[This article was first published on Wiekvoet, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
I wanted to know a bit more about the number of people suffering from Alzheimer. It has been getting more attention and it runs in my family. From CBS (Statistics Netherlands) I pulled the data regarding the number of people dying from it. I am afraid that means some Dutch words but that’s been kept low. Obviously death is not the worst of this particular disease. At a personal level, if your loved ones do not recognize you any more. At a society level, the amount of care needed is huge, especially as the illness progresses, hence expensive.
Data
As mentioned, all data is from CBS (www.cbs.nl/Centraal Bureau voor de Statistiek/Statistics Netherlands). This particular data resides somewhere in population. There is a short list and a long list.Since there is a limit on the size of data one can extract I restricted myself to age 35+ and Alzheimer. It did not occur at all under age 35. The table runs 1996 onwards, so that’s where the data starts. In the end I only used from age 55, since that made the sub-plots a bit larger.
In addition I used the short list of causes of death (doodsoorzaken; korte lijst). These data also contained the total population, so I could calculate proportions per inhabitant.
How many people die of Alzheimer in the Netherlands?
The plot shows that even at 55 to 60 years old Alzheimer is not causing a lot of deaths, so removing the younger ages seems justified. The plot also shows that it occurs more at higher ages and is clearly increasing. It also seems more females than males suffer from it, but, as seen below, that may also be because there are more old females.
Overall number of death
For overall death the short list of causes of death is used. In contrast, in the overall number of death there is a marked decrease, especially ages 65 to 80.
As proportion of the population
These plots show again the big increase in Alzheimer. Note the use of a logarithmic scale. It increases with age and increases over the years. In the 16 years the data covers, and the 5 years for each subplot seem to give similar increases. (note, the outlier in ’95 and older’ has been confirmed via a check of the CBS data)
The plot of all death shows the marked improvements made in general over time. Even age 90 to 95 shows a small decrease. The expenses for health care have grown, that’s sure, but the results are visible for anybody looking at the data.
R code
library(ggplot2)
Alz <- read.csv(‘alzheimer.csv’,sep=’;’,na.strings=’-‘)
Alz$Waarde[is.na(Alz$Waarde)] <- 0
Alza <- data.frame(Age=Alz$Leeftijd,
Year=Alz$Perioden,
Gender=c(‘Male’,’Female’)[Alz$Geslacht],
NumDie=Alz$Waarde
)
ggplot(data=Alza[!Alza$Age%in% levels(Alza$Age)[1:5],],
aes(x=Year,y=NumDie,col=Gender)) +
geom_point() +
scale_y_continuous(‘Number of Alzheimer dead’) +
facet_wrap( ~ Age, drop=TRUE)
ggsave(‘plot1.png’)
All <- read.csv(‘Doodsoorzaken__korte_010313214257.csv’,
sep=’;’,na.strings=’-‘)
Allt <- reshape(All,drop=c(‘Onderwerpen_3′,’Geslacht’),
varying=list(c(‘Mannen’,’Vrouwen’)),
v.names=’NumDie’,
timevar=’Gender’,times=c(‘Male’,’Female’),
idvar=c(‘Onderwerpen_1′,’Onderwerpen_2′,’Onderwerpen_4’
,’Leeftijd’,’Perioden’),
direction=’long’)
Alla <- data.frame(Age=Allt$Leeftijd,
Year=Allt$Perioden,
Gender=Allt$Gender,
NumDie=Allt$NumDie,
Cause1=Allt$Onderwerpen_1,
Cause4=Allt$Onderwerpen_4
)
ggplot(data=Alla[Alla$Cause1==’Totaal alle doodsoorzaken’ &
!Alla$Age %in% levels(Alla$Age)[1:5],],
aes(x=Year,y=NumDie,col=Gender)) +
scale_y_continuous(‘Total number of dead’) +
geom_point() +
facet_wrap( ~ Age, drop=TRUE)
ggsave(‘plot2.png’)
Population <- Alla[Alla$Cause1==’Gemiddelde bevolking’,1:4]
names(Population)[names(Population)==’NumDie’] <- ‘AverPop’
AllCauses <- Alla[Alla$Cause1!=’Gemiddelde bevolking’,]
combi <- merge(Alza,Population)
combi$PropDie <- combi$NumDie/combi$AverPop
ggplot(data=combi[!combi$Age %in% levels(combi$Age)[1:5], ],
aes(x=Year,y=PropDie,col=Gender)) +
geom_point() +
scale_y_log10(‘Proportion Alzheimer dead of total popultion’) +
facet_wrap( ~ Age, drop=TRUE)
ggsave(‘plot3.png’)
combi23 <- merge(Population,AllCauses)
combi23$PropDie <- combi23$NumDie/combi23$AverPop
ggplot(data=combi23[combi23$Cause1==’Totaal alle doodsoorzaken’
& !combi23$Age %in% levels(combi23$Age)[1:5],],
aes(x=Year,y=PropDie,col=Gender)) +
scale_y_log10(‘Overall proportion dead of total population’) +
geom_point() +
facet_wrap( ~ Age, drop=TRUE)
ggsave(‘plot4.png’)
To leave a comment for the author, please follow the link and comment on their blog: Wiekvoet.
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.