MTE Project

Nishant Kumar
21/01/2021
Task 1:-
# Load packages
library(data.table)

## Warning: package ‘data.table’ was built under R version 4.0.3

# Read in the data

antibioticDT <- fread(“antibioticDT.csv”)

# Look at the first 30 rows

antibioticDT[1:30]

## patient_id day_given antibiotic_type route

## 1: 1 2 ciprofloxacin IV
## 2: 1 4 ciprofloxacin IV
## 3: 1 6 ciprofloxacin IV
## 4: 1 7 doxycycline IV
## 5: 1 9 doxycycline IV
## 6: 1 15 penicillin IV
## 7: 1 16 doxycycline IV
## 8: 1 18 ciprofloxacin IV
## 9: 8 1 doxycycline PO
## 10: 8 2 penicillin IV
## 11: 8 3 doxycycline IV
## 12: 8 6 doxycycline PO
## 13: 8 8 penicillin PO
## 14: 8 12 penicillin IV
## 15: 9 8 doxycycline IV
## 16: 9 12 doxycycline PO
## 17: 12 4 doxycycline PO
## 18: 12 9 doxycycline IV
## 19: 16 1 doxycycline IV
## 20: 16 4 amoxicillin IV
## 21: 19 3 doxycycline PO
## 22: 19 5 amoxicillin IV
## 23: 19 6 ciprofloxacin IV
## 24: 19 10 doxycycline IV
## 25: 19 12 penicillin IV
## 26: 23 1 doxycycline IV
## 27: 23 1 penicillin IV
## 28: 23 3 amoxicillin IV
## 29: 23 3 ciprofloxacin IV
## 30: 23 3 doxycycline IV
## patient_id day_given antibiotic_type route

Task 2:-
# Sort the data by id, antibiotic type, day
setorder(antibioticDT, patient_id, antibiotic_type, day_given)
antibioticDT[1:40]

## patient_id day_given antibiotic_type route

## 1: 1 2 ciprofloxacin IV
## 2: 1 4 ciprofloxacin IV
## 3: 1 6 ciprofloxacin IV
## 4: 1 18 ciprofloxacin IV
## 5: 1 7 doxycycline IV
## 6: 1 9 doxycycline IV
## 7: 1 16 doxycycline IV
## 8: 1 15 penicillin IV
## 9: 8 1 doxycycline PO
## 10: 8 3 doxycycline IV
## 11: 8 6 doxycycline PO
## 12: 8 2 penicillin IV
## 13: 8 8 penicillin PO
## 14: 8 12 penicillin IV
## 15: 9 8 doxycycline IV
## 16: 9 12 doxycycline PO
## 17: 12 4 doxycycline PO
## 18: 12 9 doxycycline IV
## 19: 16 4 amoxicillin IV
## 20: 16 1 doxycycline IV
## 21: 19 5 amoxicillin IV
## 22: 19 6 ciprofloxacin IV
## 23: 19 3 doxycycline PO
## 24: 19 10 doxycycline IV
## 25: 19 12 penicillin IV
## 26: 23 3 amoxicillin IV
## 27: 23 8 amoxicillin IV
## 28: 23 10 amoxicillin PO
## 29: 23 3 ciprofloxacin IV
## 30: 23 5 ciprofloxacin PO
## 31: 23 16 ciprofloxacin IV
## 32: 23 1 doxycycline IV
## 33: 23 3 doxycycline IV
## 34: 23 4 doxycycline IV
## 35: 23 5 doxycycline IV
## 36: 23 6 doxycycline IV
## 37: 23 6 doxycycline PO
## 38: 23 9 doxycycline PO
## 39: 23 10 doxycycline IV
## 40: 23 11 doxycycline PO
## patient_id day_given antibiotic_type route

# Use shift to calculate the last day a particular drug was administered
antibioticDT[ , last_administration_day := shift(day_given, 1),
by = .(patient_id, antibiotic_type)]

# Calculate the number of days since the drug was last administered
antibioticDT[ , days_since_last_admin := day_given – last_administration_day]

# Create antibiotic_new with an initial value of one, then reset it to zero as needed
antibioticDT[ , antibiotic_new := 1]
antibioticDT[days_since_last_admin <= 2, antibiotic_new := 0]

Task 3 :-
# Read in blood_cultureDT.csv
blood_cultureDT <- fread(“blood_cultureDT.csv”)

# Print the first 30 rows

blood_cultureDT[1:30]

## patient_id blood_culture_day
## 1: 1 3
## 2: 1 13
## 3: 8 2
## 4: 8 13
## 5: 23 3
## 6: 39 10
## 7: 45 4
## 8: 45 9
## 9: 45 11
## 10: 51 3
## 11: 51 6
## 12: 59 2
## 13: 64 1
## 14: 66 9
## 15: 66 10
## 16: 69 2
## 17: 69 6
## 18: 69 7
## 19: 69 11
## 20: 69 16
## 21: 76 1
## 22: 77 3
## 23: 79 5
## 24: 79 11
## 25: 79 12
## 26: 80 3
## 27: 80 12
## 28: 81 2
## 29: 112 6
## 30: 115 2
## patient_id blood_culture_day

Task 4:-
# Merge antibioticDT with blood_cultureDT
combinedDT <- merge(blood_cultureDT,antibioticDT,all = FALSE,by = ‘patient_id’)

