GroupLens: an open architecture for collaborative filtering of netnews
CSCW '94 Proceedings of the 1994 ACM conference on Computer supported cooperative work
Fab: content-based, collaborative recommendation
Communications of the ACM
An algorithmic framework for performing collaborative filtering
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Recommender systems in e-commerce
Proceedings of the 1st ACM conference on Electronic commerce
Empirical analysis of predictive algorithms for collaborative filtering
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
| Hi-index | 0.00 |
Collaborative Filtering is a well-approved method for prediction of consumer behaviour in marketing strategies. We adapt and evaluate this method for prognosis of the longterm metabolic control level in diabetic patients. The underlying data for the prediction were extracted from a central diabetic data pool (DPVSCIENT) [1],[2], containing longtime documentation of about 60% of all young patients with type-1 diabetes in Germany. Prediction results were successfully checked against random values and evaluated calculating sensitivity, specifity and total performance of a prognosis test. Best results were: sensitivity = 76%, specifity = 92% and total performance = 84%. This novel approach in diabetology demonstrates tracking for metabolic control and allows to predict favorable or unfavorable results, providing an objective basis to target intervention in individual patients.