酮/舒巴坦耐药率最低（47.6%）,其次是氨苄西林/舒巴坦（72.7%）、亚胺培南和美罗培南（81.8%）。相符组有效率85.71%;不符组有效率57.14%。结论鲍曼不动杆菌感染常见于重症监护室;根据药敏结果用药,对指导临床治疗鲍曼不动杆菌具有重要意义。     

303株肺炎克雷伯杆菌的药敏结果及耐药性分析

目的：探讨肺炎克雷伯杆菌的药敏结果及其对临床常用药物的耐药性,为合理用药提供依据。方法回顾性分析2011年1月至2014年11月我院门诊和住院患者送检的痰标本中分离出的非重复性肺炎克雷伯杆菌的数量以及产超广谱β-内酰胺酶(ESBLs)检出率和耐药谱。结果1327份痰标本中分离出303株肺炎克雷伯杆菌,检出率为22.8%,其中产ESBLs检出137株,占45.2%。产ESBLs肺炎克雷伯菌青霉素类100%耐药,头孢类78.8%以上耐药,且以成人组居多,而氨基糖苷类在产ESBLs肺炎克雷伯菌中耐药性最低的是阿米卡星,占31.4%。β-内酰胺酶抑制剂占35.1%~43.8%、喹若酮类耐药率占46.7%。结论长期动态监测肺炎克雷伯杆菌的药敏及耐药趋势,积极筛查肺炎克雷伯杆菌产ESBLs者对合理应用抗生素至关重要。     

临床大肠埃希菌感染分布与药物敏感分析研究

目的 研究大肠埃希菌临床分布及其耐药情况,为临床医生提供帮助.方法 采用VITEK 2 Compact鉴定系统,对临床感染患者的标本进行病原菌分离培养鉴定和体外药敏试验.结果 在694株大肠埃希菌中,尿液标本分离率最高(47.6%);超广谱β-内酰胺酶(ESBLs)阳性率为60.8%,其中阳性菌株对氨苄西林、氨苄西林/舒巴坦、头孢替坦、头孢他啶、头孢曲松、头孢吡肟、环丙沙星和复方新诺明等有较高的耐药率,阴性菌株对大部分抗菌药物有较低耐药率.结论 产ESBLs大肠埃希菌比阴性菌株具有较高的耐药率,临床要重视对大肠埃希菌ESBLs的检测.     

1887份血培养病原菌分布及药物敏感性分析

目的 分析我院血培养标本各种病原菌分布情况及主要病原菌的耐药特点.方法 不同患者选择合适的标准需氧瓶、厌氧瓶,中和抗生索培养瓶及儿童专用培养瓶,采用BACT/ALERT3D全自动血培养仪对1887份血液标本进行血培养,分离所得菌株用MICROSCANPc12/NC21鉴定药敏系统进行鉴定和药敏试验.结果 培养时间缩短至5天,血培养的阳性率为8.2%(155/1887),155株阳性病原菌中革兰阳性球菌占43.2%(67/155),革兰阴性杆菌占48.4%(75/155),真菌占7.1%(11/155),革兰阳性杆菌占1.3%(2/155).最常见的病原菌是大肠埃希菌和金黄色葡萄球菌,未发现耐万古霉素的革兰阳性球菌,革兰阴性杆菌对碳青霉烯类抗菌素高度敏感.结论 全自动血培养仪提高了培养阳性率,缩短了培养时间,为血行性感染的早期诊断及合理用药提供实验依据.     

一起成人白喉爆发流行的细菌鉴定及药敏试验

通过对一起成人白喉爆发流行的细菌鉴定及药物试验的详细论述,结论:细菌鉴定及药物试验对白喉的诊断与治疗具有重要意义     

医学大数据研究进展及应用前景

医学大数据具有数据量庞大、结构复杂、分析难度大等特点,包括临床数据、多种组学数据、环境暴露、日常生活习惯、地理位置信息、社交媒体及其他多种与个体健康和疾病状态相关的数据维度.医学大数据的重要应用方向包括群体层面的疾病预防及诊疗体系的评价、特定疾病的机制阐释,逐步完善精准医学知识体系、构建具有自主学习能力的临床决策支持系统等.     

1078例血液细菌培养及药敏分析

目的了解血液培养细菌分离和耐药情况。方法对本院1078例血培养标本细菌分离和耐药情况进行回顾性分析。结果1078份血标本中分离出细菌95株,分离率为8．81％。革兰阴性菌53株。革兰阳性菌42株,其中真菌7株。大肠埃希菌、肺炎克雷伯菌对亚胺培南、美罗培南敏感率100％,万古霉素、替考拉宁对革兰氏阳性球菌敏感率100％。结论掌握本院血培养细菌感染的分布及药敏情况,对临床调整治疗方案,及时发现耐药菌株更好服务于临床有重要意义。     

