We will be running a joint workshop with members of FHAIVE, Dario Greco's research group based in Tampere, Finland. We will explore some of the applications of AI in the biomedical domain. The Programme is as follows:
Opening: 9:00 –9:05
- 9:05 – 9:20: Building knowledge graphs from electronic health records for adverse event prediction (Paola, AIML)
Abstract: With older age, there is an increased chance of being diagnosed with more than one long-term condition. The medical treatment of patients with multiple conditions is challenging because the interactions of symptoms and medications are complex and hard to predict. In this talk, I will discuss an ongoing project using knowledge-graph methods to detect people who are likely to have unexpected health problems (like falls or bleeding), with the ultimate goal of supporting doctors in the choice of proper treatment and preventive care. I will briefly introduce the Clinical Practice Research Datalink (CPRD) dataset and the data model underlying the knowledge graph. I will then present a first attempt at repurposing a knowledge graph recommender system (KGAT) in the context of adverse events predictions. I will conclude with an overview of the challenges and open questions left to address.
- 9:20 – 9:35: Graph learning for toxicology and chemical safety assessment – Highlight KE - (Angela, FHAIVE)
- 9:35 – 9:50: Network analysis for precision pharmacology (Tonino, FHAIVE)
Break: 9:50 – 10:00
- 10:00 – 10:15: A multi-dimensional disease map (Lena, FHAIVE)
- 10:15 – 10:30: A Bayesian network approach for a robust estimate of disease co-occurrence (Guillermo, AIML)
Abstract: Examining associations between long-term conditions may be important in identifying opportunities for intervention in multimorbidity, but is challenging when data is limited. Previous literature in multimorbidity typically relies on association measures that are flawed when using small sample sizes, do not report confidence intervals or otherwise appropriately account for uncertainty, which is crucial in measures such as Relative Risk, as they are known to overestimate rare events. We have developed a Bayesian inference framework that is robust to small data samples and used it to quantify morbidity associations in the oldest old, a population with limited available data. We analysed associations obtained with Relative Risk (RR), and compared them with our proposed measure, Associations Beyond Chance (ABC), examining both parirwise associations and network aggregations. Our Bayesian framework was appropriately more cautious in attributing association when evidence is lacking, particularly in less common conditions. This caution in reporting association was also present in reporting differences in associations between sex and affected the aggregated measures of multimorbidity and network representations. Incorporating uncertainty into multimorbidity research is crucial to avoid misleading findings when data is limited, a problem that particularly affects small but important subgroups. Our proposed framework improves the reliability of estimations of associations and, more in general, of research into disease mechanisms and multimorbidity.
- 10:30 – 10:45: MARS: A Neurosymbolic System for Biomedical Mechanism-of-Action Retrieval (Lauren, AIML)
Abstract: Recently, several machine learning approaches have aided drug discovery by identifying promising candidates and predicting potential indications. However, understanding the ways in which drugs achieve their therapeutic effects, otherwise known as their mechanisms-of-action (MoA), is important for understanding potency, side effects, and interactions with various tissue types, among other things. We leveraged and improved the interpretability of a neurosymbolic reinforcement learning method in an attempt to reveal MoAs. While doing so, we observed that our findings raised several concerns with the reasoning process. Specifically, we debate situations in which patterns following a "guilt-by-association" trend are useful for predictions regarding novel compounds. We present our results to facilitate discussion about how generalizable ML-based models are to the drug discovery process as well as how important interpretability can be to such models.
Discussion/Closing: 10:45 – 11:00