# Sort by patient_id, blood_culture_day, day_given, and antibiotic_type

setorder(combinedDT, patient_id, blood_culture_day, day_given, antibiotic_type)
# Print and examine the first 30 rows
combinedDT[1:30]

## patient_id blood_culture_day day_given antibiotic_type route

## 1: 1 3 2 ciprofloxacin IV
## 2: 1 3 4 ciprofloxacin IV
## 3: 1 3 6 ciprofloxacin IV
## 4: 1 3 7 doxycycline IV
## 5: 1 3 9 doxycycline IV
## 6: 1 3 15 penicillin IV
## 7: 1 3 16 doxycycline IV
## 8: 1 3 18 ciprofloxacin IV
## 9: 1 13 2 ciprofloxacin IV
## 10: 1 13 4 ciprofloxacin IV
## 11: 1 13 6 ciprofloxacin IV
## 12: 1 13 7 doxycycline IV
## 13: 1 13 9 doxycycline IV
## 14: 1 13 15 penicillin IV
## 15: 1 13 16 doxycycline IV
## 16: 1 13 18 ciprofloxacin IV
## 17: 8 2 1 doxycycline PO
## 18: 8 2 2 penicillin IV
## 19: 8 2 3 doxycycline IV
## 20: 8 2 6 doxycycline PO
## 21: 8 2 8 penicillin PO
## 22: 8 2 12 penicillin IV
## 23: 8 13 1 doxycycline PO
## 24: 8 13 2 penicillin IV
## 25: 8 13 3 doxycycline IV
## 26: 8 13 6 doxycycline PO
## 27: 8 13 8 penicillin PO
## 28: 8 13 12 penicillin IV
## 29: 23 3 1 doxycycline IV
## 30: 23 3 1 penicillin IV
## patient_id blood_culture_day day_given antibiotic_type route
## last_administration_day days_since_last_admin antibiotic_new
## 1: NA NA 1
## 2: 2 2 0
## 3: 4 2 0
## 4: NA NA 1
## 5: 7 2 0
## 6: NA NA 1
## 7: 9 7 1
## 8: 6 12 1
## 9: NA NA 1
## 10: 2 2 0
## 11: 4 2 0
## 12: NA NA 1
## 13: 7 2 0
## 14: NA NA 1
## 15: 9 7 1
## 16: 6 12 1
## 17: NA NA 1
## 18: NA NA 1
## 19: 1 2 0
## 20: 3 3 1
## 21: 2 6 1
## 22: 8 4 1
## 23: NA NA 1
## 24: NA NA 1
## 25: 1 2 0
## 26: 3 3 1
## 27: 2 6 1
## 28: 8 4 1
## 29: NA NA 1
## 30: NA NA 1
## last_administration_day days_since_last_admin antibiotic_new

Task 5:-
# Make a new variable called drug_in_bcx_window
combinedDT[ , drug_in_bcx_window :=
as.numeric(day_given - blood_culture_day <= 2 &
day_given - blood_culture_day >= -2)]

Task 6:-
# Create a variable indicating if there was at least one I.V. drug given in the window
combinedDT[ ,
any_iv_in_bcx_window := as.numeric(any(route == 'IV' & drug_in_bcx_window ==
1)),
by = .(patient_id, blood_culture_day)]

# Exclude rows in which the blood_culture_day does not have any I.V. drugs in window
combinedDT <- combinedDT[any_iv_in_bcx_window == 1]

Task 7:-
# Create a new variable called day_of_first_new_abx_in_window
combinedDT[ ,
day_of_first_new_abx_in_window :=
day_given[antibiotic_new == 1 & drug_in_bcx_window == 1][1],
by = .(patient_id, blood_culture_day)]

# Remove rows where the day is before this first qualifying day
combinedDT <- combinedDT[day_given >= day_of_first_new_abx_in_window]

Task 8
# Create a new data.table containing only patient_id, blood_culture_day, and day_given
simplified_data <- combinedDT[ , .(patient_id, blood_culture_day, day_given)]

# Remove duplicate rows

simplified_data <- unique(simplified_data)

Task 9
# Count the antibiotic days within each patient/blood culture day combination
simplified_data[ , num_antibiotic_days := .N, by = .(patient_id, blood_culture_day)]
# Remove blood culture days with less than four rows
simplified_data <- simplified_data[num_antibiotic_days >= 4]

# Select the first four days for each blood culture

first_four_days <- simplified_data[ , .SD[1:4], by = .(patient_id, blood_culture_day)]

Task 10:-
# Make the indicator for consecutive sequence
first_four_days[ , four_in_seq := as.numeric(max(diff(day_given)) < 3), by = .
(patient_id, blood_culture_day)]

Task 11:-
# Select the rows which have four_in_seq equal to 1
suspected_infection <- first_four_days[four_in_seq == 1]

# Retain only the patient_id column

suspected_infection <- suspected_infection[ , .(patient_id)]

# Remove duplicates
suspected_infection <- unique(suspected_infection)

# Make an infection indicator

suspected_infection[ , infection := 1]

Task 12:-
# Read in "all_patients.csv"
all_patientsDT <- fread("all_patients.csv")

# Merge this with the infection flag data

all_patientsDT <- merge(all_patientsDT,suspected_infection,by = "patient_id",
all = TRUE)

# Set any missing values of the infection flag to 0

all_patientsDT[is.na(infection) , infection := 0]

# Calculate the percentage of patients who met the criteria for presumed infection
ans <- all_patientsDT[ , 100*mean(infection == 1)]