library(ggplot2)
library(cluster)
library(factoextra)
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
library(maps)
##
## 载入程辑包:'maps'
## The following object is masked from 'package:cluster':
##
## votes.repub
library(dplyr)
##
## 载入程辑包:'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(arules)
## 载入需要的程辑包:Matrix
##
## 载入程辑包:'arules'
## The following object is masked from 'package:dplyr':
##
## recode
## The following objects are masked from 'package:base':
##
## abbreviate, write
Understanding how health threats affect life expectancy is essential for improving global health outcomes. Factors such as diseases, pollution, and lifestyle choices can significantly impact the longevity of populations worldwide. This project aims to explore the relationship between health threats in various countries and their life expectancyto identify most significant health indicators, so each region can target interventions to improve healthcare service. Using unsupervised learning, we’ll identify patterns in health data and visualize the global distribution of life expectancy and health threats.
This phase involves preparing the dataset for analysis by loading it, renaming columns for clarity, and visualizing the distribution of life expectancy across countries. We need to understand the distribution of life expectancy and identify any preliminary patterns or outliers that may require attention, such as zero values that could skew the analysis.
First I prepare the data for analysis by loading and renaming the column
dataset <- read.csv("C:/Users/PC/Documents/Life_expectancy.csv", header = TRUE, sep = ",", fileEncoding = "ISO-8859-1")
colnames(dataset) <- c('Country', 'LifeExpectancy', 'ViolenceAgainstWomen', 'MaternalMortality', 'UnsafeWASHMortality', 'PM25Concentration', 'CleanFuelAndTechnology', 'HypertensionPrevalence', 'SuicideMortality', 'ObesityPrevalence', 'HIVInfectionRate', 'TuberculosisIncidence', 'MalariaIncidence', 'RoadTrafficMortality', 'HomicideMortality', 'AlcoholConsumptionPerCapita', 'TobaccoUsePrevalence')
str(dataset)
