Skip to content. | Skip to navigation

Informatik 5
Information Systems
Prof. Dr. M. Jarke
Sections
Personal tools
You are here: Home Theses Development and Optimization of a STOPP/START Rule Base to Identify Potential Adverse Drug Reactions in Polypharmacy Cases

Contact

Prof. Dr. M. Jarke
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 

Development and Optimization of a STOPP/START Rule Base to Identify Potential Adverse Drug Reactions in Polypharmacy Cases

Thesis type
  • Bachelor
Student Jonas W. Könning
Status Finished
Submitted in 2017
Supervisor(s)
Advisor(s)

The demographic change in many parts of the world, especially in Europe and the USA, is potentially one of the biggest challenges for those societies. As the number of older people grows and surpasses the number of children, while lives in general tend to be longer, the healthcare sector is facing a new set of tasks and responsibilities. Patients with multiple chronic illnesses tend to have a complicated medication prescribed from multiple sources that often have incomplete knowledge on what substances the patient is actually and effectively using.
In the context of the POLYCARE project, a system was to be developed to evaluate a set of recommendations regarding drug prescriptions for the elderly in the form of the START/STOPP criteria against data from electronic health records, such as medication plans, and eventually together with sensor data. For this a rule base for use in a production rule system was devised and evaluated against generated data sets that mimic simple patient records. To achieve this, the structure of the mentioned medication guidelines was analysed and transformed into a schema for their machine readable representation. Medical coding systems were used to represent drugs and diagnosis.
Though the developed rules are naively translated from the original statements and the used drugs and diagnosis codes were not selected based on a consensus process by medical professionals or in a similar fashion, they work well as a proof of concept.
The created rule base shows good performance and the accompanying system was built with the other technologies and applications of the POLYCARE workflow in mind. Multiple extensions and improvements are conceivable, the used decision tables allow easy manipulation of the knowledge base, without extensive changes of source code.

Related projects

Document Actions