Diabetes Mellitus and Latent Tuberculosis among HIV infected patients attending comprehensive care clinics in Nairobi, Kenya
Principal Investigator - Lucy Kanyara, Author-Allan Lusui
1/8/2021
Specific Objective
- To determine the prevalence of Diabetes among HIV infected patients
- To determine the prevalence of Latent TB among HIV infected patients
- To determine the Correlates of diabetes among HIV infected patients
- To determine the Correlates of latent TB among HIV infected patients
Setting up environment
Notes:The following packages were used(description shown)
library(tidyverse)#For data cleaning and organizing## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.5 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.0.2 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(ggplot2)#For plotting
library(knitr)#For use with rmarkdown oin presentation
library(lubridate)#For sdate use and conversion##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(readr)#For importing data
library(dplyr)#For making manipulations
library(rmarkdown)#For creating a sharable document
library(janitor)#For easing data cleaning##
## Attaching package: 'janitor'## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testlibrary(skimr)#For easy summaryIMPORT THE DATA(PREPARE)
Notes: Just the first 6 rows & then look at the structure
LabDatadf<-read.csv("C:\\Users\\Lusui\\Downloads\\Viral Load DMLTBi Demographic and Laboratory Data (1) (1).csv",stringsAsFactors = F)PREVIEW THE DATA AND FIND THE STRUCTURE
Notes: Just the first 6 rows & then look at the structure
head(LabDatadf)## DemographicData.Interviewer_Name DemographicData.participants_ID
## 1 1 383
## 2 2 686
## 3 3 2357
## 4 4 2375
## 5 5 3845
## 6 6 1510
## DemographicData.participants_residence DemographicData.participants_gender
## 1 Dandora Male
## 2 South B Male
## 3 Kitengela Female
## 4 UMOJA 1 Q61 Female
## 5 Gatundu Male
## 6 Mlango Kubwa Pangani Female
## Sputum.Results LBTi.QFT.Results Random.Blood.Sugar HbA1c eAG.mg.dL.
## 1 No AFB seen 0 10.3 0.101 243
## 2 No AFB seen 1 3.5
## 3 No AFB seen 0 4 0.066 143
## 4 No AFB seen 0 1.2
## 5 No AFB seen 0 5.3
## 6 No AFB seen 0 6.1
## Viral.Load.cp.ml.
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0tail(LabDatadf)## DemographicData.Interviewer_Name DemographicData.participants_ID
## 268 301 604
## 269 302 1636
## 270 303 2305
## 271 304 3754
## 272 305 2597
## 273 306 815
## DemographicData.participants_residence DemographicData.participants_gender
## 268 Dagoretti Corner Male
## 269 Githunguri Male
## 270 Utawala Female
## 271 Ng'ong road Female
## 272 Kitengela Female
## 273 Kitui Female
## Sputum.Results LBTi.QFT.Results Random.Blood.Sugar HbA1c eAG.mg.dL.
## 268 No AFB seen 1 6.8 0.073 163
## 269 No AFB seen 1 4.3
## 270 No AFB seen 0 1 0.06 126
## 271 Falcon empty 0 4.5
## 272 No AFB seen 1 4.1
## 273 No AFB seen 0 3
## Viral.Load.cp.ml.
## 268 0
## 269 0
## 270 0
## 271 0
## 272 0
## 273 0#Structure
str(LabDatadf)## 'data.frame': 273 obs. of 10 variables:
## $ DemographicData.Interviewer_Name : int 1 2 3 4 5 6 7 9 10 11 ...
## $ DemographicData.participants_ID : int 383 686 2357 2375 3845 1510 1152 2809 3854 3239 ...
## $ DemographicData.participants_residence: chr "Dandora" "South B" "Kitengela" "UMOJA 1 Q61" ...
## $ DemographicData.participants_gender : chr "Male" "Male" "Female" "Female" ...
## $ Sputum.Results : chr "No AFB seen" "No AFB seen" "No AFB seen" "No AFB seen" ...
## $ LBTi.QFT.Results : chr "0" "1" "0" "0" ...
## $ Random.Blood.Sugar : chr "10.3" "3.5" "4" "1.2" ...
## $ HbA1c : chr "0.101" "" "0.066" "" ...
## $ eAG.mg.dL. : chr "243" "" "143" "" ...
## $ Viral.Load.cp.ml. : chr "0" "0" "0" "0" ...CLEANING(PROCESS)
CHECK FOR ANY DUPLICATES AND MISSING VALUES
CLEAN COLUMN NAMES
Notes: Check is done by different simple functions
#cleaning column names
LD2<-clean_names(LabDatadf)
#changing character values to numerical
LD3 <- LD2 %>%
mutate_at(c('hb_a1c','random_blood_sugar','e_ag_mg_d_l','viral_load_cp_ml','lb_ti_qft_results','sputum_results'), as.numeric)## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion#confirming if the attributes have changed
str(LD3)## 'data.frame': 273 obs. of 10 variables:
## $ demographic_data_interviewer_name : int 1 2 3 4 5 6 7 9 10 11 ...
## $ demographic_data_participants_id : int 383 686 2357 2375 3845 1510 1152 2809 3854 3239 ...
## $ demographic_data_participants_residence: chr "Dandora" "South B" "Kitengela" "UMOJA 1 Q61" ...
## $ demographic_data_participants_gender : chr "Male" "Male" "Female" "Female" ...
## $ sputum_results : num NA NA NA NA NA NA NA NA NA NA ...
## $ lb_ti_qft_results : num 0 1 0 0 0 0 0 0 1 0 ...
## $ random_blood_sugar : num 10.3 3.5 4 1.2 5.3 6.1 3.1 4.7 8.4 3.3 ...
## $ hb_a1c : num 0.101 NA 0.066 NA NA NA NA NA 0.057 NA ...
## $ e_ag_mg_d_l : num 243 NA 143 NA NA NA NA NA 117 NA ...
## $ viral_load_cp_ml : num 0 0 0 0 0 0 0 0 0 0 ...#changing the induced nas to zero
LD3[is.na(LD3)]=0
#check for any na values
sum(is.na(LD3))## [1] 0#check for duplicates
sum(duplicated(LD3))## [1] 0#Conclusuion:there are no missing values in the data set
#The nas,negative,LD3,NO AFB were changed to zero
#Indeterminate and positives were changed to 1Summary of the cleaning process involved
1)The names were changed to a readable format(to the r studio)
2)Upon looking at the structure of the columns the HbA1c,Random Blood sugar eAg Viral Load Latent Tb results and Sputum results were formatted as a character data type they were changed to numeric data type. Naturally this introduced a lot of Nas
3)On the sputum results column All “No AFB seen” were changed to zero since absence is implied for this specific term
4)On the eAg column all Nas were introduced by coercion on the 2nd step. They were originally zeros and this was maintained by converting the nas on this row to zero
5)On the viral load column, All positives were changed to 1s and negatives to 0s.The goal was to operate with boolean values *In addition to this all indeterminates were changed to 1s since viral load was present but at normal levels. All this wa done on spreadsheets
6)There are no duplicates or missing values in our dataset since they were all dealt with