## 'data.frame': 198 obs. of 17 variables:
## $ Country : chr "Afghanistan" "Albania" "Algeria" "Andorra" ...
## $ LifeExpectancy : num 63.2 78 77.1 0 63.1 76.5 76.6 76 83 81.6 ...
## $ ViolenceAgainstWomen : int 46 13 0 0 38 0 27 10 23 15 ...
## $ MaternalMortality : num 62 0.8 7.8 0 22.2 2.1 4.5 2.7 0.3 0.5 ...
## $ UnsafeWASHMortality : num 16.6 3.2 4.1 0 48.9 2.5 11.4 5.8 1.9 2 ...
## $ PM25Concentration : num 75.2 16.6 22.9 8.9 32.3 8.4 11.2 36.2 9.1 12.4 ...
## $ CleanFuelAndTechnology : int 35 84 100 100 50 100 100 98 100 100 ...
## $ HypertensionPrevalence : num 40.2 41.8 36.2 31 38.7 42.6 47.5 47.3 29.3 33.8 ...
## $ SuicideMortality : num 4.1 4.3 2.5 0 6.1 0.4 8.4 3.3 12.5 14.6 ...
## $ ObesityPrevalence : num 5.5 21.7 27.4 25.6 8.2 18.9 28.3 20.2 29 20.1 ...
## $ HIVInfectionRate : num 0.4 0.3 0.4 0 5.2 0 1.1 0 0.2 0 ...
## $ TuberculosisIncidence : num 18.9 1.7 5.4 0.29 32.5 0.49 3 2.7 0.65 0.5 ...
## $ MalariaIncidence : num 0.63 0 0 0 25.49 ...
## $ RoadTrafficMortality : num 15.9 11.7 20.9 0 26.1 0 14.1 20 4.9 4.9 ...
## $ HomicideMortality : num 8.5 3.6 1.7 0 9.2 2.4 6.1 3.8 1 0.5 ...
## $ AlcoholConsumptionPerCapita: num 0 5.1 0.6 11.1 6.2 8.5 8 5 10.1 12 ...
## $ TobaccoUsePrevalence : num 23.3 22.4 21 31.8 0 0 24.5 25.5 13.6 26.4 ...
I use histogram visualizes how life expectancy values are distributed across the countries
ggplot(data = dataset, aes(x = LifeExpectancy)) +
geom_histogram(fill = "lightblue", color = "black", bins = 20) +
labs(
title = "Histogram of Life Expectancy",
x = "Life Expectancy",
y = "Frequency"
) +
theme_minimal()
A skewed histogram might indicate disparities in global health, with a
significant number of countries having lower life expectancies. we can
see some zero value which affect the data so we need to clean it
generate_scatter_plot <- function(x, y, xlab, main) {
ggplot(data = dataset, aes(x = x, y = y)) +
geom_point(color = "lightblue", size = 2) +
geom_smooth(method = "lm", color = "red") +
labs(
title = main,
x = xlab,
y = "Life Expectancy"
) +
theme_minimal()
}
for (i in 3:ncol(dataset)) {
x_col <- colnames(dataset)[i]
main_title <- paste("Scatter Plot -", x_col)
x_label <- colnames(dataset)[i]
scatter_plot <- generate_scatter_plot(x = dataset[[i]], y = dataset$LifeExpectancy, xlab = x_label, main = main_title)
print(scatter_plot)
}
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
scatter plots suggest correlations between these health indicators and
life expectancy.
dataset <- subset(dataset, MalariaIncidence != 0 & TobaccoUsePrevalence != 0 & ViolenceAgainstWomen & LifeExpectancy !=0)
Then apply PCA to reduce the dataset’s dimensionality to identify the most significant health indicators affecting life expectancy.This step helps to identify the most significant health indicators affecting life expectancy, simplifying the dataset for further analysis
dataset_scaled <- as.data.frame(scale(dataset[, -1]))
pca_result <- prcomp(dataset_scaled, center = TRUE, scale. = TRUE)
summary(pca_result)
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7
## Standard deviation 2.2067 1.5958 1.3661 1.1164 1.09561 0.9550 0.85967
## Proportion of Variance 0.3043 0.1592 0.1166 0.0779 0.07502 0.0570 0.04619
## Cumulative Proportion 0.3043 0.4635 0.5801 0.6580 0.73305 0.7901 0.83624
## PC8 PC9 PC10 PC11 PC12 PC13 PC14
## Standard deviation 0.7949 0.65147 0.60178 0.57253 0.51730 0.51026 0.38515
## Proportion of Variance 0.0395 0.02653 0.02263 0.02049 0.01673 0.01627 0.00927
## Cumulative Proportion 0.8757 0.90226 0.92489 0.94538 0.96211 0.97838 0.98765
## PC15 PC16
## Standard deviation 0.37003 0.24631
## Proportion of Variance 0.00856 0.00379
## Cumulative Proportion 0.99621 1.00000
plot(pca_result, col = "dodgerblue")
The PCA results show that the first few principal components capture a
significant portion of the variance in the dataset.
fviz_pca_var(pca_result, col.var="steelblue")
ind <- get_pca_ind(pca_result)
head(ind$contrib)
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5 Dim.6
## 1 1.0661401685 1.46867013 1.2453999 0.50488479 7.135530557 5.41007746
## 14 0.0002983408 8.41979787 3.8787641 0.91674582 0.004774331 0.23944118
## 19 2.5581882971 0.07995157 2.7597102 0.09451185 2.379933480 0.25587836
## 21 1.1799900104 1.02158382 0.2118801 1.40493680 0.567451080 0.47200638
## 23 0.8505729121 9.20404649 3.4915913 0.08153334 0.872794841 0.05476251
## 24 5.8598526561 0.93339953 1.8983516 0.16833424 1.144310977 0.95214738
## Dim.7 Dim.8 Dim.9 Dim.10 Dim.11 Dim.12 Dim.13
## 1 3.84141946 8.625137 0.170118910 3.046148849 1.462695401 0.41804671 4.372736
## 14 1.93079832 3.285279 0.095604837 0.001171430 0.239730411 2.64625471 2.763541
## 19 3.01416943 1.500791 0.513685395 0.001888027 0.129953687 0.09768395 2.168054
## 21 1.80747554 1.054365 0.001303432 1.947241575 0.079361121 0.53686590 1.582704
## 23 0.02600951 1.842669 1.767003186 0.844044618 6.714826485 1.11016751 1.941449
## 24 0.05012578 1.046191 4.150012666 3.543181283 0.001695033 0.05582562 1.431367
## Dim.14 Dim.15 Dim.16
## 1 0.3466162 6.2709857 8.69253462
## 14 0.5691387 0.7789764 9.07280035
## 19 0.2660868 1.0046203 0.09496903
## 21 1.0197559 0.5989603 12.94129958
## 23 4.1245107 0.3847417 3.94821219
## 24 14.7326510 0.2187694 0.24889458
the first country (ID 1) contributes significantly to Dim.5 (7.14%) and Dim.6 (5.41%), indicating that this country’s health indicators strongly influence the variance explained by these two components
High contributions to a PC from a country suggest that the country’s health indicators are strongly associated with the patterns or features that the PC represents.
