Artificial Neural Networks as Adjuncts for Assessing Medical Students; Problem Solving Performances on Computer-Based Simulations

Ronald H. Stevens and Katayoun Najafi

Artificial neural networks were trained by supervised learning to recognize the test selection patterns associated with students' successful solutions to seven immunology computer-based simulations. new test selection patterns evaluated by the trained neural network were correctly classified as successful or unsuccessful solutions to the problem >90% of the time. The examination of the neural networks output weights after each test selection revealed a progressive and selective increase for the relevant problem suggesting that a successful solution is represented by the neural network as the accumulation of relevant tests. Unsuccessful problem solutions were classified by the neural networks software into two patterns of students performance. The first pattern was characterized by low neural network output relevant information. In the second pattern, the output weights from the neural networks were biased toward one of the remaining six incorrect problems suggesting that the student misrepresented the current problem as an instance of a previous problem. Finally neural network analysis could detect cases where the students switched hypotheses during the problem solving exercises.

Computers and Biomedical Research 26, 172-187 (1993)