首页 | 本学科首页   官方微博 | 高级检索  
文章检索
  按 检索   检索词:      
出版年份:   被引次数:   他引次数: 提示:输入*表示无穷大
  收费全文   1562篇
  免费   194篇
  国内免费   48篇
耳鼻咽喉   21篇
儿科学   26篇
妇产科学   7篇
基础医学   329篇
口腔科学   13篇
临床医学   129篇
内科学   229篇
皮肤病学   46篇
神经病学   76篇
特种医学   50篇
外科学   91篇
综合类   239篇
预防医学   246篇
眼科学   21篇
药学   126篇
  1篇
中国医学   104篇
肿瘤学   50篇
  2024年   1篇
  2023年   31篇
  2022年   55篇
  2021年   95篇
  2020年   71篇
  2019年   66篇
  2018年   50篇
  2017年   70篇
  2016年   60篇
  2015年   85篇
  2014年   120篇
  2013年   115篇
  2012年   87篇
  2011年   92篇
  2010年   57篇
  2009年   65篇
  2008年   80篇
  2007年   95篇
  2006年   77篇
  2005年   42篇
  2004年   59篇
  2003年   52篇
  2002年   31篇
  2001年   33篇
  2000年   21篇
  1999年   18篇
  1998年   20篇
  1997年   24篇
  1996年   14篇
  1995年   17篇
  1994年   10篇
  1993年   7篇
  1992年   9篇
  1991年   10篇
  1990年   5篇
  1989年   7篇
  1988年   9篇
  1987年   6篇
  1986年   4篇
  1985年   11篇
  1984年   5篇
  1983年   2篇
  1982年   2篇
  1980年   4篇
  1979年   4篇
  1978年   4篇
  1976年   1篇
  1975年   1篇
排序方式: 共有1804条查询结果,搜索用时 15 毫秒
1.
目的 应用决策树C5.0和Logistic回归分别建立产后压力性尿失禁的风险预测模型,比较2种模型的预测效果。方法 选取2020年7月—2021年1月于山东省某三级甲等医院产后康复门诊就诊的女性505例,采用问卷调查法筛查产后压力性尿失禁并获取产妇的一般资料,采用生物反馈治疗仪评估产妇的盆底肌电值。将所有数据按照7∶3的比例建立训练集与测试集(训练集450例,测试集145例),运用决策树C5.0及Logistic回归建立产后压力性尿失禁的风险预测模型,采用特异度、灵敏度、准确率、阴性预测值、阳性预测值、约登指数和受试者工作特征曲线的曲线下面积对2种模型的预性能进行比较。结果 在训练集中,决策树C5.0与Logistic回归的准确度分别为98.9%、85.6%,灵敏度为94.7%、48.7%,特异度为100.0%、95.4%,阳性预测值为100.0%、74.0%,阴性预测值为98.6%、87.4%,约登指数为94.7%,44.1%,受试者工作特征曲线的曲线下面积为0.974、0.721,2种模型的受试者工作特征曲线的曲线下面积相比较差异具有统计学意义(P<0.05);在测试集中,决策树C5.0和Logistic回归的准确度为87.6%、82.8%,灵敏度为78.6%、46.4%,特异度为89.7%、91.5%,阳性预测值为64.7%、56.5%,阴性预测值为94.6%、87.7%,约登指数为68.3%、37.9%,受试者工作特征曲线的曲线下面积为0.842、0.689,2种模型的受试者工作特征曲线的曲线下面积相比较差异具有统计学意义(P<0.05)。结论 决策树C5.0对产后压力性尿失禁的预测性能优于Logistic回归。  相似文献   
2.
