Case classification analysis

Author

Raphael Saldanha

Last modification

February 19, 2024 | 10:01:36 +01:00

This is a descriptive report about dengue case classification and criteria.

Packages

library(tidyverse)
library(arrow)
library(knitr)
library(lubridate)
source("../functions.R")

Execution node

node_name()

[1] "rfsaldanha"

Load data

important_vars <- c("DT_SIN_PRI", "RESUL_SORO", "SOROTIPO", "CLASSI_FIN", "CRITERIO")

valid_interval <- interval(ymd("2011-01-01"), ymd("2022-12-31"))

dengue_files_list <- c(
  data_dir("dengue_data/parquets/dengue_2011.parquet"),
  data_dir("dengue_data/parquets/dengue_2012.parquet"),
  data_dir("dengue_data/parquets/dengue_2013.parquet"),
  data_dir("dengue_data/parquets/dengue_2014.parquet"),
  data_dir("dengue_data/parquets/dengue_2015.parquet"),
  data_dir("dengue_data/parquets/dengue_2016.parquet"),
  data_dir("dengue_data/parquets/dengue_2017.parquet"),
  data_dir("dengue_data/parquets/dengue_2018.parquet"),
  data_dir("dengue_data/parquets/dengue_2019.parquet"),
  data_dir("dengue_data/parquets/dengue_2020.parquet"),
  data_dir("dengue_data/parquets/dengue_2021.parquet"),
  data_dir("dengue_data/parquets/dengue_2022.parquet")
)

dengue <- open_dataset(sources = dengue_files_list) %>%
  select(all_of(important_vars)) %>%
  collect() %>%
  mutate(DT_SIN_PRI = ymd(DT_SIN_PRI)) %>%
  filter(DT_SIN_PRI %within% valid_interval) %>%
  filter(CLASSI_FIN != "6")

Final classification and criteria

dengue %>%
  group_by(CLASSI_FIN, CRITERIO) %>%
  summarise(freq = n()) %>%
  ungroup() %>%
  kable(
    format.args = list(big.mark = ".", decimal.mark = ",")
  )

`summarise()` has grouped output by 'CLASSI_FIN'. You can override using the
`.groups` argument.

CLASSI_FIN	CRITERIO	freq
Dengue	Clínico epidemiológico	4.175.127
Dengue	Em investigação	69.101
Dengue	Laboratório	2.633.671
Dengue	NA	24
Dengue clássico	Clínico epidemiológico	1.439.136
Dengue clássico	Em investigação	16.796
Dengue clássico	Laboratório	880.966
Dengue clássico	NA	7
Dengue com complicações	Clínico epidemiológico	8.249
Dengue com complicações	Em investigação	595
Dengue com complicações	Laboratório	9.973
Dengue com sinais de alarme	Clínico epidemiológico	50.756
Dengue com sinais de alarme	Em investigação	2.553
Dengue com sinais de alarme	Laboratório	47.633
Dengue grave	Clínico epidemiológico	1.770
Dengue grave	Em investigação	488
Dengue grave	Laboratório	6.662
Descartado	Clínico epidemiológico	2.495.885
Descartado	Em investigação	9.383
Descartado	Laboratório	2.845.372
Descartado	NA	26
Febre hemorrágica do dengue	Clínico epidemiológico	2
Febre hemorrágica do dengue	Em investigação	230
Febre hemorrágica do dengue	Laboratório	5.041
Inconclusivo	Clínico epidemiológico	19.689
Inconclusivo	Em investigação	62.982
Inconclusivo	Laboratório	8.654
Inconclusivo	NA	2.052.830
Síndrome do choque do dengue	Clínico epidemiológico	5
Síndrome do choque do dengue	Em investigação	17
Síndrome do choque do dengue	Laboratório	273

dengue_classifications <- c("Febre hemorrágica do dengue", "Síndrome do choque do dengue", "Dengue com sinais de alarme",
  "Dengue clássico", "Dengue com complicações", "Dengue",
  "Dengue grave")

