Theoretical models in dentistry.

For the exchange between science and practice, a language that is as precise as possible is also required in dentisty. This language is necessarily based on our ideas about the relationships in reality. Since standardization is unavoidable, various methods have been developed in informatics as to how these models can be represented and made more precise. On this basis, it is possible to neutrally discuss the situations in which a given form of treatment is expedient or not. A step-by-step approach to standardization of dental language with the aid of meta models is shown by reference to examples. The medrapid.info service is presented as on approach to making medical and dental language more precise.

Introducing DoT-U2--an XML-based knowledge supported checklist software for documentation of a newborn clinical screening examination.

In a project concerning the German newborn screening examination "U2" we developed a software system called DoT-U2 for concurrent documentation at the point of care. Physicians can enter findings in(to) a tree structured protocol with management of logical dependencies. Additionally, all findings except free text annotations can be entered by speech recognition. The software system program is written in Java and uses separate XML-based modules both for knowledge and language representation. It can, therefore, easily be adapted to other languages and further documentation scenarios. We showed the high flexibility of the software system by integrating it in a completely new setting in Salt Lake City without major problems. We found that modular software development with platform independent Java and XML leads to highly flexible software which can be adapted to very different scenarios without knowing their requirements ahead of time.

AIDA: web agents in dental treatment planning.

The objective of the AIDA project (Artificial Intelligent Dental Agents, http://aida.uni-hd.de) is the analysis of dental decision-making, the design of a computer-based decision support system, as well as the testing of the decision structure in interactions with dental experts, practicing dentists, and patients. The planning of the solution alternatives for an individual patient is based on a top-down structure for dental decision-making, aiming at a standardization of the argumentation. From a theoretical point of view, decision support can be provided only for anticipated decisions (planning). Moreover, only parts of these anticipated decisions can be supported. Accordingly, a separation of these partial aspects has to take place before one is able to build decision support systems. For prosthetic dentistry, clinicians have been shown how to use individual patient findings to sketch the possible treatment alternatives and later derive guidelines for the treatment. The planning module for fixed prostheses has already been integrated into a software agent. Planning modules for other types of prostheses are currently specified, implemented, and verified.

AIDA--experiences in compensating the mutual weaknesses of knowledge-based and object-oriented development in a complex dental planning domain.

OBJECTIVES: Dentistry is a discipline with two properties that pose a serious challenge to knowledge based decision support: (1) It has to integrate six subdisciplines ranging from conservative measures to invasive disciplines, such as implantology; (2) A plan may have to cover a complex treatment often lasting one year or more. It is the aim of the AIDA-project to set up a planning strategy that is suited to incorporate all dental peculiarities in one methodology. METHODS: Generic tasks, that can be assigned to individual persons involved in dental treatment, have been designed with the help of KADS. They have been integrated into a planning super-structure for the planning of all dental solution alternatives, that can principally be applied on the basis of the given patient status. RESULTS: Besides an evaluation of the implemented planning system itself, it has been evaluated how well the development is supported by (1) knowledge-engineering methods and (2) object-oriented methods. CONCLUSION: Common knowledge-based tools are not powerful enough for the planning of complex dental constructions. Therefore, a solution combining object-oriented and knowledge-based methods is proposed.

MedRapid--medical community & business intelligence system.

OBJECTIVE: currently, it takes at least 6 months for researchers to communicate their results. This delay is caused (a) by partial lacks of machine support for both representation as well as communication and (b) by media breaks during the communication process. METHODS: To make an integrated communication between researchers and practitioners possible, a general structure for medical content representation has been set up. The procedure for data entry and quality management has been generalized and implemented in a web-based authoring system. RESULTS: The MedRapid-system supports the medical experts in entering their knowledge into a database. Here, the level of detail is still below that of current medical guidelines representation. However, the symmetric structure for an area-wide medical knowledge representation is highly retrievable and thus can quickly be communicated into daily routine for the improvement of the treatment quality. In addition, other sources like journal articles and medical guidelines can be references within the MedRapid-system and thus be communicated into daily routine. CONCLUSIONS: The fundamental system for the representation of medical reference knowledge (from reference works/books) itself is not sufficient for the friction-less communication amongst medical staff. Rather, the process of (a) representing medical knowledge, (b) refereeing the represented knowledge, (c) communicating the represented knowledge, and (d) retrieving the represented knowledge has to be unified. MedRapid will soon support the whole process on one server system.

AIDA: Web agents to support dental treatment planning.

Dental treatment planning is highly dependent on the educational background and personal experience of the dentist and on the thoroughness with which findings are taken. The objective of research in the AIDA (Artificially Intelligent Dental Agents) project is therefore the analysis of dental decision making and the design of a decision-supportive software module to test the decision-making process and make it transparent for both dentists and patients. In the AIDA project (aida.uni-hd.de), an expert system has been set up to identify treatment alternatives with integrated decision rationale for experts, practicing dentists, and eventually also patients. It is based on a top-down structure for dental decision-making, which was developed to standardize argumentation. For prosthetic dentistry, how one uses individual patient findings to arrive at possible treatment alternatives was clarified in greater detail. The planning rules for fixed prostheses have already been integrated into a software agent. Other modules should soon specify and verify these suggestions in terms of further fields of dentistry (e.g., restorative dentistry). In the near future, AIDA will be able to deliver dentally-founded justifications for every individual decision.