ObjectiveTo develop a prediction model for survival of patients with coronary artery disease (CAD) using health conditions beyond cardiovascular risk factors, including maximal exercise capacity, through the application of machine learning (ML) techniques.MethodsAnalysis of data from a retrospective cohort linking clinical, administrative, and vital status databases from 1995 to 2016 was performed. Inclusion criteria were age 18 years or older, diagnosis of CAD, referral to a cardiac rehabilitation program, and available baseline exercise test results. Primary outcome was death from any cause. Feature selection was performed using supervised and unsupervised ML techniques. The final prognostic model used the survival tree (ST) algorithm.ResultsFrom the cohort of 13,362 patients (60±11 years; 2400 [18%] women), 1577 died during a median follow-up of 8 years (interquartile range, 4 to 13 years), with an estimated survival of 67% up to 21 years. Feature selection revealed age and peak metabolic equivalents (METs) as the features with the greatest importance for mortality prediction. Using these 2 features, the ST generated a long-term prediction with a C-index of 0.729 by splitting patients in 8 clusters with different survival probabilities (P<.001). The ST root node was split by peak METs of 6.15 or less or more than 6.15, and each patient’s subgroup was further split by age or other peak METs cut points.ConclusionApplying ML techniques, age and maximal exercise capacity accurately predict mortality in patients with CAD and outperform variables commonly used for decision-making in clinical practice. A novel and simple prognostic model was established, and maximal exercise capacity was further suggested to be one of the most powerful predictors of mortality in CAD.  相似文献   
3.
背景与目的:胃肠道间质瘤(gastrointestinal stromal tumor,GIST)的生物危险度可分为极低危、低危、中危和高危,术前就危险度进行准确预判对临床制订诊疗方案至关重要。探讨基于超声征象的决策树模型在预测GIST危险度中的应用价值。方法:收集福建医科大学附属协和医院2016年12月—2020年12月收治的206例GIST患者,建立决策树模型,并判断模型预测的准确度。结果:低危、中危和高危3组间病灶长径、短径/长径(short diameter/long diameter,S/L)、肿瘤部位、回声高低、回声均匀性、边界、形态、是否坏死囊变和血流信号的差异均有统计学意义(P均<0.05)。以病灶长径、肿瘤部位、回声均匀性及形态为节点建立的决策树模型预测的准确度为72.33%,其中低危组和高危组预测的准确度可高达80.90%和93.90%。结论:以超声特征为主要指标构建的决策树模型在预测GIST危险度中具有较高的应用价值。  相似文献   
4.
Hepatitis B virus (HBV) DNA is detectable in the nails and hair of patients with chronic HBV infection. However, it remains unclear whether HBV DNA can be detectable in the nails and hair of patients with acute HBV infection. We encountered two cases of children with acute HBV infection. HBV DNA in the nails and hair from the two children was evaluated by real-time PCR. To clarify the characteristics of HBV DNA, full-length HBV genome sequencing and phylogenetic tree analysis were performed. The levels of serum HBV DNA in children of cases 1 and 2 at day 0 were 7.6 Log IU/mL and 7.4 Log IU/mL, respectively. Nail HBV DNA was detected in both children (case 1: 4.6 Log IU/mL at day 0, case 2: 5.5 Log IU/mL at day 14). Moreover, hair HBV DNA was detectable in case 2 (4.0 Log IU/mL at day 14). Serum HBV DNA became undetectable within approximately 3–4 months after the first hospital visit. After the resolution of HBV viremia, nail and hair HBV DNA became undetectable. The sequence analysis of serum, nail and hair HBV DNA showed the same HBV genotype in each case (case1: genotype C, case 2: genotype A). In case 1, 3 nucleotides were different in the full-genome HBV sequence between the serum and nails. In case 2, the full-genome HBV sequences were identical among the serum, nails and hair. In conclusion, HBV DNA was detectable in nails and hair of children with acute HBV infection.  相似文献   
5.
目的 探讨临床决策树法与积分模型法对结核性胸膜炎的诊断效能。方法 采用前瞻性随机对照研究方法,以2019年1月1日—2019年6月30日武汉市肺科医院收治的胸腔积液患者为研究对象。符合入组标准的胸腔积液患者随机入组临床决策树法组和积分模型法组,分别采用两种综合诊断模型进行诊断,对比两组方法的诊断效能。结果 临床决策树组共纳入127例患者,其中男性90例,女性37例,年龄18~88岁,平均(49.33±19.63)岁,最后诊断结核性胸膜炎108例,非结核性胸膜炎19例;积分模型组共纳入120例患者,其中男性89例,女性31例,年龄13~84岁,平均(46.41±20.01)岁,最后诊断结核性胸膜炎94例,非结核性胸膜炎26例。临床决策树法诊断结核性胸膜炎的敏感度57.4%,特异度78.9%,阳性预测值93.9%,阴性预测值24.6%,诊断准确率60.6%;积分模型法诊断结核性胸膜炎的敏感度75.5%,特异度96.2%,阳性预测值98.6%,阴性预测值52.1%,诊断准确率80.0%。结论 积分模型法诊断结核性胸膜炎敏感度、特异度及诊断准确率均高于临床决策树法,方法简单,可推广应用于结核性胸膜炎的临床诊断。  相似文献   
6.
