Abstract-Computer based analysis of Electronic Health Records (EHRs) has the potential to provide major novel insights of benefit both to specific individuals in the context of personalized medicine, as well as on the level of populationwide health care and policy. The present paper introduces a novel algorithm that uses machine learning for the discovery of longitudinal patterns in the diagnoses of diseases. Two key technical novelties are introduced: one in the form of a novel learning paradigm which enables greater learning specificity, and another in the form of a risk driven identification of confounding diagnoses. We present a series of experiments which demonstrate the effectiveness of the proposed techniques, and which reveal novel insights regarding the most promising future research directions.

Large amounts of rich, heterogeneous information nowadays routinely collected by healthcare providers across the world possess remarkable potential for the extraction of novel medical data and the assessment of different practices in real-world conditions. Specifically in this work, our goal is to use electronic health records (EHRs) to predict progression patterns of future diagnoses of ailments for a particular patient, given the patient's present diagnostic history. Following the highly promising results of a recently proposed approach that introduced the diagnosis history vector representation of a patient's diagnostic record, we introduce a series of improvements to the model and conduct thorough experiments that demonstrate its scalability, accuracy, and practicability in the clinical context. We show that the model is able to capture well the interaction between a large number of ailments that correspond to the most frequent diagnoses, show how the original learning framework can be adapted to increase its prediction specificity, and describe a principled, probabilistic method for incorporating explicit, human clinical knowledge to overcome semantic limitations of the raw EHR data.

Semantic representations in the form of directed acyclic graphs (DAGs) have been introduced in recent years, and to model them, we need probabilistic models of DAGs. One model that has attracted some attention is the DAG automaton, but it has not been studied as a probabilistic model. We show that some DAG automata cannot be made into useful probabilistic models by the nearly universal strategy of assigning weights to transitions. The problem affects single-rooted, multi-rooted, and unbounded-degree variants of DAG automata, and appears to be pervasive. It does not affect planar variants, but these are problematic for other reasons.