Werner Horn

Effective data validation of high-frequency data: time-point-, time-interval-, and trend-based methods.

Real-time systems for monitoring and therapy planning, which receive their data from on-line monitoring equipment and computer-based patient records, require reliable data. Data validation has to utilize and combine a set of fast methods to detect, eliminate, and repair faulty data, which may lead to life-threatening conclusions. The strength of data validation results from the combination of numerical and knowledge-based methods applied to both continuously-assessed high-frequency data and discontinuously-assessed data. Dealing with high-frequency data, examining single measurements is not sufficient. It is essential to take into account the behavior of parameters over time. We present time-point-, time-interval-, and trend-based methods for validation and repair. These are complemented by time-independent methods for determining an overall reliability of measurements. The data validation benefits from the temporal data-abstraction process, which provides automatically derived qualitative values and patterns. The temporal abstraction is oriented on a context-sensitive and expectation-guided principle. Additional knowledge derived from domain experts forms an essential part for all of these methods. The methods are applied in the field of artificial ventilation of newborn infants. Examples from the real-time monitoring and therapy-planning system VIE-VENT illustrate the usefulness and effectiveness of the methods.

AI in medicine on its way from knowledge-intensive to data-intensive systems

The last 20 years of research and development in the field of artificial intelligence in medicine (AIM) show a path from knowledge-intensive systems, which try to capture the essential knowledge of experts in a knowledge-based system, to data-intensive systems available today. Nowadays enormous amounts of information is accessible electronically. Large datasets are collected continuously monitoring physiological parameters of patients. Knowledge-based systems are needed to make use of all these data available and to help us to cope with the information explosion. In addition, temporal data analysis and intelligent information visualization can help us to get a summarized view of the change over time of clinical parameters. Integrating AIM modules into the daily-routine software environment of our care providers gives us a great chance for maintaining and improving quality of care.

Therapy Planning Using Qualtitative Trend Descriptions

This paper addresses a method of therapy planning applicable in the absence of an appropriate curve-fitting model. It incorporates knowledge about data points, data intervals, and expected qualitative trend description to arrive at unified qualitative descriptions of parameters (temporal data abstraction). Our approach benefits from derived qualitative values which can be used for recommending therapeutic actions as well as for assessing the effectiveness of these actions within a certain period. It results in an easily comprehensible and transparent concept of therapy planning. Furthermore, we improved the system model of data interpretation and therapy planning by using importance ranking of variables, priority lists of attainable goals, and pruning of contradictory therapy recommendations.

Development and evaluation of VIE-PNN, a knowledge-based system for calculating the parenteral nutrition of newborn infants

Calculating the daily changing composition of parenteral nutrition for small newborn infants is troublesome and time consuming routine work in neonatal intensive care. The task needs expertise and experience and is prone to inherent calculation errors. We designed VIE-PNN (Vienna Expert System for Parenteral Nutrition of Neonates), a knowledge-based system (KBS) in order to reduce daily routine work and calculation errors. VIE-PNN was redesigned several times because the clinicians accepted the system only when it saved time. The most recent version of VIE-PNN uses an Hypertext Markup Language (HTML)-based client-server architecture and is integrated into the intranet of the local patient data management system. Since more than 3 years all parenteral nutrition plans are calculated using VIE-PNN. Evaluating the systems performance and the users contentedness, we compared 50 nutrition plans calculated in parallel using VIE-PNN or a hand-held calculator, retrospectively analyzed more than 5000 nutrition plans stored in VIE-PNNs database and evaluated a user questionnaire. Nutrition plans were calculated in a mean time of 2.4 versus 7.1min using VIE-PNN or the hand-held calculator. Errors and omissions in the nutrition plans were detected in 22% versus 56% and errors in the VIE-PNNs plans occurring only with interactively changed values. Reviews of stored plans show that a mean of 4 out of 16 parameters were interactively changed. VIE-PNN was well accepted. Most important reasons for the successful operation of VIE-PNN in the daily routine work were time savings and robustness of the system.

