Wald Nicholas J, Morris Joan K, Rish Simon
Wolfson Institute of Preventive Medicine, Barts and the London Queen Mary's School of Medicine and Dentistry, Charterhouse Square, London EC1 M 6BQ, UK.
J Med Screen. 2005;12(4):197-201. doi: 10.1258/096914105775220642.
To determine the quantitative effect on overall screening performance (detection rate for a given false-positive rate) of using several moderately strong, independent risk factors in combination as screening markers.
Theoretical statistical analysis.
For the purposes of this analysis, it was assumed that all risk factors were independent, had Gaussian distributions with the same standard deviation in affected and unaffected individuals and had the same screening performance. We determined the overall screening performance associated with using an increasing number of risk factors together, with each risk factor having a detection rate of 10%, 15% or 20% for a 5% false-positive rate. The overall screening performance was estimated as the detection rate for a 5% false-positive rate.
Combining the risk factors increased the screening performance, but the gain in detection at a constant false-positive rate was relatively modest and diminished with the addition of each risk factor. Combining three risk factors, each with a 15% detection rate for a 5% false-positive rate, yields a 28% detection rate. Combining five risk factors increases the detection rate to 39%. If the individual risk factors have a detection rate of 10% for a 5% false-positive rate, it would require combining about 15 such risk factors to achieve a comparable overall detection rate (41%).
It is intuitively thought that combining moderately strong risk factors can substantially improve screening performance. For example, most cardiovascular risk factors that may be used in screening for ischaemic heart disease events, such as serum cholesterol and blood pressure, have a relatively modest screening performance (about 15% detection rate for a 5% false-positive rate). It would require the combination of about 15 or 20 such risk factors to achieve detection rates of about 80% for a 5% false-positive rate. This is impractical, given the risk factors so far discovered, because there are too few risk factors and their associations with disease are too weak.
确定联合使用多个中等强度的独立风险因素作为筛查标志物对整体筛查性能（给定假阳性率下的检测率）的定量影响。
理论统计分析。
为进行该分析，假设所有风险因素相互独立，在患病和未患病个体中具有相同标准差的高斯分布，且具有相同的筛查性能。我们确定了联合使用越来越多风险因素时的整体筛查性能，每个风险因素在5%假阳性率下的检测率为10%、15%或20%。整体筛查性能以5%假阳性率下的检测率来估计。
联合风险因素可提高筛查性能，但在恒定假阳性率下检测率的增加相对较小，且随着每个风险因素的增加而减弱。联合三个风险因素，每个因素在5%假阳性率下的检测率为15%，则检测率为28%。联合五个风险因素可将检测率提高到39%。如果个体风险因素在5%假阳性率下的检测率为10%，则需要联合约15个这样的风险因素才能达到相当的整体检测率（41%）。
直观地认为，联合中等强度的风险因素可显著提高筛查性能。例如，大多数可用于筛查缺血性心脏病事件的心血管风险因素，如血清胆固醇和血压，筛查性能相对较低（5%假阳性率下约15%的检测率）。要在5%假阳性率下达到约80%的检测率，需要联合约15或20个这样的风险因素。鉴于目前已发现的风险因素，这是不切实际的，因为风险因素太少且它们与疾病的关联太弱。
