A Comparison

The paper presents a case study comparing text analysis approaches used to classify the current status of a patient to inform scheduling, aiming to help one of the UK's largest healthcare providers systematically capture patient outcome information after a clinic attendance. Ensuring records are closed when a patient is discharged and that follow-up appointments are scheduled within the required time-scales supports safe, effective care; analysing patient letters allows systematic extraction of discharge or follow-up information to automatically update a patient record and clarify the demand placed on the system.

Three approaches for systematic information capture are compared: phrase identification using lexicons, word frequency analysis, and supervised text mining. The approaches are evaluated according to their precision and stakeholder acceptability, and the authors present methodological lessons encouraging project objectives to be considered alongside text classification methods when building decision-support tools.