43P - Oncoguide system - A computerized self-learning interactive assistance system for the diagnosis and treatment of CML / MPN and MDS

Date 10 October 2016
Event ESMO 2016 Congress
Session Poster display
Topics Basic Science
Presenter Dirk Hempel
Citation Annals of Oncology (2016) 27 (6): 1-14. 10.1093/annonc/mdw362
Authors D. Hempel1, Y. Fischer2
  • 1Institute Of Clinical Hematology/oncology, Steinbeishochschule Berlin, 86609 - Donauwoerth/DE
  • 2Iosb, Fraunhofer Institut, 76131 - Karlsruhe/DE

Abstract

Background

Clinical practice guidelines (CPG) represent the current state of research. Usually they were passive disseminations (e.g. via print media), but this doesn't assist the physician in the adaptation of CPG into the daily diagnostic and treatment algorithm to the given boundary conditions (patient, equipment, medical experience).The project aims to develop and implement a computerized interactive assistance system for the diagnosis and treatment of CML / MPN and MDS.

Methods

To create the system experts from the medical and the technical domains were necessary. They developed a CPG model in the form of a Unified Modeling Language (UML) activity followed by translation of UML activities into Bayesian nets. The future system is planned to be self-learning by weighing the decision criteria. The knowledge-based system is implemented as a client-server architecture. The server acts as a central data storage in the form of a database. As a client, for example, Internet browsers can be used. The knowledge of guidelines and interviews with experts have to be formalized in an appropriate manner. There are approaches based on an ontological or logic-based modeling. The underlying methodology is based on approaches from artificial intelligence, such as the Bayesian inference or machine learning methods.

Results

On the client's side the system suggests the user appropriate decisions for the diagnosis and further treatment of diseases. The user is navigated through the complex recommendations of current guidelines and decision trees of the CML/MPN and MDS, similar to a car navigation system. In contrast to common print media the system actively supports the physician in the adaptation of CPG into the daily diagnostic and treatment algorithm to the given boundary conditions (patient, equipment, medical experience) and has self learning components.

Conclusions

The presented computerized interactive assistance system could help to increase the accuracy of diagnosis, treatment and follow up of CML/MPN and MDS.

Clinical trial identification

Legal entity responsible for the study

Steinbeishochschule Berlin, Institute of Clinical Hematology/Oncology

Funding

Celgene, Novartis

Disclosure

D. Hempel: Supported by a grant of Celegene and Novartis.

All other authors have declared no conflicts of interest.