dengue_cases_classification <- dengue %>% 
  mutate(CLASSI_FIN = case_when(
    CLASSI_FIN %in% dengue_classifications ~ "Confirmed",
    CLASSI_FIN == "Descartado" ~ "Discarded",
    CLASSI_FIN == "Inconclusivo" ~ "Inconclusive",
    CLASSI_FIN == 6 ~ "Invalid",
    is.na(CLASSI_FIN) ~ "Missing",
    .default = CLASSI_FIN
  )) %>%
  mutate(DT_SIN_PRI = lubridate::ceiling_date(x = DT_SIN_PRI, unit = "month")) %>%
  group_by(DT_SIN_PRI, CLASSI_FIN) %>%
  summarise(freq = n()) %>%
  ungroup()

`summarise()` has grouped output by 'DT_SIN_PRI'. You can override using the
`.groups` argument.

write_parquet(x = dengue_cases_classification, sink = data_dir("dengue_data/parquet_classification/dengue_cases_classification.parquet"))

ggplot(data =  dengue_cases_classification, aes(x = DT_SIN_PRI, weight = freq, fill = CLASSI_FIN)) +
  geom_bar() +
  scale_fill_hue(direction = 1) +
  scale_y_continuous(labels = scales::comma) +
  labs(fill = "Classificação") +
  theme_minimal() +
  theme(legend.position = "bottom") +
  labs(x = "Month of first symptom's onset", y = "Records", fill = "Classification")

ggsave(filename = "dengue_cases_classification.pdf")

Saving 7 x 5 in image

Sorological examination

dengue %>%
  filter(CLASSI_FIN %in% dengue_classifications) %>%
  group_by(SOROTIPO) %>%
  summarise(freq = n()) %>%
  ungroup()

# A tibble: 5 × 2
  SOROTIPO    freq
  <chr>      <int>
1 DEN 1      46707
2 DEN 2      18891
3 DEN 3        213
4 DEN 4       6141
5 <NA>     9277123

Session info

sessionInfo()

R version 4.3.2 (2023-10-31)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 22.04.4 LTS

Matrix products: default
BLAS:   /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.10.0 
LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_CA.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_CA.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_CA.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_CA.UTF-8 LC_IDENTIFICATION=C       

time zone: Europe/Paris
tzcode source: system (glibc)

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] knitr_1.45      arrow_14.0.0.2  lubridate_1.9.3 forcats_1.0.0  
 [5] stringr_1.5.1   dplyr_1.1.4     purrr_1.0.2     readr_2.1.5    
 [9] tidyr_1.3.1     tibble_3.2.1    ggplot2_3.4.4   tidyverse_2.0.0

loaded via a namespace (and not attached):
 [1] bit_4.0.5         gtable_0.3.4      jsonlite_1.8.8    compiler_4.3.2   
 [5] tidyselect_1.2.0  assertthat_0.2.1  textshaping_0.3.7 systemfonts_1.0.5
 [9] scales_1.3.0      yaml_2.3.8        fastmap_1.1.1     R6_2.5.1         
[13] labeling_0.4.3    generics_0.1.3    htmlwidgets_1.6.4 munsell_0.5.0    
[17] pillar_1.9.0      tzdb_0.4.0        rlang_1.1.3       utf8_1.2.4       
[21] stringi_1.8.3     xfun_0.42         bit64_4.0.5       timechange_0.3.0 
[25] cli_3.6.2         withr_3.0.0       magrittr_2.0.3    digest_0.6.34    
[29] grid_4.3.2        hms_1.1.3         lifecycle_1.0.4   vctrs_0.6.5      
[33] evaluate_0.23     glue_1.7.0        farver_2.1.1      ragg_1.2.7       
[37] fansi_1.0.6       colorspace_2.1-0  rmarkdown_2.25    tools_4.3.2      
[41] pkgconfig_2.0.3   htmltools_0.5.7