IAAI ON THURSDAY, JULY 18TH, 2013

ABSTRACT. This paper describes the Advanced Text Exploitation Assistant (ATEA), a system developed to enable intelligence analysts to perform link analysis and visualization (A&V) from information in large volumes of unstructured text. One of the key design challenges that had to be addressed was that of imperfect Information Extraction (IE) technology. While IE seems like a promising candidate for exploiting information in unstructured text, it makes mistakes. As a result, analysts do not trust its results. In this paper, we discuss how ATEA overcomes the obstacle of imperfect IE by incorporating a human-in-the-loop for review and correction of extraction results. We also discuss how coupling consolidated extraction results (corpus-level information objects) with an intuitive use interface facilitates interactive navigation of the resulting information. With these key features, ATEA enables effective link analysis and visualization of information in unstructured text.

ABSTRACT. Patterns of life are observable regularities that emerge from the everyday goals, behaviors, and interactions of a community of individuals. Computational modeling for patterns of life would offer significant opportunities for practical application and theoretical research. We introduce three related scalability challenges for modeling patterns of life and outline how AI algorithms and representations are likely to be critical in meeting the challenges.

ABSTRACT. Unplanned hospital readmissions raise health care costs and cause significant distress to patients. Hence, predicting which patients are at risk to be readmitted is of great interest. In this paper, we mine large amounts of administrative information from claim data, including patients demographics, dispensed drugs, medical or surgical procedures performed, and medical diagnosis, in order to predict readmission using supervised learning methods. Our objective is to gain knowledge about the predictive power of the available information. Our preliminary results on data from the provincial hospital system in Quebec illustrate the potential for this approach to reveal important information on factors that trigger hospital readmission. Our findings suggest that a substantial portion of readmissions is inherently hard to predict. Consequently, the use of the raw readmission rate as an indicator of the quality of provided care might not be appropriate.

ABSTRACT. Coronary heart disease (CHD) is a major cause of death worldwide. In the U.S. CHD is responsible for approximated 1 in every 6 deaths with a coronary event occurring every 25 seconds and about 1 death every minute based on data current to 2007. Although a multitude of cardiovascular risks factors have been identified, CHD actually reflects complex interactions of these factors over time. Today's datasets from longitudinal studies offer great promise to uncover these interactions but also pose enormous analytical problems due to typically large amount of both discrete and continuous measurements and risk factors with potential long-range interactions over time. Our investigation demonstrates that a statistical relational analysis of longitudinal data can easily uncover complex interactions of risks factors and actually predict future coronary artery calcification (CAC) levels --- an indicator of the risk of CHD present subclinically in an individual --- significantly better than traditional non-relational approaches. The uncovered long-range interactions between risk factors conform to existing clinical knowledge and are successful in identifying risk factors at the early adult stage. This may contribute to monitoring young adults via smartphones and to designing patient-specific treatments in young adults to mitigate their risk later.

ABSTRACT. Before laboratory testing, bioinformatics problems often require a machine-learned predictor to identify the most likely choices among a wealth of possibilities. Researchers may advocate different predictors for the same problem, no one of which is best in all situations. This paper introduces a case-based meta-predictor that combines a set of elaborate, pre-existing predictors to improve their accuracy on a difficult and important problem: protein-ligand docking. The method focuses on the reliability of each of its component predictors, and has broad potential applications in biology and chemistry. Despite noisy and biased input, the method outperforms its individual components on benchmark data. It provides a promising solution for the performance improvement of compound virtual screening, which would thereby reduce the time and cost of drug discovery.