Skip to main content
. 2024 Dec 18;19(12):e0314145. doi: 10.1371/journal.pone.0314145

Table 1. Features of the patient EHR used as inputs into the predictive model.

Data Type Description Percentage missing information
Age Patient age at Prediction Date 0%
Sex Patient sex at Prediction Date 0%
Ethnicity Patient ethnicity at Prediction Date 8%
Medications British National Formulary (BNF) Subsection codes <5%
Laboratories Urea, Estimated Glomerular Filtration Rate (EGFR), Creatinine, Potassium, Haemoglobin, Neutrophils, Lymphocytes, N-terminal pro b-type natriuretic peptide (NT-proBNP), <5
Hospitalisations All ICD-10 codes associated with admission, Length of stay associated with admission, Primary clinical speciality 0%
A&E Attendances ICD-10 codes associated with attendances 0%
Outpatients Appointment speciality, ICD-10 codes associated with each appointment 0%
Vital Signs Systolic blood pressure, Body Mass Index (BMI) 58%