Calculating the variance explained by each principal component in the PCA result helps in deciding how many components to retain for further analysis
explained_variance <- pca_result$sdev^2 / sum(pca_result$sdev^2)
cumulative_variance <- cumsum(explained_variance)
cumulative_variance
## [1] 0.3043374 0.4634943 0.5801322 0.6580305 0.7330532 0.7900498 0.8362388
## [8] 0.8757346 0.9022606 0.9248942 0.9453813 0.9621064 0.9783791 0.9876505
## [15] 0.9962081 1.0000000
The first principal component (PC1) explains 30.4337450% of the variance, the first five principal components together explain approximately 73.30532% of the variance. It’s sufficient to represent the data effectively, allowing for a reduced-dimensional space that still retains the core information.
loadings <- pca_result$rotation
head(loadings)
## PC1 PC2 PC3 PC4
## LifeExpectancy 0.3554685 0.27375002 -0.22526908 0.092795242
## ViolenceAgainstWomen -0.1259074 0.07748016 0.21968403 -0.557288791
## MaternalMortality -0.3638541 -0.10412888 -0.12472823 0.029207667
## UnsafeWASHMortality -0.3946506 -0.12519880 -0.03916546 0.007197427
## PM25Concentration -0.2783558 0.12892257 -0.08406027 0.143688546
## CleanFuelAndTechnology 0.3782774 -0.02174464 -0.06793482 0.105671535
## PC5 PC6 PC7 PC8
## LifeExpectancy -0.01915459 0.02392332 0.18011854 -0.10433018
## ViolenceAgainstWomen -0.33492119 0.13712570 0.52442897 -0.26452998
## MaternalMortality 0.17857432 0.22283288 0.19077271 0.08016183
## UnsafeWASHMortality 0.02442923 0.15018765 -0.18493172 0.20208679
## PM25Concentration 0.25375519 0.49469738 0.05342298 -0.53437561
## CleanFuelAndTechnology 0.13462804 0.22291283 0.02351048 -0.28071654
## PC9 PC10 PC11 PC12
## LifeExpectancy -0.030319728 0.1666963 0.041238038 -0.03339757
## ViolenceAgainstWomen -0.142517980 -0.1117464 0.034178700 0.12037046
## MaternalMortality 0.007227015 0.2581364 -0.417706473 0.53600945
## UnsafeWASHMortality -0.023713758 0.2033078 -0.232928867 -0.09089350
## PM25Concentration -0.098086475 -0.1320969 0.037467778 -0.29640302
## CleanFuelAndTechnology -0.200158460 0.5114744 0.008535036 0.01832408
## PC13 PC14 PC15 PC16
## LifeExpectancy -0.05337996 0.21709852 -0.0686893989 -0.78029284
## ViolenceAgainstWomen 0.05854748 0.22705460 -0.1894987098 0.06314710
## MaternalMortality 0.06911298 0.07102952 0.3985784650 -0.13724322
## UnsafeWASHMortality -0.23151640 0.13814191 -0.7325860510 -0.12255312
## PM25Concentration 0.03206296 -0.39795295 0.0007619608 -0.07022606
## CleanFuelAndTechnology -0.31271394 0.28400213 -0.0099431560 0.46136555
From this result, we can conclude that ‘Unsafe WASH Mortality’,‘Tuberculosis Incidence’, ‘Hypertension Prevalence’,‘Violence Against Women’,‘Tobacco Use Prevalence’ have strong relationship
A scree plot is generated to visualize the proportion of variance explained by each principal component
plot(explained_variance, type = "b", xlab = "Principal Component", ylab = "Proportion of Variance Explained", main = "Scree Plot")
abline(h = 0.7, col = "lightblue", lty = 2)
From the result, I decide to take the first 5 principal components, then applies K-means clustering to these scores to group countries into clusters based on their health indicators. This is expected to reveal patterns or groupings that correspond to different health and life expectancy profiles which is important to target interventions By comparing clusters, we can understand the key differences in health indicators that contribute to varying life expectancies across countries. This can reveal which factors are most critical in determining health outcomes.
