CE19 - Technologies pour la santé

Off-label Use in Psychiatric Specialty – PSYHAMM

Submission summary

Psychiatric diseases are a public health priority: they represent almost 20% of health spending and if we add the direct and indirect costs costing almost double the cost of neurological and neurodegenerative diseases. Drug prescriptions shows a field where the therapy is evolving with more or less well analyzed effects. Psychiatry is particularly a field where there are many off-label prescriptions with both sources of identification of new uses and, opposite, adverse events. We offer equip psychiatric specialty with tools of the Knowledge Engineering to analyze these off-label prescriptions on relatively large samples from the CH Sainte-Anne.
To achieve this, a number of tools and resources have to be developed, mainly:
- "Classic" computing tools to retrieve the structured data contained in the different hospital software (prescription software, drug knowledge-base, medico-economic coding tools);
- Semantic resources, i.e. (i) an ontology describing the drugs and their MAs and (ii) an ontology of diseases, in the standard formats of the semantic web. These will be completed during the development of the system by more conventional terminologies accessible via HeTOP (http://www.hetop.eu/hetop/), a search engine of medical knowledge that contains the main medical terminologies aligned to each other. We will thus have access to other terminologies adapted to our subjects of interest, drugs and especially non-psychiatric diseases;
- A tool of Natural Language Processing (NLP) for search the electronic health record for diagnoses on patients, other drugs dispensed and any information necessary for the analysis of off-label prescriptions. This is called semantic annotation. This tool will be developed from semantic annotation prototypes developed in LIMICS.
- Standard statistical tools adapted to specific studies of the analysis of off-label prescriptions.
The results of this work will enable psychiatrists and pharmacists to obtain the necessary data to study off-label prescriptions, their nature, frequency and motivation. From a medical point of view, the work will be an opportunity to follow the implementation of the recommendations but also a source to identify new uses. From the Knowledge Engineering point of view, the tools developed could be made available to CH Sainte-Anne and, in a short time, to other hospitals of the Hospital Group Territory using the same prescription and Electronic Health Record software.

Project coordination

Marie-Christine Jaulent (Laboratoire d'Informatique Médicale et Imagerie des Connaissances pour la e-Santé)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.


CHSA Centre Hospitalier Sainte-Anne
LIMICS Laboratoire d'Informatique Médicale et Imagerie des Connaissances pour la e-Santé

Help of the ANR 214,920 euros
Beginning and duration of the scientific project: - 30 Months

Useful links

Explorez notre base de projets financés



ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter