Biomedical subjects

D G Melvin

Publications and source records attributed to D G Melvin.

3 recordsLinked to original sources

PubMed2002

Collusion detection in multiple choice examinations.

OBJECTIVE: To develop and test a novel method for collusion detection in multiple choice examinations. SUBJECTS AND METHODS: Answers from two negatively marked medical prize examinations for two different years were analysed. Both examinations were administered electronically. One examination was formally invigilated, while the second was not; instead, candidates were able to sit the test at any time and at any computer with an internet connection. We examine pairs of students and compare correlations between their answers. Our approach allows us to correct for the difficulty of individual questions and for the estimated ability and the degree of risk aversion of the students. We compare the results of this statistical analysis with other information on the timing of the answers and the physical location of the computer, both of which are available to the web-server. RESULTS: Significant correlation between several candidates who either admitted having cheated or could be linked to other corroborating evidence of collusion was found. CONCLUSION: It is possible to detect collusion in multiple choice examinations in a statistical way by examining the patterns of answers between pairs of candidates. In examinations that are delivered on-line, information is often available on the location of the candidates and the timings of their answers, and can be used as additional corroborative evidence.

Bayes Theorem↗

PubMed2001

Clinical validation of an artificial neural network trained to identify acute allograft rejection in liver transplant recipients.

Artificial neural networks (ANNs) are techniques of nonlinear data modeling that have been studied in a wide variety of medical applications. An ANN was developed to assist in the diagnosis of acute rejection in liver transplant recipients. We investigated the diagnostic accuracy of this ANN on a new data set of patients from the same hospital. In addition, we compared the diagnostic accuracy of the ANN with that of the individual input variables (alanine aminotransferase [ALT] and bilirubin levels and day posttransplantation). Clinical and biochemical data were collected retrospectively for 124 consecutive liver transplantations (117 patients) over the first 3 months after transplantation. Diagnostic accuracy was calculated using receiver operating characteristic (ROC) curve analysis. The ANN differentiated rejection from rejection-free episodes in the new data set over the first 3 months posttransplantation with an area under the ROC curve of 0.902 and sensitivity and specificity of 80.0% and 90.1% at the optimum decision threshold, respectively. The ANN was significantly more specific than ALT or bilirubin level or day posttransplantation at their corresponding optimum decision thresholds (P <.0001). Peak ANN output occurred 1 day earlier than peak values for either ALT or bilirubin (P <.005). The diagnostic accuracy of the ANN was greater than that of any of the individual variables that had been used as inputs. It would be a useful adjunct to conventional liver function tests for monitoring liver transplant recipients in the early postoperative period.

Acute Disease↗

PubMed2000

Neuro-computing versus linear statistical techniques applied to liver transplant monitoring: a comparative study.

This paper explores the potential for the application of neurocomputing in on-line monitoring in the liver transplantation domain. It extends our previously documented work to provide both an assessment of the performance gains achievable by incorporating temporal and dynamical information about the measurements made on a patient as well as presenting a novel computerized clinical decision aid for this domain. A comparison of the performance of linear and nonlinear classification system is made and used to motivate the final selection of the diagnostic inputs.

Biomedical Engineering↗