Journal of Healthcare Engineering / 2018 / Article / Tab 1

Research Article

An Evolutionary Computation Approach for Optimizing Multilevel Data to Predict Patient Outcomes

Table 1

Common multilevel predictor data available in electronic health records.

Multilevel predictorsDescriptionExamples

Reasons for visitDescriptors of the reason for the healthcare system encounterAmbulatory care chief complaints; inpatient admission diagnoses
DiagnosesDescriptors of patients’ differential or final diagnosis departing the healthcare systemInternational classification of disease codes (e.g., ICD-10); read codes
Medical historyDescriptors of previous medical history and chronic conditionsEHR problem lists (e.g., diabetes, previous coronary artery bypass graft (CABG), hypertension)
Diagnostic and therapeutic proceduresDescriptors of diagnostic and therapeutic courses of action takenProcedure coding system (ICD-10-PCS), surgical procedures, rehabilitation
Diagnostic examsDescriptors of medical tests conductedLaboratory exams, imaging exams, physical exams
MedicationDescriptors of medications administeredUS Food and Drug Administration Drug Class (e.g., opioids and hydrocodone)
AdministrativeDescriptor of the administrative status of patientsInpatient, outpatient, observation