Reinhard Hatko

Pain perception and detailed visual pain mapping in breast cancer survivors

Chronic pain and neural irritation after breast surgery and radiation are still relevant sequelae of the treatment. Pain quantification and localization in patient groups are difficult to standardize. In order to quantify and localize pain in a group of breast cancer patients, a Java-based program was developed to visualize the frequency of pain in “pain maps.” A questionnaire with structured questions on the perception of pain included pictograms of a body to mark possible pain areas. A group of 343 breast cancer survivors completed the questionnaires. The image information was digitalized and processed using a Java applet. Gray-scale summation pictures with numbers from “0,” indicating black (100% pain), to “255,” indicating white (0% pain), were generated. The visualization of pain by creating pain maps revealed the location of pain in breast cancer survivors on pictograms of the body. Analyzing the total number of pixels, in which pain was stated, made it possible to compare pain areas in several subgroups, showing that patients after mastectomy versus breast-conserving therapy (3,011 vs. 2,224 pixels), and patients with lymphedema versus patients without lymphedema (3,010 vs. 2,239 pixels), have larger pain areas. This study presents a method of visualizing pain areas and assigning them to a pictogram of the body in a sample of breast cancer patients. The method is easy to use and could help generate pain maps in several types of disease.

Diaflux: a graphical language for computer-interpretable guidelines

In this paper, we introduce the formal representation language DiaFlux, that is simple and easy to use on the one hand. On the other hand it allows for the definition of Computer-Interpretable Guidelines (CIGs), that can solve valuable tasks being executed in the clinical context. Further, we describe a wiki-driven development process using the stepwise formalization and allowing for almost self-acquisition by the domain specialists. The applicability of the approach is demonstrated by a protocol for sepsis monitoring and treatment developed by a collaboration of clinicians.

Agent Learning Instead of Behavior Implementation for Simulations --- A Case Study Using Classifier Systems

Although multi-agent simulations are an intuitive way of conceptualizing systems that consist of autonomous actors, a major problem is the actual design of the agent behavior. In this contribution, we examine the potential of using agent-based learning for implementing the agent behavior. We enhanced SeSAm, a platform for agent-based simulation, by replacing the usual rule-based agent architecture by XCS, a well-known learning classifier system (LCS). The resulting model is tested using a simple evacuation scenario. The results show that on the one hand side plausible agent behavior could be learned. On the other hand side, though, the results are quite brittle concerning the frame of environmental feedback, perception and action modeling.

Implementing an automated ventilation guideline using the semantic wiki KnowWE

In this paper, we report on the experiences made during the implementation of a therapeutic process, i.e. a guideline, for automated mechanical ventilation of patients in intensive care units. The semantic wiki KnowWE was used as a collaborative development platform for domain specialists, knowledge and software engineers, and reviewers. We applied the graphical guideline language DiaFlux to represent medical expertise about mechanical ventilation in a flowchart-oriented manner. Finally, the computerized guideline was embedded seamlessly into a mechanical ventilator for autonomous execution.