Ontology-driven hypothesis generation to explain anomalous patient responses to treatment

Within the medical domain there are clear expectations as to how a patient should respond to treatments administered. When these responses are not observed it can be challenging for clinicians to understand the anomalous responses. The work reported here describes a tool which can detect anomalous patient responses to treatment and further suggest hypotheses to explain the anomaly. In order to develop this tool, we have undertaken a study to determine how Intensive Care Unit (ICU) clinicians identify anomalous patient responses; we then asked further clinicians to provide potential explanations for such anomalies. The high level reasoning deployed by the clinicians has been captured and generalised to form the procedural component of the ontology-driven tool. An evaluation has shown that the tool successfully reproduced the clinician’s hypotheses in the majority of cases. Finally, the paper concludes by describing planned extensions to this work.     

An architecture for a self-improving instructional planner for intelligent tutoring systems

Machine instructional planners use changing and uncertain data to incrementally configure plans and control the execution and dynamic refinement of these plans. Current instructional planners cannot adequately plan, replan, and monitor the delivery of instruction. This is due in part to the fact that current instructional planners are incapable of planning in a global context, developing competing plans in parallel, monitoring their planning behavior, and dynamically adapting their control behavior. In response to these and other deficiencies of instructional planners a generic system architecture based on the blackboard model was implemented. This self-improving instructional planner (SUP) dynamically creates instructional plans, requests execution of these plans, replans, and improves its planning behavior based on a student's responses to tutoring. Global planning was facilitated by explicitly representing decisions about past, current, and future plans on a global data structure called the plan blackboard. Planning in multiple worlds is facilitated by labeling plan decisions by the context in which they were generated. Plan monitoring was implemented as a set of monitoring knowledge sources. The flexible control capability for instructional planner was adapted from the blackboard architecture BB1. The explicit control structure of SUP enabled complex and flexible planning behavior while maintaining a simple planning architecture.     

Mathematical and computational models of drug transport in tumours

The ability to predict how far a drug will penetrate into the tumour microenvironment within its pharmacokinetic (PK) lifespan would provide valuable information about therapeutic response. As the PK profile is directly related to the route and schedule of drug administration, an in silico tool that can predict the drug administration schedule that results in optimal drug delivery to tumours would streamline clinical trial design. This paper investigates the application of mathematical and computational modelling techniques to help improve our understanding of the fundamental mechanisms underlying drug delivery, and compares the performance of a simple model with more complex approaches. Three models of drug transport are developed, all based on the same drug binding model and parametrized by bespoke in vitro experiments. Their predictions, compared for a ‘tumour cord’ geometry, are qualitatively and quantitatively similar. We assess the effect of varying the PK profile of the supplied drug, and the binding affinity of the drug to tumour cells, on the concentration of drug reaching cells and the accumulated exposure of cells to drug at arbitrary distances from a supplying blood vessel. This is a contribution towards developing a useful drug transport modelling tool for informing strategies for the treatment of tumour cells which are ‘pharmacokinetically resistant’ to chemotherapeutic strategies.     

Aristoforin, a novel stable derivative of hyperforin, is a potent anticancer agent

Hyperforin, a natural product of St. John's wort (Hypericum perforatum L.), has a number of pharmacological activities, including antidepressive and antibacterial properties. Furthermore, hyperforin has pronounced antitumor properties against different tumor cell lines, both in vitro and in vivo. Despite being a promising novel anticancer agent, the poor solubility and stability of hyperforin in aqueous solution limits its potential clinical application. In this study, we present the synthesis of hyperforin derivatives with improved pharmacological activity. The synthesized compounds were tested for their solubility and stability properties. They were also investigated for their antitumor properties, both in vitro and in vivo. One of these hyperforin derivatives, Aristoforin, is more soluble in aqueous solution than hyperforin and is additionally highly stable. Importantly, it retains the antitumor properties of the parental compound without inducing toxicity in experimental animals. These data strongly suggest that Aristoforin has potential as an anticancer drug.     

Effective and Efficient Knowledge Base Refinement

This paper presents the STALKER knowledge base refinement system. Like its predecessor KRUST, STALKER proposes many alternative refinements to correct the classification of each wrongly classified example in the training set. However, there are two principal differences between KRUST and STALKER. Firstly, the range of misclassified examples handled by KRUST has been augmented by the introduction of inductive refinement operators. Secondly, STALKER's testing phase has been greatly speeded up by using a Truth Maintenance System (TMS). The resulting system is more effective than other refinement systems because it generates many alternative refinements. At the same time, STALKER is very efficient since KRUST's computationally expensive implementation and testing of refined knowledge bases has been replaced by a TMS-based simulator.     

Modelling student's problem solving

The task of modelling a student's problem solving is intrinsically one of induction. In this paper, a further instance of induction formulated as a search is reported. A formulation of this search problem which ‘contains’ the Combinatorics is discussed at some length; and several heuristics which further reduce the size of the space defined by the domain's rules and mal-rules are presented.The Production Rule representation of (some) arithmetic operators is given, and the behaviour of generated models with examples is included. The paper concludes with a review of the basic assumptions made by the Modelling System, LMS, and suggestions for some extensions.     

Theory and Applications of Ignition with Variable Activation Energy

The determination of critical conditions for thermal ignition of combustible materials has been traditionally studied by the use of one overall reaction with bounded parameter values for the activation energy and other chemical constants, Significant errors can occur in the values of the threshold parameters for ignition when there are two (or more) simultaneous reactions present with distinct values of the chemical constants. Recent work with simultaneous parallel reactions showed the thresholds for ignition could be lowered in this case. In this paper, motivated by experimental results for forest litter and coal, it is shown that for sequential reactions (different values of parameters in different temperature ranges) that the threshold conditions are changed (safer for lower ambient temperatures and less safe for higher ambient temperatures).The mathematical analysis is summarised and a detailed analysis is given for the forest litter and crushed coal applications. The experimental results show that variable activation energy does occur and that this extension of the classical Frank-Kamenetskii theory is needed. Here the analysis is confined to the slab geometry only but the ideas developed can easily be extended to more general systems, including those involving mass transport, consumption, and phase changes.