Solving the huge challenge to lessen the increasing burden of dementias on our society requires more efficient solutions in diagnostics and more effective treatments.
Additionally, treatments need to be combined in an optimal manner - the right treatment for the right individual at the right moment.The results of a given treatment in a particular patient depend on a wide range of factors, including age, physical condition, gender, fitness, previous exposure to illness and more.
Although medical professionals can now be much better informed on their patients' conditions, such data also complicate their work. ICT tools can help gather these data and analyse them.
Early diagnosis matters
Current treatments combined with early diagnosis can delay institutionalisation by one year which leads to major cost savings for society, as well as maintains a better quality of life for the patients and their nearest. In addition, life-style changes have been shown to be able to delay the progression of the disease.
Thus,it is essential to have efficient tools for diagnostics and functional clinical protocols ready. Nevertheless, clinical decision support systems (CDSS) that use machine learning and artificial intelligence, are hardly present in dementia diagnostics, as they are in many other disease areas. PredictND has understood how such CDSS’s could be used in clinical practice in general and in solving the huge challenge of dementias.
Saving €300 per patient on average
PredictND has showed that a hospital could save on average €300 per patient with a stratified approach using a CDSS as compared with the situation when all data are acquired for all patients.
The use of CDSSs will bring equality between citizens by harmonizing the quality of care, in particular when the clinicians and centers are less experienced. Keeping in mind that dementia accounts for costs equivalent to about 1% of the global GDP (about 461 billion euros annually), early diagnosis combined with the current treatments could enable citizens to live independently at home up to one year longer. In fact, delaying institutionalization by one year will bring a 20% reduction in costs, which PredictND hopes to achieve if used in actual clinical practice.
Already being used in clinical practice
The PredictND project was exceptional in the sense that the CDSS developed and validated in the project became available for actual clinical use in Europe already during the project. This means that from now on, it is possible to start measuring concrete cost savings in clinical practice.
This sets PredictND apart from usual research projects that use non-certified CDSS prototypes that can provide only coarse estimates, since the tools cannot be used in actual clinical practice.
Virtual Physiological Human concept
The concept of a Virtual Physiological Human (VPH) is a sophisticated computer modelling tool, which compares observations of an individual patient and relates them to a vast dataset of observations of others with similar symptoms and known conditions. By processing all this information, the model can simulate the likely reaction of the individual patient to possible treatments or interventions. Such personalised tools will improve the quality of treatment with better results and fewer side effects.
Not only for patients who are already ill or injured, but models like this could also be used in preventive medicine, to predict occurrence or worsening of specific diseases in people at risk, for example through family history. Through its initiatives within the Digital Single Market policy, the European Commission aims at leveraging digital technologies for the emergence of new personalised prevention and treatments for European citizens.