ANALYZING OUR DATA
Correlates of diabetes among HIV infected patients
Correlates of latent TB among HIV infected patients
Notes:We Get summaries of our data
# is there a relation between blood sugar and viral load in blood?
cor(LD3$random_blood_sugar,LD3$viral_load_cp_ml,use = "complete.obs")## [1] 0.04229719# 4.2% relation(minimal relation)
# is there a relation between hbA1c Levels and viral load in blood?
cor(LD3$hb_a1c,LD3$viral_load_cp_ml,use = "complete.obs")## [1] -0.03421149# -3.2% relation(no relatrion)
# is there a relation between Latent TB and viral load in blood?
cor(LD3$viral_load_cp_ml,LD3$lb_ti_qft_results,use = "complete.obs")## [1] 0.08953833#7.4% relation(little)
# is there a relation between sputum results and viral load in blood?
cor(LD3$viral_load_cp_ml,LD3$sputum_results ,use = "complete.obs")## Warning in cor(LD3$viral_load_cp_ml, LD3$sputum_results, use = "complete.obs"):
## the standard deviation is zero## [1] NA#-0.8(absolutely no relation)Results of our correlation analysis
Conclusion:Given the size of the data set and sample sizesthe folowing was observed;
- Sputum results and hbA1c show no(negative) correlation to viral load in blood
- Blood sugar showed a0 4.2% correlation with viral load in blood
- Latent Tb showed a 7.4% correlation with viral load(highest) We will use a model to further confirm these results
Creating a model with blood sugar as our constant
This is an effort to determine a formula that will determine the prevelance of Diabetes among Hiv patients
test_mod_1 <- lm(random_blood_sugar~
demographic_data_interviewer_name+
demographic_data_participants_id+
demographic_data_participants_gender+
sputum_results+
lb_ti_qft_results+
hb_a1c+
e_ag_mg_d_l+
viral_load_cp_ml
, data = LD3)
summary(test_mod_1)##
## Call:
## lm(formula = random_blood_sugar ~ demographic_data_interviewer_name +
## demographic_data_participants_id + demographic_data_participants_gender +
## sputum_results + lb_ti_qft_results + hb_a1c + e_ag_mg_d_l +
## viral_load_cp_ml, data = LD3)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6982 -0.8116 -0.2198 0.7689 16.4260
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.196e+00 3.230e-01 12.991 < 2e-16
## demographic_data_interviewer_name 3.690e-04 1.377e-03 0.268 0.789
## demographic_data_participants_id 1.355e-05 6.028e-05 0.225 0.822
## demographic_data_participants_genderMale 7.828e-02 2.618e-01 0.299 0.765
## sputum_results NA NA NA NA
## lb_ti_qft_results -2.831e-01 2.485e-01 -1.139 0.256
## hb_a1c -3.892e+02 6.721e+01 -5.791 1.97e-08
## e_ag_mg_d_l 1.844e-01 2.948e-02 6.256 1.58e-09
## viral_load_cp_ml 1.335e-05 1.398e-05 0.955 0.340
##
## (Intercept) ***
## demographic_data_interviewer_name
## demographic_data_participants_id
## demographic_data_participants_genderMale
## sputum_results
## lb_ti_qft_results
## hb_a1c ***
## e_ag_mg_d_l ***
## viral_load_cp_ml
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.022 on 265 degrees of freedom
## Multiple R-squared: 0.2258, Adjusted R-squared: 0.2053
## F-statistic: 11.04 on 7 and 265 DF, p-value: 3.05e-12ANOVA FOR THE FIRST MODEL
This is an effort to determine a formula that will determine the prevelance of Diabetes among Hiv patients
anova(test_mod_1)## Analysis of Variance Table
##
## Response: random_blood_sugar
## Df Sum Sq Mean Sq F value Pr(>F)
## demographic_data_interviewer_name 1 0.76 0.761 0.1862 0.66649
## demographic_data_participants_id 1 0.04 0.044 0.0107 0.91777
## demographic_data_participants_gender 1 2.94 2.944 0.7200 0.39690
## lb_ti_qft_results 1 17.92 17.921 4.3824 0.03726 *
## hb_a1c 1 129.98 129.985 31.7864 4.402e-08 ***
## e_ag_mg_d_l 1 160.65 160.654 39.2864 1.476e-09 ***
## viral_load_cp_ml 1 3.73 3.729 0.9118 0.34050
## Residuals 265 1083.67 4.089
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1The significant variables in this models were: * the intercept for random blood sugar * The Limuru Residence * Latent TB results * hbA1c results * e-ag results
Take aways from the first model
Model type= Multiple linear regression
- The model Pvalue 0.7788>0.05 which is an indicator of non significance of the model
- The model R squared was at 51%…we can translate this as the prevelance of this model can be described by this model correctly at a 51% rate
- The r(r=squareroot(Multiple R)) of this model is at 7.35% this means that this model is 7% accurate
- The significance of the variables is indicated by the stars on the model as well as the anova for this model
Conclusion
This model is not accurate enough to describe the prevalence of Diabetes in HIV infected patients
Creating a model with blood sugar as our constant
This is an effort to determine a formula that will determine the prevelance of TB among Hiv patients
Here I used a logistic model in place of a multiple regression model because latent tb results are boolean
test_mod_2 <- glm(lb_ti_qft_results~.,family = "binomial", data = LD3)
summary(test_mod_2)##
## Call:
## glm(formula = lb_ti_qft_results ~ ., family = "binomial", data = LD3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.70632 -0.63112 -0.00008 0.33710 2.12853
