11/30 reading and revise articles

敏感性(sensitivity)與特異性(specificity)
乃臨床診斷正確性之評價指標﹐亦可以引用到製造業對策之評價﹐以下表說明之：
sensitivity（敏感性）：疾病發現之能力﹐計算式：a/(a+c)　 最佳狀況為100%
specificity（特異性）：無病發現之能力﹐計算是：d/(b+d) 最佳狀況為100%

如上所示﹐乃健康者與罹患者之BioMark定量分布圖﹐圖中重疊區的上緣是疾病的指標﹐下緣則是健康的指標﹐一般而言均假設兩者間有重疊。

重疊區包括假陽性(False Positive)是誤判健康者為罹患者﹐假陰性(False Negative)則是誤判罹患者為健康者。
降低上緣值固可以提高診斷的敏感度﹐但此時診斷的特異性會降地（亦即假陽性增加）﹐兩者之間有取捨之關係。診斷之目的在於正確之判斷﹐通常在95%信賴區間外之情況﹐吾人視之為異常！
參考資料：http://homepage3.nifty.com/m_nw/dataac10j.htm

False positive rate (α) = FP / (FP + TN) = 18 / (18 + 182) = 9% = 1 - specificity
False negative rate (β) = FN / (TP + FN) = 1 / (2 + 1) = 33% = 1 - sensitivity
Power = 1 − β

sensitivity =number of true positives /(number of true positives +number of false positives )
@A sensitivity of 100% means that the test recognizes all sick people as such.
@Sensitivity alone does not tell us how well the test predicts other classes (that is, about the negative cases). In the binary classification, as illustrated above, this is the corresponding specificity test, or equivalently, the sensitivity for the other classes.
@Sensitivity is not the same as the positive predictive value (ratio of true positives to combined true and false positives), which is as much a statement about the proportion of actual positives in the population being tested as it is about the test.
@The calculation of sensitivity does not take into account indeterminate test results. If a test cannot be repeated, the options are to exclude indeterminate samples from analyses (but the number of exclusions should be stated when quoting sensitivity), or, alternatively, indeterminate samples can be treated as false negatives (which gives the worst-case value for sensitivity and may therefore underestimate it).

--------------------------------------------------------------------------------
一個診斷工具不會同時具有良好的Sensitivity & Specificity
通常Sensitivity好的工具Specificity會較差，而Specificity好的工具Sensitivity較差。
Sensitivity（以下簡稱Sen.）與Specificity（以下簡稱Spe.）是對診斷工具而言的。
然而對病人而言，重要的不是診斷工具的Sen.與Spe.
而是該診斷結果對病人的意義。亦即：
陽性預測值 Positive Predictive Value (PPV.) 與
陰性預測值 Negative Predictive Value (NPV.)
所謂的陽性預測值，就是檢查結果是陽性，而確實是得病而不是偽陽性的機率。
而陰性預測值，就是檢查結果是陰性，而確實沒有得病而不是偽陰性的機率。