7.
8.
The biological behavior of neuroendocrine tumors (NETs) is heterogeneous and differs from that of cholangiocarcinoma, which is the most common malignant tumor of the biliary tree. However, the preoperative diagnosis of NET in the biliary tree is extremely difficult and to our knowledge, diagnosis by brush cytology has not previously been reported. Herein, we first reported a case of biliary NET preoperatively diagnosed by brush cytology in a 33‐year‐old female patient. Imaging study revealed a 2.6‐cm mass in the common hepatic duct. The brush cytology was characterized by loosely cohesive plasmacytoid tumor cells and scattered clusters of thin vascular septa. The tumor cells showed abundant cytoplasm and severe nuclear size variation but mitosis was not observed. Immunohistochemical staining of the cell block (CB) showed strong positivity for both synaptophysin and chromogranin A and a Ki‐67 labeling index of 3.5%. The surgically resected bile duct mass was pathologically confirmed as NET, G2 with lymphovascular and perineural invasion of the tumor cells. The patient showed no evidence of tumor recurrence 10 months after operation without adjuvant chemotherapy. Suspicion of this rare tumor and immunohistochemical staining of the CB are important for the preoperative diagnosis of NET in the biliary tree.  相似文献   
9.
ABSTRACT

Growing trees on farmland continues to be a promising land-use option for smallholders in Indonesia as they look to diversify their enterprises beyond the main agricultural sector. While most smallholders integrate trees into their farming systems, selling timber and other tree products has usually been infrequent and opportunistic. Because of this infrequent trade, most smallholders rarely adopt silvicultural practices that would increase the commercial value of their trees. A research project trialled an alternative approach to forestry extension in Indonesia, known as the Master TreeGrower (MTG) training course. The MTG training courses used a farmer-centred approach to teach smallholders about forest science and took participants to market hubs so they could better understand how different forest products were valued by traders. The MTG training approach was trialled in 2014 in five districts in Indonesia and involved 118 smallholders and 27 non-farmers as course participants. This article reports on a recent evaluation of the MTG training courses held about three years earlier to explore the enduring impacts of the training approach and whether it can be scaled-out to other areas of Indonesia. The evaluation data were collected via focus group discussions (FGDs), in-depth interviews, household surveys and observations at three project sites: Pati (Central Java), Gunungkidul (Yogyakarta) and Bulukumba (South Sulawesi). A questionnaire was distributed among the participants of the FGDs to assess the extent different knowledge and skills of tree management that had been adopted by them following the MTG courses. The evaluation of the MTG approach revealed that the courses were effective in increasing smallholders’ knowledge of commercial forestry and their silvicultural skills. Many participants were more active with silviculture and planned to invest further in commercial forestry following the MTG training. In effect, the MTG training appeared to change the hearts and minds of the farmers about how commercial forestry could enhance their livelihoods.  相似文献   
10.
【目的】分析糖尿病肾脏疾病(DKD)患者进展到终末期肾病(ESRD)的相关危险因素,筛查进展到ESRD的高风险人群,以早期预防。【方法】收集本院231例糖尿病肾脏疾病患者的临床资料,随访3年,据是否出现ESRD分为未进展到ESRD(133例)、ESRD组(98例)。使用分类树模型分析进展到ESRD相关危险因素,通过节点增益分析筛选进展到ESRD的高风险人群。【结果】从预测变量中筛选到4个重要解释变量:载脂蛋B(ApoB)、性别、糖尿病视网膜病变、收缩压;ApoB升高是DKD进展的重要的危险因素;ApoB>1.14mmol/L的慢性肾脏病(CKD)3~4期DKD患者,3年进展到ESRD的概率是75.0%,如合并糖尿病视网膜病变,有79.7%的概率进展到ESRD。【结论】分类树模型能有效筛选并分析进展到ESRD危险因素,并识别高风险人群特征,有利于早期防治。  相似文献   
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号