##
## Coefficients: (1 not defined because of singularities)
## Estimate
## (Intercept) -1.907e+01
## demographic_data_interviewer_name 4.367e-04
## demographic_data_participants_id 9.236e-05
## demographic_data_participants_residenceAthi River 1.959e+01
## demographic_data_participants_residenceBaba Dogo 3.436e-01
## demographic_data_participants_residenceBurburu 3.692e-01
## demographic_data_participants_residenceBuruburu Phase 1 3.913e+01
## demographic_data_participants_residenceBusia 3.916e+01
## demographic_data_participants_residenceCorner 3.872e+01
## demographic_data_participants_residenceDagoŕetti 3.534e+01
## demographic_data_participants_residenceDagoretti 1.878e+01
## demographic_data_participants_residenceDagoretti Corner 1.983e+01
## demographic_data_participants_residenceDagoretti North 3.805e+01
## demographic_data_participants_residenceDandora 1.930e+01
## demographic_data_participants_residenceDandora Phase 2 -9.503e-02
## demographic_data_participants_residenceDonholm 6.283e-02
## demographic_data_participants_residenceEastleigh -3.536e-01
## demographic_data_participants_residenceEastleigh Section 1 4.417e-02
## demographic_data_participants_residenceEmbakasi 2.040e+01
## demographic_data_participants_residenceEmbakasi South -6.558e-01
## demographic_data_participants_residenceEmbu 3.902e+01
## demographic_data_participants_residenceGachie 3.897e+01
## demographic_data_participants_residenceGatundu 1.943e+01
## demographic_data_participants_residenceGithunguri 1.881e+01
## demographic_data_participants_residenceGithurai 1.829e+01
## demographic_data_participants_residenceGithurai 44 3.975e+01
## demographic_data_participants_residenceGumba 3.639e-02
## demographic_data_participants_residenceHighrise -4.675e-02
## demographic_data_participants_residenceHoma Bay -7.767e-01
## demographic_data_participants_residenceHuruma 1.988e+01
## demographic_data_participants_residenceHuruma Kiamaiko -7.821e-02
## demographic_data_participants_residenceImara 3.914e+01
## demographic_data_participants_residenceJericho 2.054e+01
## demographic_data_participants_residenceJogoo Road -5.091e-02
## demographic_data_participants_residenceJoska 3.930e+01
## demographic_data_participants_residenceJuja 3.924e+01
## demographic_data_participants_residenceKaane -1.673e-01
## demographic_data_participants_residenceKabete 3.889e+01
## demographic_data_participants_residenceKahawa 1.959e+01
## demographic_data_participants_residenceKahawa Sukari 3.861e+01
## demographic_data_participants_residenceKahawa Wendani 2.527e-01
## demographic_data_participants_residenceKahawa West 1.942e+01
## demographic_data_participants_residenceKaloleni 3.894e+01
## demographic_data_participants_residenceKamulu 3.899e+01
## demographic_data_participants_residenceKangemi 1.796e+01
## demographic_data_participants_residenceKangundo Road 3.927e+01
## demographic_data_participants_residenceKariobangi North 3.905e+01
## demographic_data_participants_residenceKariobangi South 1.595e-01
## demographic_data_participants_residenceKariobangi South Sivo -8.184e-02
## demographic_data_participants_residenceKasarani 2.023e+01
## demographic_data_participants_residenceKasarani Mwiki 3.884e+01
## demographic_data_participants_residenceKasarani Ruai 3.873e+01
## demographic_data_participants_residenceKasarani Santon 3.878e+01
## demographic_data_participants_residenceKatani 3.928e+01
## demographic_data_participants_residenceKatwekera 3.959e+01
## demographic_data_participants_residenceKawañgware 3.916e+01
## demographic_data_participants_residenceKawangware 1.736e+01
## demographic_data_participants_residenceKayole 1.907e+01
## demographic_data_participants_residenceKayole Junction -3.001e-01
## demographic_data_participants_residenceKiambu 1.900e+01
## demographic_data_participants_residenceKibera 1.920e+01
## demographic_data_participants_residenceKibera Lindi 3.897e+01
## demographic_data_participants_residenceKibera Mashimoni 3.855e+01
## demographic_data_participants_residenceKikoko 3.837e+01
## demographic_data_participants_residenceKikuyu -1.866e-01
## demographic_data_participants_residenceKikuyu Regen 3.935e+01
## demographic_data_participants_residenceKirigiti -1.009e-01
## demographic_data_participants_residenceKiserian 1.092e-01
## demographic_data_participants_residenceKitengela 2.027e+01
## demographic_data_participants_residenceKitui 1.954e+01
## demographic_data_participants_residenceKomarock -3.620e-01
## demographic_data_participants_residenceKwa Njenga -1.742e-01
## demographic_data_participants_residenceLakisama -9.981e-01
## demographic_data_participants_residenceLand Mawe 3.941e+01
## demographic_data_participants_residenceLang'ata 1.947e+01
## demographic_data_participants_residenceLavington -1.116e+00
## demographic_data_participants_residenceLimuru 2.110e+01
## demographic_data_participants_residenceLoitoktok 1.112e+00
## demographic_data_participants_residenceLower Kabete 3.877e+01
## demographic_data_participants_residenceMachakos 7.722e-02
## demographic_data_participants_residenceMakongeni 3.913e+01
## demographic_data_participants_residenceMakueni 1.958e-02
## demographic_data_participants_residenceMaringo -3.758e-01
## demographic_data_participants_residenceMathare Hospital 3.891e+01
## demographic_data_participants_residenceMathare North -3.414e-01
## demographic_data_participants_residenceMatuu 1.856e+00
## demographic_data_participants_residenceMbotela 6.621e-01
## demographic_data_participants_residenceMlango Kubwa Pangani 5.081e-01
## demographic_data_participants_residenceMlolongo 3.920e+01
## demographic_data_participants_residenceMombasa 1.970e+01
## demographic_data_participants_residenceMuchatha -3.843e-02
## demographic_data_participants_residenceMulera 3.870e+01
## demographic_data_participants_residenceMurang'a 1.962e+01
## demographic_data_participants_residenceMuthaiga North 3.886e+01
## demographic_data_participants_residenceMwihoko 1.927e+01
## demographic_data_participants_residenceMwiki 2.011e+01
## demographic_data_participants_residenceMwingi West 3.924e+01
## demographic_data_participants_residenceNaivasha 1.962e+01
## demographic_data_participants_residenceNaivasha town -4.361e-02
## demographic_data_participants_residenceNakuru 1.969e+01
## demographic_data_participants_residenceNamanga 3.941e+01
## demographic_data_participants_residenceNg'ong 1.984e+01
## demographic_data_participants_residenceNg'ong road -1.291e-01
## demographic_data_participants_residenceNgara 1.896e+01
## demographic_data_participants_residenceNiavasha 1.888e-01
## demographic_data_participants_residenceNjiiru 3.896e+01
## demographic_data_participants_residenceNyandarua -1.474e-02
## demographic_data_participants_residenceNyeri 3.928e+01
## demographic_data_participants_residenceOlympic Kibera -1.388e-01
## demographic_data_participants_residenceOng'ata Rongai 3.894e+01
## demographic_data_participants_residenceOngata Rongai -4.934e-01
## demographic_data_participants_residencePangani 3.886e+01
## demographic_data_participants_residencePathenias -1.888e-01
## demographic_data_participants_residencePipeline -1.475e-01
## demographic_data_participants_residencePsyka -3.652e-01
