09. Cohort Study - Incidence Rate - YouTube

So that is the reason why we need another  incidence measure to take account into the time  

information that each member of the cohort contributes. And the calculation of incidence  

rate well seems simple based on that equation. Here in the numerator the number of new  

cases during a specified period of time goes, which  is basically the same as the incidence proportion.  

However, the calculation of denominator can  be a bit complicated, which is defined as a  

total sum of the time each person was observed  without disease until one of the 4 endpoints.  

So for example, a person is followed up for 10  years without developing disease in a 10 year  

longitudinal study and the person contributed 10  person-years of observation. So that is the unit of  

the incidence rate: person-years, or person-months,  or even person-hours. So it is depending upon

the length of the study basically. So the unit follows the length of the study. On the  

other hand, if another person develops a disease at  year 5, then the person contributed 5 person-

years. So let's take a look at a sample question how to calculate the incidence rate. So here is  

question saying a cohort of 2100  over 60 years old was enrolled in a study  

and followed up over 4 years to determine the incidence rate of AMD. So they were examined  

4 times at each year-end. So from the first  year, there was no case but 100 loss to follow up  

and in the second year examination, there was one new case of AMD and there was another 99 loss to  

follow up and in third year examination, 7, there were 7 new cases and another 793 loss  

to follow up and at the  fourth-year examination they found 8 extra new  

cases of AMD and another 392 more loss to follow up. Because it is much easier to calculate the  

numerator, so let's just calculate the  numerator, which is just the number of new cases of  

AMD over the study period, the follow-up  period. So as you can see, you can just add  

all the new cases from across all 4 years so that's zero plus one plus 7 plus  

8 becomes 16. So 16 will go to the numerator but  the calculation of denominator will become quite  

convoluted. So the denominator is basically the sum of the person-year observation. So let's  

just start with the first year. So we do not have a case of AMD. So there's no contribution

and loss to follow up, we had 100 loss to follow up. So 100

but because we do not know exactly  when these people are lost to follow up,  

we're going to just assume as a conservative guess, just kind of way of imputation. So they're  

going to just contribute half a year. So  this is going to by convention how  

people impute the data. So that's 50 years and  then healthy people is... you have to take away 100  

because you have 100 loss to follow up and that's  2000. So they all contributed a year

without the disease. So total will become you  just add all these together it will become 2050  

for the first year. So the  total person-year observation  

for the first year is a 2050 person-years. Got it? So now we're going to just move on to  

the second year. So that's  what we just calculated.

And we have one case and because we do not know  

when this person actually got the disease  again so we're going to multiply 0.5.

So this person contributed 0.5 year, half a year  and then there's another 99 lost to follow up  

oops and I mean it's all there but I'm just trying to show you how I calculate this. So that's

29.5 and now we are left with

2000 minus 1 minus 99. So that's another 100. So we have one case  

and 99 loss to follow up so that's 1900. We add all these 0.5 49.5 1900 that's 50

1900 that's 1950.

Yes that's what we have. and now I think  you get the hang of it so I'll just move on.  

next year and then

now we got to the final year and  

now you're going to have to add all  these subtotals and which are these.

So if you add these two that's 4000 and this  is 2400, 4000 +

2400 will become 6400. So let's just finalise the calculation.

The numerator we already calculate the numerator  which is just the number of new cases of AMD  

and we had 16 cases and the denominator is a person-year observation and I just 

calculated 6400 person-years. So it  goes 16 over 6 400 person-years.  

So it's either 0.0025 cases per person-years  or I mean I prefer this notation to this  

decimal notation. So you want to make it like a whole number 25 cases per 10000 person-years. So  

whichever you report the incidence rate is fine  but personally, I prefer the same latter one.