Reference: Ohno-Machado, L. & Musen, M. A. Sequential versus standard neural networks for temporal pattern recognition: An example using the domain of coronary heart disease. Knowledge Systems Laboratory, Medical Computer Science, February, 1996.
Abstract: Medical researchers who perform prognostic modeling usually oversimplify the problem by choosing a single point in time to predict outcomes (e.g., death in five years). This approach not only fails to differentiate patterns of disease progression, but also wastes important information that is usually available in time-oriented research data bases. The adequate use of time-oriented data bases can improve the performance of prognostic systems if the interdependencies among prognoses at different intervals of time are explicitly modeled. In such models, predictions for a certain interval of time (e.g., death within one year) are influenced by predictions made for other intervals, and prognostic survival curves that provide consistent estimates for several points in time can be produced. We developed a system of neural network models that makes use of time- oriented data to predict development of coronary heart disease (CHD), using a set of 2594 patients. The output of the neural network system was a prognostic curve representing survival without CHD, and the inputs were the values of demographic, clinical, and laboratory variables. The system of neural networks was trained by backprogation and its results were evaluated in test sets of previously unseen cases. We showed that, by explicitly modeling time in the neural net work architecture, the performance of the prognostic index, measured by the area under the receiver operating characteristic (ROC) curve, was significantly improved (p<0.05).