Once an epidemic has ended, it is calculated with the formula: deaths / cases.But while an epidemic is still ongoing, as it is the case with the current novel coronavirus outbreak, this formula is, at the very least, "naïve" and can be "misleading" if, at the time of analysis, the outcome is unknown for a non negligible proportion of patients." The correct formula, therefore, would appear to be: CFR = deaths at day.x / cases at day.x-{T} (where T = average time period from case confirmation to death) This would constitute a fair attempt to use values for cases and deaths belonging to the same group of patients. An alternative method, which has the advantage of not having to estimate a variable, and that is mentioned in the American Journal of Epidemiology study cited previously as a simple method that nevertheless could work reasonably well if the hazards of death and recovery at any time t measured from admission to the hospital, conditional on an event occurring at time t, are proportional, would be to use the formula: CFR = deaths / (deaths + recovered) 这个帖子里可以看出有多少人计算的时候只知道用公式，而不去思考公式背后的含义。一个非慢性病，死亡率加治愈率远远小于100%，难道这个make sense？
Once an epidemic has ended, it is calculated with the formula: deaths / cases.But while an epidemic is still ongoing, as it is the case with the current novel coronavirus outbreak, this formula is, at the very least, "naïve" and can be "misleading" if, at the time of analysis, the outcome is unknown for a non negligible proportion of patients." The correct formula, therefore, would appear to be: CFR = deaths at day.x / cases at day.x-{T} (where T = average time period from case confirmation to death) This would constitute a fair attempt to use values for cases and deaths belonging to the same group of patients. An alternative method, which has the advantage of not having to estimate a variable, and that is mentioned in the American Journal of Epidemiology study cited previously as a simple method that nevertheless could work reasonably well if the hazards of death and recovery at any time t measured from admission to the hospital, conditional on an event occurring at time t, are proportional, would be to use the formula: CFR = deaths / (deaths + recovered) 这个帖子里可以看出有多少人计算的时候只知道用公式，而不去思考公式背后的含义。一个病，死亡率加治愈率远远小于100%，难道这个make sense？
如果知道一个确诊病人平均需要30天出现结果（死亡或治愈），那么你这个算法也make sense. 这个算法唯一的问题是需要估计这个从确疹到出结果的时间，也就是说，一个硬币从扔出去到落地的时间。 这里有篇文章讨论流行病流行其间死亡率的估计办法 https://www.worldometers.info/coronavirus/coronavirus-death-rate/ Once an epidemic has ended, it is calculated with the formula: deaths / cases.But while an epidemic is still ongoing, as it is the case with the current novel coronavirus outbreak,this formula is, at the very least, "naïve" and can be "misleading"if, at the time of analysis, the outcome is unknown for a non negligible proportion of patients." The correct formula, therefore, would appear to be:CFR = deaths at day.x / cases at day.x-{T}(where T = average time period from case confirmation to death)This would constitute a fair attempt to use values for cases and deaths belonging to the same group of patients. An alternative method, which has the advantage of not having to estimate a variable, and that is mentioned in theAmerican Journal of Epidemiology studycited previously as a simple method that nevertheless could work reasonably well if the hazards of death and recovery at any time t measured from admission to the hospital, conditional on an event occurring at time t , are proportional, would be to use the formula:CFR = deaths / (deaths + recovered) 这个帖子里可以看出有多少人计算的时候只知道用公式，而不去思考公式背后的含义。一个非慢性病，死亡率加治愈率远远小于100%，难道这个make sense？ purplebasil 发表于 2/14/2020 3:25:00 PM
🔥 最新回帖
wiki : death / total patient 叫实时死亡率，real time, 参考价值有限. ，宣传用这个参考价值低的实时死亡率，降低恐惧
假设现在没人人再生病，这个real time death rate 肯定不停的涨。
假设更多人生病，但是出了特效药或者医疗跟上来了，没人死了，这个 real time death rate 就会跌。
用死亡/（死亡+出院），肯定让人恐惧，基本会高估了，因为前期没有好治疗方法和医疗跟不上。
说到底，两种算法的有有限的参考意义
在治疗的就不算分子了？
你上过本科吗？ 知道什么叫大数定理吗？ 重复试验多次，随机事件的频率收敛于它的概率。零星几个没有统计意义。
看来国内五毛的素质必须要提高了。
🛋️ 沙发板凳
死亡/（死亡+治愈）
哈哈哈
治愈的很多又复发了。。。。。
这个也不合理。我认为还是死亡人数／确诊人数。
在流行病还没有settle之前，这个算法是make sense的，因为有大量的确疹病人还生死未定。用（死亡／确疹）来计算死亡率是在流行病结束以后的算法，只有那时候才知道这么多确疹病人里面总共死了多少。
用你这个算法，SARS流行其间的死亡率是3%多一点，最后的死亡率是9.6%，两者相差很远。这个算法的死亡率，over time 是从lower end逐渐接近最后的实际数值，隐含的假设是确疹病人中生死未定的那些人都不会病死。
不是号召抽治愈的人的血浆来治病吗，就不怕反复感染
问题是高血压是慢性病，新冠是急性病。对于慢性病大家计算五年，10年死亡率。
你别造谣了行不?