## demographic_data_participants_residenceRiruta Satellite 2.559e-01
## demographic_data_participants_residenceRiver Bank 4.266e-01
## demographic_data_participants_residenceRongai 1.810e+01
## demographic_data_participants_residenceRuai 1.976e+01
## demographic_data_participants_residenceRuaka 2.823e-01
## demographic_data_participants_residenceRuiru 2.238e+01
## demographic_data_participants_residenceSafari Park 3.907e+01
## demographic_data_participants_residenceSatellite 1.851e+01
## demographic_data_participants_residenceSavannah 3.928e+01
## demographic_data_participants_residenceSouth B 1.883e+01
## demographic_data_participants_residenceSouth C 3.923e+01
## demographic_data_participants_residenceSultan Hamud 1.833e+01
## demographic_data_participants_residenceSyka 1.916e+01
## demographic_data_participants_residenceSyokimau 1.924e+01
## demographic_data_participants_residenceThika 1.927e+01
## demographic_data_participants_residenceThika Road 3.556e-03
## demographic_data_participants_residenceThindigua 1.967e+01
## demographic_data_participants_residenceThome -7.671e-02
## demographic_data_participants_residenceUhuru Estate 1.361e-02
## demographic_data_participants_residenceUmoja 1.892e+01
## demographic_data_participants_residenceUmoja 1 3.900e+01
## demographic_data_participants_residenceUMOJA 1 Q61 -4.892e-01
## demographic_data_participants_residenceUmoja II -3.555e-02
## demographic_data_participants_residenceUtawala 1.853e+01
## demographic_data_participants_residenceUthiru 3.906e+01
## demographic_data_participants_residenceVihiga 3.903e+01
## demographic_data_participants_residenceWaiyaki Way -4.725e-01
## demographic_data_participants_residenceWangige 3.909e+01
## demographic_data_participants_residenceWestlands Spring valley 3.877e+01
## demographic_data_participants_residenceWiathaka 3.945e+01
## demographic_data_participants_residenceZambezi 3.887e+01
## demographic_data_participants_residenceZimmerman -1.836e-01
## demographic_data_participants_genderMale 2.825e-01
## sputum_results NA
## random_blood_sugar -1.874e-01
## hb_a1c 1.246e+02
## e_ag_mg_d_l -5.865e-02
## viral_load_cp_ml 1.331e-04
## Std. Error
## (Intercept) 1.075e+04
## demographic_data_interviewer_name 2.379e-03
## demographic_data_participants_id 9.139e-05
## demographic_data_participants_residenceAthi River 1.075e+04
## demographic_data_participants_residenceBaba Dogo 1.521e+04
## demographic_data_participants_residenceBurburu 1.521e+04
## demographic_data_participants_residenceBuruburu Phase 1 1.521e+04
## demographic_data_participants_residenceBusia 1.521e+04
## demographic_data_participants_residenceCorner 1.521e+04
## demographic_data_participants_residenceDagoŕetti 1.521e+04
## demographic_data_participants_residenceDagoretti 1.075e+04
## demographic_data_participants_residenceDagoretti Corner 1.075e+04
## demographic_data_participants_residenceDagoretti North 1.521e+04
## demographic_data_participants_residenceDandora 1.075e+04
## demographic_data_participants_residenceDandora Phase 2 1.521e+04
## demographic_data_participants_residenceDonholm 1.521e+04
## demographic_data_participants_residenceEastleigh 1.521e+04
## demographic_data_participants_residenceEastleigh Section 1 1.521e+04
## demographic_data_participants_residenceEmbakasi 1.075e+04
## demographic_data_participants_residenceEmbakasi South 1.521e+04
## demographic_data_participants_residenceEmbu 1.316e+04
## demographic_data_participants_residenceGachie 1.521e+04
## demographic_data_participants_residenceGatundu 1.075e+04
## demographic_data_participants_residenceGithunguri 1.075e+04
## demographic_data_participants_residenceGithurai 1.075e+04
## demographic_data_participants_residenceGithurai 44 1.521e+04
## demographic_data_participants_residenceGumba 1.317e+04
## demographic_data_participants_residenceHighrise 1.521e+04
## demographic_data_participants_residenceHoma Bay 1.521e+04
## demographic_data_participants_residenceHuruma 1.075e+04
## demographic_data_participants_residenceHuruma Kiamaiko 1.521e+04
## demographic_data_participants_residenceImara 1.521e+04
## demographic_data_participants_residenceJericho 1.075e+04
## demographic_data_participants_residenceJogoo Road 1.521e+04
## demographic_data_participants_residenceJoska 1.521e+04
## demographic_data_participants_residenceJuja 1.521e+04
## demographic_data_participants_residenceKaane 1.521e+04
## demographic_data_participants_residenceKabete 1.521e+04
## demographic_data_participants_residenceKahawa 1.075e+04
## demographic_data_participants_residenceKahawa Sukari 1.521e+04
## demographic_data_participants_residenceKahawa Wendani 1.521e+04
## demographic_data_participants_residenceKahawa West 1.075e+04
## demographic_data_participants_residenceKaloleni 1.317e+04
## demographic_data_participants_residenceKamulu 1.521e+04
## demographic_data_participants_residenceKangemi 1.075e+04
## demographic_data_participants_residenceKangundo Road 1.521e+04
## demographic_data_participants_residenceKariobangi North 1.521e+04
## demographic_data_participants_residenceKariobangi South 1.315e+04
## demographic_data_participants_residenceKariobangi South Sivo 1.521e+04
## demographic_data_participants_residenceKasarani 1.075e+04
## demographic_data_participants_residenceKasarani Mwiki 1.521e+04
## demographic_data_participants_residenceKasarani Ruai 1.521e+04
## demographic_data_participants_residenceKasarani Santon 1.521e+04
## demographic_data_participants_residenceKatani 1.521e+04
## demographic_data_participants_residenceKatwekera 1.521e+04
## demographic_data_participants_residenceKawañgware 1.521e+04
## demographic_data_participants_residenceKawangware 1.075e+04
## demographic_data_participants_residenceKayole 1.075e+04
## demographic_data_participants_residenceKayole Junction 1.315e+04
## demographic_data_participants_residenceKiambu 1.075e+04
## demographic_data_participants_residenceKibera 1.075e+04
## demographic_data_participants_residenceKibera Lindi 1.521e+04
## demographic_data_participants_residenceKibera Mashimoni 1.521e+04
## demographic_data_participants_residenceKikoko 1.521e+04
## demographic_data_participants_residenceKikuyu 1.521e+04
## demographic_data_participants_residenceKikuyu Regen 1.521e+04
## demographic_data_participants_residenceKirigiti 1.316e+04
## demographic_data_participants_residenceKiserian 1.521e+04
## demographic_data_participants_residenceKitengela 1.075e+04
## demographic_data_participants_residenceKitui 1.075e+04
## demographic_data_participants_residenceKomarock 1.316e+04
## demographic_data_participants_residenceKwa Njenga 1.521e+04
## demographic_data_participants_residenceLakisama 1.312e+04
## demographic_data_participants_residenceLand Mawe 1.521e+04
## demographic_data_participants_residenceLang'ata 1.075e+04
## demographic_data_participants_residenceLavington 1.521e+04
## demographic_data_participants_residenceLimuru 1.075e+04
## demographic_data_participants_residenceLoitoktok 1.521e+04
## demographic_data_participants_residenceLower Kabete 1.521e+04
## demographic_data_participants_residenceMachakos 1.521e+04
## demographic_data_participants_residenceMakongeni 1.312e+04
## demographic_data_participants_residenceMakueni 1.521e+04
