A SCREENING ALGORITHM TO IDENTIFY CLINICALLY SIGNIFICANT CHANGES IN NEUROPSYCHOLOGICAL FUNCTIONS IN THE DIABETES CONTROL AND COMPLICATIONS TRIAL

Neuropsychological (NP) evaluations provide an accepted means of monit oring safety in multi-center long-term medical trials. However, using neuropsychologists to review test protocols and rate level of clinical impairment can be a costly and logistically complex undertaking. To f acilitate that process, the DCCT Research Group developed a computeriz ed screening strategy that utilized statistical models to identify ind ividuals with possible cognitive deterioration.Two hundred and eight s ubjects with insulin-dependent diabetes mellitus were assessed twice, 2 years apart, with an extensive battery of NP tests, and the results were rated by expert clinicians. Multiple logistic regression was used to develop a statistical model to predict clinically significant NP wo rsening(as determined by clinical raters) on the basis of changes in s cores (year 2 - baseline) derived from the actual tests. A subsequent performance evaluationwith an additional 1087 subjects demonstrated th at the computerized algorithmwas highly successful in identifying indi viduals with significantly worsened NP performance. Despite a high fal se positive rate, the algorithm can achieve an 80-90% reduction in the number of cases requiring evaluation by expert neuropsychologists.