tb_burden
Naimul Islam
2025-11-26
Load libraries
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
##
## Attaching package: 'janitor'
##
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
##
##
##
## Attaching package: 'scales'
##
##
## The following object is masked from 'package:purrr':
##
## discard
##
##
## The following object is masked from 'package:readr':
##
## col_factorRead data from Google Sheet
## Rows: 5,347
## Columns: 50
## $ country <chr> "Afghanistan", "Afghanistan", "Afghanistan", …
## $ iso2 <chr> "AF", "AF", "AF", "AF", "AF", "AF", "AF", "AF…
## $ iso3 <chr> "AFG", "AFG", "AFG", "AFG", "AFG", "AFG", "AF…
## $ iso_numeric <dbl> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, …
## $ g_whoregion <chr> "EMR", "EMR", "EMR", "EMR", "EMR", "EMR", "EM…
## $ year <dbl> 2000, 2001, 2002, 2003, 2004, 2005, 2006, 200…
## $ e_pop_num <dbl> 20130323, 20284311, 21378110, 22733047, 23560…
## $ e_inc_100k <dbl> 148, 175, 197, 215, 228, 237, 242, 241, 235, …
## $ e_inc_100k_lo <dbl> 46, 66, 83, 97, 109, 118, 124, 127, 127, 126,…
## $ e_inc_100k_hi <dbl> 1510, 1320, 1140, 992, 862, 754, 662, 597, 55…
## $ e_inc_num <dbl> 30000, 35000, 42000, 49000, 54000, 58000, 620…
## $ e_inc_num_lo <dbl> 9200, 13000, 18000, 22000, 26000, 29000, 3200…
## $ e_inc_num_hi <dbl> 305000, 267000, 245000, 225000, 203000, 18400…
## $ e_tbhiv_prct <dbl> 0.02, 0.01, 0.01, 0.01, 0.01, 0.02, 0.02, 0.0…
## $ e_tbhiv_prct_lo <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ e_tbhiv_prct_hi <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ e_inc_tbhiv_100k <dbl> 0.03, 0.03, 0.03, 0.03, 0.03, 0.04, 0.04, 0.0…
## $ e_inc_tbhiv_100k_lo <dbl> 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.0…
## $ e_inc_tbhiv_100k_hi <dbl> 0.07, 0.08, 0.08, 0.09, 0.10, 0.12, 0.13, 0.1…
## $ e_inc_tbhiv_num <dbl> 5, 5, 6, 7, 8, 9, 11, 13, 13, 14, 15, 15, 16,…
## $ e_inc_tbhiv_num_lo <dbl> 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ e_inc_tbhiv_num_hi <dbl> 15, 16, 18, 21, 24, 28, 33, 37, 39, 42, 44, 4…
## $ e_mort_exc_tbhiv_100k <dbl> 50.00, 55.00, 59.00, 68.00, 67.00, 66.00, 64.…
## $ e_mort_exc_tbhiv_100k_lo <dbl> 32.00, 37.00, 41.00, 48.00, 47.00, 47.00, 46.…
## $ e_mort_exc_tbhiv_100k_hi <dbl> 70.00, 76.00, 80.00, 92.00, 89.00, 88.00, 85.…
## $ e_mort_exc_tbhiv_num <dbl> 10000, 11000, 13000, 15000, 16000, 16000, 160…
## $ e_mort_exc_tbhiv_num_lo <dbl> 6500, 7600, 8700, 11000, 11000, 11000, 12000,…
## $ e_mort_exc_tbhiv_num_hi <dbl> 14000, 15000, 17000, 21000, 21000, 21000, 220…
## $ e_mort_tbhiv_100k <dbl> 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.0…
## $ e_mort_tbhiv_100k_lo <dbl> 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.00, 0.0…
## $ e_mort_tbhiv_100k_hi <dbl> 0.05, 0.05, 0.05, 0.05, 0.06, 0.06, 0.07, 0.0…
## $ e_mort_tbhiv_num <dbl> 3, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 7, 7, 7, 8, …
## $ e_mort_tbhiv_num_lo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, …
## $ e_mort_tbhiv_num_hi <dbl> 9, 9, 10, 12, 13, 15, 17, 17, 19, 21, 21, 21,…
## $ e_mort_100k <dbl> 50.00, 55.00, 59.00, 68.00, 67.00, 66.00, 64.