Can past academic criteria predict students at risk of future failure?

Summary. A significant minority of medical and dental students fail their undergraduate courses. Early warning systems (EWSs) have been developed in some areas of higher education to predict ‘at‐risk’ students at an early remedial stage. An attempt is made to develop an EWS to predict failure in the bacteriology component of the Batchelor of Dental Surgery course at Manchester Dental School. A system based on class tests and previous end‐of‐year performance is derived which is used to predict those students likely to fail or fall in the bottom 20–25% in their finals examination. The predictors are combined by a simple equal weights method, which is found to have the same predictive power as using multiple regression. Failure was correctly predicted in 60% of cases, at the expense of 71% false alarms. The high number of false alarms reflects the low failure rate rather than the lack of predictive information. The need for effective cross‐validation of EWSs is discussed; many previous studies have not been tested on independent data.