Structural positional encoding for knowledge integration in transformer-based medical process monitoring and trace classification

Predictive process monitoring is a process mining task aimed at forecasting information about a running process trace, such as the most correct next activity to be executed. In medical domains, predictive process monitoring can provide valuable decision support in atypical and nontrivial situations. On the other hand, process trace classification exploits the logged activity sequences to classify traces on the basis of some properties; in medical applications, this information can be fruitfully adopted for quality assessment and process/resource optimization. Decision support and quality assessment in medicine cannot ignore domain knowledge, in order to be grounded on all the available information (which is not limited to data) and to be really acceptable by end users. In this paper, we propose a predictive process monitoring approach relying on the use of a transformer, a deep learning architecture based on the attention mechanism. A major contribution of our work lies in the incorporation of ontological domain-specific knowledge, carried out through a graph positional encoding technique. Interestingly, the transformer-based knowledge-enhanced architecture has been adopted to cover the trace classification task as well, by incorporating the class label as the last trace activity to predict. The paper presents and discusses the encouraging experimental result we are collecting in the domain of stroke management.