## demographic_data_participants_residenceMaringo 1.521e+04
## demographic_data_participants_residenceMathare Hospital 1.521e+04
## demographic_data_participants_residenceMathare North 1.315e+04
## demographic_data_participants_residenceMatuu 1.521e+04
## demographic_data_participants_residenceMbotela 1.521e+04
## demographic_data_participants_residenceMlango Kubwa Pangani 1.521e+04
## demographic_data_participants_residenceMlolongo 1.315e+04
## demographic_data_participants_residenceMombasa 1.075e+04
## demographic_data_participants_residenceMuchatha 1.521e+04
## demographic_data_participants_residenceMulera 1.521e+04
## demographic_data_participants_residenceMurang'a 1.075e+04
## demographic_data_participants_residenceMuthaiga North 1.521e+04
## demographic_data_participants_residenceMwihoko 1.075e+04
## demographic_data_participants_residenceMwiki 1.075e+04
## demographic_data_participants_residenceMwingi West 1.521e+04
## demographic_data_participants_residenceNaivasha 1.075e+04
## demographic_data_participants_residenceNaivasha town 1.521e+04
## demographic_data_participants_residenceNakuru 1.075e+04
## demographic_data_participants_residenceNamanga 1.521e+04
## demographic_data_participants_residenceNg'ong 1.075e+04
## demographic_data_participants_residenceNg'ong road 1.521e+04
## demographic_data_participants_residenceNgara 1.075e+04
## demographic_data_participants_residenceNiavasha 1.521e+04
## demographic_data_participants_residenceNjiiru 1.521e+04
## demographic_data_participants_residenceNyandarua 1.521e+04
## demographic_data_participants_residenceNyeri 1.521e+04
## demographic_data_participants_residenceOlympic Kibera 1.521e+04
## demographic_data_participants_residenceOng'ata Rongai 1.317e+04
## demographic_data_participants_residenceOngata Rongai 1.521e+04
## demographic_data_participants_residencePangani 1.521e+04
## demographic_data_participants_residencePathenias 1.521e+04
## demographic_data_participants_residencePipeline 1.521e+04
## demographic_data_participants_residencePsyka 1.521e+04
## demographic_data_participants_residenceRiruta Satellite 1.521e+04
## demographic_data_participants_residenceRiver Bank 1.521e+04
## demographic_data_participants_residenceRongai 1.075e+04
## demographic_data_participants_residenceRuai 1.075e+04
## demographic_data_participants_residenceRuaka 1.521e+04
## demographic_data_participants_residenceRuiru 1.075e+04
## demographic_data_participants_residenceSafari Park 1.521e+04
## demographic_data_participants_residenceSatellite 1.075e+04
## demographic_data_participants_residenceSavannah 1.521e+04
## demographic_data_participants_residenceSouth B 1.075e+04
## demographic_data_participants_residenceSouth C 1.521e+04
## demographic_data_participants_residenceSultan Hamud 1.075e+04
## demographic_data_participants_residenceSyka 1.075e+04
## demographic_data_participants_residenceSyokimau 1.075e+04
## demographic_data_participants_residenceThika 1.075e+04
## demographic_data_participants_residenceThika Road 1.521e+04
## demographic_data_participants_residenceThindigua 1.075e+04
## demographic_data_participants_residenceThome 1.521e+04
## demographic_data_participants_residenceUhuru Estate 1.521e+04
## demographic_data_participants_residenceUmoja 1.075e+04
## demographic_data_participants_residenceUmoja 1 1.521e+04
## demographic_data_participants_residenceUMOJA 1 Q61 1.521e+04
## demographic_data_participants_residenceUmoja II 1.521e+04
## demographic_data_participants_residenceUtawala 1.075e+04
## demographic_data_participants_residenceUthiru 1.521e+04
## demographic_data_participants_residenceVihiga 1.521e+04
## demographic_data_participants_residenceWaiyaki Way 1.521e+04
## demographic_data_participants_residenceWangige 1.521e+04
## demographic_data_participants_residenceWestlands Spring valley 1.521e+04
## demographic_data_participants_residenceWiathaka 1.521e+04
## demographic_data_participants_residenceZambezi 1.521e+04
## demographic_data_participants_residenceZimmerman 1.521e+04
## demographic_data_participants_genderMale 4.375e-01
## sputum_results NA
## random_blood_sugar 1.036e-01
## hb_a1c 1.765e+02
## e_ag_mg_d_l 8.026e-02
## viral_load_cp_ml 1.126e-04
## z value Pr(>|z|)
## (Intercept) -0.002 0.9986
## demographic_data_interviewer_name 0.184 0.8544
## demographic_data_participants_id 1.011 0.3122
## demographic_data_participants_residenceAthi River 0.002 0.9985
## demographic_data_participants_residenceBaba Dogo 0.000 1.0000
## demographic_data_participants_residenceBurburu 0.000 1.0000
## demographic_data_participants_residenceBuruburu Phase 1 0.003 0.9979
## demographic_data_participants_residenceBusia 0.003 0.9979
## demographic_data_participants_residenceCorner 0.003 0.9980
## demographic_data_participants_residenceDagoŕetti 0.002 0.9981
## demographic_data_participants_residenceDagoretti 0.002 0.9986
## demographic_data_participants_residenceDagoretti Corner 0.002 0.9985
## demographic_data_participants_residenceDagoretti North 0.003 0.9980
## demographic_data_participants_residenceDandora 0.002 0.9986
## demographic_data_participants_residenceDandora Phase 2 0.000 1.0000
## demographic_data_participants_residenceDonholm 0.000 1.0000
## demographic_data_participants_residenceEastleigh 0.000 1.0000
## demographic_data_participants_residenceEastleigh Section 1 0.000 1.0000
## demographic_data_participants_residenceEmbakasi 0.002 0.9985
## demographic_data_participants_residenceEmbakasi South 0.000 1.0000
## demographic_data_participants_residenceEmbu 0.003 0.9976
## demographic_data_participants_residenceGachie 0.003 0.9980
## demographic_data_participants_residenceGatundu 0.002 0.9986
## demographic_data_participants_residenceGithunguri 0.002 0.9986
## demographic_data_participants_residenceGithurai 0.002 0.9986
## demographic_data_participants_residenceGithurai 44 0.003 0.9979
## demographic_data_participants_residenceGumba 0.000 1.0000
## demographic_data_participants_residenceHighrise 0.000 1.0000
## demographic_data_participants_residenceHoma Bay 0.000 1.0000
## demographic_data_participants_residenceHuruma 0.002 0.9985
## demographic_data_participants_residenceHuruma Kiamaiko 0.000 1.0000
## demographic_data_participants_residenceImara 0.003 0.9979
## demographic_data_participants_residenceJericho 0.002 0.9985
## demographic_data_participants_residenceJogoo Road 0.000 1.0000
## demographic_data_participants_residenceJoska 0.003 0.9979
## demographic_data_participants_residenceJuja 0.003 0.9979
## demographic_data_participants_residenceKaane 0.000 1.0000
## demographic_data_participants_residenceKabete 0.003 0.9980
## demographic_data_participants_residenceKahawa 0.002 0.9985
## demographic_data_participants_residenceKahawa Sukari 0.003 0.9980
## demographic_data_participants_residenceKahawa Wendani 0.000 1.0000
## demographic_data_participants_residenceKahawa West 0.002 0.9986
## demographic_data_participants_residenceKaloleni 0.003 0.9976
## demographic_data_participants_residenceKamulu 0.003 0.9980
## demographic_data_participants_residenceKangemi 0.002 0.9987
## demographic_data_participants_residenceKangundo Road 0.003 0.9979
## demographic_data_participants_residenceKariobangi North 0.003 0.9980
## demographic_data_participants_residenceKariobangi