…
## $ e_mort_100k_lo <dbl> 32.00, 37.00, 41.00, 48.00, 47.00, 47.00, 46.…
## $ e_mort_100k_hi <dbl> 70.0, 76.0, 80.0, 92.0, 89.0, 88.0, 85.0, 79.…
## $ e_mort_num <dbl> 10000, 11000, 13000, 15000, 16000, 16000, 160…
## $ e_mort_num_lo <dbl> 6500, 7600, 8700, 11000, 11000, 11000, 12000,…
## $ e_mort_num_hi <dbl> 14000, 15000, 17000, 21000, 21000, 21000, 220…
## $ cfr <dbl> 0.34, 0.32, 0.30, 0.32, 0.29, 0.28, 0.27, 0.2…
## $ cfr_lo <dbl> 0.19, 0.20, 0.19, 0.21, 0.20, 0.19, 0.18, 0.1…
## $ cfr_hi <dbl> 0.50, 0.46, 0.42, 0.44, 0.40, 0.38, 0.36, 0.3…
## $ cfr_pct <dbl> 34, 32, 30, 32, 29, 28, 27, 25, 25, 26, 25, 2…
## $ cfr_pct_lo <dbl> 19, 20, 19, 21, 20, 19, 18, 17, 17, 18, 17, 1…
## $ cfr_pct_hi <dbl> 50, 46, 42, 44, 40, 38, 36, 33, 34, 36, 34, 3…
## $ c_newinc_100k <dbl> 35, 50, 65, 61, 78, 90, 100, 111, 107, 95, 99…
## $ c_cdr <dbl> 24, 29, 33, 28, 34, 38, 41, 46, 45, 42, 45, 4…
## $ c_cdr_lo <dbl> 2.3, 3.8, 5.6, 6.1, 9.1, 12.0, 15.0, 19.0, 19…
## $ c_cdr_hi <dbl> 77, 76, 78, 63, 72, 76, 81, 87, 84, 75, 81, 8…Basic descriptive summary
## country iso2 iso3 iso_numeric
## Length:5347 Length:5347 Length:5347 Min. : 4.0
## Class :character Class :character Class :character 1st Qu.:212.0
## Mode :character Mode :character Mode :character Median :430.0
## Mean :432.5
## 3rd Qu.:646.0
## Max. :894.0
##
## g_whoregion year e_pop_num e_inc_100k
## Length:5347 Min. :2000 Min. :1.552e+03 Min. : 0.0
## Class :character 1st Qu.:2006 1st Qu.:7.594e+05 1st Qu.: 11.0
## Mode :character Median :2012 Median :5.963e+06 Median : 53.5
## Mean :2012 Mean :3.350e+07 Mean : 138.2
## 3rd Qu.:2018 3rd Qu.:2.163e+07 3rd Qu.: 181.0
## Max. :2024 Max. :1.451e+09 Max. :2700.0
## NA's :25
## e_inc_100k_lo e_inc_100k_hi e_inc_num e_inc_num_lo
## Min. : 0.00 Min. : 0.0 Min. : 0 Min. : 0.0
## 1st Qu.: 9.30 1st Qu.: 14.0 1st Qu.: 270 1st Qu.: 202.5
## Median : 40.00 Median : 69.0 Median : 3500 Median : 2500.0
## Mean : 87.12 Mean : 252.4 Mean : 52875 Mean : 33578.6
## 3rd Qu.: 114.75 3rd Qu.: 276.0 3rd Qu.: 19000 3rd Qu.: 12000.0
## Max. :2200.00 Max. :23500.0 Max. :3590000 Max. :2620000.0
## NA's :25 NA's :25 NA's :25 NA's :25
## e_inc_num_hi e_tbhiv_prct e_tbhiv_prct_lo e_tbhiv_prct_hi
## Min. : 0 Min. : 0.00 Mode:logical Mode:logical
## 1st Qu.: 340 1st Qu.: 1.10 NA's:5347 NA's:5347
## Median : 4500 Median : 5.00
## Mean : 82710 Mean :11.86
## 3rd Qu.: 31000 3rd Qu.:15.00
## Max. :7070000 Max. :84.00
## NA's :25 NA's :895
## e_inc_tbhiv_100k e_inc_tbhiv_100k_lo e_inc_tbhiv_100k_hi