pca_scores <- pca_result$x[, 1:5]
set.seed(123)
kmeans_result <- kmeans(pca_scores, centers = 3)
print(kmeans_result$size)
## [1] 25 12 17
print(kmeans_result$centers)
## PC1 PC2 PC3 PC4 PC5
## 1 -1.8597302 -0.2800062 -0.4219174 0.02560692 -0.15982340
## 2 0.2707778 1.5946251 1.4979131 0.33624473 0.36251564
## 3 2.5437600 -0.7138439 -0.4368836 -0.27500646 -0.02085898
Cluster 1 contains 25 countries. Cluster 2 contains 12 countries. Cluster 3 contains 17 countries.
pca_clusters combines the scores of the first five principal components with the cluster assignments obtained through K-means clustering. Each row in pca_clusters represents a country with its scores on the principal components and its corresponding cluster label
pca_clusters <- data.frame(pca_scores, Cluster = kmeans_result$cluster)
I use the ggplot2 package to create a scatter plot to visualize how the clusters are distributed in the reduced-dimensional space created by PCA, revealing patterns or groupings that correspond to different health and life expectancy profiles
ggplot(pca_clusters, aes(x = PC1, y = PC2, color = factor(Cluster))) +
geom_point(alpha = 0.6) +
theme_minimal() +
labs(color = 'Cluster') +
theme(legend.position = "right")
Countries in cluster 1 have predominantly negative scores on PC1,
suggesting a profile of health indicators negatively correlated with
those that have a strong positive loading on PC1. cluster 3 includes
countries with positive PC1 scores, suggesting that the health
indicators with positive loadings on PC1 are more prevalent or
significant in these countries.
Then I create a ‘numeric_data’ dataframe which has a cluster label indicating the group to which the corresponding observation has been assigned based on the PCA and clustering analysis
numeric_data <- dataset[, c(1, which(sapply(dataset, is.numeric)))]
numeric_data$Cluster <- kmeans_result$cluster
calculate the mean of each numeric feature for each cluster,summarizes the average profile of health indicators for each cluster, providing insights into the characteristics that differentiate the clusters.
numeric_data_without_country <- numeric_data[, -1]
cluster_profiles <- aggregate(. ~ Cluster, data = numeric_data_without_country, mean)
cluster_profiles
## Cluster LifeExpectancy ViolenceAgainstWomen MaternalMortality
## 1 1 64.29600 32.64000 41.98400
## 2 2 68.43333 30.83333 19.20833
## 3 3 72.43529 28.41176 11.11765
## UnsafeWASHMortality PM25Concentration CleanFuelAndTechnology
## 1 44.36000 35.53600 10.84000
## 2 24.55000 31.14167 37.25000
## 3 13.10588 16.60000 74.05882
## HypertensionPrevalence SuicideMortality ObesityPrevalence HIVInfectionRate
## 1 35.40000 6.612000 8.388000 5.1120000
## 2 33.35000 5.841667 8.458333 0.9916667
## 3 36.65294 10.617647 21.929412 7.8176471
## TuberculosisIncidence MalariaIncidence RoadTrafficMortality HomicideMortality
## 1 16.72800 21.5780000 29.48400 8.028000
## 2 26.69167 3.1750000 16.39167 6.166667
## 3 12.64706 0.4170588 22.75294 18.682353
## AlcoholConsumptionPerCapita TobaccoUsePrevalence
## 1 4.368000 9.46800
## 2 3.083333 29.91667
## 3 5.476471 12.72353
Cluster 1 appears to represent countries with the most significant health challenges, including higher mortality rates and lower life expectancy. Cluster 2 includes countries with moderate life expectancy and better health outcomes than Cluster 1 but still facing significant health challenges. Cluster 3 consists of countries with the best average health indicators, highest life expectancy, and better access to clean technologies, although they face non-communicable disease challenges.
