Host Institution: Median
Department that hosts the PhD: Department of Quality and Innovation
The goal of this project is to improve the quality of rehabilitation care by developing patient-specific data-driven treatment pathways. The key task is to develop a model to predict patient-specific, evidence-based treatment pathways by exploiting machine learning techniques. Employing machine learning techniques enables to show the interactions between different components affecting the outcome of a treatment, in line with a systems approach.
In the first phase of the project, retrospective analyses will be performed which aim at linking sociodemographic data, data on the therapy units delivered and outcome parameters to identify superior therapy combinations. Outcome parameters and sociodemographic data have been collected since the beginning of 2019, providing a solid database. Outcome parameter reliability and interactions between different parameters and the sociodemographic data will also be tested. Employing machine learning techniques will enable to show the interactions between different components affecting the outcome of a treatment, in line with a systems approach.
In the second phase the identified superior therapy combinations will be tested in prospective studies. The focus is on integrating the findings into everyday clinical practice in order to guarantee patients the best possible therapy tailored to their individual needs and therewith integrating the systems approach into medical practice. All of this aims at
answers the question of what the model is relating the outcome parameters with sociodemographic data so that the type and duration of the treatment for individual patients can be predicted at the beginning of the rehabilitation stay.
This innovative approach will strengthen rehabilitation care as a cost-reducing and quality-enhancing third pillar of the health care system in the supply chain alongside physicians in private practice and inpatient acute medicine.