South 0.000 1.0000
## demographic_data_participants_residenceKariobangi South Sivo 0.000 1.0000
## demographic_data_participants_residenceKasarani 0.002 0.9985
## demographic_data_participants_residenceKasarani Mwiki 0.003 0.9980
## demographic_data_participants_residenceKasarani Ruai 0.003 0.9980
## demographic_data_participants_residenceKasarani Santon 0.003 0.9980
## demographic_data_participants_residenceKatani 0.003 0.9979
## demographic_data_participants_residenceKatwekera 0.003 0.9979
## demographic_data_participants_residenceKawañgware 0.003 0.9979
## demographic_data_participants_residenceKawangware 0.002 0.9987
## demographic_data_participants_residenceKayole 0.002 0.9986
## demographic_data_participants_residenceKayole Junction 0.000 1.0000
## demographic_data_participants_residenceKiambu 0.002 0.9986
## demographic_data_participants_residenceKibera 0.002 0.9986
## demographic_data_participants_residenceKibera Lindi 0.003 0.9980
## demographic_data_participants_residenceKibera Mashimoni 0.003 0.9980
## demographic_data_participants_residenceKikoko 0.003 0.9980
## demographic_data_participants_residenceKikuyu 0.000 1.0000
## demographic_data_participants_residenceKikuyu Regen 0.003 0.9979
## demographic_data_participants_residenceKirigiti 0.000 1.0000
## demographic_data_participants_residenceKiserian 0.000 1.0000
## demographic_data_participants_residenceKitengela 0.002 0.9985
## demographic_data_participants_residenceKitui 0.002 0.9986
## demographic_data_participants_residenceKomarock 0.000 1.0000
## demographic_data_participants_residenceKwa Njenga 0.000 1.0000
## demographic_data_participants_residenceLakisama 0.000 0.9999
## demographic_data_participants_residenceLand Mawe 0.003 0.9979
## demographic_data_participants_residenceLang'ata 0.002 0.9986
## demographic_data_participants_residenceLavington 0.000 0.9999
## demographic_data_participants_residenceLimuru 0.002 0.9984
## demographic_data_participants_residenceLoitoktok 0.000 0.9999
## demographic_data_participants_residenceLower Kabete 0.003 0.9980
## demographic_data_participants_residenceMachakos 0.000 1.0000
## demographic_data_participants_residenceMakongeni 0.003 0.9976
## demographic_data_participants_residenceMakueni 0.000 1.0000
## demographic_data_participants_residenceMaringo 0.000 1.0000
## demographic_data_participants_residenceMathare Hospital 0.003 0.9980
## demographic_data_participants_residenceMathare North 0.000 1.0000
## demographic_data_participants_residenceMatuu 0.000 0.9999
## demographic_data_participants_residenceMbotela 0.000 1.0000
## demographic_data_participants_residenceMlango Kubwa Pangani 0.000 1.0000
## demographic_data_participants_residenceMlolongo 0.003 0.9976
## demographic_data_participants_residenceMombasa 0.002 0.9985
## demographic_data_participants_residenceMuchatha 0.000 1.0000
## demographic_data_participants_residenceMulera 0.003 0.9980
## demographic_data_participants_residenceMurang'a 0.002 0.9985
## demographic_data_participants_residenceMuthaiga North 0.003 0.9980
## demographic_data_participants_residenceMwihoko 0.002 0.9986
## demographic_data_participants_residenceMwiki 0.002 0.9985
## demographic_data_participants_residenceMwingi West 0.003 0.9979
## demographic_data_participants_residenceNaivasha 0.002 0.9985
## demographic_data_participants_residenceNaivasha town 0.000 1.0000
## demographic_data_participants_residenceNakuru 0.002 0.9985
## demographic_data_participants_residenceNamanga 0.003 0.9979
## demographic_data_participants_residenceNg'ong 0.002 0.9985
## demographic_data_participants_residenceNg'ong road 0.000 1.0000
## demographic_data_participants_residenceNgara 0.002 0.9986
## demographic_data_participants_residenceNiavasha 0.000 1.0000
## demographic_data_participants_residenceNjiiru 0.003 0.9980
## demographic_data_participants_residenceNyandarua 0.000 1.0000
## demographic_data_participants_residenceNyeri 0.003 0.9979
## demographic_data_participants_residenceOlympic Kibera 0.000 1.0000
## demographic_data_participants_residenceOng'ata Rongai 0.003 0.9976
## demographic_data_participants_residenceOngata Rongai 0.000 1.0000
## demographic_data_participants_residencePangani 0.003 0.9980
## demographic_data_participants_residencePathenias 0.000 1.0000
## demographic_data_participants_residencePipeline 0.000 1.0000
## demographic_data_participants_residencePsyka 0.000 1.0000
## demographic_data_participants_residenceRiruta Satellite 0.000 1.0000
## demographic_data_participants_residenceRiver Bank 0.000 1.0000
## demographic_data_participants_residenceRongai 0.002 0.9987
## demographic_data_participants_residenceRuai 0.002 0.9985
## demographic_data_participants_residenceRuaka 0.000 1.0000
## demographic_data_participants_residenceRuiru 0.002 0.9983
## demographic_data_participants_residenceSafari Park 0.003 0.9980
## demographic_data_participants_residenceSatellite 0.002 0.9986
## demographic_data_participants_residenceSavannah 0.003 0.9979
## demographic_data_participants_residenceSouth B 0.002 0.9986
## demographic_data_participants_residenceSouth C 0.003 0.9979
## demographic_data_participants_residenceSultan Hamud 0.002 0.9986
## demographic_data_participants_residenceSyka 0.002 0.9986
## demographic_data_participants_residenceSyokimau 0.002 0.9986
## demographic_data_participants_residenceThika 0.002 0.9986
## demographic_data_participants_residenceThika Road 0.000 1.0000
## demographic_data_participants_residenceThindigua 0.002 0.9985
## demographic_data_participants_residenceThome 0.000 1.0000
## demographic_data_participants_residenceUhuru Estate 0.000 1.0000
## demographic_data_participants_residenceUmoja 0.002 0.9986
## demographic_data_participants_residenceUmoja 1 0.003 0.9980
## demographic_data_participants_residenceUMOJA 1 Q61 0.000 1.0000
## demographic_data_participants_residenceUmoja II 0.000 1.0000
## demographic_data_participants_residenceUtawala 0.002 0.9986
## demographic_data_participants_residenceUthiru 0.003 0.9980
## demographic_data_participants_residenceVihiga 0.003 0.9980
## demographic_data_participants_residenceWaiyaki Way 0.000 1.0000
## demographic_data_participants_residenceWangige 0.003 0.9979
## demographic_data_participants_residenceWestlands Spring valley 0.003 0.9980
## demographic_data_participants_residenceWiathaka 0.003 0.9979
## demographic_data_participants_residenceZambezi 0.003 0.9980
## demographic_data_participants_residenceZimmerman 0.000 1.0000
## demographic_data_participants_genderMale 0.646 0.5184
## sputum_results NA NA
## random_blood_sugar -1.808 0.0706
## hb_a1c 0.706 0.4803
## e_ag_mg_d_l -0.731 0.4649
## viral_load_cp_ml 1.182 0.2374
##
## (Intercept)
## demographic_data_interviewer_name
## demographic_data_participants_id
## demographic_data_participants_residenceAthi River
## demographic_data_participants_residenceBaba Dogo
## demographic_data_participants_residenceBurburu
## demographic_data_participants_residenceBuruburu Phase 1
## demographic_data_participants_residenceBusia
## demographic_data_participants_residenceCorner
## demographic_data_participants_residenceDagoŕetti
## demographic_data_participants_residenceDagoretti
## demographic_data_participants_residenceDagoretti