Then calculate the silhouette scores of the clusters identified by K-means clustering to assess their quality
silhouette_score <- silhouette(kmeans_result$cluster, dist(dataset_scaled))
plot(silhouette_score, col = "lightblue", bg = "lightgray")
Cluster 1 seems to be relatively better separated from the others,
meaning the countries in this cluster are more similar to each other
than to those in the other clusters. Clusters 2 and 3 have lower
silhouette scores, which may suggest that the countries in these
clusters are not as tightly grouped, or that these clusters are not as
distinct from one another.
Then I use ggplot to create a map where countries are colored based on their cluster assignment, represent how clusters are distributed worldwide
numeric_data$region <- numeric_data$Country
world_map <- map_data("world")
data_map <- merge(world_map, numeric_data, by = "region", all.x = TRUE)
ggplot() +
geom_polygon(data = data_map, aes(x = long, y = lat, group = group, fill = factor(Cluster)), color = "white") +
theme_minimal() +
labs(fill = "Cluster", title = "Geographical Distribution of Clusters") +
theme(legend.position = "bottom") + coord_cartesian(xlim = c(-10, 120), ylim = c(-50, 40))
Cluster 1 region has the lowest life expectancy, indicating widespread
public health issues and a lack of access to essential health services.
High maternal mortality and violence against women, alongside
significant mortality due to unsafe WASH conditions, suggest critical
needs in healthcare infrastructure and social services. Cluster 2
display moderate life expectancy and show improvements in public health
compared to Cluster 1. They have lower violence against women and
maternal mortality rates, indicating better health systems, but face
challenges such as high tobacco use and tuberculosis incidence. Cluster
3 has the highest life expectancy, reflecting advanced healthcare
systems and better health outcomes. Despite this, they face challenges
with non-communicable diseases, as indicated by high rates of obesity,
hypertension, and alcohol consumption, as well as mental health concerns
highlighted by the highest suicide mortality rate.
Then we apply Association Rule Mining uncover the relationships between various health indicators and life expectancy across each countries First I do the Data Categorization and tranform the data into categorical levels (Low, Medium, High). This step helps the discovery of rules to be more interpretable
categorize_column <- function(column) {
cut(column,
breaks = quantile(column, probs = c(0, .33, .67, 1), na.rm = TRUE),
labels = c("Low", "Medium", "High"),
include.lowest = TRUE)
}
dataset_cat <- dataset %>%
mutate(across(-1 & where(is.numeric), categorize_column))
head(dataset_cat)
## Country LifeExpectancy ViolenceAgainstWomen
## 1 Afghanistan Low High
## 14 Bangladesh High High
## 19 Benin Low Medium
## 21 Bolivia (Plurinational State of) High High
## 23 Botswana Low Medium
## 24 Brazil High Low
## MaternalMortality UnsafeWASHMortality PM25Concentration
## 1 High Low High
## 14 Low Medium High
## 19 High High Medium
## 21 Medium Low Medium
## 23 Medium Medium Low
## 24 Low Low Low
## CleanFuelAndTechnology HypertensionPrevalence SuicideMortality
## 1 Medium High Low
## 14 Medium Low Low
## 19 Low Low High
## 21 High Low Medium
## 23 High High High
## 24 High High Medium
## ObesityPrevalence HIVInfectionRate TuberculosisIncidence MalariaIncidence
## 1 Low Low Medium Medium
## 14 Low Low High Low
## 19 Medium Medium Low High
## 21 High Medium Medium Low
## 23 High High High Low
## 24 High Medium Low Medium
## RoadTrafficMortality HomicideMortality AlcoholConsumptionPerCapita
## 1 Low Medium Low
## 14 Low Low Low
## 19 Medium Low High
## 21 Medium Medium Medium
## 23 Medium High High
## 24 Low High High
## TobaccoUsePrevalence
## 1 High
## 14 High
## 19 Low
## 21 Medium
## 23 High
## 24 Medium
transactions <- apply(dataset_cat, 1, function(row) {
items <- paste(names(row), as.character(row), sep="=")
return(items)
})
transactions <- transactions[-1, ]
transactions_list <- apply(transactions, 2, function(col) {
list(as.character(col))
})
transactions_list <- unlist(transactions_list, recursive = FALSE)
trans <- as(transactions_list, "transactions")
Then I Apply the apriori algorithm to discover frequent itemsets which are presumably composed of categorized health indicators and life expectancy levels and generate rules
rules <- apriori(trans,
parameter = list(supp = 0.2, conf = 0.6),
appearance = list(default = "lhs", rhs = c("LifeExpectancy=High", "LifeExpectancy=Medium", "LifeExpectancy=Low")),
control = list(verbose = TRUE))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.6 0.1 1 none FALSE TRUE 5 0.2 1