Abstracting Steady Qualitative Descriptions over Time from Noisy, High-Frequency Data

On-line monitoring at neonatal intensive care units produces high volumes of data. Numerous devices generate data at high frequency (one data set every second). Both, the high volume and the quite high error-rate of the data make it essential to reach at higher levels of description from such raw data. These abstractions should improve the medical decision making. We will present a time-oriented data-abstraction method to derive steady qualitative descriptions from oscillating high-frequency data. The method contains tunable parameters to guide the sensibility of the abstraction process. The benefits and limitations of the different parameter settings will be discussed.

Using Time-Oriented Data Abstraction Methods to Optimize Oxygen Supply for Neonates

Therapy management needs sophisticated patient monitoring and therapy planning, especially in high-frequency domains, like Neonatal Intensive Care Units (NICUs), where complex data sets are collected every second. An elegant method to tackle this problem is the use of time-oriented, skeletal plans. Asgaard is a framework for the representation, visualization, and execution of such plans. These plans work on qualitative abstracted time-oriented data which closely resemble the concepts used by experienced clinicians.This papers presents the data abstraction unit of the Asgaard system. It provides a range of connectable data abstraction methods bridging the gap between the raw data collected by monitoring devices and the abstract concepts used in therapeutic plans. The usability of this data abstraction unit is demonstrated by the implementation of a controller for the automated optimization of the fraction of inspired oxygen (FiO2). The use of the time-oriented data abstraction methods results in safe and smooth adjustment actions of our controller in a neonatal care setting.

Time-Oriented Skeletal Plans: Support to Design and Execution

Skeletal plans are a powerful way to reuse existing domain-specific procedural knowledge. In the Asgaard project, a set of tasks that support the design and the execution of skeletal plans by a human executing agent other than the original plan designer are designed. The underlying requirement to develop task-specific problem-solving methods is a modeling language. Therefore, within the Asgaard project, a time-oriented, intention-based language, called Asbru, was developed. During the design phase of plans, Asbru allows to express durative actions and plans caused by durative states of an observed agent. The intentions underlying these plans are represented explicitly as temporal patterns to be maintained, achieved or avoided. We will present the underlying idea of the Asgaard project and explain the time-oriented Asbru language. Finally, we show the benefits and limitations of the time-oriented, skeletal plan representation to be applicable in real-world, high-frequency domains.

Utilizing detailed anatomical knowledge for hypothesis formation and hypothesis testing in rheumatological decision support

Diagnostic decisions in rheumatology are based to a large extent on a good understanding of the anatomy of the human body. A decision support system for rheumatology has to represent this fundamental anatomical knowledge in order to be able to reason about causal relationships between disturbances affecting the musculoskeletal system. We have built a knowledge-based system incorporating a detailed representation of the anatomy. This yields two main advantages: (1) it enables us to build generic disease descriptions. Instantiation automatically constructs specific disease descriptions by filling in the anatomical details which describe the situation of the patient; (2) the system provides a user interface showing all the anatomical details within the context of the patients problem. This is essential for the intended field of application, namely, primary medical care. This paper concentrates on the usage of the anatomical knowledge during hypothesis formation and during hypothesis testing.

Paper: Automatic knowledge base refinement: Learning from examples and deep knowledge in rheumatology

MESICAR is a second generation expert system which contains very general descriptions of rheumatological disorders in the primary medical care field. With the help of a detailed hierarchical description of the human anatomy the system is able to support diagnostic decisions. The paper describes how machine learning techniques are used to automatically construct more specific disease descriptions for common, frequently occurring cases. The system MESICAR-LEARN implements a learning method which integrates analytical and empirical learning techniques. Cases diagnosed by MESICAR form the training examples, and MESICARs knowledge base is used as domain theory. The learned concepts are integrated into a hierarchy of disease descriptions. They support efficient and fast reasoning on common cases in addition to the general diagnostic support afforded by MESICARs deep knowledge.

Mesicar-a medical expert system integrating causal and associative reasoning

A fundamental understanding of the anatomy of the human body is a prerequisite for the successful application of a rheumatological expert system designed for use in an outpatient setting. MESICAR incorporates extensive anatomical knowledge that provides the basis for the reasoning methods, which try to explain which structures may be the cause of visible problems of the patient. Associative relations between diseases and manifestations are combined with expressions that define conditions on the manifestations. These conditions are evaluated following the causal relations in the anatomical net. This paper concentrates on the associative and causal reasoning methods of MESICAR and their integration.