Corner
## demographic_data_participants_residenceDagoretti North
## demographic_data_participants_residenceDandora
## demographic_data_participants_residenceDandora Phase 2
## demographic_data_participants_residenceDonholm
## demographic_data_participants_residenceEastleigh
## demographic_data_participants_residenceEastleigh Section 1
## demographic_data_participants_residenceEmbakasi
## demographic_data_participants_residenceEmbakasi South
## demographic_data_participants_residenceEmbu
## demographic_data_participants_residenceGachie
## demographic_data_participants_residenceGatundu
## demographic_data_participants_residenceGithunguri
## demographic_data_participants_residenceGithurai
## demographic_data_participants_residenceGithurai 44
## demographic_data_participants_residenceGumba
## demographic_data_participants_residenceHighrise
## demographic_data_participants_residenceHoma Bay
## demographic_data_participants_residenceHuruma
## demographic_data_participants_residenceHuruma Kiamaiko
## demographic_data_participants_residenceImara
## demographic_data_participants_residenceJericho
## demographic_data_participants_residenceJogoo Road
## demographic_data_participants_residenceJoska
## demographic_data_participants_residenceJuja
## demographic_data_participants_residenceKaane
## demographic_data_participants_residenceKabete
## demographic_data_participants_residenceKahawa
## demographic_data_participants_residenceKahawa Sukari
## demographic_data_participants_residenceKahawa Wendani
## demographic_data_participants_residenceKahawa West
## demographic_data_participants_residenceKaloleni
## demographic_data_participants_residenceKamulu
## demographic_data_participants_residenceKangemi
## demographic_data_participants_residenceKangundo Road
## demographic_data_participants_residenceKariobangi North
## demographic_data_participants_residenceKariobangi South
## demographic_data_participants_residenceKariobangi South Sivo
## demographic_data_participants_residenceKasarani
## demographic_data_participants_residenceKasarani Mwiki
## demographic_data_participants_residenceKasarani Ruai
## demographic_data_participants_residenceKasarani Santon
## demographic_data_participants_residenceKatani
## demographic_data_participants_residenceKatwekera
## demographic_data_participants_residenceKawañgware
## demographic_data_participants_residenceKawangware
## demographic_data_participants_residenceKayole
## demographic_data_participants_residenceKayole Junction
## demographic_data_participants_residenceKiambu
## demographic_data_participants_residenceKibera
## demographic_data_participants_residenceKibera Lindi
## demographic_data_participants_residenceKibera Mashimoni
## demographic_data_participants_residenceKikoko
## demographic_data_participants_residenceKikuyu
## demographic_data_participants_residenceKikuyu Regen
## demographic_data_participants_residenceKirigiti
## demographic_data_participants_residenceKiserian
## demographic_data_participants_residenceKitengela
## demographic_data_participants_residenceKitui
## demographic_data_participants_residenceKomarock
## demographic_data_participants_residenceKwa Njenga
## demographic_data_participants_residenceLakisama
## demographic_data_participants_residenceLand Mawe
## demographic_data_participants_residenceLang'ata
## demographic_data_participants_residenceLavington
## demographic_data_participants_residenceLimuru
## demographic_data_participants_residenceLoitoktok
## demographic_data_participants_residenceLower Kabete
## demographic_data_participants_residenceMachakos
## demographic_data_participants_residenceMakongeni
## demographic_data_participants_residenceMakueni
## demographic_data_participants_residenceMaringo
## demographic_data_participants_residenceMathare Hospital
## demographic_data_participants_residenceMathare North
## demographic_data_participants_residenceMatuu
## demographic_data_participants_residenceMbotela
## demographic_data_participants_residenceMlango Kubwa Pangani
## demographic_data_participants_residenceMlolongo
## demographic_data_participants_residenceMombasa
## demographic_data_participants_residenceMuchatha
## demographic_data_participants_residenceMulera
## demographic_data_participants_residenceMurang'a
## demographic_data_participants_residenceMuthaiga North
## demographic_data_participants_residenceMwihoko
## demographic_data_participants_residenceMwiki
## demographic_data_participants_residenceMwingi West
## demographic_data_participants_residenceNaivasha
## demographic_data_participants_residenceNaivasha town
## demographic_data_participants_residenceNakuru
## demographic_data_participants_residenceNamanga
## demographic_data_participants_residenceNg'ong
## demographic_data_participants_residenceNg'ong road
## demographic_data_participants_residenceNgara
## demographic_data_participants_residenceNiavasha
## demographic_data_participants_residenceNjiiru
## demographic_data_participants_residenceNyandarua
## demographic_data_participants_residenceNyeri
## demographic_data_participants_residenceOlympic Kibera
## demographic_data_participants_residenceOng'ata Rongai
## demographic_data_participants_residenceOngata Rongai
## demographic_data_participants_residencePangani
## demographic_data_participants_residencePathenias
## demographic_data_participants_residencePipeline
## demographic_data_participants_residencePsyka
## demographic_data_participants_residenceRiruta Satellite
## demographic_data_participants_residenceRiver Bank
## demographic_data_participants_residenceRongai
## demographic_data_participants_residenceRuai
## demographic_data_participants_residenceRuaka
## demographic_data_participants_residenceRuiru
## demographic_data_participants_residenceSafari Park
## demographic_data_participants_residenceSatellite
## demographic_data_participants_residenceSavannah
## demographic_data_participants_residenceSouth B
## demographic_data_participants_residenceSouth C
## demographic_data_participants_residenceSultan Hamud
## demographic_data_participants_residenceSyka
## demographic_data_participants_residenceSyokimau
## demographic_data_participants_residenceThika
## demographic_data_participants_residenceThika Road
## demographic_data_participants_residenceThindigua
## demographic_data_participants_residenceThome
## demographic_data_participants_residenceUhuru Estate
## demographic_data_participants_residenceUmoja
## demographic_data_participants_residenceUmoja 1
## demographic_data_participants_residenceUMOJA 1 Q61
## demographic_data_participants_residenceUmoja II
## demographic_data_participants_residenceUtawala
## demographic_data_participants_residenceUthiru
## demographic_data_participants_residenceVihiga
## demographic_data_participants_residenceWaiyaki Way
## demographic_data_participants_residenceWangige
## demographic_data_participants_residenceWestlands Spring valley
## demographic_data_participants_residenceWiathaka
## demographic_data_participants_residenceZambezi
## demographic_data_participants_residenceZimmerman
## demographic_data_participants_genderMale
## sputum_results
## random_blood_sugar .
## hb_a1c
## e_ag_mg_d_l
## viral_load_cp_ml
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 377.63 on 272 degrees of freedom
