临床科研设计基本原则和设计方案.ppt

设计方案类型 随机对照试验 队列研究 病例-对照研究 病例报道 研究对象选择 纳入、排除标准明确 随机方法完善 组间基线可比 分配方案隐藏 纳入、排除标准明确 除暴露因素外，其它条件可比 纳入、排除标准明确 病例的定义明确 对照应从与病例同一来源的人群中随机选择 组间影响结果的因素应一致 纳入、排除标准明确 清楚描述研究对象的情况 盲法 患者/研究人员/结果测量者 结果测量者应不知道患者的暴露情况 结果测量者应不知道研究对象是病例还是对照 ---- 随访 随访期足够长 失访人数 随访期足够长 失访人数 随访期足够长 随访期足够长 结果测量 客观、独立评估结果 意向分析法 客观、独立评估结果 所有研究对象均应纳入分析 客观、独立评估结果 所有研究对象均应纳入分析 病例、对照应采用相同方法评估结果 客观、独立评估结果 所有研究对象均应纳入分析 研究方案 治疗证据（RCT）的评价 Is this evidence about therapy (from an individual randomized trial) valid? Was there a fair start? 1. Was the assignment of patients to treatment randomized?（随机分配？） 2. Was the randomization concealed?（分配方案隐藏？） 3. Were the groups similar at the start of the trial?（基线可比？） Was there a fair race? 4. Was follow-up of patients sufficiently long and complete?（随访足够长且完整？） 5. Were all patients analyzed in the groups to which they were randomized?（ITT分析） Some finer points: 6. Were patients, clinicians and study personnel kept blind to treatment?（盲法？） 7. Were groups treated equally, apart from the experimental therapy?（基础治疗？） Is this valid evidence about therapy (from an individual randomized trial) important? 1. What is the magnitude of the treatment effect?（效应值大小？） 2. How precise is the estimate of the treatment effect?（效应值的精确性？） Is this valid and important evidence (from an individual randomized trial) applicable to our patient? 1. Is our patient so different from those in the study that its results cannot apply?（差异？） 2. Is the treatment feasible in our setting?（可行性？） 3. What are our patient’s potential benefits and harms from the therapy?（利弊？） 4. What are our patient’s values and expectations for both the outcome we are trying to prevent and the treatment we are offering?（价值观和期望？） ? Straus, Glasziou, Richardson, Haynes: Evidence-Based Medicine, 4 th Edition. * 随机分配 治疗组 对照组 结果测量 交叉 退出研究或失访 Do changes in group and/or loss to follow up produce bias? 退出研究或失访 结果分析 * 效力分析（efficacy analysis，per protocol，PP分析） ②与③比较 实际治疗分析（treatment received analysis） ①+ ③与②+④比较 “意向治疗原则”分析（intention-to-tre