e_inc_tbhiv_num
## Min. : 0.00 Min. : 0.0 Min. : 0.00 Min. : 0
## 1st Qu.: 0.27 1st Qu.: 0.1 1st Qu.: 0.48 1st Qu.: 18
## Median : 2.60 Median : 1.3 Median : 4.05 Median : 210
## Mean : 38.03 Mean : 17.3 Mean : 70.23 Mean : 7413
## 3rd Qu.: 15.00 3rd Qu.: 7.8 3rd Qu.: 24.00 3rd Qu.: 2300
## Max. :1320.00 Max. :693.0 Max. :4610.00 Max. :466000
## NA's :895 NA's :895 NA's :895 NA's :895
## e_inc_tbhiv_num_lo e_inc_tbhiv_num_hi e_mort_exc_tbhiv_100k
## Min. : 0 Min. : 0.0 Min. : 0.00
## 1st Qu.: 8 1st Qu.: 31.8 1st Qu.: 1.20
## Median : 110 Median : 330.0 Median : 6.10
## Mean : 3167 Mean : 13921.2 Mean : 22.22
## 3rd Qu.: 1100 3rd Qu.: 3825.0 3rd Qu.: 27.00
## Max. :220000 Max. :1160000.0 Max. :1210.00
## NA's :895 NA's :895 NA's :815
## e_mort_exc_tbhiv_100k_lo e_mort_exc_tbhiv_100k_hi e_mort_exc_tbhiv_num
## Min. : 0.00 Min. : 0.00 Min. : 0
## 1st Qu.: 1.10 1st Qu.: 1.30 1st Qu.: 52
## Median : 4.50 Median : 7.50 Median : 480
## Mean : 14.21 Mean : 32.55 Mean : 8089
## 3rd Qu.: 17.00 3rd Qu.: 39.00 3rd Qu.: 2800
## Max. :765.00 Max. :1760.00 Max. :848000
## NA's :815 NA's :815 NA's :815
## e_mort_exc_tbhiv_num_lo e_mort_exc_tbhiv_num_hi e_mort_tbhiv_100k
## Min. : 0 Min. : 0 Min. : 0.00
## 1st Qu.: 43 1st Qu.: 57 1st Qu.: 0.06
## Median : 350 Median : 590 Median : 0.62
## Mean : 5692 Mean : 11078 Mean : 14.50
## 3rd Qu.: 1700 3rd Qu.: 3800 3rd Qu.: 5.00
## Max. :567000 Max. :1210000 Max. :510.00
## NA's :815 NA's :815 NA's :815
## e_mort_tbhiv_100k_lo e_mort_tbhiv_100k_hi e_mort_tbhiv_num e_mort_tbhiv_num_lo
## Min. : 0.000 Min. : 0.00 Min. : 0 Min. : 0.0
## 1st Qu.: 0.020 1st Qu.: 0.11 1st Qu.: 4 1st Qu.: 2.0
## Median : 0.300 Median : 1.10 Median : 55 Median : 26.5
## Mean : 6.596 Mean : 26.42 Mean : 2914 Mean : 1235.2
## 3rd Qu.: 2.600 3rd Qu.: 8.60 3rd Qu.: 770 3rd Qu.: 370.0
## Max. :224.000 Max. :1620.00 Max. :223000 Max. :112000.0
## NA's :815 NA's :815 NA's :815 NA's :815
## e_mort_tbhiv_num_hi e_mort_100k e_mort_100k_lo e_mort_100k_hi
## Min. : 0 Min. : 0.00 Min. : 0.00 Min. : 0.0
## 1st Qu.: 8 1st Qu.: 0.85 1st Qu.: 0.67 1st Qu.: 1.0
## Median : 87 Median : 4.80 Median : 3.70 Median : 5.7
## Mean : 5480 Mean : 31.41 Mean : 19.63 Mean : 46.9
## 3rd Qu.: 1300 3rd Qu.: 30.00 3rd Qu.: 21.00 3rd Qu.: 40.0
## Max. :554000 Max. :1320.00 Max. :848.00 Max. :1890.0
## NA's :815 NA's :25 NA's :25 NA's :25
## e_mort_num e_mort_num_lo e_mort_num_hi cfr
## Min. : 0 Min. : 0 Min. : 0 Min. :0.0000
## 1st Qu.: 22 1st Qu.: 17 1st Qu.: 27 1st Qu.:0.0700
## Median : 300 Median : 250 Median : 340 Median :0.1200
## Mean : 9368 Mean : 6398 Mean : 13053 Mean :0.1632
## 3rd Qu.: 3200 3rd Qu.: 2175 3rd Qu.: 4100 3rd Qu.:0.2400
## Max. :1040000 Max. :707000 Max. :1440000 Max. :1.0000
## NA's :25 NA's :25 NA's :25 NA's :815
## cfr_lo cfr_hi cfr_pct cfr_pct_lo
## Min. :0.0000 