The Patient Path: a first approach
Résumé
European healthcare systems are faced with multiple challenges, including an
aging population, an increase in chronic diseases and patients with
multi-morbidity, and limited financial and human resources. The response to
these challenges is based in particular on the organisation of care into care
pathways. Namely, Once the data necessary for the construction of a care
pathway are acquired and processed, one has to model the patient pathway
mathematically in a generic way. After that, using clustering algorithms, one can
identify patients subgroups, then, mine for common treatments, predict the
future of patient pathways and answer clinicians’ questions. All these steps would
lead to an automated processes which has to be evaluated by medical experts.
Available statistical methods remain limited and inefficient to construct care
pathways. Indeed, data obtained from health care providers and insurance
companies are all time-dependent, highly heterogeneous, qualitative in part, with
several thousand possible modalities and mainly made up of missing data. We
propose an approach based on functional data analysis combined with
longitudinal data analysis in order to construct care pathways.
Origine | Fichiers produits par l'(les) auteur(s) |
---|