## Residual deviance: 184.38 on 121 degrees of freedom
## AIC: 488.38
##
## Number of Fisher Scoring iterations: 18Take aways from the 2nd model
- The only significant variable was random blood sugar with a P value of 0.0326 ### Conclusion
- Given the all the variables we can determine the prevalence of TB using the formula below ** (-1.892e+01)-(2.133e-01)(random blood sugar levels) **
- None of the variables were significant in this model therefore a logistic model is not sufficient enough to carry out an analysis
PLOTS (Share phase)
FOR THE FIRST MODEL(DIABETES)
Notes: there is a negative linear relation
library(car)## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recode## The following object is masked from 'package:purrr':
##
## someavPlots(test_mod_1,id=FALSE, pt.wts=TRUE)## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear## Warning in lsfit(res[, 1], res[, 2], wt = wt): 'X' matrix was collinear## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
Interpretation
From the following scatterplots above we can see that the model has;
- a neither positive nor negative correlation with participants ID and Interviewer name since these values were ordered randomly *(from the 306 partcipants)We can see that there is also no correlation between random blood sugarand Gender, latent tb results and sputum results
- We can see a strong negative correlation between random bnlood sugar and hbA1c
- Finally We can see a strong positive correlation between random blood sugar and eAg(this makes sense since they are measuered together), same applies to viral load
Bar chart for Viral ditribution vs Latent Tb
Notes: 1-Latent Tb Present 2-Latent Tb absent
library(patchwork)
library(ggplot2)
ggplot(LD3, aes(x=lb_ti_qft_results, y =viral_load_cp_ml))+
geom_bar(stat='identity',fill = "black",)+
labs(title = "viral load distribution tb",x= "Latent Tb results",y= "Viral Load(cp/ml)")
Takeaways
- We can see that when Latent Tb is Present we get a high count/level of Viral load.This is a clear indication that the two are related and that the presence of Latent TB is influenced greatly by the viral load levels in blood
VIRAL LOAD CORRELATION TO LATENT TB
Here our main focus is to look at how the variables relate to latent tb
Last plot is our main focus
test_mod_4 <- lm(lb_ti_qft_results~
demographic_data_interviewer_name+
demographic_data_participants_id+
demographic_data_participants_gender+
sputum_results+
random_blood_sugar+
hb_a1c+
e_ag_mg_d_l+
viral_load_cp_ml
, data = LD3)
avPlots(test_mod_4,id=FALSE, pt.wts=TRUE)## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear## Warning in lsfit(res[, 1], res[, 2], wt = wt): 'X' matrix was collinear## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
## Warning in lsfit(mod.mat[, -var], cbind(mod.mat[, var], response), wt = wt, :
## 'X' matrix was collinear
Takeaways
There is a no correlation between latent tb and: the interviewer name, participants gender and sputum results.
We see a positive correlation between latent tb and participants id. W e will disregard this since
We see a negative correlation between latent tb and random blood sugar-Basically as latent tb decreases random blood sugar increases
We see a negative correlation between latent tb and hbA1c results-Basically as latent tb increases hbA1c results increase
We see a negative correlation between latent tb and random blood sugar-Basically as latent tb decreases random blood sugar increases
Finally We can see a very strong positive correlation between latent tb and viral load; This means that a high Viral load will most likely indicate that there exists Latent Tb in this patient
Viral Load distribution by Gender
ggplot(LD3, aes(x=viral_load_cp_ml, y =lb_ti_qft_results,color=demographic_data_participants_gender))+
geom_point()+geom_smooth(method = lm)+
labs(title = "Distribution of latent TB in HIV patients",
x="Viral Load Distribution(cp/ml)",
y="Latent TB results")## `geom_smooth()` using formula 'y ~ x'
Take aways
- There is a strong positive correlation between viral load and Ltent TB as suspected
- There seems to be a higher correlation women than in men despite men having a higher distribution of viral load. This is indicated by the nature of the trendline. what could be the cause of this?
Viral Load distribution by Gender
library(ggplot2)
ggplot(LD3, aes(x=demographic_data_participants_gender, y =viral_load_cp_ml))+
geom_bar(stat='identity')+
geom_col()+
theme(axis.title.y=element_blank())+
labs(title = "Prevelance of Viral Load by Gender")+
annotate("text",x=1,y=200000,label="", color="green",fontface="bold")
Takeaways
- Males have a higher viral load distribution in as compared to females
ggplot(LD3, aes(x=viral_load_cp_ml, y =random_blood_sugar, color=demographic_data_participants_gender))+
geom_point()+geom_smooth(method = lm)+
labs(title = "Distribution of Diabetes in HIV patients",
subtitle = "Random Blood Sugar",
x="Viral Load Distribution(cp/ml)",
y="random blood sugar")## `geom_smooth()` using formula 'y ~ x'
Take aways
- There seems to be a positive correlation between viral load and random blood sugar in males but surprisingly there is a negative correlation for the same in females. This could be attributed to the fact that most men miss medications due to social factors
- This scatter plot is confirmed by the gender bar graph above
CONCLUSION
- It is evident from our dataset that there is a clear cut correlation with Hiv and Latent TB with the highest correlation factor of 0.07498797 among our variables.This can be confirmed by our latent TB vs viral Load graph where a strong positive correlation is shown by the last avplots on model4
- We can also see that random blood sugar levels have the 2nd highest correlation factor with viral load at 0.04263593.This indicates that random blood sugar is truly a factor that affects HIV viral load albeit in small amounts
- From the gender plot we can also see that Males have a significantly high amount of viral load than females this is a clear indicator that males are more likely to acquire latent TB since Viral load has a hugh correlation with Latent TB
From the model 1 scatter plots we can see that the model has; * a neither positive nor negative correlation with participants ID and Interviewer name since these values were ordered randomly (from the 306 participants)We can see that there is also no correlation between random blood sugar and Gender, latent tb results and sputum results We can see a strong negative correlation between random blood sugar and hbA1c * Finally We can see a strong positive correlation between random blood sugar and eAg(this makes sense since they are measured together), same applies to viral load The first model, With a Pvalue of 6.442e-10 shows that keeping the random blood sugar levels as our y value we can see that hbA1C levels as well eAg levels have an effect on the prevalence of diabetes among HIV patients Despite our Models having p values that are greater than bar the first model, We can say that thanks to the bar charts and scatter plots generated that there definitely exists a correlation between latent tb and the prevalence of HIV