现在有啥医疗 可以避免轻症变成重症
你算的是全国总死亡率，把武汉单拎出来，死亡率也是超过30%
死亡人数／（死亡+治愈）×100%这个病进入重症后，死亡率很高
2019中国出生1523万，死亡993万，中国人口死亡率40%。
你家死了一半？
那些“离婚率50%”的哗众取宠数据都是这么算的，这么低级的错误
国外这么多治愈出院的了，是不是有后遗症也不光看大陆的数据
你拿回这个数据来比对犯了一个根本性的错误，用类比的方式来说，如果把人一生当成一场慢性病的话，新出生儿相当于“确诊”而不是“治愈”，所以死亡率是100%
这次武汉疫情可以用治愈病例和死亡病例来粗略计算的依据在于，无论治愈还是死亡，都是差不多花22天时间左右，所以基本上可以看出同一批病人的治愈/死亡比例。
考虑到还有很多病人不能得到及时救治在家里死亡的，死亡率应该会更高。
你拿这个数据来比对犯了一个根本性的错误，用类比的方式来说，如果把人一生当成一场慢性病的话，新出生儿相当于“确诊”而不是“治愈”，所以死亡率是100%
这次武汉疫情可以用治愈病例和死亡病例来粗略计算的依据在于，无论治愈还是死亡，都是差不多花22天时间左右，所以基本上可以看出同一批病人的治愈/死亡比例。当然这种方式也就是粗略计算，出入肯定会有，但不会差很多。
考虑到还有很多病人不能得到及时救治在家里死亡的，死亡率应该会更高。
这莫不是个傻子吧……
比较同意这个说法
死亡率变不奇怪呀，随着对疫情逐渐重视，各方支援，还有一线医护逐渐积累经验，死亡率有变化才是正常的事情。疫情之后的死亡率是整个疫情中各阶段死亡率的平均值左右。
正解！
如果知道一个确诊病人平均需要30天出现结果（死亡或治愈），那么你这个算法也make sense. 这个算法唯一的问题是需要估计这个从确疹到出结果的时间，也就是说，一个硬币从扔出去到落地的时间。
这里有篇文章讨论流行病流行其间死亡率的估计办法
https://www.worldometers.info/coronavirus/coronavirus-death-rate/
Once an epidemic has ended, it is calculated with the formula: deaths / cases. But while an epidemic is still ongoing, as it is the case with the current novel coronavirus outbreak, this formula is, at the very least, "naïve" and can be "misleading" if, at the time of analysis, the outcome is unknown for a non negligible proportion of patients."
The correct formula, therefore, would appear to be: CFR = deaths at day.x / cases at day.x-{T} (where T = average time period from case confirmation to death) This would constitute a fair attempt to use values for cases and deaths belonging to the same group of patients.
An alternative method, which has the advantage of not having to estimate a variable, and that is mentioned in the American Journal of Epidemiology study cited previously as a simple method that nevertheless could work reasonably well if the hazards of death and recovery at any time t measured from admission to the hospital, conditional on an event occurring at time t, are proportional, would be to use the formula: CFR = deaths / (deaths + recovered)
这个帖子里可以看出有多少人计算的时候只知道用公式，而不去思考公式背后的含义。一个非慢性病，死亡率加治愈率远远小于100%，难道这个make sense？
难道是半死不活的占大多数？
还在治疗的人，是一个抛出去的硬币，还没有落地，不知道最后结果是什么。你把他们放在分母里，不放在分子（死亡人数）里，隐含的意思就是假设他们都不会死，结果就是under estimate死亡率。
所以尽管人类掌握了病毒的基因排序，但后果还远远的不清楚。这大概也是中南山后另一个王院士说拐点无法预计的重要原因。今天已经是二月中旬，以今天的官方谣言，死亡数加治愈数还是只有确诊数的不到15%，这个说明了此次病毒的可怕杀伤力。
剩下的在治疗中。
剩下的还在治疗的，就是可以看成是半死不活的呀，因为不知道治完了结果是死还是活，所以不知道应该进不进分子，那么凭什么进分母认为一定将是治愈的
正在治病的人也应该放进分子
这种算法对指导临床很重要，目前的武汉基本是3个患者中，治愈2个，死亡1个，为什么死亡率这么高？必须好好反思，拿出切实可行的办法降低死亡率
因为他们有可能死亡
那是怎么算的，你倒是说啊
我也很想知道