Personalised cAnceR TreatmeNt and caRe platform
The PARTNR project will develop an intelligent system to provide optimal cancer-related fatigue treatment based on a holistic, complete patient view, including for example the preference of patients. For this, the University of Twente collaborates with the Ziekenhuis Groep Twente, Helen Dowling Institute, Roessingh rehabilitation center, University Medical Centre Groningen, Netherlands Comprehensive Cancer Organisation and the companies Ivido, Evidencio and Roessingh Research and Development.
Five year after breast cancer, most patients still experience health problems. It is difficult to cope with these problems and patients express strong unmet needs. Fatigue is one of the most referred symptoms of breast cancer patients (>90%) and has a highly negative impact on the quality of life. Treatment of cancer-related fatigue is complicated and personalisation can optimise the treatment results.
For a holistic view on patients, clinical data will be supplemented with data from real-life. With this, the health of patients will be quantified in health scores for several health-related domains. This holistic view makes personalising care possible, with the direct effect for the patients that treatment is more effective and their quality of life increases. The health scores also provide insight for patients themselves and makes their health (progression) more tangible. This will empower patients and their environment to take an active role in their recovery. The holistic patient data will be used as input for a self-learning algorithm to make a tailored treatment recommendation. Patients will be monitored (semi)continuously, so that changes over time can be identified as well as the extent to which certain treatment objectives have been met.
The PARTNR platform will be implemented in a personal health environment and will include prediction models for the risk of chronic cancer-related fatigue, methods and tools for patient profiling and monitoring, and a decision support tool for personalized recommendations.