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 10
##
## set item appearances ...[3 item(s)] done [0.00s].
## set transactions ...[48 item(s), 54 transaction(s)] done [0.00s].
## sorting and recoding items ... [48 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 done [0.00s].
## writing ... [19 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_sorted <- sort(rules, by = "confidence")
inspect(rules_sorted[1:10])
## lhs rhs support confidence coverage lift count
## [1] {MalariaIncidence=Low,
## UnsafeWASHMortality=Low} => {LifeExpectancy=High} 0.2037037 1.0000000 0.2037037 3.176471 11
## [2] {MalariaIncidence=High,
## UnsafeWASHMortality=High} => {LifeExpectancy=Low} 0.2407407 1.0000000 0.2407407 3.000000 13
## [3] {MaternalMortality=High,
## UnsafeWASHMortality=High} => {LifeExpectancy=Low} 0.2037037 1.0000000 0.2037037 3.000000 11
## [4] {CleanFuelAndTechnology=High,
## UnsafeWASHMortality=Low} => {LifeExpectancy=High} 0.2407407 0.9285714 0.2592593 2.949580 13
## [5] {MaternalMortality=Low,
## UnsafeWASHMortality=Low} => {LifeExpectancy=High} 0.2037037 0.9166667 0.2222222 2.911765 11
## [6] {CleanFuelAndTechnology=High,
## MaternalMortality=Low,
## UnsafeWASHMortality=Low} => {LifeExpectancy=High} 0.2037037 0.9166667 0.2222222 2.911765 11
## [7] {CleanFuelAndTechnology=High,
## MaternalMortality=Low} => {LifeExpectancy=High} 0.2222222 0.8571429 0.2592593 2.722689 12
## [8] {MalariaIncidence=High,
## MaternalMortality=High} => {LifeExpectancy=Low} 0.2037037 0.8461538 0.2407407 2.538462 11
## [9] {UnsafeWASHMortality=Low} => {LifeExpectancy=High} 0.2777778 0.8333333 0.3333333 2.647059 15
## [10] {CleanFuelAndTechnology=High} => {LifeExpectancy=High} 0.2592593 0.7777778 0.3333333 2.470588 14
Rules [1], [2], and [8] highlight a strong association between MalariaIncidence, UnsafeWASHMortality, and life expectancy. Rules [3] and [5] show that high maternal mortality and high unsafe WASH mortality are strongly linked to low life expectancy The presence of clean fuel and technology combined with low unsafe WASH mortality ([4], [6], and [7]) is predominantly associated with high life expectancy These rules collectively suggest that improving access to clean fuel and technology, reducing unsafe WASH mortality, and addressing malaria and maternal mortality could be effective strategies for increasing life expectancy.
The results show the critical impact of controlling malaria, improving maternal health, and ensuring safe water, sanitation, and hygiene on increasing life expectancy. High access to clean fuel and technology appears to be a key factor in achieving higher life expectancy, suggesting that energy and infrastructure policies can have significant health impacts. Public health strategies that target these areas are likely to be effective in improving life expectancy based on the dataset. Improvements in infrastructure, particularly in access to clean fuel and technology, along with better healthcare services, could lead to higher life expectancy.