168株痢疾杆菌的菌群鉴定及药敏试验结果分析

目的了解本地区腹泻患者检出痢疾杆菌菌群分布及对药物敏感情况。方法收集我院肠道门诊2006年6～10月腹泻患者粪便标本进行痢疾杆菌分离,以生化试验和血清学试验进行菌株鉴定分群,以K—B法进行药物敏感试验。结果共分离出168株痢疾杆菌,生化及血清鉴定结果,宋内志贺菌占63．7％,福氏志贺菌占35．1％,鲍氏志贺菌占1．2％,未检出痢疾志贺菌;药敏显示检出菌株对诺氟沙星、奥格门丁的耐药率分别为8.3％、9．5％,对磺胺、氨苄西林、四环素、萘啶酸、利福平有较高的耐药率均超过75％。结论宋内痢疾杆菌为优势菌群,检出菌株对诺氟沙星、奥格门丁的耐药率较低。可为临床使用抗生素提供参考。     

miRNA与肿瘤耐药关系的研究进展

微小RNA(miRNA)参与生命过程中一系列的重要过程,其异常表达与肿瘤的发生、发展密切相关。不同miRNA可呈现出癌基因或抑癌基因样功能,并有一定的组织特异性。一些miRNA以肿瘤细胞中对药物敏感的相关基因为靶点,以此提高抗肿瘤药物的疗效。天然提取物(如大豆异黄酮3、3,'-二吲哚甲烷、儿茶素酸酯等)可改变miRNA表达谱,使肿瘤细胞对传统治疗方法的敏感性增加,提示以特定的miRNA为靶点,通过克服耐药性开辟新的途径,可以改进肿瘤治疗的结果。     

电位滴定法与手动滴定法测定药品含量的比较

目的对比电位滴定法与手动滴定法在测定药品含量方面的效果。方法将我区医疗机构常用药物阿司匹林、盐酸左旋咪唑、氯化钠注射液作为研究对象,分别应用电位滴定法与手动滴定法对上述药品含量进行测定,并对不同检测方法下阿司匹林、盐酸左旋咪唑、氯化钠注射液三类药品的定量检测结果及相对标准偏差进行对比分析。结果对比两种检测方法下的定量检测结果,电位滴定法下对阿司匹林、盐酸左旋咪唑、氯化钠注射液的检测结果与手动电位滴定法无明显差异(P0.05)。两种检测方法下的相对标准偏差对比,电位滴定法下对阿司匹林、盐酸左旋咪唑、氯化钠注射液的相对标准偏差均显著低于手动滴定法,差异有统计学意义(P0.05)。结论电位滴定法对药品含量的检测结果准确可靠,相对标准偏差小,具有精密度高的优势,可逐步取代传统手动滴定法,并在药品含量检测分析领域中推广应用。     

斑马鱼肿瘤异种移植模型在抗癌药敏感性评价中的应用

目的应用人类肺癌、胃癌和肝癌细胞斑马鱼异种移植模型,分别评价5种临床常用抗癌药的体内敏感性。方法分别建立斑马鱼肺癌A549、胃癌SGC-7901和肝癌Hep G2异种移植模型,顺铂、紫杉醇、长春瑞滨、恩度和贝伐单抗设计3个剂量分别处理斑马鱼肺癌A549移植模型,紫杉醇、伊立替康、羟基脲、顺铂和5-氟尿嘧啶(5-fluorouracil,5-FU)设计3个浓度或剂量分别处理斑马鱼胃癌SGC-7901移植模型,阿霉素、吉西他滨、羟基脲、顺铂和5-氟尿嘧啶设计3个浓度或剂量分别处理斑马鱼肝癌Hep G2移植模型。实验结束后,使用荧光显微镜进行体内肿瘤定量图像分析,计算药物对斑马鱼体内肿瘤生长抑制率,通过与模型对照组相比,分析是否具有统计学意义。结果受试的抗肿瘤药物在斑马鱼肿瘤异种移植模型中均有效,并且基本都呈剂量依赖性。在抗肺癌A549药敏试验中,药效从高到低分别为贝伐单抗(65%)顺铂(55%)长春瑞滨(40%)恩度(39%)紫杉醇(27%);在抗胃癌SGC-7901药敏试验中,药效从高到底分别为羟基脲(46%)5-FU(31%)=伊立替康(31%)紫杉醇(26%)顺铂(24%);在抗肝癌Hep G2药敏试验中,药效从高到底分别为顺铂(64%)羟基脲(56%)吉西他滨(46%)阿霉素(45%)5-FU(38%)。结论斑马鱼肿瘤异种移植模型适合用于抗癌药体内药敏试验。     

重庆地区非淋菌性泌尿生殖道感染病原体及耐药性分析

目的:了解重庆地区非淋菌性尿道炎(NGU)病人的病原体构成及支原体感染耐药状况.方法:对1265例NGU患者的分泌物进行培养、鉴定和12种抗生素药敏试验.结果:1265例病人中,单一病原体感染546例(43.16%),两种混合感染537例(42.46%),CT UU MH三种混合感染182例(14.39%),且男女不同组别间及年龄分布间病原体的构成有显著性差异.UU和MH均对强力霉素最敏感,其次分别为米诺环素和克拉霉素,耐药性最高的均为罗红霉素、红霉素、环丙沙星等.结论:重庆地区NGU患者病原体以UU为主,治疗以强力霉素、米诺环素和克拉霉素等为佳,但应原则上进行培养和药敏试验,以获得最佳效果的治疗作用和最大限度地减少耐药菌株的产生.     