Min. :0.0000 Min. : 0.00 Min. : 0.000
## 1st Qu.:0.0500 1st Qu.:0.0900 1st Qu.: 7.00 1st Qu.: 5.000
## Median :0.0800 Median :0.1600 Median : 12.00 Median : 8.000
## Mean :0.0929 Mean :0.2421 Mean : 16.32 Mean : 9.292
## 3rd Qu.:0.1300 3rd Qu.:0.3600 3rd Qu.: 24.00 3rd Qu.:13.000
## Max. :0.4400 Max. :1.0000 Max. :100.00 Max. :44.000
## NA's :815 NA's :815 NA's :815 NA's :815
## cfr_pct_hi c_newinc_100k c_cdr c_cdr_lo
## Min. : 0.00 Min. : 0.00 Min. : 2.60 Min. : 0.46
## 1st Qu.: 9.00 1st Qu.: 9.90 1st Qu.: 51.00 1st Qu.: 34.00
## Median : 16.00 Median : 36.00 Median : 66.00 Median : 53.00
## Mean : 24.21 Mean : 73.06 Mean : 66.16 Mean : 50.94
## 3rd Qu.: 36.00 3rd Qu.: 94.25 3rd Qu.: 81.00 3rd Qu.: 66.00
## Max. :100.00 Max. :947.00 Max. :190.00 Max. :160.00
## NA's :815 NA's :207 NA's :364 NA's :364
## c_cdr_hi
## Min. : 4.10
## 1st Qu.: 74.00
## Median : 90.00
## Mean : 92.29
## 3rd Qu.: 100.00
## Max. :1600.00
## NA's :364## # A tibble: 1 × 4
## n_rows n_countries year_min year_max
## <int> <int> <dbl> <dbl>
## 1 5347 217 2000 2024Visualizations
Incidence histogram (color gradient)
## Warning: The dot-dot notation (`..count..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(count)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
CDR histogram – colorful & clean
## Incidence vs mortality – colorful scatter by region
## `geom_smooth()` using formula = 'y ~ x'
CFR (%) over time by WHO region
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## Warning: Removed 815 rows containing missing values or values outside the scale range
## (`geom_line()`).
Incidence trend by region – filled ribbons (extra pretty)
prepare data
Overall summary table (gtsummary → gt)
| Characteristic | N = 2151 |
|---|---|
| Incidence per 100,000 | 96.9 (142.1) |
| Unknown | 1 |
| Mortality (HIV-negative) per 100,000 | 12.5 (19.7) |
| Unknown | 33 |
| Case fatality ratio (%) | 13.0 (9.8) |
| Unknown | 33 |
| Case detection ratio (%) | 76.0 (15.6) |
| Unknown | 22 |
| 1 Mean (SD) | |
| Indicator | N | AFR N = 471 |
AMR N = 451 |
EMR N = 221 |
EUR N = 541 |
SEA N = 101 |
WPR N = 371 |
|---|---|---|---|---|---|---|---|
| Incidence per 100,000 | 214 | 187.6 (132.7) | 32.4 (40.3) | 71.0 (117.7) | 22.0 (30.3) | 227.7 (162.0) | 152.9 (217.7) |
| Unknown | 0 | 0 | 0 | 0 | 1 | 0 | |
| Mortality (HIV-negative) per 100,000 | 182 | 22.8 (16.4) | 3.2 (3.7) | 11.3 (27.5) | 1.9 (2.9) | 32.3 (26.2) | 18.7 (27.0) |
| Unknown | 1 | 16 | 0 | 5 | 1 | 10 | |
| Case fatality ratio (%) | 182 | 19.0 (5.6) | 10.9 (6.8) | 14.5 (20.5) | 8.9 (5.4) | 13.3 (6.3) | 11.4 (7.2) |
| Unknown | 1 | 16 | 0 | 5 | 1 | 10 | |
| Case detection ratio (%) | 193 | 70.4 (10.3) | 81.9 (14.1) | 71.0 (11.9) | 82.1 (16.4) | 68.0 (14.2) | 73.1 (19.6) |
| Unknown | 1 | 11 | 1 | 2 | 1 | 6 | |
| 1 Mean (SD) | |||||||