898例泌尿生殖道患者支原体感染的检测及药敏分析

目的了解2010年4月-2011年4月吉林市某医院898例泌尿生殖道感染患者进行解脲脲原体（Uu）和人型支原体（Mh）实验室检测结果进行分析,了解其感染状况及耐药性。方法解脲脲原体（Uu）和人型支原体（Mh）的分离鉴定、半定量计数和抗生素的药物敏感性试验。结果对来自898例患者的标本进行Uu和Mh体外培养,共检出阳性标本397例,阳性检出率为44.21%（397/898）。在阳性标本中,男性占18.14%（72/397）,女性占81.86%（325/397）,女性高于男性。其中,Uu单项感染占74.81%（297/397）,Mh单项感染占3.52%（14/397）,Uu和Mh混合感染占21.67%（86/397）,即Uu〉Uu＋Mh〉Mh。在这三种类型感染中,女性感染的Uu、Mh及Uu＋Mh均大于男性,Uu＋Mh混合感染大有增加趋势。支原体感染的年龄段21-40岁居首位。药敏结果,397例支原体（Uu、Mh、Uu＋Mh）均对强力霉素、美满霉素、交沙霉素较敏感,对罗红霉素、氧氟沙星、阿奇霉素耐药率高,但与各地报告的结果也有差别。结论泌尿生殖道支原体感染以Uu感染为主,大部分细菌都产生耐药性,混合性感染的耐药更加严重。     

泌尿系感染细菌的分布及药敏结果分析

目的探讨本院泌尿系感染细菌的分布及耐药状况。方法统计近两年来尿培养的结果,对658株细菌及药敏结果进行回顾性分析。结果感染的细菌以革兰氏阴性杆菌为主,共522株,占79.3%。革兰氏阴性菌以大肠埃希菌最多,共375株,占57.0%。革兰氏阳性菌为136株,占20.7%,其中屎肠球菌68株,占10.3%,粪肠球菌41株,占6.2%。大肠埃希菌对亚胺培南耐药率最低,肠球菌对万古霉素和替考拉宁的耐药率最低。结论泌尿系感染的细菌以肠杆菌为主,对药物的耐药率明显升高,临床医生应根据药敏结果合理选择抗菌药物进行治疗,不应盲目经验用药,减少和控制细菌的耐药性。     

住院患者医院感染病原菌药物敏感性及相关因素调查

目的调查住院患者医院感染现状,主要病原菌分布及药物敏感性,分析相关危险因素,探讨护理干预措施。方法收集和采集2011年6~9月住院患者和送检菌株,分析主要病原菌及药物敏感性和医院感染的危险因素。结果纳入的调查对象为7281例,发生医院感染158例,感染发生率为2.17%,送检样本以G-菌感染为主,G+病原菌多药耐药率前2位分别为金黄色葡萄球菌、凝固酶阴性葡萄球菌,G-病原菌多药耐药率前2位分别为铜绿假单胞菌、肺炎克雷伯菌。年龄、糖尿病、插管操作、使用呼吸机是医院感染的独立危险因素(P<0.05)。结论多药耐药菌是医院感染的主要致病菌,应进行药敏试验确定敏感药物,高龄、糖尿病、插管操作和使用呼吸机的患者发生医院感染风险高,强化预防护理措施能有效降低医院感染发生率。     

Research and applications: Extracting coordinated patterns of DNA methylation and gene expression in ovarian cancer

Objective

DNA methylation, a regulator of gene expression, plays an important role in diverse biological processes including developmental process, carcinogenesis and aging. In particular, aberrant DNA methylation has been largely observed in several types of cancers. Currently, it is important to extract disease-specific gene sets associated with the regulation of DNA methylation.

Materials and methods

Here we propose a novel approach to find the minimum regulatory units of genes, co-methylated and co-expressed gene pairs (MEGP) that are highly correlated gene pairs between DNA methylation and gene expression showing the co-regulatory relationship. To evaluate whether our method is applicable to extract disease-associated genes, we applied our method to a large-scale dataset from the Cancer Genome Atlas extracting significantly associated MEGP and analyzed their functional correlation.

Results

We observed that many MEGP physically interacted with each other and showed high semantic similarity with gene ontology terms. Furthermore, we performed gene set enrichment tests to identify how they are correlated in a complex biological process. Our MEGP were highly enriched in the biological pathway associated with ovarian cancers.

Conclusions

Our approach is useful for discovering coordinated epigenetic markers associated with specific diseases.